WO2023142816A1 - 障碍物信息确定方法、装置、电子设备以及存储介质 - Google Patents
障碍物信息确定方法、装置、电子设备以及存储介质 Download PDFInfo
- Publication number
- WO2023142816A1 WO2023142816A1 PCT/CN2022/141398 CN2022141398W WO2023142816A1 WO 2023142816 A1 WO2023142816 A1 WO 2023142816A1 CN 2022141398 W CN2022141398 W CN 2022141398W WO 2023142816 A1 WO2023142816 A1 WO 2023142816A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- coordinates
- point
- point cloud
- current
- obstacle
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 64
- 238000001514 detection method Methods 0.000 claims abstract description 28
- 239000011159 matrix material Substances 0.000 claims description 80
- 238000007781 pre-processing Methods 0.000 claims description 20
- 238000006243 chemical reaction Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 5
- 230000003068 static effect Effects 0.000 claims description 5
- 238000013500 data storage Methods 0.000 description 17
- 230000006870 function Effects 0.000 description 11
- 238000004364 calculation method Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 5
- 238000009434 installation Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000000087 stabilizing effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000011426 transformation method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
- G06T7/75—Determining position or orientation of objects or cameras using feature-based methods involving models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30241—Trajectory
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
- G06T2207/30261—Obstacle
Definitions
- the embodiments of the present application relate to the technical field of intelligent driving, for example, to a method, device, electronic device, and storage medium for determining obstacle information.
- the driver often directly observes the obstacles around the vehicle, or the driver determines the obstacles on the left and right sides of the vehicle by observing the door rearview mirror, and then the vehicle drives according to the driver's instructions.
- the way is easily affected by the driver's subjective experience or environmental factors, and the safety of the vehicle is low.
- the present application provides a method, device, electronic device and storage medium for determining obstacle information, so as to improve the accuracy of determining obstacles around a vehicle, thereby improving the driving safety of the vehicle.
- the embodiment of the present application provides a method for determining obstacle information, the method including:
- the point cloud data includes point cloud coordinates in a local coordinate system with the current vehicle as the origin;
- the obstacle identification condition includes a point cloud
- the embodiment of the present application also provides a device for determining obstacle information, which includes:
- the point cloud data acquisition module is configured to acquire at least one point cloud data within the preset range of the current vehicle; wherein, the point cloud data includes point cloud coordinates in a local coordinate system with the current vehicle as the origin;
- the obstacle information identification module is configured to obtain at least one obstacle identification condition, and based on the obstacle identification condition and the point cloud coordinates, identify the obstacle information of the obstacle within the preset range of the current vehicle; wherein, the The obstacle identification conditions include the detection distance condition between the point cloud coordinates and the current vehicle, the first adjacent distance condition between the point cloud coordinates and the right adjacent point coordinates, the point cloud coordinates and the left adjacent point coordinates respectively The adjacent angle condition between the point cloud coordinates and the right adjacent point coordinates and the second adjacent distance condition between the point cloud coordinates and the right adjacent point coordinates.
- the embodiment of the present application further provides an electronic device, the electronic device comprising:
- processors one or more processors
- storage means configured to store one or more programs
- the one or more processors When the one or more programs are executed by the one or more processors, the one or more processors are made to implement the method for determining obstacle information provided in any embodiment of the present application.
- the embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the method for determining obstacle information provided in any embodiment of the present application is implemented.
- FIG. 1 is a schematic flowchart of a method for determining obstacle information provided by an embodiment of the present application
- FIG. 2 is a schematic flowchart of a method for determining obstacle information provided by another embodiment of the present application
- FIG. 3 is a schematic flowchart of a method for determining obstacle information provided by another embodiment of the present application.
- FIG. 4 is a schematic flowchart of a method for determining obstacle information provided by another embodiment of the present application.
- Fig. 5 is a schematic structural diagram of an obstacle information determining device provided by an embodiment of the present application.
- FIG. 6 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.
- Figure 1 is a flow chart of a method for determining obstacle information provided by the embodiment of the present application. This embodiment can be applied to the situation of determining obstacles around the vehicle when the vehicle is driving automatically; Determines the condition of obstacles around the vehicle when restricted.
- the method can be executed by an obstacle information determining device, and the device can be realized by software and/or hardware.
- the application scenarios include: currently in the process of driving, the driver often directly observes the obstacles around the vehicle, or the driver determines the obstacles on the left and right sides of the vehicle by observing the door rearview mirror, and then the vehicle drives according to the driver's instructions , and this artificial determination method is easily affected by the driver's subjective experience or environmental factors, and the safety of the vehicle is low.
- the obstacle information around the vehicle is mostly obtained based on the camera installed around the vehicle, but the camera will be damaged and the function is limited, resulting in the vehicle controller being unable to obtain the obstacle information around the vehicle, resulting in Automated driving of vehicles poses a greater safety risk.
- the technical solution in this embodiment calculates the status information of obstacles around the self-driving vehicle through the acquired radar data, and provides necessary information for the self-driving vehicle to decelerate, avoid obstacles, and plan paths around obstacles.
- the technical solution of this embodiment obtains at least one point cloud data within the preset range of the current vehicle; wherein, the point cloud data includes the point cloud coordinates in the local coordinate system with the current vehicle as the origin; thus obtaining more Accurate radar data provides the necessary information for automatic driving vehicles to decelerate and avoid obstacles, and plan paths around obstacles; obtain at least one obstacle recognition condition, and based on the obstacle recognition condition and point cloud coordinates, identify the location of obstacles within the preset range of the current vehicle Obstacle information; wherein, the obstacle recognition condition includes the detection distance condition between the point cloud coordinates and the current vehicle, the first adjacent distance condition between the point cloud coordinates and the right adjacent point coordinates, the point cloud coordinates and the left phase coordinates respectively The adjacent angle condition between the adjacent point coordinates and the right adjacent point coordinates and the second adjacent distance condition between the point cloud coordinates and the right adjacent point coordinates; through multiple obstacle recognition conditions, the scanned point cloud The data is identified to determine the obstacle information around the vehicle, which improves the accuracy of obstacle identification,
- the method includes the following steps:
- the surroundings of the vehicle may be detected based on various radar detection devices, so as to acquire point cloud data within a preset range around the vehicle.
- the method for acquiring point cloud data may include: scanning a preset range of the current vehicle based on a preset radar sensor, and acquiring initial point cloud coordinates in the scan result.
- the installation position of the preset radar sensor on the current vehicle determines the perception range and ability of the sensor obstacle detection, in order to reduce the occlusion as much as possible and increase the detection range of the lidar. For example, you can choose to install it above the roof or under the current vehicle.
- the above installation positions of the radar sensors are only exemplary installation positions, and this embodiment does not limit the installation positions of the radar sensors.
- the type of the preset radar sensor may be a laser radar, a vehicle millimeter-wave radar, or other types of radar sensors.
- the surrounding area of the vehicle is continuously scanned, and the scanned point cloud data is stored in real time.
- the scanning angle of the radar sensor can be 360 degrees, of course, the scanning angle can also be set in real time according to the current environment of the vehicle.
- the stored point cloud data may include point cloud coordinates in a local coordinate system with the current vehicle as the origin.
- Each point cloud data packet may include (X, Y) coordinate information based on the local coordinate system where the current vehicle is located.
- the origin of the local coordinate system is the center point of the current vehicle
- the positive X direction is the driving direction of the current vehicle
- the Y direction is the left direction of the current vehicle.
- the initial point cloud data of radar scanning may have single-frame false positives or multi-frame jitter, it is necessary to perform data preprocessing on the initial point cloud data before identifying obstacle information based on the initial point cloud data. Eliminate these accidental factors as much as possible, so as to improve the accuracy of obstacle information identification. Therefore, after obtaining the initial point cloud data scanned by the radar sensor, the technical solution of this embodiment performs data preprocessing on the initial point cloud coordinates to obtain the target point cloud coordinates within the preset range of the current vehicle.
- the method for data preprocessing of the initial point cloud data may include: obtaining a preset coordinate storage matrix, shifting the column coordinate data in the preset coordinate storage matrix to the right by one column, and shifting the corresponding column coordinate data in the initial point cloud coordinates Store in the first column of the preset coordinate storage matrix to obtain a coordinate adjustment matrix; sort the coordinate data in the coordinate adjustment matrix according to the preset sorting rules to obtain a coordinate sorting matrix; obtain at least two columns of coordinate data in the coordinate sorting matrix, Determine the row coordinate mean value of the row coordinate data in at least two columns of coordinate data, and use the row coordinate mean value as the corresponding point cloud coordinates in the target point cloud coordinates.
- the data preprocessing method is exemplarily introduced by taking the above 90 point cloud data as an example.
- read the initial point cloud data of the current vehicles FSP_0-FSP_90 at the current moment and store the initial point cloud data in the newly created initial point cloud data matrix.
- the matrix name of the initial point cloud data matrix can be FSP_n_XY, and the matrix is a 90 ⁇ 2 coordinate matrix.
- the initial coordinate data information in FSP_n_XY is shown in the following table:
- the preprocessing method of this embodiment needs to follow the principle that error generation and distribution follow a normal distribution in order to avoid single-frame false positives while stabilizing multi-frame jitter, so as to eliminate error points through median mean filtering.
- a data storage matrix is established in advance to store the point cloud data after data preprocessing at the previous moment.
- this embodiment divides the data storage matrix into an X coordinate data storage sub-matrix and a Y coordinate data storage sub-matrix.
- the matrix name of the X-coordinate data storage sub-matrix may be FSP_save_X
- the matrix name of the Y-coordinate data storage sub-matrix may be FSP_save_Y.
- the matrix size of the X-coordinate data storage sub-matrix is a matrix of 90 ⁇ N, where the size of N is the key to median mean filtering.
- the minimum value of N is not less than 10, and the maximum value is not more than 50; for example, in the technical solution of this embodiment, N can be temporarily taken as 30, and of course N can also be Except for other numerical values, the present embodiment does not limit the numerical value of N.
- the method of processing the coordinate data in the X coordinate data storage sub-matrix exemplarily introduces the data preprocessing method of the initial point cloud data. For example, move the column coordinates in the X coordinate data storage submatrix to the right by one column, and store the first column coordinates in the initial point cloud data matrix, that is, the coordinate data in the X column coordinates, into the X coordinate data storage submatrix, and get Coordinate data after data adjustment.
- the coordinate data after data adjustment in the X coordinate data storage sub-matrix is sorted.
- the row data may be sorted in descending order to obtain sorted coordinate data.
- the beneficial effect of sorting the coordinate data in this embodiment is that the invalid coordinate data in the current matrix can be screened out according to the sorted coordinate data, and the reliability of the data is improved, thereby improving the accuracy of obstacle information identification.
- At least one column of data in the sorted coordinate data in the X coordinate data storage sub-matrix is acquired, for example, at least one column in the middle may be acquired, or at least one column may be randomly acquired.
- the column coordinate data of the middle preset column number of the X coordinate data storage sub-matrix can be selected, and the navigation coordinate mean value of each row coordinate data in the selected column coordinate data can be calculated, and the row coordinate mean value As the corresponding point cloud coordinates in the target point cloud coordinates.
- M is temporarily set to 10, which means the row mean value of the 11th column to the 20th column of the FSP_n_X calculation matrix.
- the method of data preprocessing is introduced by taking the X coordinate data storage sub-matrix as an example.
- the coordinate data in the Y coordinate data storage sub-matrix can also be processed in the same way. preprocessing.
- the data preprocessing process of the information in the second column of the FSP_n_XY matrix includes:
- M is temporarily set to 10, which means the row mean value of the 11th column to the 20th column of the FSP_n_X calculation matrix.
- the obstacle identification condition is used to identify the point cloud data in the above embodiments, and determine whether the object corresponding to the point cloud data is an obstacle.
