WO2024216768A1 - 车辆的路径规划方法及装置、车辆 - Google Patents
车辆的路径规划方法及装置、车辆 Download PDFInfo
- Publication number
- WO2024216768A1 WO2024216768A1 PCT/CN2023/107129 CN2023107129W WO2024216768A1 WO 2024216768 A1 WO2024216768 A1 WO 2024216768A1 CN 2023107129 W CN2023107129 W CN 2023107129W WO 2024216768 A1 WO2024216768 A1 WO 2024216768A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- trajectory
- vehicle
- target vehicle
- intersection
- condition
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000012216 screening Methods 0.000 claims description 26
- 238000010586 diagram Methods 0.000 description 8
- 230000008447 perception Effects 0.000 description 8
- 238000004891 communication Methods 0.000 description 7
- 230000008901 benefit Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 101001121408 Homo sapiens L-amino-acid oxidase Proteins 0.000 description 2
- 101000827703 Homo sapiens Polyphosphoinositide phosphatase Proteins 0.000 description 2
- 102100026388 L-amino-acid oxidase Human genes 0.000 description 2
- 102100023591 Polyphosphoinositide phosphatase Human genes 0.000 description 2
- 101100012902 Saccharomyces cerevisiae (strain ATCC 204508 / S288c) FIG2 gene Proteins 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 101100233916 Saccharomyces cerevisiae (strain ATCC 204508 / S288c) KAR5 gene Proteins 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Definitions
- the present invention relates to the field of intelligent driving technology, and in particular to a vehicle path planning method and device, and a vehicle.
- driverless vehicles will follow real-time planned paths when driving on the road.
- the autonomous driving vehicle needs to perceive the road conditions in real time and obtain lane line information around the intersection for real-time path planning.
- existing vehicles usually plan the driving direction of the path based on the identified lane lines of the intersection ahead when passing through an intersection.
- the vehicle cannot accurately plan the driving direction of the path, resulting in reduced accuracy and effectiveness of the path planning of the vehicle at the intersection.
- the present invention provides a vehicle path planning method and device, and a vehicle to solve the problem that existing vehicles cannot effectively plan paths through intersections when no lane lines at intersections are detected or there is no map data.
- a vehicle path planning method comprising:
- the path planning of the target vehicle is performed according to the historical trajectory points of the target vehicle-following object.
- the embodiment of the present invention follows the trajectory of the preceding vehicle and imitates the preceding vehicle's driving behavior at an intersection, thereby realizing an intersection crossing function without map data or lane line information at an intersection.
- determining the target following object of the target vehicle includes:
- reference trajectory points of the objects to be followed are obtained, and based on the trajectory difference between the reference trajectory points and the driving trajectory points of the target vehicle, a target following object is screened from the objects to be followed.
- the trajectory difference includes at least one of a trajectory overlap difference, a trajectory angle difference, and a trajectory distance difference.
- the track distance difference is obtained by comparing the first track length of the first track route with the second track length of the second track route.
- the selecting a target vehicle-to-be-followed object from the vehicle-to-be-followed objects based on the trajectory difference between the reference trajectory point and the driving trajectory point of the target vehicle comprises:
- the object to be followed that matches the preset vehicle following screening condition is determined as a target vehicle following object, and the preset vehicle following screening condition includes a maximum condition or a minimum condition for screening the target vehicle following object according to at least one of the trajectory overlap difference, the trajectory angle difference, and the trajectory distance difference.
- the method further comprises:
- the step of determining the target following object of the target vehicle under the condition that the recognition result is that the intersection lane line is not detected is re-executed.
- the lane marking at the intersection includes a lane marking at an exit, and the method further includes:
- the lane center line is determined based on the exit lane line, and the path of the target vehicle is planned according to the lane center line.
- the lane marking at the intersection includes a lane marking at an entrance to the intersection, and the method further includes:
- the lane center line of the entrance lane line is obtained, and a guided driving path is generated based on the lane center line, so that the path of the target vehicle is planned according to the lane center line of the exit lane line under the condition that the target vehicle travels according to the guided driving path and recognizes the exit lane line.
- a vehicle path planning device comprising:
- the determination module is used to obtain the lane line of the intersection when the target vehicle is driving at the intersection.
- An acquisition module used for determining a target following vehicle of the target vehicle and acquiring historical track points of the target following vehicle under the condition that the recognition result is that no lane line of the intersection is detected;
- the planning module is used to plan the path of the target vehicle according to the historical trajectory points of the target vehicle-following object.
- the acquisition module includes:
- a search unit used to search for a vehicle to be followed corresponding to the target vehicle
- a determination unit configured to determine the object to be followed as a target vehicle to be followed if there is only one vehicle to be followed;
- the acquisition unit is used to acquire reference trajectory points of the objects to be followed under the condition that there are at least two objects to be followed, and to select a target following object from the objects to be followed based on the trajectory difference between the reference trajectory points and the driving trajectory points of the target vehicle.
- the trajectory difference includes at least one of a trajectory overlap difference, a trajectory angle difference, and a trajectory distance difference
- the acquisition module further includes:
- a generating unit configured to generate a first trajectory route corresponding to the reference trajectory point and a second trajectory route corresponding to the driving trajectory point respectively based on a time frame unit;
- the comparison unit is used to compare the first trajectory route with the second trajectory route to obtain a trajectory overlap difference; or to compare the first trajectory angle of the first trajectory route with the second trajectory angle of the second trajectory route to obtain a trajectory angle difference; or to compare the first trajectory length of the first trajectory route with the second trajectory length of the second trajectory route to obtain a trajectory distance difference.
- the acquisition unit is specifically used to determine the object to be followed that matches the preset vehicle following screening condition as the target vehicle following object under the condition that at least one of the trajectory overlap difference, the trajectory angle difference, and the trajectory distance difference matches the preset vehicle following screening condition, and the preset vehicle following screening condition includes the maximum condition or minimum condition for screening the target vehicle following object according to at least one of the trajectory overlap difference, the trajectory angle difference, and the trajectory distance difference.
- the device also includes:
- An identification module is used to identify the lateral offset distance or driving angle of the target vehicle when the target vehicle is driving along the driving path obtained by path planning;
- the execution module is used to re-execute the step of determining the target following object of the target vehicle under the condition that the recognition result is that the intersection lane line is not detected, under the condition that the lateral offset distance is greater than the preset offset distance or the driving angle is greater than the preset driving angle.
- the lane marking at the intersection includes a lane marking at an exit
- the device further includes:
- a planning module is used to determine a lane center line based on the exit lane line when the recognition result is that a lane line at the intersection is detected, and to plan a path for the target vehicle according to the lane center line.
- the lane markings at the intersection include lane markings at an entrance to the intersection, and the device further includes:
- a generation module is used to obtain the lane center line of the lane line of the entrance, under the condition that the recognition result is that there is a lane line of the entrance and the object to be followed is not searched, and based on the The lane centerline generates a guided driving path, so that the path of the target vehicle is planned according to the lane centerline of the exit lane line under the condition that the target vehicle travels according to the guided driving path and recognizes the exit lane line.
- a vehicle comprising a path planning device for the above-mentioned vehicle.
- a readable storage medium on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of the vehicle path planning method as described above are implemented.
- a computer device comprising at least one processor, wherein the processor is coupled to a memory, wherein the memory stores a program or instruction running on the processor, and wherein the program or instruction, when executed by the processor, implements the steps of the vehicle path planning method as described above.
- FIG1 shows a flow chart of a vehicle path planning method provided by an embodiment of the present invention
- FIG2 shows a schematic diagram of a lane line at an entrance provided by an embodiment of the present invention
- FIG3 shows a schematic diagram of a lane line at an exit provided by an embodiment of the present invention
- FIG4 shows a schematic diagram of vehicle path planning based on a target vehicle following object provided by an embodiment of the present invention
- FIG5 shows a block diagram of a vehicle path planning device provided by an embodiment of the present invention
- FIG6 shows a schematic diagram of the structure of a computer device provided by an embodiment of the present invention.
- An embodiment of the present invention provides a vehicle path planning method, as shown in FIG1 , the method comprising:
- the automatic driving processor as the current execution subject can be a processor configured on the vehicle side, or a cloud server matching the vehicle, etc.
- the current execution subject controls the vehicle to travel at the intersection
- effective path planning is required to improve the effectiveness of the vehicle traveling at the intersection.
- the intersection driving includes driving into the intersection, driving in the intersection and driving out of the intersection, which can be determined by a Cartesian coordinate system or a Frent coordinate system, and the embodiment of the present invention does not make specific limitations.
- the intersection lane line includes the road lane line where the target vehicle enters the intersection (referred to as "entry lane line”) and the road lane line where the target vehicle plans to exit the intersection (referred to as "exit lane line”), and the recognition result of the intersection lane line can be obtained by the perception system, such as the schematic diagram of the entrance lane line shown in Figure 2, and the schematic diagram of the exit lane line shown in Figure 3.
- the scenario of "the target vehicle is traveling at an intersection” in the embodiment of the present invention may include that the target vehicle is about to travel through the intersection, and at this time, the target vehicle is still some distance away from the stop line at the intersection.
- the condition of "the target vehicle is traveling at an intersection” is met based on the distance between the target vehicle and the stop line at the intersection of the lane entering the intersection. For example, when it is detected that the target vehicle is a predetermined distance (such as 50 meters) from the stop line at the intersection of the lane entering the intersection, it is determined that the target vehicle meets the condition of traveling at an intersection, and the recognition result of the lane line at the intersection is obtained at this time.
- "the target vehicle is traveling at an intersection” may include that the vehicle has entered the intersection.
- the condition of the target vehicle traveling at an intersection is met, and the recognition result of the lane line at the intersection is obtained at this time.
- the embodiment of the present invention does not make specific limitations.
- the vehicle is a vehicle with an automatic control system in the autonomous driving scenario, including passenger cars and commercial vehicles.
- passenger cars include but are not limited to sedans, sport utility vehicles, multi-person commercial vehicles, etc.
- commercial vehicles include but are not limited to pickup trucks, microvans, self-unloading vehicles, trucks, tractors, trailers and mining vehicles, etc.
- the vehicle can achieve autonomous driving based on the automatic control system.
- the current execution subject can determine the target vehicle following object based on the recognition result.
- the target vehicle following object is a vehicle that can be followed as the target vehicle.
- the target vehicle following object may include but is not limited to any vehicle located in front of or to the side of the target vehicle, such as a large car, a small car, etc., and the embodiment of the present invention does not make specific restrictions.
- the recognition result is that the lane line of the intersection is not detected, it means that when the vehicle enters or exits the intersection, it is difficult for the vehicle to determine the driving direction when performing path planning. Therefore, the current execution subject determines the target vehicle following object of the target vehicle under the condition that the lane line of the intersection does not exist, and obtains the historical trajectory points of the target vehicle following object as reference information for the vehicle to plan the driving trajectory through the intersection.
- the perception system in the embodiment of the present invention will record the driving trajectory of the vehicle to be followed adjacent to the target vehicle according to the time frame unit.
- the vehicle moving position is recorded for 8 frames in 1 second, and then the historical trajectory points of the vehicle can be constructed according to the vehicle moving position of the 8 frames.
- the embodiment of the present invention does not specifically limit the time frame.
- the current execution subject uses the historical trajectory points as a reference for the path planning of the target vehicle, thereby performing the trajectory planning of the vehicle based on the trajectory of the target vehicle.
- the lateral trajectory planning of the target vehicle can be performed based on the lateral distance of the historical trajectory points
- the longitudinal trajectory planning of the target vehicle can also be performed based on the longitudinal distance of the historical trajectory points, as shown in FIG4, thereby meeting the effectiveness of the vehicle passing through the intersection when there is no lane line as a reference.
- the step of determining the target following vehicle of the target vehicle under the condition that the recognition result is that the lane line of the intersection is not detected includes:
- reference trajectory points of the objects to be followed are obtained, and based on the trajectory difference between the reference trajectory points and the driving trajectory points of the target vehicle, a target following object is screened from the objects to be followed.
- the current execution subject first searches for the vehicle-to-be-followed object corresponding to the target vehicle.
- the current execution subject can search within a preset distance range (such as a radius circle distance of 10 meters or 20 meters) of the target vehicle based on the perception system or the global positioning system to determine at least one vehicle-to-be-followed object that can be used as the target vehicle-following object.