- the obstacle information includes the number of obstacles, the number of obstacles, the number of boundary points of obstacles, the numbers of boundary points of obstacles, and the coordinates of boundary points of obstacles.
- the boundary point of the obstacle can be understood as the inflection point of the obstacle, that is, the point cloud scanned by the radar sensor during the scanning process around the vehicle.
- the obstacle identification conditions include the detection distance condition between the point cloud coordinates and the current vehicle, the first adjacent distance condition between the point cloud coordinates and the right adjacent point coordinates, the point cloud coordinates and the left adjacent point coordinates and The adjacent angle condition between the right adjacent point coordinates and the second adjacent distance condition between the point cloud coordinates and the right adjacent point coordinates.
- the distance between the point cloud coordinates and the right adjacent point is set to 0; if the current point cloud data is the leftmost end point , then there is no left adjacent point, then the distance between the point cloud coordinates and the left adjacent point is set to 0. Moreover, since the starting point and the ending point cannot form an included angle, set the adjacent included angle of the point cloud coordinates corresponding to FSP_90 and FSP_0 to 180°.
- the obstacle information of the obstacle within the preset range of the current vehicle is recognized based on the obstacle recognition condition and the point cloud coordinates respectively.
- the identification method for identifying obstacle information of obstacles within the preset range of the current vehicle includes: for any point cloud coordinates, if the distance between the current point cloud coordinates and the current vehicle meets the detection distance condition, then obtain the current point cloud coordinates and The current first adjacent distance between the right adjacent points of the current point cloud coordinates; if the current first adjacent distance does not meet the first adjacent distance condition, the number of obstacles, the number of obstacles, and the number of obstacles are accumulated. The number of boundary points is accumulated, the number of boundary points is accumulated, and the coordinates of the boundary points are determined based on the current point cloud coordinates.
- any point cloud coordinates scanned by the current vehicle obtain the current distance between the current point cloud coordinates and the vehicle, and then match the current distance with the preset detection distance condition. If the current distance meets the detection distance condition, that is, the distance is within the detection distance condition, it means that the point cloud data is within the identification range of the current vehicle to identify obstacles. For example, obtain the coordinates of the right adjacent point of the current point cloud coordinates, and obtain the current first adjacent distance between the coordinates of the right adjacent point, and then combine the current adjacent distance with the preset first adjacent distance condition to match.
- the current point cloud coordinates are determined as obstacle, and update the obstacle information of the obstacle.
- the current point is the starting point of the obstacle boundary, add 1 to the number of obstacles, add 1 to the obstacle number to record as the new target obstacle number, add 1 to the number of boundary points, and use the current point cloud coordinates as the coordinates of the boundary point.
- the current point cloud coordinates are the rightmost point cloud coordinates
- the default current first neighbor distance between the current point cloud coordinates and the right neighbor point is 0, that is, the current first neighbor distance does not conform to The preset first adjacent distance condition, and continue to execute the corresponding identification step that does not meet the first adjacent distance condition.
- the current first adjacent distance meets the first adjacent distance condition, then obtain the current adjacent angle between the current point cloud coordinates and the left adjacent point coordinates and right adjacent point coordinates of the current point cloud coordinates; If the current adjacent angle does not meet the adjacent angle conditions, match the current boundary point number of the obstacle with the preset number threshold; if the current boundary point number is within the preset number threshold range, then accumulate the boundary point numbers , and determine the boundary point coordinates; if the current boundary point number is not within the preset number threshold range, accumulate the number of obstacles, the number of obstacles, the number of boundary points, the number of boundary points, and determine the coordinates of the boundary point.
- the current first adjacent distance meets the first adjacent condition, that is, the distance between the right adjacent point of the current point cloud coordinates and the current point cloud coordinates is within the preset distance range
- Identify whether the current point cloud coordinates are obstacles For example, obtain the current adjacent angle between the current point cloud coordinates and the current point cloud coordinates of the adjacent point coordinates and the right adjacent point coordinates, and then use the current adjacent angle and the preset adjacent angle condition to match.
- the current adjacent angle does not meet the adjacent angle condition, that is, the angle of the current adjacent angle is not within the preset adjacent angle threshold range. If the current adjacent angle does not meet the adjacent angle condition, that is, the angle of the current adjacent angle is not within the preset adjacent angle threshold range, then obtain the boundary point number of the boundary point in the identified obstacle, And match the boundary point number with the preset number threshold, if the boundary point number is within the preset number threshold range, continue to accumulate the boundary point number, and determine the current point cloud coordinates as the corresponding to the new boundary point number Boundary point coordinates. On the contrary, if the boundary point number is not within the preset number threshold range, the current point cloud coordinates are determined as a new obstacle, and the obstacle information of the obstacle is updated.
- the current point is the starting point of the obstacle boundary
- add 1 to the number of obstacles add 1 to the obstacle number and record it as the new target obstacle number
- add 1 to the number of boundary points and use the current point cloud coordinates as the coordinates of the boundary point.
- the default angle between the current point cloud coordinates as the adjacent point coordinates and the right adjacent point coordinates is 180° , that is, the current adjacent included angle does not meet the preset adjacent included angle condition, and continue to execute the corresponding identification step that does not meet the adjacent included angle condition.
- the current second adjacent distance between the current point cloud coordinates and the left adjacent point of the current point cloud coordinates is obtained; if the current second adjacent distance does not meet the For the second adjacent condition, the number of the boundary point is accumulated; if the current second adjacent distance meets the second adjacent condition, and it is determined that the identification of the current point cloud data is completed, then traverse other point cloud coordinates, and the identified obstacle.
- the number of obstacles, obstacle numbers, number of boundary points, number of boundary points, and coordinates of boundary points are stored.
- the current adjacent angle meets the adjacent angle condition, that is, the angle of the current adjacent angle is within the preset adjacent angle threshold range
- identify whether the current point cloud coordinates are obstacles based on other obstacle identification conditions thing For example, obtain the coordinates of the left adjacent point of the current point cloud coordinates, and obtain the current second adjacent distance between the coordinates of the left adjacent point, and then combine the current adjacent distance with the preset second adjacent distance condition to match. If the current second adjacent distance does not meet the second adjacent condition, that is, the distance between the right adjacent point of the current point cloud coordinates and the current point cloud coordinates is not within the preset distance range, then obtain the recognized obstacle The boundary point number of the middle boundary point, and add 1 to the boundary point number.
- the current second adjacent distance meets the second adjacent condition, and there are other obstacle identification conditions, it is identified whether the current point cloud coordinates are obstacles based on other obstacle identification conditions. For example, if the current second adjacent distance meets the second adjacent condition and there is no other obstacle identification condition, it is determined that the current point cloud data identification ends.
- the current point cloud coordinates are the leftmost point cloud coordinates
- the default current second adjacent distance between the current point cloud coordinates and the left adjacent point is 0, that is, the current second adjacent distance does not conform to The preset second adjacent distance condition, and continue to execute the corresponding identification step that does not meet the second adjacent distance condition.
- point cloud data is identified based on the above identification conditions, and the number of obstacles, obstacle numbers, number of boundary points, number of boundary points, and coordinates of boundary points of the recognized obstacles are stored.
- the obstacle information of the current frame can be stored in the obstacle information matrix.
- the matrix size of the obstacle matrix is initially set to 30x7.
- each row represents the corresponding information of the obstacle of the current number;
- the first column represents The number ID of the obstacle, the second column represents the number of boundary points of the corresponding obstacle, and the third to seventh columns represent the information ID of multiple boundary points.
- the obstacle information is shown in the following table:
- the vehicle controller can complete the obstacle avoidance function of the vehicle according to the obstacle information provided by the embodiment of the present application.
- the technical solution of this embodiment obtains at least one point cloud data within the preset range of the current vehicle; wherein, the point cloud data includes the point cloud coordinates in the local coordinate system with the current vehicle as the origin; thereby obtaining more accurate radar data for automatic Provide necessary information for driving the vehicle to decelerate to avoid obstacles and plan paths around obstacles; obtain at least one obstacle recognition condition, and based on the obstacle recognition condition and point cloud coordinates, identify the obstacle information of the obstacle within the preset range of the current vehicle; , the obstacle recognition conditions include the detection distance condition between the point cloud coordinates and the current vehicle, the first adjacent distance condition between the point cloud coordinates and the right adjacent point coordinates, the point cloud coordinates and the left adjacent point coordinates and the right adjacent point coordinates respectively The adjacent angle condition between the adjacent point coordinates and the second adjacent distance condition between the point cloud coordinates and the right adjacent point coordinates; identify the scanned point cloud data through multiple obstacle identification conditions, and determine Obstacle information around the vehicle improves the accuracy of obstacle recognition, thereby improving the safety of vehicle driving.
- Fig. 3 is a flow chart of a method for determining obstacle information provided by another embodiment of the present application.
- this embodiment in the step of "identifying obstacles within the preset range of the current vehicle "Information” is followed by the addition of “acquire the global coordinate system, and based on the boundary point coordinates of the boundary point of the obstacle in the local coordinate system and the preset coordinate transformation method, determine the global boundary point coordinates of the boundary point in the global coordinate system" which is the same as Explanations of terms that are the same as or corresponding to the above multiple embodiments are not repeated here.
- the method for determining obstacle information provided in this embodiment includes:
- the appearance of obstacles will prevent the current vehicle from traveling according to the original planned route, but if the current vehicle bypasses the obstacle by modifying the original planned route, it can also continue to drive.
- the coordinate position of the obstacle needs to be determined to assist the current vehicle in detour route planning.
- the coordinate position of the obstacle is determined to be the coordinate position of the obstacle in the global coordinate system where the current route is located, not the coordinate position in the local coordinate system where the current vehicle is located.
- the method for obtaining the coordinate position of the obstacle in the global coordinate system may include: obtaining the global coordinate system, and based on the boundary point coordinates of the boundary point of the obstacle in the local coordinate system and the preset coordinate conversion method, determine that the boundary point is at The global boundary point coordinates in the global coordinate system.
- the global coordinate system can be based on the starting point of the vehicle's driving route where the current vehicle is located, with the initial driving direction of the vehicle as the positive direction of the X-axis, and with the vehicle's initial The left side when driving is the positive direction of the Y axis.
- the positive direction of the X-axis and the positive direction of the Y-axis of the global coordinate system are both the same.
- the local coordinate system where the current vehicle is located respectively determine the horizontal and vertical distances between the origin of the local coordinate system and the origin of the global coordinate system, and the X-axis direction of the local coordinate system and the X-axis of the global coordinate system The direction angle between directions.
- a coordinate conversion method between the local coordinate system and the global coordinate system is determined based on the above-mentioned horizontal distance, vertical distance and direction angle.
- the global boundary point coordinates of the boundary point in the global coordinate system are determined based on the boundary point coordinates of the boundary point of the obstacle in the local coordinate system and a preset coordinate conversion method.
- the conversion method of the boundary point 2 in FIG. 4 is taken as an example to determine the conversion steps of the boundary point in the local coordinate system and the global coordinate system.
- the coordinate information of the boundary point 2 of the obstacle recognized in the local coordinate system is (x2, y2).
- the vehicle is displaced along the positive direction of the X-axis as b, and along the positive direction of the Y-axis is a, the turned angle is ⁇ , and the coordinate conversion calculation is performed based on the coordinate conversion method determined above.
- the coordinate transformation formula is as follows:
- the coordinate information conversion of the boundary point 2 is completed based on the above expression, that is, in the global coordinate system XY-O, the coordinates of the boundary point 2 are (X_2, Y_2).
- the boundary point type of the boundary point is determined.
- the boundary point is determined to be a static boundary point, and the obstacle information is filled into the static boundary point information matrix in the global coordinate system; on the contrary, if the global coordinate difference is not within the preset If the coordinate threshold is within the boundary point, it is determined that the boundary point is a dynamic boundary point, and the obstacle information is filled into the dynamic boundary point information matrix in the global coordinate system.