- the vehicle-to-be-followed object can be one, two or three, and the embodiment of the present invention does not make specific limitations.
- the vehicle-to-be-followed object is preferably a vehicle directly in front of, in front of the left, or in front of the right of the target vehicle, and the embodiment of the present invention does not make specific limitations.
- the to-be-followed object is directly determined as a target to-be-followed object, so as to speed up the determination of the target to-be-followed object.
- the reference trajectory points of each object to be followed are obtained, so as to select the target object to be followed based on the trajectory difference between the reference trajectory points and the driving trajectory points of the target vehicle.
- the determination of the reference trajectory points and the driving trajectory points is the same as the determination method of the historical trajectory points, and the embodiment of the present invention does not make specific limitations.
- the trajectory difference includes at least one of the trajectory overlap difference, trajectory angle difference, and trajectory distance difference, that is, the trajectory overlap difference, trajectory angle difference, and trajectory distance difference are determined by comparing the position difference, angle difference, and distance difference between the reference trajectory point and the driving trajectory point to select the optimal target object to follow.
- the step of selecting a target vehicle to be followed from the vehicle to be followed is based on the trajectory difference between the reference trajectory point and the driving trajectory point of the target vehicle.
- the method also includes:
- the track distance difference is obtained by comparing the first track length of the first track route with the second track length of the second track route.
- the current execution subject In order to accurately select the target vehicle to be followed based on the trajectory difference, and the trajectory difference includes at least one of the trajectory overlap difference, trajectory angle difference, and trajectory distance difference, the current execution subject first determines the trajectory overlap difference, trajectory angle difference, and trajectory distance difference respectively before selecting the target vehicle to be followed. Among them, since the current execution subject can identify the vehicle's trajectory point by time frame unit, the current execution subject first generates the first trajectory path corresponding to the reference trajectory point and the second trajectory path corresponding to the driving trajectory point in accordance with the perception system according to the time frame unit, that is, the trajectory path of each vehicle to be followed and the trajectory path of the target vehicle.
- the current execution subject in order to determine the track overlap difference, directly compares the route overlap of multiple first track routes with the second track route, and can calculate the position overlap distance between the closest track points in the first track route and the second track route in turn, and determine the average value of the position overlap distance in combination with the average value calculation method as the overlap difference, which is not specifically limited in the embodiment of the present invention.
- the overlap difference 1 between the first track route 1 and the second track route L, and the overlap difference 2 between the first track route 2 and the second track route L so as to select the vehicle to be followed based on the overlap difference 1 and the overlap difference 2.
- the current execution subject in order to determine the difference in trajectory angles, the current execution subject first calculates the trajectory angles of each first trajectory route and the trajectory angle of the second trajectory route.
- the angles can be determined by the overall angle of the trajectory curve or based on the curvature of each point on the trajectory.
- the embodiment of the present invention does not make any specific limitations.
- the current execution subject compares the angles of each first trajectory angle with the second trajectory angle.
- the angles are directly compared according to the overall angles; if the angles are determined according to the curvature of each point, the angles are compared one by one according to each curvature, thereby determining the comparison result based on the average value.
- the embodiment of the present invention does not make any specific limitations.
- the current execution subject in order to determine the trajectory length, the current execution subject first calculates the trajectory length of each first trajectory route and the trajectory length of the second trajectory route.
- the trajectory length is the length of the trajectory curve that can be perceived in the preset time unit frame.
- the curve length of each trajectory route can be directly calculated based on the position coordinates, that is, as the trajectory length, which is not specifically limited in the embodiment of the present invention.
- the curve length of each first trajectory route and the curve length of the second trajectory route can be directly compared, which is not specifically limited in the embodiment of the present invention.
- the step of selecting a target vehicle to be followed from the objects to be followed based on the trajectory difference between the reference trajectory point and the driving trajectory point of the target vehicle comprises:
- the vehicle to be followed that matches the preset vehicle following screening condition is determined as a target vehicle following object.
- the current execution subject matches the pre-configured vehicle following screening condition after obtaining at least one of the trajectory overlap difference, trajectory angle difference, and trajectory distance difference.
- the preset vehicle following screening condition includes the maximum condition or minimum condition for screening the target vehicle following object according to at least one of the trajectory overlap difference, trajectory angle difference, and trajectory distance difference.
- the maximum condition includes the pre-set maximum value of the trajectory overlap difference, the maximum value of the trajectory angle difference, and the maximum value of the trajectory distance difference.
- the minimum condition includes the pre-set minimum value of the trajectory overlap difference, the minimum value of the trajectory angle difference, and the minimum value of the trajectory distance difference, so as to screen the matching vehicle to be followed according to the above maximum value and minimum value and determine it as the target vehicle following object.
- the trajectory angle difference between the vehicle to be followed object a and the target vehicle is 10 degrees
- the trajectory angle difference between the vehicle to be followed object b and the target vehicle is 20 degrees.
- the pre-set preset vehicle following screening condition is that the maximum value of the trajectory angle difference is 15 degrees, then the vehicle to be followed object a is determined as the target vehicle following object, and the embodiment of the present invention does not make specific restrictions.
- the object to be followed that is closest to the target vehicle can be selected as the target vehicle following object to ensure the rationality of the driving trajectory planning.
- the current execution subject can travel according to the preset driving trajectory, or re-search for the object to be followed after a specific time interval has arrived, which is not specifically limited in the embodiments of the present invention.
- the steps further include:
- the step of determining the target following object of the target vehicle under the condition that the recognition result is that the intersection lane line is not detected is re-executed.
- the current execution subject obtains a driving path after performing path planning based on the historical trajectory points of the target vehicle-following object, so as to control the target vehicle to travel along this driving path.
- the current execution subject identifies the lateral offset distance or driving angle of the target vehicle in real time, so as to compare it with the preset offset distance or preset driving angle, to ensure that the target vehicle can travel through the intersection according to the predetermined trajectory, and avoid excessive lateral deviation and angle deviation.
- the lateral offset distance is the distance based on the comparison of the lateral position of the driving path after path planning with the driving path of the target vehicle before entering the intersection driving state
- the driving angle is the driving angle of the target vehicle after path planning, which can be determined based on the curvature of the trajectory point, and the embodiment of the present invention does not make specific limitations.