- the boundary point type is a dynamic boundary point
- update the global boundary point coordinates of the boundary point in real time and update the current vehicle's driving trajectory in real time based on the real-time updated boundary point until the boundary point is not within the detection distance condition range, or the current vehicle Detour around the boundary point
- the boundary point type is a static boundary point
- the current vehicle's driving trajectory is determined based on the boundary point until the boundary point is not within the detection distance condition range, or the current vehicle detours through the boundary point.
- the vehicle controller cancels the obstacle detour
- the obstacle information conversion is no longer performed, and the current vehicle continues to drive according to the predetermined driving route.
- the technical solution of this embodiment obtains at least one point cloud data within the preset range of the current vehicle; wherein, the point cloud data includes the point cloud coordinates in the local coordinate system with the current vehicle as the origin; thereby obtaining more accurate radar data for automatic Provide necessary information for driving the vehicle to decelerate to avoid obstacles and plan paths around obstacles; obtain at least one obstacle recognition condition, and based on the obstacle recognition condition and point cloud coordinates, identify the obstacle information of the obstacle within the preset range of the current vehicle; , the obstacle recognition conditions include the detection distance condition between the point cloud coordinates and the current vehicle, the first adjacent distance condition between the point cloud coordinates and the right adjacent point coordinates, the point cloud coordinates and the left adjacent point coordinates and the right adjacent point coordinates respectively The adjacent angle condition between the adjacent point coordinates and the second adjacent distance condition between the point cloud coordinates and the right adjacent point coordinates; identify the scanned point cloud data through multiple obstacle identification conditions, and determine Obstacle information around the vehicle improves the accuracy of obstacle recognition, thereby improving the safety of vehicle driving.
- the following is an embodiment of the obstacle information determination device provided by the embodiment of the present application.
- This device belongs to the same application concept as the obstacle information determination method of the above-mentioned multiple embodiments, and is not described in detail in the embodiments of the obstacle information determination device. For details, reference may be made to the above embodiment of the method for determining obstacle information.
- Fig. 5 is a schematic structural diagram of an obstacle information determination device provided by an embodiment of the present application. This embodiment can be applied to the situation of determining obstacles around the vehicle when the vehicle is driving automatically; it is more suitable for situations where the camera is not used or the camera is damaged and the function is limited. When determining the situation of obstacles around the vehicle.
- the structure of the obstacle information determination device includes: a point cloud data acquisition module 310 and an obstacle information identification module 320; wherein,
- the point cloud data acquisition module 310 is configured to acquire at least one point cloud data within the preset range of the current vehicle; wherein, the point cloud data includes point cloud coordinates in a local coordinate system with the current vehicle as the origin;
- the obstacle information identification module 320 is configured to obtain at least one obstacle identification condition, and based on the obstacle identification condition and the point cloud coordinates, identify the obstacle information of the obstacle within the preset range of the current vehicle; wherein,
- the obstacle identification conditions include the detection distance condition between the point cloud coordinates and the current vehicle, the first adjacent distance condition between the point cloud coordinates and the right adjacent point coordinates, the point cloud coordinates and the left adjacent point coordinates respectively The adjacent angle condition between the coordinates and the right adjacent point coordinates and the second adjacent distance condition between the point cloud coordinates and the right adjacent point coordinates.
- the technical solution of this embodiment obtains at least one point cloud data within the preset range of the current vehicle; wherein, the point cloud data includes the point cloud coordinates in the local coordinate system with the current vehicle as the origin; thereby obtaining more accurate
- the radar data provides the necessary information for the automatic driving vehicle to decelerate and avoid obstacles, and plan the path around obstacles; obtain at least one obstacle recognition condition, and based on the obstacle recognition condition and the point cloud coordinates, identify the current vehicle preset Obstacle information of obstacles within the range; wherein, the obstacle recognition condition includes the detection distance condition between the point cloud coordinates and the current vehicle, the first adjacent distance between the point cloud coordinates and the coordinates of the right adjacent point Condition, the adjacent angle condition between the point cloud coordinates and the left adjacent point coordinates and the right adjacent point coordinates, and the second adjacent distance condition between the point cloud coordinates and the right adjacent point coordinates; through multiple obstacles
- the object recognition conditions are used to recognize the scanned point cloud data, determine the obstacle information around the vehicle, and improve the accuracy of obstacle recognition, thereby improving the
- the obstacle information includes the number of obstacles, the number of obstacles, the number of boundary points of the obstacles, the numbers of the boundary points of the obstacles, and the coordinates of the boundary points of the obstacles.
- the point cloud data acquisition module 310 includes:
- the initial point cloud coordinate acquisition unit is configured to scan the preset range of the current vehicle based on the preset radar sensor, and acquire the initial point cloud coordinates in the scanning result;
- the target point cloud coordinate acquisition unit is configured to perform data preprocessing on the initial point cloud coordinates to obtain target point cloud coordinates within the preset range of the current vehicle.
- the target point cloud coordinate acquisition unit includes:
- the coordinate adjustment matrix acquisition subunit is configured to acquire a preset coordinate storage matrix, shift the column coordinate data in the preset coordinate storage matrix to the right by one column, and store the corresponding column coordinate data in the initial point cloud coordinates in the The first column of the preset coordinate storage matrix is obtained to obtain the coordinate adjustment matrix;
- the coordinate sorting matrix acquisition subunit is configured to sort the coordinate data in the coordinate adjustment matrix according to a preset sorting rule to obtain a coordinate sorting matrix
- the point cloud coordinate acquisition subunit is configured to acquire at least two columns of coordinate data in the coordinate sorting matrix, determine the row coordinate mean value of the row coordinate data in the at least two column coordinate data, and use the row coordinate mean value as the target The corresponding point cloud coordinates in the point cloud coordinates.
- the obstacle information identification module 320 includes:
- the current first adjacent distance acquiring unit is configured to obtain the distance between the current point cloud coordinates and the current vehicle if the distance between the current point cloud coordinates and the current vehicle meets the detection distance condition for any point cloud coordinates.
- the first obstacle information acquisition unit is configured to: if the current first adjacent distance does not meet the first adjacent distance condition, then accumulate the obstacle number of the obstacle, the obstacle number, and the Accumulate the number of boundary points and the number of the boundary points, and determine the coordinates of the boundary points based on the current point cloud coordinates.
- the obstacle information identification module 320 includes:
- the current adjacent angle acquisition unit is configured to obtain the left adjacent points of the current point cloud coordinates and the current point cloud coordinates respectively if the current first adjacent distance meets the first adjacent distance condition The current adjacent angle between the coordinates and the coordinates of the right adjacent point;
- the second obstacle information acquisition unit is configured to match the current boundary point number of the obstacle with a preset number threshold if the current adjacent angle does not meet the adjacent angle condition; If the number of the current boundary point is within the preset number threshold range, the number of the boundary point is accumulated, and the coordinates of the boundary point are determined; if the number of the current boundary point is not within the preset number threshold range, the Accumulating the number of obstacles, accumulating the number of obstacles, accumulating the number of boundary points, accumulating the number of the boundary points, and determining the coordinates of the boundary points.
- the obstacle information identification module 320 includes:
- the current second adjacent distance acquisition unit is configured to obtain the distance between the current point cloud coordinates and the left adjacent point of the current point cloud coordinates if the current adjacent angle meets the adjacent angle condition.
- the third obstacle information acquisition unit is configured to accumulate the numbers of the boundary points if the current second adjacent distance does not meet the second adjacent condition
- the obstacle information storage unit is configured to traverse other point cloud coordinates and store the identified obstacles if the current second adjacent distance meets the second adjacent condition and it is determined that the identification of the current point cloud data ends.
- the number of obstacles, the number of obstacles, the number of boundary points, the number of boundary points and the coordinates of boundary points are stored.
- the device includes:
- the global boundary point coordinate determination module is configured to obtain the global coordinate system after identifying the obstacle information of the obstacle within the preset range of the current vehicle, and based on the boundary point coordinates of the boundary point of the obstacle in the local coordinate system And a preset coordinate conversion method, determining the global boundary point coordinates of the boundary point in the global coordinate system;
- the boundary point type determination module is configured to respectively determine the global boundary point coordinates within the preset range of the current vehicle at the next moment, and based on the global coordinates between the global boundary point coordinates at the current moment and the global boundary point coordinates at the next moment.
- the boundary point type of the boundary point is determined from the comparison result of the difference with the preset coordinate threshold.
- the boundary point types include dynamic boundary points and dynamic boundary points
- the unit also includes:
- the first driving track update module is configured to update the global boundary point coordinates of the boundary point in real time if the boundary point type is a dynamic boundary point after determining the boundary point type of the boundary point, and based on the real-time updated
- the boundary point updates the driving trajectory of the current vehicle in real time until the boundary point is not within the range of the detection distance condition, or the current vehicle detours through the boundary point;
- the second driving trajectory update module is configured to determine the current vehicle's driving trajectory based on the boundary point after determining the boundary point type of the boundary point, if the boundary point type is a static boundary point, until the The boundary point is not within the range of the detection distance condition, or the current vehicle detours through the boundary point.
- the obstacle information determining device provided in the embodiment of the present application can execute the obstacle information determining method provided in any embodiment of the present application, and has corresponding functional modules and beneficial effects for executing the method.
- the multiple units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized;
- the specific names of multiple functional units are only for the convenience of distinguishing each other, and are not used to limit the protection scope of the present application.
- FIG. 6 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.
- FIG. 6 shows a block diagram of an exemplary electronic device 12 suitable for implementing embodiments of the present application.
- the electronic device 12 shown in FIG. 6 is only an example, and should not limit the functions and scope of use of the embodiment of the present application.
- electronic device 12 takes the form of a general computing electronic device.
- Components of electronic device 12 may include, but are not limited to, one or more processors or processing units 16, system memory 28, bus 18 connecting various system components including system memory 28 and processing unit 16.
- Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus structures.
- bus structures include, by way of example, but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect ( PCI) bus.
- ISA Industry Standard Architecture
- MAC Micro Channel Architecture
- VESA Video Electronics Standards Association
- PCI Peripheral Component Interconnect
- Electronic device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by electronic device 12 and include both volatile and nonvolatile media, removable and non-removable media.
- System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and/or cache memory 32 .
- Electronic device 12 may include other removable/non-removable, volatile/nonvolatile computer system storage media.
- storage system 34 may be configured to read and write to non-removable, non-volatile magnetic media (not shown in FIG. 6, commonly referred to as a "hard drive”).
- a disk drive for reading and writing to removable nonvolatile disks e.g., "floppy disks”
- removable nonvolatile optical disks e.g., CD-ROM, DVD-ROM. or other optical media
- each drive may be connected to bus 18 via one or more data media interfaces.
- the system memory 28 may include at least one program product having a set (eg, at least one) of program modules configured to perform the functions of the embodiments of the present application.
- Program/utility 40 may be stored, for example, in system memory 28 as a set (at least one) of program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include the realization of the network environment.
- the program modules 42 generally perform the functions and/or methods of the embodiments described herein.
- the electronic device 12 may also communicate with one or more external devices 14 (e.g., a keyboard, pointing device, display 24, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 12, and/or communicate with Any device (eg, network card, modem, etc.) that enables the electronic device 12 to communicate with one or more other computing devices. Such communication may occur through input/output (I/O) interface 22 .
- the electronic device 12 can also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN) and/or a public network such as the Internet) through the network adapter 20 . As shown in FIG. 6 , network adapter 20 communicates with other modules of electronic device 12 via bus 18 .
- the processing unit 16 executes a variety of functional applications and sample data acquisition by running the program stored in the system memory 28, for example, implementing the steps of a method for determining obstacle information provided in the embodiment of the present invention.
- the method for determining obstacle information includes:
- the point cloud data includes point cloud coordinates in a local coordinate system with the current vehicle as the origin;
- the obstacle identification condition includes a point cloud
- processor can also implement the technical solution of the sample data acquisition method provided in any embodiment of the present application.