- the current execution subject obtains the lateral offset distance of the target vehicle
- the lateral offset distance is compared with the preset offset distance or the driving angle is compared with the preset driving angle, if the lateral offset distance is greater than the preset offset distance and the driving angle is greater than the preset driving angle, it indicates that the route of the target vehicle in the intersection is offset. At this time, it may be caused by the target vehicle following object turning or changing lanes. Therefore, in order to avoid the deviation of the target vehicle's driving route, in a specific implementation scenario, the current execution subject re-executes the step of determining the target vehicle following object to re-plan the driving path according to the historical trajectory points of the target vehicle following object.
- the steps further include:
- the lane center line is determined based on the exit lane line, and the path of the target vehicle is planned according to the lane center line.
- the intersection lane lines include exit lane lines
- the perception system can sense that the vehicle is located at the intersection and identifies the exit lane line, then in order to improve the accuracy of path planning, the current execution entity determines the identified exit lane line as the lane center line, and plans the path of the target vehicle based on this lane center line, which not only avoids the safety hazards caused by long-term following of the vehicle, but also improves the planning efficiency of the vehicle when exiting the intersection.
- the steps further include:
- the lane center line of the entrance lane line is obtained, and a guided driving path is generated based on the lane center line, so that the path of the target vehicle is planned according to the lane center line of the exit lane line under the condition that the target vehicle travels according to the guided driving path and recognizes the exit lane line.
- the guided driving intersection can be generated by the lane center line of the lane line of the entrance.
- the guided driving intersection is extended into the intersection until the perception system recognizes the lane line of the exit or the object to be followed, and then the corresponding steps are executed, so that the vehicle can smoothly enter the intersection without the guidance in front, meet the driving safety requirements, and thus improve the planning efficiency when the vehicle enters the intersection.
- the embodiment of the present invention obtains the recognition result of the lane line of the intersection when the target vehicle is traveling at the intersection; under the condition that the recognition result is that the lane line of the intersection is not detected, determines the target following object of the target vehicle and obtains the historical trajectory points of the target following object; performs path planning for the target vehicle according to the historical trajectory points of the target following object, and achieves the purpose of performing path planning for crossing the intersection when there is no map data or no lane line information at the intersection by performing path planning in a vehicle-following driving manner when the vehicle crosses the intersection, thereby improving the effectiveness of path planning for vehicles traveling at the intersection and achieving the function of crossing the intersection without map data or lane line information at the intersection.
- an embodiment of the present invention provides a vehicle path planning device, as shown in FIG. 5 , the device includes:
- Determination module 21 used to obtain the lane of the intersection when the target vehicle is at the intersection Line recognition results
- An acquisition module 22 for determining a target following object of the target vehicle and acquiring historical track points of the target following object under the condition that the recognition result is that no lane line of the intersection is detected;
- the planning module 23 is used to plan the path of the target vehicle according to the historical trajectory points of the target vehicle-following object.
- the acquisition module includes:
- a search unit used to search for a vehicle to be followed corresponding to the target vehicle
- a determination unit configured to determine the object to be followed as a target vehicle to be followed if there is only one vehicle to be followed;
- the acquisition unit is used to acquire reference trajectory points of the objects to be followed under the condition that there are at least two objects to be followed, and to select a target following object from the objects to be followed based on the trajectory difference between the reference trajectory points and the driving trajectory points of the target vehicle.
- the trajectory difference includes at least one of a trajectory overlap difference, a trajectory angle difference, and a trajectory distance difference
- the acquisition module further includes:
- a generating unit configured to generate a first trajectory route corresponding to the reference trajectory point and a second trajectory route corresponding to the driving trajectory point respectively based on a time frame unit;
- the comparison unit is used to compare the first trajectory route with the second trajectory route to obtain a trajectory overlap difference; or to compare the first trajectory angle of the first trajectory route with the second trajectory angle of the second trajectory route to obtain a trajectory angle difference; or to compare the first trajectory length of the first trajectory route with the second trajectory length of the second trajectory route to obtain a trajectory distance difference.
- the acquisition unit is specifically used to determine the object to be followed that matches the preset vehicle following screening condition as the target vehicle following object under the condition that at least one of the trajectory overlap difference, the trajectory angle difference, and the trajectory distance difference matches the preset vehicle following screening condition, and the preset vehicle following screening condition includes the maximum condition or minimum condition for screening the target vehicle following object according to at least one of the trajectory overlap difference, the trajectory angle difference, and the trajectory distance difference.
- the device also includes:
- An identification module is used to identify the lateral offset distance or driving angle of the target vehicle when the target vehicle is driving along the driving path obtained by path planning;
- the execution module is used to re-execute the step of determining the target following object of the target vehicle under the condition that the recognition result is that the intersection lane line is not detected, under the condition that the lateral offset distance is greater than the preset offset distance or the driving angle is greater than the preset driving angle.
- the lane marking at the intersection includes a lane marking at an exit
- the device further includes:
- a planning module is used to determine a lane centerline based on the exit lane line under the condition that the recognition result is that the intersection lane line is detected, and to plan the path of the target vehicle according to the lane centerline.
- the lane markings at the intersection include lane markings at an entrance to the intersection, and the device further includes:
- a generating module is used to generate a lane line when the recognition result shows that there is a lane line at the entrance and the lane line is not found.
- the lane centerline of the entrance lane line is obtained, and a guided driving path is generated based on the lane centerline, so that the path of the target vehicle is planned according to the lane centerline of the exit lane line under the condition that the target vehicle travels according to the guided driving path and recognizes the exit lane line.
- the embodiment of the present invention obtains the recognition result of the lane line of the intersection when the target vehicle is traveling at the intersection; under the condition that the recognition result is that the lane line of the intersection is not detected, determines the target following object of the target vehicle and obtains the historical trajectory points of the target following object; performs path planning for the target vehicle according to the historical trajectory points of the target following object, and achieves the purpose of performing path planning for crossing the intersection when there is no map data or no lane line information at the intersection by performing path planning in a vehicle-following driving manner when the vehicle crosses the intersection, thereby improving the effectiveness of path planning for vehicles traveling at the intersection and achieving the function of crossing the intersection without map data or lane line information at the intersection.
- a readable storage medium on which a program or instruction is stored.
- the program or instruction is executed by a processor, the steps of the vehicle path planning method as described above are implemented.
- FIG6 shows a schematic diagram of the structure of a computer device provided according to an embodiment of the present invention, comprising at least one processor, the processor and a memory are coupled, the memory stores a program or instruction running on the processor, and the program or instruction is executed by the processor to implement the steps of the vehicle path planning method as described above.
- the specific embodiment of the present invention does not limit the specific implementation of the computer device.
- the computer device may include: a processor (processor) 302, a communication interface (Communications Interface) 304, a memory (memory) 306, and a communication bus 308.
- processor processor
- communication interface Communication Interface
- memory memory
- the processor 302 , the communication interface 304 , and the memory 306 communicate with each other via the communication bus 308 .
- the communication interface 304 is used to communicate with other devices such as clients or other servers.
- the processor 302 is used to execute the program 310, and specifically can execute the relevant steps in the above-mentioned vehicle path planning method embodiment.
- the program 310 may include program codes, which include computer operation instructions.
- the processor 302 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention.
- the one or more processors included in the terminal may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.
- the memory 306 is used to store the program 310.
- the memory 306 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.
- the program 310 may be specifically configured to enable the processor 302 to perform the following operations:
- the path planning of the target vehicle is performed according to the historical trajectory points of the target vehicle-following object.
- modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation.
- the present invention is not limited to any specific combination of hardware and software.
Landscapes
- Traffic Control Systems (AREA)
Abstract
本发明公开了一种车辆的路径规划方法及装置、车辆，涉及智能驾驶技术领域。包括：在目标车辆处于路口行驶的条件下，获取路口车道线的识别结果；在所述识别结果为未检测到路口车道线的条件下，确定所述目标车辆的目标跟车对象，并获取所述目标跟车对象的历史轨迹点；根据所述目标跟车对象的历史轨迹点进行所述目标车辆的路径规划。本发明在车辆通过路口时以跟车行驶的方式进行路径规划，大大减少了车辆通过无车道线的路口时安全隐患的产生，实现基于跟车对车辆进行路径规划的目的，从而提高车辆位于路口处行驶的路径规划准确性以及有效性。
Description
本申请要求于2023年04月20日提交中国专利局、申请号为202310426222.9、申请名称为“车辆的路径规划方法及装置、车辆”的中国专利申请的优先权，其全部内容通过引用结合在申请中。
本发明涉及一种智能驾驶技术领域，特别是涉及一种车辆的路径规划方法及装置、车辆。
随着智能驾驶技术的快速发展，无人驾驶车辆在路面行驶时会按照实时规划的路径进行行驶。尤其是，在经过十字路口时，为了保证车辆的自动驾驶需求，自动驾驶车辆需要实时感知路面情况，获取路口周围车道线信息，用于进行实时路径规划。
目前，现有车辆在经过路口时通常基于识别到的前进路口车道线规划路径的行驶方向，但是，在无法获取路口车道线信息或地图数据时，车辆无法准确规划路径行驶方向，导致车辆位于路口处的路径规划的准确性及有效性降低。