- This embodiment provides a computer-readable storage medium, on which a computer program is stored.
- the program is executed by a processor, for example, the steps of a method for determining obstacle information provided in the embodiment of the present invention are realized.
- Obstacle information determination Methods include:
- the point cloud data includes point cloud coordinates in a local coordinate system with the current vehicle as the origin;
- the obstacle identification condition includes a point cloud
- the computer storage medium in the embodiments of the present application may use any combination of one or more computer-readable media.
- the computer readable medium may be a computer readable signal medium or a computer readable storage medium.
- a computer-readable storage medium may be, for example but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination thereof. More specific examples (non-exhaustive list) of computer readable storage media include: electrical connections with one or more leads, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), Erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
- a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
- the computer readable storage medium may be a non-transitory computer readable
- a computer readable signal medium may include a data signal carrying computer readable program code in baseband or as part of a carrier wave. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
- a computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. .
- Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
- Computer program codes for performing the operations of the present application may be written in one or more programming languages or combinations thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional Procedural Programming Language - such as "C" or a similar programming language.
- the program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server.
- the remote computer can be connected to the user computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (such as through the Internet using an Internet service provider). connect).
- LAN local area network
- WAN wide area network
- connect such as AT&T, MCI, Sprint, EarthLink, MSN, GTE, etc.
- the above-mentioned multiple modules or multiple steps of the present application can be realized by general-purpose computing devices, and they can be concentrated on a single computing device, or distributed on a network formed by multiple computing devices , for example, they can be implemented with executable program codes of computer devices, so that they can be stored in storage devices and executed by computing devices, or they can be made into a plurality of integrated circuit modules respectively, or a plurality of them can be Modules or steps are implemented as a single integrated circuit module.
- the application is not limited to any specific combination of hardware and software.
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
Abstract
本申请实施例公开了一种障碍物信息确定方法、装置、电子设备以及存储介质。该方法包括:获取当前车辆预设范围内的至少一个点云数据;其中,所述点云数据包括以所述当前车辆为原点的局部坐标系下的点云坐标;获取至少一个障碍物识别条件,并基于所述障碍物识别条件以及所述点云坐标,识别所述当前车辆预设范围内障碍物的障碍物信息;其中,所述障碍物识别条件包括点云坐标与所述当前车辆之间的检测距离条件、点云坐标与右相邻点坐标之间的第一相邻距离条件、点云坐标分别与左相邻点坐标和右相邻点坐标之间的相邻夹角条件和点云坐标与右相邻点坐标之间的第二相邻距离条件。
Description
本申请要求在2022年1月26日提交中国专利局、申请号为202210091407.4的中国专利申请的优先权,该申请的全部内容通过引用结合在本申请中。
本申请实施例涉及智能驾驶技术领域,例如涉及一种障碍物信息确定方法、装置、电子设备以及存储介质。
随着汽车工业的快速发展和人们生活水平的不断提高,汽车已快速进入普通家庭。车辆行驶安全问题受到人们越来越广泛的关注。
目前在行车过程中,常常是驾驶员直接观察车辆周围障碍物,或者是驾驶员通过观察车门后视镜确定车辆左右两侧的障碍物,然后车辆按照驾驶员的指示行驶,而这种人为确定方式易受驾驶员主观经验或环境因素的影响,车辆行驶的安全性较低。
发明内容
本申请提供一种障碍物信息确定方法、装置、电子设备以及存储介质,以实现提高车辆周围障碍物确定的准确性,从而提高车辆驾驶的安全性。
第一方面,本申请实施例提供了一种障碍物信息确定方法,该方法包括:
获取当前车辆预设范围内的至少一个点云数据;其中,所述点云数据包括以所述当前车辆为原点的局部坐标系下的点云坐标;
获取至少一个障碍物识别条件,并基于所述障碍物识别条件以及所述点云坐标,识别所述当前车辆预设范围内障碍物的障碍物信息;其中,所述障碍物识别条件包括点云坐标与所述当前车辆之间的检测距离条件、点云坐标与右相邻点坐标之间的第一相邻距离条件、点云坐标分别与左相邻点坐标和右相邻点坐标之间的相邻夹角条件和点云坐标与右相邻点坐标之间的第二相邻距离条件。
第二方面,本申请实施例还提供了一种障碍物信息确定装置,该装置包括:
点云数据获取模块,设置为获取当前车辆预设范围内的至少一个点云数据;其中,所述点云数据包括以所述当前车辆为原点的局部坐标系下的点云坐标;
障碍物信息识别模块,设置为获取至少一个障碍物识别条件,并基于所述障碍物识别条件以及所述点云坐标,识别所述当前车辆预设范围内障碍物的障碍物信息;其中,所述障碍物识别条件包括点云坐标与所述当前车辆之间的检测距离条件、点云坐标与右相邻点坐标之间的第一相邻距离条件、点云坐标分别与左相邻点坐标和右相邻点坐标之间的相邻夹角条件和点云坐标与右相邻点坐标之间的第二相邻距离条件。
第三方面,本申请实施例还提供了一种电子设备,所述电子设备包括:
一个或多个处理器;
存储装置,设置为存储一个或多个程序,
当所述一个或多个程序被所述一个或多个处理器执行,使得所述一个或多个处理器实现如本申请任意实施例提供的障碍物信息确定方法。
第四方面,本申请实施例还提供了一种计算机可读存储介质,其上存储有计算机程序,该程序被处理器执行时实现本申请任意实施例提供的障碍物信息确定方法。
图1是本申请一实施例提供的障碍物信息确定方法的流程示意图;
图2是本申请另一实施例提供的障碍物信息确定方法的流程示意图;
图3是本申请另一实施例提供的障碍物信息确定方法的流程示意图;
图4是本申请另一实施例提供的障碍物信息确定方法的流程示意图;
图5是本申请一实施例提供的障碍物信息确定装置的结构示意图;
图6为本申请一实施例提供的电子设备的结构示意图。
图1为本申请实施例提供的一种障碍物信息确定方法的流程图,本实施例可适用于车辆自动驾驶时确定车辆周围障碍物的情况;更适用于不通过摄像头或在摄像头损坏、功能受限时确定车辆周围障碍物的情况。该方法可以由障碍物信息确定装置来执行,该装置可以由软件和/或硬件的方式来实现。
在对本申请实施例的技术方案进行介绍之前,先对实施本实施例的技术方案的应用场景进行示例性的介绍。当然,下述应用场景只是作为可选应用场景,本实施例的还可以在其他应用场景进行实施,本实施例对实施的技术方法的应用场景不加以限制。例如,应用场景包括:目前在行车过程中,常常是驾驶员直接观察车辆周围障碍物,或者是驾驶员通过观察车门后视镜确定车辆左右两侧的障碍物,然后车辆按照驾驶员的指示行驶,而这种人为确定方式易受驾驶员主观经验或环境因素的影响,车辆行驶的安全性较低。并且在自动驾驶过程中大多基于安装在车辆周身的摄像头获取车辆周围的障碍物信息,但是摄像头会存在损坏以及功能受限的情况,导致车辆控制器不能获取到车辆周围的障碍物信息,从而导致车辆自动驾驶存在较大的安全风险。
本实施例中的技术方案通过获取到的雷达数据计算得到自动驾驶车辆周围障碍物状态信息,为自动驾驶车辆减速避障、障碍物绕行规划路径提供必要信息。
基于上述技术思路,本实施例的技术方案通过获取当前车辆预设范围内的至少一个点云数据;其中,点云数据包括以当前车辆为原点的局部坐标系下的点云坐标;从而得到更加准确雷达数据为自动驾驶车辆减速避障、障碍物绕行规划路径提供必要信息;获取至少一个障碍物识别条件,并基于障碍物识别条件以及点云坐标,识别当前车辆预设范围内障碍物的障碍物信息;其中,障碍物识别条件包括点云坐标与当前车辆之间的检测距离条件、点云坐标与右相邻点坐标之间的第一相邻距离条件、点云坐标分别与左相邻点坐标和右相邻点坐标之间的相邻夹角条件和点云坐标与右相邻点坐标之间的第二相邻距离条件;通过多个障碍物识别条件对扫描到的点云数据进行识别,确定车辆周围的障碍物信息,实现了提高障碍物识别的准确性,从而提高车辆驾驶的安全性。