发明内容
有鉴于此，本发明提供一种车辆的路径规划方法及装置、车辆，以解决在未检测到路口车道线或无地图数据的情况下，现有车辆无法有效进行过路口路径规划的问题。
依据本发明一个方面，提供了一种车辆的路径规划方法，包括：
在目标车辆处于路口行驶的条件下，获取路口车道线的识别结果；
在所述识别结果为未检测到路口车道线的条件下，确定所述目标车辆的目标跟车对象，并获取所述目标跟车对象的历史轨迹点；
根据所述目标跟车对象的历史轨迹点进行所述目标车辆的路径规划。
本发明实施例在无地图数据或无路口车道线信息的情况下，跟随前车轨迹行驶，模仿前车的过路口驾驶行为，从而实现无地图数据或无路口车道线信息的过路口功能。
进一步地，所述在所述识别结果为未检测到路口车道线的条件下，确定所述目标车辆的目标跟车对象包括：
搜索与所述目标车辆对应的待跟车对象；
在所述待跟车对象为一个的条件下，将所述待跟车对象确定为目标跟车对象；
在所述待跟车对象为至少两个的条件下，获取所述待跟车对象的参考轨迹点，并基于所述参考轨迹点与所述目标车辆的行驶轨迹点之间的轨迹差异，从所述待跟车对象中筛选目标跟车对象。
进一步地，所述轨迹差异包括轨迹重合差异、轨迹角度差异、轨迹距离差异中至少一项，所述基于所述参考轨迹点与所述目标车辆的行驶轨迹点之间的轨迹差异，从所述待跟车对象中筛选目标跟车对象之前，所述方法还包括：
基于时间帧单位分别生成与所述参考轨迹点对应的第一轨迹路线以及与所述行驶轨迹点对应的第二轨迹路线；
通过第一轨迹路线与所述第二轨迹路线进行路线重合对比，得到轨迹重合差异；或，
基于所述第一轨迹路线的第一轨迹角度与所述第二轨迹路线的第二轨迹角度进行角度对比，得到轨迹角度差异；或，
通过所述第一轨迹路线的第一轨迹长度与所述第二轨迹路线的第二轨迹长度进行长度对比，得到轨迹距离差异。
进一步地，所述基于所述参考轨迹点与所述目标车辆的行驶轨迹点之间的轨迹差异，从所述待跟车对象中筛选目标跟车对象包括：
在所述轨迹重合差异、所述轨迹角度差异、所述轨迹距离差异中至少一项与预设跟车筛选条件匹配的条件下，将与所述预设跟车筛选条件匹配的所述待跟车对象确定为目标跟车对象，所述预设跟车筛选条件包括按照轨迹重合差异、轨迹角度差异、轨迹距离差异至少一项进行筛选目标跟车对象的最大条件或最小条件。
进一步地，所述方法还包括：
在所述目标车辆按照路径规划得到的行驶路径进行行驶过程中，识别所述目标车辆的横向偏移距离或行驶角度；
在所述横向偏移距离大于预设偏移距离或所述行驶角度大于预设行驶角度的条件下，重新执行在所述识别结果为未检测到路口车道线的条件下，确定所述目标车辆的目标跟车对象的步骤。
进一步地，所述路口车道线包括出路口车道线，所述方法还包括：
在所述识别结果为检测到路口车道线的条件下，基于所述出路口车道线确定车道中心线，并根据所述车道中心线进行所述目标车辆的路径规划。
进一步地，所述路口车道线包括进路口车道线，所述方法还包括：
在所述识别结果为存在进路口车道线且未搜索到所述待跟车对象的条件下，获取所述进路口车道线的车道中心线，并基于所述车道中心线生成引导行驶路径，以在所述目标车辆按照所述引导行驶路径行驶且识别到出路口车道线的条件下根据所述出路口车道线的车道中心线进行所述目标车辆的路径规划。
依据本发明另一个方面，提供了一种车辆的路径规划装置，包括：
确定模块，用于在目标车辆处于路口行驶的条件下，获取路口车道线
的识别结果；
获取模块，用于在所述识别结果为未检测到路口车道线的条件下，确定所述目标车辆的目标跟车对象，并获取所述目标跟车对象的历史轨迹点；
规划模块，用于根据所述目标跟车对象的历史轨迹点进行所述目标车辆的路径规划。
进一步地，所述获取模块包括：
搜索单元，用于搜索与所述目标车辆对应的待跟车对象；
确定单元，用于在所述待跟车对象为一个的条件下，将所述待跟车对象确定为目标跟车对象；
获取单元，用于在所述待跟车对象为至少两个的条件下，获取所述待跟车对象的参考轨迹点，并基于所述参考轨迹点与所述目标车辆的行驶轨迹点之间的轨迹差异，从所述待跟车对象中筛选目标跟车对象。
进一步地，所述轨迹差异包括轨迹重合差异、轨迹角度差异、轨迹距离差异中至少一项，所述获取模块还包括：
生成单元，用于基于时间帧单位分别生成与所述参考轨迹点对应的第一轨迹路线以及与所述行驶轨迹点对应的第二轨迹路线；
对比单元，用于通过第一轨迹路线与所述第二轨迹路线进行路线重合对比，得到轨迹重合差异；或，基于所述第一轨迹路线的第一轨迹角度与所述第二轨迹路线的第二轨迹角度进行角度对比，得到轨迹角度差异；或，通过所述第一轨迹路线的第一轨迹长度与所述第二轨迹路线的第二轨迹长度进行长度对比，得到轨迹距离差异。
进一步地，所述获取单元，具体用于在所述轨迹重合差异、所述轨迹角度差异、所述轨迹距离差异中至少一项与预设跟车筛选条件匹配的条件下，将与所述预设跟车筛选条件匹配的所述待跟车对象确定为目标跟车对象，所述预设跟车筛选条件包括按照轨迹重合差异、轨迹角度差异、轨迹距离差异至少一项进行筛选目标跟车对象的最大条件或最小条件。
进一步地，所述装置还包括：
识别模块，用于在所述目标车辆按照路径规划得到的行驶路径进行行驶过程中，识别所述目标车辆的横向偏移距离或行驶角度；
执行模块，用于在所述横向偏移距离大于预设偏移距离或所述行驶角度大于预设行驶角度的条件下，重新执行在所述识别结果为未检测到路口车道线的条件下，确定所述目标车辆的目标跟车对象的步骤。
进一步地，所述路口车道线包括出路口车道线，所述装置还包括：
规划模块，用于在所述识别结果为检测到路口车道线的条件下，基于所述出路口车道线确定车道中心线，并根据所述车道中心线进行所述目标车辆的路径规划。
进一步地，所述路口车道线包括进路口车道线，所述装置还包括：
生成模块，用于在所述识别结果为存在进路口车道线且未搜索到所述待跟车对象的条件下，获取所述进路口车道线的车道中心线，并基于所述
车道中心线生成引导行驶路径，以在所述目标车辆按照所述引导行驶路径行驶且识别到出路口车道线的条件下根据所述出路口车道线的车道中心线进行所述目标车辆的路径规划。
依据本发明一个方面，提供了一种车辆，包括上述车辆的路径规划装置。
根据本发明的又一方面，提供了一种可读存储介质，其上存储有程序或指令，所述程序或指令被处理器执行时实现如上述车辆的路径规划方法的步骤。