如图1所示,该方法包括以下步骤:
S110、获取当前车辆预设范围内的至少一个点云数据。
在本实施例中,可以是基于多种雷达检测装置对车辆周围进行检测,从而获取车辆周围预设范围内的点云数据。
例如,获取点云数据的方法可以包括:基于预设雷达传感器对当前车辆的预设范围进行扫描,并获取扫描结果中的初始点云坐标。
其中,预设雷达传感器在当前车辆上的安装位置决定了传感器障碍检测的感知范围和能力,为了尽可能的减少遮挡、增大激光雷达的探测范围。例如,可以选择将其安装在当前车辆的车顶上方或者车底。上述雷达传感器的安装位置只是示例性的安装位置,本实施例对雷达传感器的安装位置不加以限制。预设雷达传感器的类型可以是激光雷达、车辆毫米波雷达,当然还可以是其他类型雷达传感器。
例如,基于雷达传感器不间断地对车辆周围进行扫描,并实时将扫描的点云数据进行存储。雷达传感器的扫描角度可以是360度,当然也可以根据当前车辆所处的环境对扫描的角度进行实时设置。本实施例中,存储的点云数据可以包括以当前车辆为原点的局部坐标系下的点云坐标。
示例性的如图2所示,以当前车辆前方±45°的点云信息为例,点云数据的数据密度以每1度为间隔,依次定义每条点云数据的名称为FSP_0~90。每条点云数据包可以包括基于当前车辆所在局部坐标系的(X,Y)坐标信息。例如,局部坐标系的原点为当前车辆的中心点,X正方向为当前车辆行驶的方向、Y方向当前车辆的左侧方向。
因为雷达扫描的初始点云数据会存在单帧误报或多帧抖动的情况,所以在基于该初始点云数据进行障碍物信息识别之前,需要进行对该初始点云数据进行数据预处理,以尽可能消除这些偶然因素,从而实现提高障碍物信息识别的准确性。所以,本实施例的技术方案还在获取到雷达传感器扫描的初始点云数据之后,对初始点云坐标进行数据预处理,得到当前车辆预设范围内的目标点云坐标。
例如,对初始点云数据进行数据预处理的方法可以包括:获取预设坐标存储矩阵,将预设坐标存储矩阵中的列坐标数据右移一列,并将初始点云坐标中对应的列坐标数据存储于预设坐标存储矩阵的第一列,得到坐标调整矩阵;按预设排序规则对坐标调整矩阵中的坐标数据进行排序,得到坐标排序矩阵;获取坐标排序矩阵中的至少两列坐标数据,确定至少两列坐标数据中行坐标数据的行坐标均值,并将行坐标均值作为目标点云坐标中对应的点云坐标。
本实施例中以上述90个点云数据为例对数据预处理方法进行示例性的介绍。例如,读取当前时刻下当前车辆FSP_0~FSP_90的初始点云数据,并将该初始点云数据存储于新建的初始点云数据矩阵中。其中,该初始点云数据矩阵的矩阵名称可以是FSP_n_XY,矩阵为90×2的坐标矩阵。例如,FSP_n_XY中的初始坐标数据信息如下表所示:
表1初始坐标数据信息表
FSP_0_X | FSP_0_Y |
FSP_1_X | FSP_1_Y |
… | … |
FSP_90_X | FSP_90_Y |
本实施例预处理方法为了避免在剔除单帧误报的同时,平稳多帧抖动情况,所以需要遵循误差产生及分布遵循正态分布的原理,从而通过中位均值滤波来剔除误差点。
在对数据进行预处理之前,预先建立数据存储矩阵,用于存储之前时刻进行数据预处理后的点云数据。例如,为了方便同时对坐标数据中的X坐标数据和Y坐标数据进行数据,本实施例将数据存储矩阵划分为X坐标数据存储子矩阵和Y坐标数据存储子矩阵。例如,X坐标数据存储子矩阵的矩阵名称可以是FSP_save_X,Y坐标数据存储子矩阵的矩阵名称可以是FSP_save_Y。以X坐标数据存储子矩阵为例介绍数据存储矩阵的大小,X坐标数据存储子矩阵的矩阵大小为90×N的矩阵,此处N的大小为中位均值滤波关键。为了保证数据预处理后的及时性与准确性,原则上N值最小不低于10,最大不超过50;示例性的,本实施例的技术方案中可以暂取N为30,当然N还可以去其他的数值,本实施例对N的数值不加以限制。
同样的以对X坐标数据存储子矩阵中的坐标数据进行处理的方法示例性的介绍初始点云数据的数据预处理方法。例如,将X坐标数据存储子矩阵中的列坐标向右移动一列,并将初始点云数据矩阵中第一列坐标,即X列坐标中的坐标数据存储到X坐标数据存储子矩阵中,得到数据调整后的坐标数据。
例如,对X坐标数据存储子矩阵中数据调整后的坐标数据进行排序。例如,对于每一行数据,可以按从大到小的顺序将行数据进行排序,得到排序后的坐标数据。本实施例中对坐标数据进行排序的有益效果在于可以根据排序后的坐标数据对当前矩阵中的无效坐标数据进行筛除,提高数据的可靠性,从而提高障碍物信息识别的准确性。
例如,获取X坐标数据存储子矩阵中排序后的坐标数据中至少一列数据,例如,获取的方式可以是获取中间的至少一列,也可以是随机获取至少一列。本实施例中为了得到可靠的数据,可以选取X坐标数据存储子矩阵的中间预设列数的列坐标数据,计算选取的列坐标数据中每一行坐标数据的航坐标均值,并将行坐标均值作为目标点云坐标中对应的点云坐标。
示例性的,以介绍预处理FSP_n_XY矩阵矩阵第一列信息为例:
1)对于当前帧的坐标数据,将FSP_save_X矩阵中的的列数据向右移一列,并将第一列数据置为0。
2)将FSP_n_XY矩阵中第一列的坐标数据存储填入FSP_save_X矩阵的第一列当中,完成数据更新输入。
3)将FSP_save_X矩阵中每一行坐标数据按从大到小或从小到大顺序排列,按大小顺序填入计算矩阵FSP_n_X当中。本实施例中对坐标数据的排序作用是为了便于筛除无效坐标数据,将排序后的数据存储至FSP_n_X矩阵的作用是将区分出已筛选的数据与未筛选的数据。
4)取FSP_n_X矩阵的中间M列的每一行坐标数据的行坐标均值,并对应填入FSP_n_XY矩阵的第一列当中。M值的大小关系到预处理数据的稳定性和及时性,本方案暂取M为10,既取FSP_n_X计算矩阵的第11列到第20列的行均值。
5)完成当前帧的FSP_n_XY矩阵的第一列信息预处理,并将处理后的数据更新到FSP_save_X矩阵中,便于对后续帧的数据进行预处理。
需要说明的是,本实施例中以X坐标数据存储子矩阵为例对数据预处理的方法进行了介绍,本实施例中还可以同样的方法对Y坐标数据存储子矩阵中的坐标数据进行数据预处理。
示例性的,FSP_n_XY矩阵矩阵第二列信息的数据预处理过程包括:
1)对于当前帧的坐标数据,将FSP_save_Y矩阵中的的列数据向右移一列,并将第一列数据置为0。
2)将FSP_n_XY矩阵中第二列的坐标数据存储填入FSP_save_Y矩阵的第一列当中,完 成数据更新输入。
3)将FSP_save_Y矩阵中每一行坐标数据按从大到小或从小到大顺序排列,按大小顺序填入计算矩阵FSP_n_Y当中。本实施例中对坐标数据的排序作用是为了便于筛除无效坐标数据,将排序后的数据存储至FSP_n_Y矩阵的作用是将区分出已筛选的数据与未筛选的数据。
4)取FSP_n_Y矩阵的中间M列的每一行坐标数据的行坐标均值,并对应填入FSP_n_XY矩阵的第二列当中。M值的大小关系到预处理数据的稳定性和及时性,本方案暂取M为10,既取FSP_n_X计算矩阵的第11列到第20列的行均值。
5)完成当前帧的FSP_n_XY矩阵的第二列信息预处理,并将处理后的数据更新到FSP_save_Y矩阵中,便于对后续帧的数据进行预处理。
S120、获取至少一个障碍物识别条件,并基于障碍物识别条件以及点云坐标,识别当前车辆预设范围内障碍物的障碍物信息。
本实施例中,障碍物识别条件用于对上述实施例中的点云数据识别,并确定该点云数据对应的目标是否为障碍物。
在本实施例中,障碍物信息包括障碍物数量、障碍物编号、障碍物的边界点数量、障碍物的边界点编号以及障碍物的边界点坐标。其中,障碍物的边界点可以理解为障碍物的拐点,即雷达传感器对车辆周围进行扫描过程中扫描到的点点云。
障碍物识别条件的数量为多个,从而可以保证识别结果的准确性。例如,障碍物识别条件包括点云坐标与当前车辆之间的检测距离条件、点云坐标与右相邻点坐标之间的第一相邻距离条件、点云坐标分别与左相邻点坐标和右相邻点坐标之间的相邻夹角条件和点云坐标与右相邻点坐标之间的第二相邻距离条件。
值得注意的是,若当前点云坐标为最右起始点,则无右相邻点,则将该点云坐标与右相邻点的距离设置为0;若当前点云数据为最左结尾点,则无左相邻点,则将该点云坐标与左相邻点的距离设置为0。并且,因为起始点与结尾点无法构成夹角,所以设定FSP_90、FSP_0分别对应的点云坐标的相邻夹角为设置为180°。
例如,在获取到障碍物识别条件之后,分别基于障碍物识别条件以及点云坐标,识别当前车辆预设范围内障碍物的障碍物信息。
例如,识别当前车辆预设范围内障碍物的障碍物信息的识别方法包括:对于任一点云坐标,若当前点云坐标与当前车辆之间的距离符合检测距离条件,则获取当前点云坐标与当前点云坐标的右相邻点之间的当前第一相邻距离;若当前第一相邻距离不符合第一相邻距离条件,则将障碍物的障碍物数量累加、障碍物编号累加、边界点数量累加、边界点编号累加,并基于当前点云坐标确定边界点坐标。
例如,获取当前车辆扫描到的任一点云坐标,获取当前点云坐标与车辆之间的当前距离,之后将该当前距离与预设的检测距离条件进行匹配。若该当前距离符合检测距离条件,即该距离在检测距离条件内,则说明该点云数据在当前车辆识别障碍物的识别范围内。例如,获取当前点云坐标的右相邻点坐标,并获取与右相邻点坐标之间的当前第一相邻距离,之后将当前的以相邻距离与预设的第一相邻距离条件进行匹配。若当前第一相邻距离不符合第一相邻条件,即当前点云坐标的右相邻点与当前点云坐标之间的距离大小不在预设距离范围内,则将当前点云坐标确定为障碍物,并更新障碍物的障碍物信息。例如,当前点为障碍物边界的起始点,将障碍物数量累加1,障碍物编号加1记为新目标障碍物编号,边界点数累加1, 并将当前点云坐标作为边界点的坐标。
需要说明的是,若当前点云坐标为最右侧点云坐标,则默认当前点云坐标与右相邻点之间的当前第一相邻距离为0,即当前第一相邻距离不符合预设的第一相邻距离条件,并继续执行不符合第一相邻距离条件对应的识别步骤。
例如,若当前第一相邻距离符合第一相邻距离条件,则获取当前点云坐标分别与当前点云坐标的左相邻点坐标和右相邻点坐标之间的当前相邻夹角;若当前相邻夹角不符合相邻夹角条件,则将障碍物的当前边界点编号与预设编号阈值进行匹配;若当前边界点编号在预设编号阈值范围内,则将边界点编号累加,并确定边界点坐标;若当前边界点编号不在预设编号阈值范围内,则将障碍物数量累加、障碍物编号累加、边界点数量累加、边界点编号累加,并确定边界点坐标。
例如,若当前第一相邻距离符合第一相邻条件,即当前点云坐标的右相邻点与当前点云坐标之间的距离大小在预设距离范围内,则基于其他障碍物识别条件识别当前点云坐标是否为障碍物。例如,获取当前点云坐标分别与当前点云坐标的做相邻点坐标和右相邻点坐标之间的当前相邻夹角,之后将当前相邻夹角和预设的相邻夹角条件进行匹配。若当前相邻夹角不符合相邻夹角条件,即当前相邻夹角的角度大小不在预设相邻夹角阈值范围内,则获取已识别到的障碍物中边界点的边界点编号,并将该边界点编号与预设编号阈值进行匹配,若该边界点编号在预设编号阈值范围内,则继续将边界点编号累加,并将当前点云坐标确定为新的边界点编号对应的边界点坐标。相反的,若边界点编号不在预设编号阈值范围内,则将当前点云坐标确定为新的障碍物,并更新障碍物的障碍物信息。例如,当前点为障碍物边界的起始点,将障碍物数量累加1,障碍物编号加1记为新目标障碍物编号,边界点数累加1,并将当前点云坐标作为边界点的坐标。
需要说明的是,若当前点云坐标为最右侧点云坐标或者最左侧点云坐标,则默认当前点云坐标做相邻点坐标与右相邻点坐标之间的夹角为180°,即当前相邻夹角不符合预设的相邻夹角条件,并继续执行不符合相邻夹角条件对应的识别步骤。
例如,若当前相邻夹角符合相邻夹角条件,则获取当前点云坐标与当前点云坐标的左相邻点之间的当前第二相邻距离;若当前第二相邻距离不符合第二相邻条件,则将边界点编号累加;若当前第二相邻距离符合第二相邻条件,且确定当前点云数据识别结束,则遍历其他点云坐标,并将识别到的障碍物的障碍物数量、障碍物编号、边界点数量、边界点编号以及边界点坐标进行存储。
例如,若当前相邻夹角符合相邻夹角条件,即当前相邻夹角的角度大小在预设相邻夹角阈值范围内,则基于其他障碍物识别条件识别当前点云坐标是否为障碍物。例如,获取当前点云坐标的左相邻点坐标,并获取与左相邻点坐标之间的当前第二相邻距离,之后将当前的以相邻距离与预设的第二相邻距离条件进行匹配。若当前第二相邻距离不符合第二相邻条件,即当前点云坐标的右相邻点与当前点云坐标之间的距离大小不在预设距离范围内,则获取已识别到的障碍物中边界点的边界点编号,并将该边界点编号累加1。相反的,若当前第二相邻距离符合第二相邻条件,且还有其他障碍物识别条件,则基于其他障碍物识别条件识别当前点云坐标是否为障碍物。例如,若当前第二相邻距离符合第二相邻条件,且没有其他障碍物识别条件,则确定当前点云数据识别结束。
需要说明的是,若当前点云坐标为最左侧点云坐标,则默认当前点云坐标与左相邻点之 间的当前第二相邻距离为0,即当前第二相邻距离不符合预设的第二相邻距离条件,并继续执行不符合第二相邻距离条件对应的识别步骤。
例如,基于上述识别条件识别点云数据,并将识别到的障碍物的障碍物数量、障碍物编号、边界点数量、边界点编号以及边界点坐标进行存储。例如,可以将当前帧的障碍物信息存储在障碍物信息矩阵中。在本方案中初步设定障碍物矩阵的矩阵大小为30x7。其中,在障碍物信息矩阵的行信息中,从第1行开始到第30行结束,每行分别代表当前编号的障碍物的对应信息;在障碍物信息矩阵的列信息中,第一列代表障碍物的编号ID,第二列代表相应障碍物的边界点数量,第三列到第七列代表多个边界点的信息ID。例如,障碍物信息如下表所示:
表2障碍物信息表
障碍物编号1 | 边界点数3 | 边界点1 | 边界点2 | 边界点3 | ||
障碍物编号2 | 边界点数2 | 边界点1 | 边界点2 | |||
障碍物编号3 | 边界点数4 | 边界点1 | 边界点2 | 边界点3 | 边界点4 | |
障碍物编号4 | 边界点数5 | 边界点1 | 边界点2 | 边界点3 | 边界点4 | 边界点5 |
… | … | … | … | … | … | … |
障碍物编号30 |
至此,障碍物信息计算完成,车辆控制器可根据本申请实施例提供的障碍物信息完成车辆的避障功能。
本实施例的技术方案通过获取当前车辆预设范围内的至少一个点云数据;其中,点云数据包括以当前车辆为原点的局部坐标系下的点云坐标;从而得到更加准确雷达数据为自动驾驶车辆减速避障、障碍物绕行规划路径提供必要信息;获取至少一个障碍物识别条件,并基于障碍物识别条件以及点云坐标,识别当前车辆预设范围内障碍物的障碍物信息;其中,障碍物识别条件包括点云坐标与当前车辆之间的检测距离条件、点云坐标与右相邻点坐标之间的第一相邻距离条件、点云坐标分别与左相邻点坐标和右相邻点坐标之间的相邻夹角条件和点云坐标与右相邻点坐标之间的第二相邻距离条件;通过多个障碍物识别条件对扫描到的点云数据进行识别,确定车辆周围的障碍物信息,实现了提高障碍物识别的准确性,从而提高车辆驾驶的安全性。
图3为本申请另一实施例提供的一种障碍物信息确定方法的流程图,本实施例在上述多个实施例的基础上,在步骤“识别当前车辆预设范围内障碍物的障碍物信息”之后增加了“获取全局坐标系,并基于障碍物的边界点在局部坐标系下的边界点坐标以及预设坐标转换方法,确定边界点在全局坐标系下的全局边界点坐标”其中与上述多个实施例相同或相应的术语的解释在此不再赘述。参见图3,本实施例提供的障碍物信息确定方法包括:
S210、获取当前车辆预设范围内的至少一个点云数据。
S220、获取至少一个障碍物识别条件,并基于障碍物识别条件以及点云坐标,识别当前车辆预设范围内障碍物的障碍物信息。
S230、获取全局坐标系,并基于障碍物的边界点在局部坐标系下的边界点坐标以及预设坐标转换方法,确定边界点在全局坐标系下的全局边界点坐标。
在本申请实施例中,有时障碍物的出现会阻碍当前车辆按照原来规划的路线行驶,但如 果当前车辆通过修改原有规划路线,绕过障碍物,则还可以也继续行驶。当然,要完成当前车辆的绕行,则需要确定障碍物的坐标位置,辅助当前车辆进行绕行路线规划。
在本身实施例中,确定障碍物的坐标位置是障碍物在当前线路所在全局坐标系下的坐标位置,并不是在以当前车辆所在的局部坐标系下的坐标位置。
例如,获取障碍物在全局坐标系下的坐标位置的方法可以包括:获取全局坐标系,并基于障碍物的边界点在局部坐标系下的边界点坐标以及预设坐标转换方法,确定边界点在全局坐标系下的全局边界点坐标。
例如,获取预先设置的全局坐标系,如图4所示,该全局坐标系可以是以当前车辆所在的车辆行驶路线起点为原点,以车辆的初始行驶方向为X轴正方向,并以车辆初始行驶时的左侧为Y轴正方向。换言之,全局坐标系的X轴正方向与Y轴正方向均相同。
在当前时刻下,获取当前车辆所在的局部坐标系,分别确定局部坐标系的原点和全局坐标系的原点之间的横向距离和纵向距离,以及局部坐标系的X轴方向和全局坐标系X轴方向之间的方向夹角。并基于上述横向距离、纵向距离以及方向夹角确定局部坐标系和全局坐标系之间的坐标转换方法。例如,基于障碍物的边界点在局部坐标系下的边界点坐标以及预设坐标转换方法,确定边界点在全局坐标系下的全局边界点坐标。
示例性的,以图4中的边界点2的转换方法为例确定边界点在局部坐标系和全局坐标系下的转换步骤。
首先,定义一个与局部坐标系中的原点及方向都相同的全局坐标系XY-O,接收并累加多帧的车辆横纵向移动距离a、b(沿正方向为正,沿负方向为负),以及旋转角度α(以逆时针为正,顺时针为负),完成障碍物信息以及障碍物的边界点从局部坐标系到全局坐标系的转换。
例如,在局部坐标系下识别到障碍物的边界点2的坐标信息为(x2,y2),在需要进行障碍物绕行时,车辆延X轴正方向位移为b,沿Y轴正方向位移为a,转过的角度为α,基于上述确定的坐标转换方法进行坐标转换计算。例如,坐标转换公式如下所示:
X_2=x2×cos(-α)+y2×sin(-α)+b
Y_2=y2×cos(-α)-x2×sin(-α)+a
基于上述表达式完成边界点2坐标信息转换,即在全局坐标系XY-O中,边界点2的坐标为(X_2,Y_2)。
例如,分别确定下一时刻当前车辆预设范围内的全局边界点坐标,并基于当前时刻的全局边界点坐标和下一时刻的全局边界点坐标之间的全局坐标差与预设坐标阈值的比对结果,确定边界点的边界点类型。
例如,获取下一时刻当前车辆预设范围内的障碍物中边界点在全局坐标系下的全局边界点坐标,并将当前时刻的全局边界点坐标和下一时刻的全局边界点坐标进行匹配,并基于当前时刻的全局边界点坐标和下一时刻的全局边界点坐标之间的全局坐标差与预设坐标阈值的比对结果,确定边界点的边界点类型。若全局坐标差在预设坐标阈值内,则确定该边界点为静态边界点,并将障碍物信息填入全局坐标系下的静态边界点信息矩阵当中;相反的,若全局坐标差不在预设坐标阈值内,则确定该边界点为动态边界点,并将障碍物信息填入全局坐标系下的动态边界点信息矩阵当中。
例如,若边界点类型为动态边界点,则实时更新边界点的全局边界点坐标,并基于实时 更新的边界点实时更新当前车辆的行驶轨迹,直到边界点不在检测距离条件范围内,或者当前车辆绕行通过边界点;相反的,若边界点类型为静态边界点,则基于边界点确定当前车辆的行驶轨迹,直到边界点不在检测距离条件范围内,或者当前车辆绕行通过边界点。
在本实施例中,当车辆绕行完毕,车辆控制器取消障碍物绕行,则不再进行障碍物信息转换,当前车辆继续按照既定的行驶路线行驶。
本实施例的技术方案通过获取当前车辆预设范围内的至少一个点云数据;其中,点云数据包括以当前车辆为原点的局部坐标系下的点云坐标;从而得到更加准确雷达数据为自动驾驶车辆减速避障、障碍物绕行规划路径提供必要信息;获取至少一个障碍物识别条件,并基于障碍物识别条件以及点云坐标,识别当前车辆预设范围内障碍物的障碍物信息;其中,障碍物识别条件包括点云坐标与当前车辆之间的检测距离条件、点云坐标与右相邻点坐标之间的第一相邻距离条件、点云坐标分别与左相邻点坐标和右相邻点坐标之间的相邻夹角条件和点云坐标与右相邻点坐标之间的第二相邻距离条件;通过多个障碍物识别条件对扫描到的点云数据进行识别,确定车辆周围的障碍物信息,实现了提高障碍物识别的准确性,从而提高车辆驾驶的安全性。
以下是本申请实施例提供的障碍物信息确定装置的实施例,该装置与上述多个实施例的障碍物信息确定方法属于同一个申请构思,在障碍物信息确定装置的实施例中未详尽描述的细节内容,可以参考上述障碍物信息确定方法的实施例。
图5为本申请实施例提供的障碍物信息确定装置的结构示意图,本实施例可适用于车辆自动驾驶时确定车辆周围障碍物的情况;更适用于不通过摄像头或在摄像头损坏、功能受限时确定车辆周围障碍物的情况。参见图5,该障碍物信息确定装置的结构包括:点云数据获取模块310和障碍物信息识别模块320;其中,
点云数据获取模块310,设置为获取当前车辆预设范围内的至少一个点云数据;其中,所述点云数据包括以所述当前车辆为原点的局部坐标系下的点云坐标;
障碍物信息识别模块320,设置为获取至少一个障碍物识别条件,并基于所述障碍物识别条件以及所述点云坐标,识别所述当前车辆预设范围内障碍物的障碍物信息;其中,所述障碍物识别条件包括点云坐标与所述当前车辆之间的检测距离条件、点云坐标与右相邻点坐标之间的第一相邻距离条件、点云坐标分别与左相邻点坐标和右相邻点坐标之间的相邻夹角条件和点云坐标与右相邻点坐标之间的第二相邻距离条件。
本实施例的技术方案通过获取当前车辆预设范围内的至少一个点云数据;其中,所述点云数据包括以所述当前车辆为原点的局部坐标系下的点云坐标;从而得到更加准确雷达数据为自动驾驶车辆减速避障、障碍物绕行规划路径提供必要信息;获取至少一个障碍物识别条件,并基于所述障碍物识别条件以及所述点云坐标,识别所述当前车辆预设范围内障碍物的障碍物信息;其中,所述障碍物识别条件包括点云坐标与所述当前车辆之间的检测距离条件、点云坐标与右相邻点坐标之间的第一相邻距离条件、点云坐标分别与左相邻点坐标和右相邻点坐标之间的相邻夹角条件和点云坐标与右相邻点坐标之间的第二相邻距离条件;通过多个障碍物识别条件对扫描到的点云数据进行识别,确定车辆周围的障碍物信息,实现了提高障碍物识别的准确性,从而提高车辆驾驶的安全性。
在上述实施例的基础上,所述障碍物信息包括障碍物数量、障碍物编号、所述障碍物的 边界点数量、所述障碍物的边界点编号以及所述障碍物的边界点坐标。
在上述实施例的基础上,点云数据获取模块310,包括:
初始点云坐标获取单元,设置为基于预设雷达传感器对所述当前车辆的预设范围进行扫描,并获取所述扫描结果中的初始点云坐标;
目标点云坐标获取单元,设置为对所述初始点云坐标进行数据预处理,得到所述当前车辆预设范围内的目标点云坐标。
在上述实施例的基础上,目标点云坐标获取单元,包括:
坐标调整矩阵获取子单元,设置为获取预设坐标存储矩阵,将所述预设坐标存储矩阵中的列坐标数据右移一列,并将所述初始点云坐标中对应的列坐标数据存储于所述预设坐标存储矩阵的第一列,得到坐标调整矩阵;
坐标排序矩阵获取子单元,设置为按预设排序规则对所述坐标调整矩阵中的坐标数据进行排序,得到坐标排序矩阵;
点云坐标获取子单元,设置为获取所述坐标排序矩阵中的至少两列坐标数据,确定所述至少两列坐标数据中行坐标数据的行坐标均值,并将所述行坐标均值作为所述目标点云坐标中对应的点云坐标。
在上述实施例的基础上,障碍物信息识别模块320,包括:
当前第一相邻距离获取单元,设置为对于任一点云坐标,若所述当前点云坐标与所述当前车辆之间的距离符合所述检测距离条件,则获取所述当前点云坐标与所述当前点云坐标的右相邻点之间的当前第一相邻距离;
第一障碍物信息获取单元,设置为若所述当前第一相邻距离不符合所述第一相邻距离条件,则将所述障碍物的障碍物数量累加、所述障碍物编号累加、所述边界点数量累加、所述边界点编号累加,并基于所述当前点云坐标确定所述边界点坐标。
在上述实施例的基础上,障碍物信息识别模块320,包括:
当前相邻夹角获取单元,设置为若所述当前第一相邻距离符合所述第一相邻距离条件,则获取所述当前点云坐标分别与所述当前点云坐标的左相邻点坐标和右相邻点坐标之间的当前相邻夹角;
第二障碍物信息获取单元,设置为若所述当前相邻夹角不符合所述相邻夹角条件,则将所述障碍物的当前边界点编号与预设编号阈值进行匹配;若所述当前边界点编号在所述预设编号阈值范围内,则将所述边界点编号累加,并确定所述边界点坐标;若所述当前边界点编号不在所述预设编号阈值范围内,则将所述障碍物数量累加、所述障碍物编号累加、所述边界点数量累加、所述边界点编号累加,并确定所述边界点坐标。
在上述实施例的基础上,障碍物信息识别模块320,包括:
当前第二相邻距离获取单元,设置为若所述当前相邻夹角符合所述相邻夹角条件,则获取所述当前点云坐标与所述当前点云坐标的左相邻点之间的当前第二相邻距离;
第三障碍物信息获取单元,设置为若所述当前第二相邻距离不符合所述第二相邻条件,则将所述边界点编号累加;