根据本发明的再一方面，提供了一种计算机设备，包括至少一个处理器，所述处理器和存储器耦合，所述存储器存储有在所述处理器上运行的程序或指令，所述程序或指令被所述处理器执行时实现如上述的车辆的路径规划方法的步骤。
上述说明仅是本发明技术方案的概述，为了能够更清楚了解本发明的技术手段，而可依照说明书的内容予以实施，并且为了让本发明的上述和其它目的、特征和优点能够更明显易懂，以下特举本发明的具体实施方式。
通过阅读下文优选实施方式的详细描述，各种其他的优点和益处对于本领域普通技术人员将变得清楚明了。附图仅用于示出优选实施方式的目的，而并不认为是对本发明的限制。而且在整个附图中，用相同的参考符号表示相同的部件。在附图中：
图1示出了本发明实施例提供的一种车辆的路径规划方法流程图；
图2示出了本发明实施例提供的一种存在进路口车道线示意图；
图3示出了本发明实施例提供的一种存在出路口车道线示意图；
图4示出了本发明实施例提供的一种基于目标跟车对象进行车辆路径规划的示意图；
图5示出了本发明实施例提供的一种车辆的路径规划装置组成框图；
图6示出了本发明实施例提供的一种计算机设备的结构示意图。
下面将参照附图更详细地描述本公开的示例性实施例。虽然附图中显示了本公开的示例性实施例，然而应当理解，可以以各种形式实现本公开而不应被这里阐述的实施例所限制。相反，提供这些实施例是为了能够更透彻地理解本公开，并且能够将本公开的范围完整的传达给本领域的技术人员。
本发明实施例提供了一种车辆的路径规划方法，如图1所示，该方法包括：
101、在目标车辆处于路口行驶的条件下，获取路口车道线的识别结果。
本发明实施例中，无人驾驶智能车辆在进行轨迹规划过程中，作为当前执行主体的自动驾驶处理器可以为车辆端配置的处理器，也可以为匹配车辆的云端服务器等，此时，当前执行主体控制车辆在路口行驶时，需要进行有效地路径规划，以提高车辆在路口行驶的有效性。其中，作为当前执行主体所要进行控制的目标车辆，可以通过感知系统、定位系统或其他通信设备确定目标车辆是否行驶于路口位置，且本发明实施例中，路口行驶包括进路口行驶、路口内行驶以及出路口行驶，可以通过笛卡尔坐标系或弗朗内特Frenrt坐标系进行确定，本发明实施例不做具体限定。其中，路口车道线包括目标车辆驶进该路口的道路车道线(简称“进路口车道线”)及目标车辆计划驶出该路口的道路车道线(简称“出路口车道线”)，路口车道线的识别结果可以通过感知系统获得，如图2所示的存在进路口车道线示意图，如图3所示的存在出路口车道线示意图。另外，本发明实施例中的“目标车辆处于路口行驶”的场景可以包括目标车辆即将行驶通过路口，此时目标车辆与路口停止线还有一段距离，可以基于目标车辆与进路口车道的路口停止线之间的距离来确定是否满足“目标车辆处于路口行驶”的条件。例如，当检测到目标车辆距离进路口车道的路口停止线预定距离(如50米)时，确定目标车辆满足处于路口行驶的条件，此时获取路口车道线的识别结果。在一个实施例中，“目标车辆处于路口行驶”可以包括车辆已经驶入路口内，当检测到目标车辆通过进路口车道的路口停止线时，则满足目标车辆处于路口行驶条件，此时获取路口车道线的识别结果，本发明实施例不做具体限定。
需要说明的是，车辆为自动驾驶场景中带有自动控制系统的车辆，包括乘用车和商用车，乘用车的常见车型包括但不限于轿车、运动型多用途汽车、多人商务车等，商用车的常见车型包括但不限于皮卡、微客、自缷车、载货车、牵引车、挂车和矿用车辆等，此时，车辆可以基于自动控制系统实现自动驾驶。
102、在所述识别结果为未检测到路口车道线的条件下，确定所述目标车辆的目标跟车对象，并获取所述目标跟车对象的历史轨迹点。
本发明实施例中，为了有效避免对目标车辆进行自动控制过程中无法准确规划车辆在路口处的行驶轨迹，当前执行主体可以根据识别结果来确定目标跟车对象。其中，目标跟车对象即为可以作为目标车辆进行跟随行驶的车辆，目标跟车对象可以包括但不限于大型汽车、小型汽车等位于目标车辆前方或侧方的任何车辆，本发明实施例不做具体限定。在识别结果为未检测到路口车道线时，说明车辆进入路口或出路口时，车辆在进行路径规划时很难确定行驶方向，因此，当前执行主体在确定不存在路口车道线的条件下，确定目标车辆的目标跟车对象，获取目标跟车对象的历史轨迹点，作为自车规划过路口行驶轨迹的参考信息。
需要说明的是，本发明实施例中的感知系统在搜索目标跟车对象的过程中，会按照时间帧单位记录与目标车辆邻近的待跟车对象的行驶轨迹，
例如，1秒记录8帧的车辆移动位置，进而可以根据8帧的车辆移动位置构建出车辆的历史轨迹点，本发明实施例对时间帧不做具体限定。
103、根据所述目标跟车对象的历史轨迹点进行所述目标车辆的路径规划。
本发明实施例中，为了避免车辆处于路口行驶时的不合理路径规划，当前执行主体将历史轨迹点作为目标车辆的路径规划的参考，从而基于目标跟车对象的轨迹进行自车轨迹规划。其中，在进行路径规划过程中，既可以基于历史轨迹点的横向距离进行目标车辆的横向轨迹规划，也可以基于历史轨迹点的纵向距离进行目标车辆的纵向轨迹规划，如图4所示，从而满足在无车道线作为参考时车辆通过路口的有效性。
在另一个本发明实施例中，步骤在所述识别结果为未检测到路口车道线的条件下，确定所述目标车辆的目标跟车对象包括：
搜索与所述目标车辆对应的待跟车对象；
在所述待跟车对象为一个的条件下，将所述待跟车对象确定为目标跟车对象；
在所述待跟车对象为至少两个的条件下，获取所述待跟车对象的参考轨迹点，并基于所述参考轨迹点与所述目标车辆的行驶轨迹点之间的轨迹差异，从所述待跟车对象中筛选目标跟车对象。
为了准确选取目标跟车对象，以确保目标车辆的有效行驶，确定目标跟车对象时，当前执行主体首先搜索目标车辆对应的待跟车对象。当前执行主体可以基于感知系统或全球定位系统对目标车辆的预设距离范围(如10米或20米的半径圆圈距离)内进行搜索，确定可以作为目标跟车对象的至少一个待跟车对象。此时，待跟车对象可以为一个，也可以为两个或三个，本发明实施例不做具体限定。另外，为了将跟车对象的历史轨迹点作为自车路径规划的参考信息，待跟车对象优选为目标车辆正前方、左前方、右前方的车辆，本发明实施例不做具限定。
在本发明实施例中的一个具体实施场景中，若搜索到一个待跟车对象，则直接将此待跟车对象确定为目标跟车对象，以加快目标跟车对象的确定。