障碍物信息存储单元,设置为若所述当前第二相邻距离符合所述第二相邻条件,且确定所述当前点云数据识别结束,则遍历其他点云坐标,并将识别到的障碍物的障碍物数量、障碍物编号、边界点数量、边界点编号以及边界点坐标进行存储。
在上述实施例的基础上,该装置包括:
全局边界点坐标确定模块,设置为在识别所述当前车辆预设范围内障碍物的障碍物信息之后,获取全局坐标系,并基于障碍物的边界点在所述局部坐标系下的边界点坐标以及预设坐标转换方法,确定所述边界点在所述全局坐标系下的全局边界点坐标;
边界点类型确定模块,设置为分别确定下一时刻所述当前车辆预设范围内的全局边界点坐标,并基于当前时刻的全局边界点坐标和下一时刻的全局边界点坐标之间的全局坐标差与预设坐标阈值的比对结果,确定所述边界点的边界点类型。
在上述实施例的基础上,所述边界点类型包括动态边界点和动态边界点;
该装置还包括:
第一行驶轨迹更新模块,设置为在确定所述边界点的边界点类型之后,若所述边界点类型为动态边界点,则实时更新所述边界点的全局边界点坐标,并基于实时更新的边界点实时更新所述当前车辆的行驶轨迹,直到所述边界点不在所述检测距离条件范围内,或者所述当前车辆绕行通过所述边界点;
第二行驶轨迹更新模块,设置为在确定所述边界点的边界点类型之后,若所述边界点类型为静态边界点,则基于所述边界点确定所述当前车辆的行驶轨迹,直到所述边界点不在所述检测距离条件范围内,或者所述当前车辆绕行通过所述边界点。
本申请实施例所提供的障碍物信息确定装置可执行本申请任意实施例所提供的障碍物信息确定方法,具备执行方法相应的功能模块和有益效果。
值得注意的是,上述障碍物信息确定装置的实施例中,所包括的多个单元和模块只是按照功能逻辑进行划分的,但并不局限于上述的划分,只要能够实现相应的功能即可;另外,多个功能单元的具体名称也只是为了便于相互区分,并不用于限制本申请的保护范围。
图6为本申请实施例提供的一种电子设备的结构示意图。图6示出了适于用来实现本申请实施方式的示例性电子设备12的框图。图6显示的电子设备12仅仅是一个示例,不应对本申请实施例的功能和使用范围带来任何限制。
如图6所示,电子设备12以通用计算电子设备的形式表现。电子设备12的组件可以包括但不限于:一个或者多个处理器或者处理单元16,系统存储器28,连接不同系统组件(包括系统存储器28和处理单元16)的总线18。
总线18表示几类总线结构中的一种或多种,包括存储器总线或者存储器控制器,外围总线,图形加速端口,处理器或者使用多种总线结构中的任意总线结构的局域总线。举例来说,这些体系结构包括但不限于工业标准体系结构(ISA)总线,微通道体系结构(MAC)总线,增强型ISA总线、视频电子标准协会(VESA)局域总线以及外围组件互连(PCI)总线。
电子设备12典型地包括多种计算机系统可读介质。这些介质可以是任何能够被电子设备12访问的可用介质,包括易失性和非易失性介质,可移动的和不可移动的介质。
系统存储器28可以包括易失性存储器形式的计算机系统可读介质,例如随机存取存储器(RAM)30和/或高速缓存存储器32。电子设备12可以包括其它可移动/不可移动的、易失性/非易失性计算机系统存储介质。仅作为举例,存储系统34可以设置为读写不可移动的、非易失性磁介质(图6未显示,通常称为“硬盘驱动器”)。尽管图6中未示出,可以提供用于 对可移动非易失性磁盘(例如“软盘”)读写的磁盘驱动器,以及对可移动非易失性光盘(例如CD-ROM,DVD-ROM或者其它光介质)读写的光盘驱动器。在这些情况下,每个驱动器可以通过一个或者多个数据介质接口与总线18相连。系统存储器28可以包括至少一个程序产品,该程序产品具有一组(例如至少一个)程序模块,这些程序模块被配置以执行本申请实施例的功能。
具有一组(至少一个)程序模块42的程序/实用工具40,可以存储在例如系统存储器28中,这样的程序模块42包括但不限于操作系统、一个或者多个应用程序、其它程序模块以及程序数据,这些示例中的每一个或某种组合中可能包括网络环境的实现。程序模块42通常执行本申请所描述的实施例中的功能和/或方法。
电子设备12也可以与一个或多个外部设备14(例如键盘、指向设备、显示器24等)通信,还可与一个或者多个使得用户能与该电子设备12交互的设备通信,和/或与使得该电子设备12能与一个或多个其它计算设备进行通信的任何设备(例如网卡,调制解调器等等)通信。这种通信可以通过输入/输出(I/O)接口22进行。并且,电子设备12还可以通过网络适配器20与一个或者多个网络(例如局域网(LAN),广域网(WAN)和/或公共网络,例如因特网)通信。如图6所示,网络适配器20通过总线18与电子设备12的其它模块通信。应当明白,尽管图6中未示出,可以结合电子设备12使用其它硬件和/或软件模块,包括但不限于:微代码、设备驱动器、冗余处理单元、外部磁盘驱动阵列、RAID系统、磁带驱动器以及数据备份存储系统等。
处理单元16通过运行存储在系统存储器28中的程序,从而执行多种功能应用以及样本数据获取,例如实现本发实施例所提供的一种障碍物信息确定方法步骤,障碍物信息确定方法包括:
获取当前车辆预设范围内的至少一个点云数据;其中,所述点云数据包括以所述当前车辆为原点的局部坐标系下的点云坐标;
获取至少一个障碍物识别条件,并基于所述障碍物识别条件以及所述点云坐标,识别所述当前车辆预设范围内障碍物的障碍物信息;其中,所述障碍物识别条件包括点云坐标与所述当前车辆之间的检测距离条件、点云坐标与右相邻点坐标之间的第一相邻距离条件、点云坐标分别与左相邻点坐标和右相邻点坐标之间的相邻夹角条件和点云坐标与右相邻点坐标之间的第二相邻距离条件。
当然,本领域技术人员可以理解,处理器还可以实现本申请任意实施例所提供的样本数据获取方法的技术方案。
本实施例提供了一种计算机可读存储介质,其上存储有计算机程序,该程序被处理器执行时实现例如实现本发实施例所提供的一种障碍物信息确定方法步骤,障碍物信息确定方法包括:
获取当前车辆预设范围内的至少一个点云数据;其中,所述点云数据包括以所述当前车辆为原点的局部坐标系下的点云坐标;
获取至少一个障碍物识别条件,并基于所述障碍物识别条件以及所述点云坐标,识别所述当前车辆预设范围内障碍物的障碍物信息;其中,所述障碍物识别条件包括点云坐标与所述当前车辆之间的检测距离条件、点云坐标与右相邻点坐标之间的第一相邻距离条件、点云 坐标分别与左相邻点坐标和右相邻点坐标之间的相邻夹角条件和点云坐标与右相邻点坐标之间的第二相邻距离条件。
本申请实施例的计算机存储介质,可以采用一个或多个计算机可读的介质的任意组合。计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质。计算机可读存储介质例如可以是但不限于:电、磁、光、电磁、红外线、或半导体的系统、装置或器件,或者任意以上的组合。计算机可读存储介质的更具体的例子(非穷举的列表)包括:具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本文件中,计算机可读存储介质可以是任何包含或存储程序的有形介质,该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。计算机可读存储介质可以是非暂态计算机可读存储介质。
计算机可读的信号介质可以包括在基带中或者作为载波一部分传播的数据信号,其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式,包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读的信号介质还可以是计算机可读存储介质以外的任何计算机可读介质,该计算机可读介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。
计算机可读介质上包含的程序代码可以用任何适当的介质传输,包括但不限于:无线、电线、光缆、RF等等,或者上述的任意合适的组合。
可以以一种或多种程序设计语言或其组合来编写用于执行本申请操作的计算机程序代码,所述程序设计语言包括面向对象的程序设计语言,诸如Java、Smalltalk、C++,还包括常规的过程式程序设计语言-诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中,远程计算机可以通过任意种类的网络,包括局域网(LAN)或广域网(WAN),连接到用户计算机,或者,可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
本领域普通技术人员应该明白,上述的本申请的多个模块或多个步骤可以用通用的计算装置来实现,它们可以集中在单个计算装置上,或者分布在多个计算装置所组成的网络上,例如,他们可以用计算机装置可执行的程序代码来实现,从而可以将它们存储在存储装置中由计算装置来执行,或者将它们分别制作成多个集成电路模块,或者将它们中的多个模块或步骤制作成单个集成电路模块来实现。这样,本申请不限制于任何特定的硬件和软件的结合。
Claims (12)
- 一种障碍物信息确定方法,包括:获取当前车辆预设范围内的至少一个点云数据;其中,所述点云数据包括以所述当前车辆为原点的局部坐标系下的点云坐标;获取至少一个障碍物识别条件,并基于所述障碍物识别条件以及所述点云坐标,识别所述当前车辆预设范围内障碍物的障碍物信息;其中,所述障碍物识别条件包括点云坐标与所述当前车辆之间的检测距离条件、点云坐标与右相邻点坐标之间的第一相邻距离条件、点云坐标分别与左相邻点坐标和右相邻点坐标之间的相邻夹角条件,和点云坐标与右相邻点坐标之间的第二相邻距离条件。
- 根据权利要求1所述的方法,其中,所述障碍物信息包括障碍物数量、障碍物编号、所述障碍物的边界点数量、所述障碍物的边界点编号,以及所述障碍物的边界点坐标。
- 根据权利要求1所述的方法,其中,所述获取当前车辆预设范围内的至少一个点云数据,包括:基于预设雷达传感器对所述当前车辆的预设范围进行扫描,并获取所述扫描结果中的初始点云坐标;对所述初始点云坐标进行数据预处理,得到所述当前车辆预设范围内的目标点云坐标。
- 根据权利要求3所述的方法,其中,所述对所述初始点云坐标进行数据预处理,得到所述当前车辆预设范围内的目标点云坐标,包括:获取预设坐标存储矩阵,将所述预设坐标存储矩阵中的列坐标数据右移一列,并将所述初始点云坐标中对应的列坐标数据存储于所述预设坐标存储矩阵的第一列,得到坐标调整矩阵;按预设排序规则对所述坐标调整矩阵中的坐标数据进行排序,得到坐标排序矩阵;获取所述坐标排序矩阵中的至少两列坐标数据,确定所述至少两列坐标数据中行坐标数据的行坐标均值,并将所述行坐标均值作为所述目标点云坐标中对应的点云坐标。
- 根据权利要求1所述的方法,其中,所述获取至少一个障碍物识别条件,并基于所述障碍物识别条件以及所述点云坐标,识别所述当前车辆预设范围内障碍物的障碍物信息,包括:对于任一点云坐标,响应于确定所述当前点云坐标与所述当前车辆之间的距离符合所述检测距离条件,获取所述当前点云坐标与所述当前点云坐标的右相邻点之间的当前第一相邻距离;响应于确定所述当前第一相邻距离不符合所述第一相邻距离条件,将所述障碍物的障碍物数量累加、所述障碍物编号累加、所述边界点数量累加、所述边界点编号累加,并基于所述当前点云坐标确定所述边界点坐标。
- 根据权利要求5所述的方法,其中,所述获取至少一个障碍物识别条件,并基于所述障碍物识别条件以及所述点云坐标,识别所述当前车辆预设范围内障碍物的障碍物信息,还包括:响应于确定所述当前第一相邻距离符合所述第一相邻距离条件,获取所述当前点云坐标分别与所述当前点云坐标的左相邻点坐标和右相邻点坐标之间的当前相邻夹角;响应于确定所述当前相邻夹角不符合所述相邻夹角条件,将所述障碍物的当前边界点编号与预设编号阈值进行匹配;响应于确定所述当前边界点编号在所述预设编号阈值范围内,将所述边界点编号累加,并确定所述边界点坐标;响应于确定所述当前边界点编号不在所述预设编号阈值范围内,将所述障碍物数量累加、所述障碍物编号累加、所述边界点数量累加、所述边界点编号累加,并确定所述边界点坐标。
- 根据权利要求5所述的方法,其中,所述获取至少一个障碍物识别条件,并基于所述障碍物识别条件以及所述点云坐标,识别所述当前车辆预设范围内障碍物的障碍物信息,还包括:响应于确定所述当前相邻夹角符合所述相邻夹角条件,获取所述当前点云坐标与所述当前点云坐标的左相邻点之间的当前第二相邻距离;响应于确定所述当前第二相邻距离不符合所述第二相邻条件,将所述边界点编号累加;响应于确定所述当前第二相邻距离符合所述第二相邻条件,确定所述当前点云数据识别结束,则遍历其他点云坐标,并将识别到的障碍物的障碍物数量、障碍物编号、边界点数量、边界点编号以及边界点坐标进行存储。