在本发明实施例中的另一个具体实施场景中，若搜索到至少两个待跟车对象，为了选取最优的轨迹作为规划参考，则获取各个待跟车对象的参考轨迹点，以基于参考轨迹点与目标车辆的行驶轨迹点之间的轨迹差异选取目标跟车对象。其中，参考轨迹点、行驶轨迹点的确定与历史轨迹点的确定方法相同，本发明实施例不做具体限定。另外，本发明实施例中，轨迹差异包括轨迹重合差异、轨迹角度差异、轨迹距离差异中至少一项，即通过对比参考轨迹点与行驶轨迹点之间的位置差异、角度差异、距离差异来确定轨迹重合差异、轨迹角度差异、轨迹距离差异，以选取最优的目标跟车对象。
在另一个本发明实施例中，步骤基于所述参考轨迹点与所述目标车辆的行驶轨迹点之间的轨迹差异，从所述待跟车对象中筛选目标跟车对象之
前，所述方法还包括：
基于时间帧单位分别生成与所述参考轨迹点对应的第一轨迹路线以及与所述行驶轨迹点对应的第二轨迹路线；
通过第一轨迹路线与所述第二轨迹路线进行路线重合对比，得到轨迹重合差异；或，
基于所述第一轨迹路线的第一轨迹角度与所述第二轨迹路线的第二轨迹角度进行角度对比，得到轨迹角度差异；或，
通过所述第一轨迹路线的第一轨迹长度与所述第二轨迹路线的第二轨迹长度进行长度对比，得到轨迹距离差异。
为了基于轨迹差异准确选取目标跟车对象，并且轨迹差异包括轨迹重合差异、轨迹角度差异、轨迹距离差异中至少一项，当前执行主体在选取目标跟车对象之前，首选分别确定出轨迹重合差异、轨迹角度差异、轨迹距离差异。其中，由于当前执行主体可以通过时间帧单位来识别车辆的轨迹点，因此，当前执行主体首先结合感知系统按照时间帧单位生成参考轨迹点对应的第一轨迹路线，以及行驶轨迹点对应的第二轨迹路径，即各个待跟车对象的轨迹路线以及目标车辆的轨迹路线。
本发明实施例中，针对轨迹重合差异的确定，当前执行主体将多个第一轨迹路线与第二轨迹路线直接进行路线重合对比，可以依次计算第一轨迹路线与第二轨迹路线中距离最近的各个轨迹点之间的位置重合距离，并结合平均值计算方式确定位置重合距离的平均值，作为重合差异，本发明实施例不做具体限定。例如，第一轨迹路线1与第二轨迹路线L之间的重合差异1，第一轨迹路线2与第二轨迹路线L之间的重合差异2，以基于重合差异1、重合差异2选取待跟车对象。
本发明实施例中，针对轨迹角度差异的确定，当前执行主体首先计算各个第一轨迹路线的轨迹角度，以及第二轨迹路线的轨迹角度，可以通过轨迹曲线的整体角度确定，也可以基于轨迹上个点的曲率确定，本发明实施例不做具体限定。当确定第一轨迹角度、第二轨迹角度后，当前执行主体将各个第一轨迹角度与第二轨迹角度进行角度对比，此时，若按照轨迹曲线的整体角度确定的，则在进行角度对比时，即直接按照整体角度进行对比；若按照各个点的曲率确定的，则在进行角度对比时，即按照每一个曲率进行一一对比，从而基于平均值确定对比结果，本发明实施例不做具体限定。
本发明实施例中，针对轨迹长度的确定，当前执行主体首先计算各个第一轨迹路线的轨迹长度，以及第二轨迹路线的轨迹长度，此时，轨迹长度即为在预设时间单位帧所能感知到的轨迹曲线的长度，可以直接基于位置坐标直接计算出各个轨迹路线的曲线长度，即作为轨迹长度，本发明实施例不做具体限定。进而的，在进行轨迹长度重合对比时，即直接对比各个第一轨迹路线与第二轨迹路线的曲线长度即可，本发明实施例不做具体限定。
在另一个本发明实施例中，步骤基于所述参考轨迹点与所述目标车辆的行驶轨迹点之间的轨迹差异，从所述待跟车对象中筛选目标跟车对象包括：
在所述轨迹重合差异、所述轨迹角度差异、所述轨迹距离差异中至少一项与预设跟车筛选条件匹配的条件下，将与所述预设跟车筛选条件匹配的所述待跟车对象确定为目标跟车对象。
为了准确且安全的基于轨迹差异选取最优的目标跟车对象，当前执行主体在获取到轨迹重合差异、轨迹角度差异、轨迹距离差异中至少一项后，与预先配置的跟车筛选条件进行匹配。其中，预设跟车筛选条件包括按照轨迹重合差异、轨迹角度差异、轨迹距离差异至少一项进行筛选目标跟车对象的最大条件或最小条件，此时，最大条件包括预先设定的轨迹重合差异最大值、轨迹角度差异最大值、轨迹距离差异最大值，最小条件包括预先设定的轨迹重合差异最小值、轨迹角度差异最小值、轨迹距离差异最小值，以按照上述的最大值、最小值筛选匹配的待跟车对象，确定为目标跟车对象。例如，待跟车对象a与目标车辆的轨迹角度差异为10度，待跟车对象b与目标车辆的轨迹角度差异为20度，预先设定的预设跟车筛选条件为轨迹角度差异最大值为15度，则将待跟车对象a确定为目标跟车对象，本发明实施例不做具体限定。
需要说明的是，当基于预设跟车筛选条件匹配的待跟车对象为多个时，可以选取距离目标车辆最近的待跟车对象为目标跟车对象，以确保行驶轨迹规划的合理性。当基于预设跟车筛选条件未匹配到待跟车对象时，当前执行主体可以按照预设的行驶轨迹进行行驶，或者在特定的时间间隔到达后重新搜索待跟车对象，本发明实施例不做具体限定。
在另一个本发明实施例中，步骤还包括：
在所述目标车辆按照路径规划得到的行驶路径进行行驶过程中，识别所述目标车辆的横向偏移距离或行驶角度；
在所述横向偏移距离大于预设偏移距离或所述行驶角度大于预设行驶角度的条件下，重新执行在所述识别结果为未检测到路口车道线的条件下，确定所述目标车辆的目标跟车对象的步骤。
为了满足车辆在通过路口时轨迹规划的合理性需求，当前执行主体在基于目标跟车对象的历史轨迹点进行路径规划后，得到行驶路径，以控制目标车辆按照此行驶路径进行行驶。在此过程中，当前执行主体实时识别目标车辆的横向偏移距离或行驶角度，以便与预设偏移距离或预设行驶角度进行对比，确保目标车辆可以按照预定的轨迹通过路口进行行驶，避免过大的横向偏离以及角度偏离。其中，横向偏移距离为基于路径规划后的行驶路径与目标车辆在进入路口行驶状态前的行驶路径的横向位置对比的距离，行驶角度即为目标车辆进行路径规划后的行驶角度，可以基于轨迹点的曲率进行确定，本发明实施例不做具体限定。
本发明实施例中，当前执行主体将获取到的目标车辆的横向偏移距离
与预设偏移距离进行对比，或将行驶角度与预设行驶角度进行对比，在横向偏移距离大于预设偏移距离行驶角度大于预设行驶角度时，说明目标车辆在路口中进行行驶的路线存在偏移，此时，可能是目标跟车对象转弯或变道所引起的。因此，为了避免目标车辆行驶路线的偏移，在具体的一个实施场景中，当前执行主体重新执行确定目标车辆的目标跟车对象的步骤，以重新根据目标跟车对象的历史