- 根据权利要求1所述的方法,在识别所述当前车辆预设范围内障碍物的障碍物信息之后,还包括:获取预设的全局坐标系,并基于障碍物的边界点在所述局部坐标系下的边界点坐标以及预设坐标转换方法,确定所述边界点在所述全局坐标系下的全局边界点坐标;确定下一时刻所述当前车辆预设范围内的全局边界点坐标,并基于当前时刻的全局边界点坐标和下一时刻的全局边界点坐标之间的全局坐标差与预设坐标阈值的比对结果,确定所述边界点的边界点类型。
- 根据权利要求8所述的方法,其中,所述边界点类型包括动态边界点和动态边界点;在确定所述边界点的边界点类型之后,还包括:响应于确定所述边界点类型为动态边界点,实时更新所述边界点的全局边界点坐标,并基于实时更新的边界点实时更新所述当前车辆的行驶轨迹,直到所述边界点不在所述检测距离条件范围内,或者所述当前车辆绕行通过所述边界点;响应于确定所述边界点类型为静态边界点,基于所述边界点确定所述当前车辆的行驶轨迹,直到所述边界点不在所述检测距离条件范围内,或者所述当前车辆绕行通过所述边界点。
- 一种障碍物信息确定装置,包括:点云数据获取模块,设置为获取当前车辆预设范围内的至少一个点云数据;其中,所述点云数据包括以所述当前车辆为原点的局部坐标系下的点云坐标;障碍物信息识别模块,设置为获取至少一个障碍物识别条件,并基于所述障碍物识别条件以及所述点云坐标,识别所述当前车辆预设范围内障碍物的障碍物信息;其中,所述障碍物识别条件包括点云坐标与所述当前车辆之间的检测距离条件、点云坐标与右相邻点坐标之间的第一相邻距离条件、点云坐标分别与左相邻点坐标和右相邻点坐标之间的相邻夹角条件和点云坐标与右相邻点坐标之间的第二相邻距离条件。
- 一种电子设备,包括:一个或多个处理器;存储装置,设置为存储一个或多个程序,当所述一个或多个程序被所述一个或多个处理器执行,使得所述一个或多个处理器实现如权利要求1-9中任一所述的障碍物信息确定方法。
- 一种计算机可读存储介质,其上存储有计算机程序,所述计算机程序被处理器执行时实现如权利要求1-9中任一所述的障碍物信息确定方法。
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210091407.4 | 2022-01-26 | ||
CN202210091407.4A CN114419601A (zh) | 2022-01-26 | 2022-01-26 | 障碍物信息确定方法、装置、电子设备以及存储介质 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2023142816A1 true WO2023142816A1 (zh) | 2023-08-03 |
Family
ID=81277841
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2022/141398 WO2023142816A1 (zh) | 2022-01-26 | 2022-12-23 | 障碍物信息确定方法、装置、电子设备以及存储介质 |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN114419601A (zh) |
WO (1) | WO2023142816A1 (zh) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118243105A (zh) * | 2024-03-28 | 2024-06-25 | 北京小米机器人技术有限公司 | 路径规划方法、装置、电子设备及存储介质 |
CN118619120A (zh) * | 2024-08-14 | 2024-09-10 | 华芯(嘉兴)智能装备有限公司 | 天车的防碰撞控制方法及装置 |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114419601A (zh) * | 2022-01-26 | 2022-04-29 | 中国第一汽车股份有限公司 | 障碍物信息确定方法、装置、电子设备以及存储介质 |
CN116792155B (zh) * | 2023-06-26 | 2024-06-07 | 华南理工大学 | 一种基于分布式光纤传感的隧道健康状态监测预警方法 |
CN117148837B (zh) * | 2023-08-31 | 2024-08-23 | 上海木蚁机器人科技有限公司 | 动态障碍物的确定方法、装置、设备和介质 |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109085608A (zh) * | 2018-09-12 | 2018-12-25 | 奇瑞汽车股份有限公司 | 车辆周围障碍物检测方法及装置 |
US10634793B1 (en) * | 2018-12-24 | 2020-04-28 | Automotive Research & Testing Center | Lidar detection device of detecting close-distance obstacle and method thereof |
CN111260789A (zh) * | 2020-01-07 | 2020-06-09 | 青岛小鸟看看科技有限公司 | 避障方法、虚拟现实头戴设备以及存储介质 |
CN111289998A (zh) * | 2020-02-05 | 2020-06-16 | 北京汽车集团有限公司 | 障碍物检测方法、装置、存储介质以及车辆 |
CN111950428A (zh) * | 2020-08-06 | 2020-11-17 | 东软睿驰汽车技术(沈阳)有限公司 | 目标障碍物识别方法、装置及运载工具 |
CN112519797A (zh) * | 2020-12-10 | 2021-03-19 | 广州小鹏自动驾驶科技有限公司 | 一种车辆安全距离预警方法、预警系统、汽车及存储介质 |
CN114419601A (zh) * | 2022-01-26 | 2022-04-29 | 中国第一汽车股份有限公司 | 障碍物信息确定方法、装置、电子设备以及存储介质 |
-
2022
- 2022-01-26 CN CN202210091407.4A patent/CN114419601A/zh active Pending
- 2022-12-23 WO PCT/CN2022/141398 patent/WO2023142816A1/zh unknown
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109085608A (zh) * | 2018-09-12 | 2018-12-25 | 奇瑞汽车股份有限公司 | 车辆周围障碍物检测方法及装置 |
US10634793B1 (en) * | 2018-12-24 | 2020-04-28 | Automotive Research & Testing Center | Lidar detection device of detecting close-distance obstacle and method thereof |
CN111260789A (zh) * | 2020-01-07 | 2020-06-09 | 青岛小鸟看看科技有限公司 | 避障方法、虚拟现实头戴设备以及存储介质 |
CN111289998A (zh) * | 2020-02-05 | 2020-06-16 | 北京汽车集团有限公司 | 障碍物检测方法、装置、存储介质以及车辆 |
CN111950428A (zh) * | 2020-08-06 | 2020-11-17 | 东软睿驰汽车技术(沈阳)有限公司 | 目标障碍物识别方法、装置及运载工具 |
CN112519797A (zh) * | 2020-12-10 | 2021-03-19 | 广州小鹏自动驾驶科技有限公司 | 一种车辆安全距离预警方法、预警系统、汽车及存储介质 |
CN114419601A (zh) * | 2022-01-26 | 2022-04-29 | 中国第一汽车股份有限公司 | 障碍物信息确定方法、装置、电子设备以及存储介质 |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118243105A (zh) * | 2024-03-28 | 2024-06-25 | 北京小米机器人技术有限公司 | 路径规划方法、装置、电子设备及存储介质 |
CN118619120A (zh) * | 2024-08-14 | 2024-09-10 | 华芯(嘉兴)智能装备有限公司 | 天车的防碰撞控制方法及装置 |
Also Published As
Publication number | Publication date |
---|---|
CN114419601A (zh) | 2022-04-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2023142816A1 (zh) | 障碍物信息确定方法、装置、电子设备以及存储介质 | |
US11042762B2 (en) | Sensor calibration method and device, computer device, medium, and vehicle | |
CN109188438B (zh) | 偏航角确定方法、装置、设备和介质 | |
US10035508B2 (en) | Device for signalling objects to a navigation module of a vehicle equipped with this device | |
CN109284348B (zh) | 一种电子地图的更新方法、装置、设备和存储介质 | |
CN108253975B (zh) | 一种建立地图信息及车辆定位的方法与设备 | |
JP7314213B2 (ja) | 車両測位方法、装置、電子デバイス、記憶媒体及びプログラム | |
JP2020166268A (ja) | 地図軌跡マッチングデータの品質決定方法、装置、サーバ及び媒体 | |
CN110163176B (zh) | 车道线变化位置识别方法、装置、设备和介质 | |
KR20210127121A (ko) | 도로 이벤트 검출 방법, 장치, 기기 및 저장매체 | |
CN112644480B (zh) | 一种障碍物检测方法、检测系统、计算机设备和存储介质 | |
WO2023040737A1 (zh) | 目标位置确定方法、装置、电子设备以及存储介质 | |
CN109558854B (zh) | 障碍物感知方法、装置、电子设备及存储介质 | |
CN112100565B (zh) | 一种道路曲率确定方法、装置、设备及存储介质 | |
CN109635861B (zh) | 一种数据融合方法、装置、电子设备及存储介质 | |
WO2020215254A1 (zh) | 车道线地图的维护方法、电子设备与存储介质 | |
CN109635868B (zh) | 障碍物类别的确定方法、装置、电子设备及存储介质 | |
CN110390252B (zh) | 基于先验地图信息的障碍物检测方法、装置和存储介质 | |
CN115424245A (zh) | 车位识别方法、电子设备和存储介质 | |
KR20220093382A (ko) | 장애물 검출 방법 및 장치 | |
CN114662600A (zh) | 一种车道线的检测方法、装置和存储介质 | |
CN109270566B (zh) | 导航方法、导航效果测试方法、装置、设备和介质 | |
CN109188419B (zh) | 障碍物速度的检测方法、装置、计算机设备及存储介质 | |
CN113313654B (zh) | 激光点云滤波去噪方法、系统、设备及存储介质 | |
CN116226782A (zh) | 传感器数据融合方法、装置、设备以及存储介质 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 22923602 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |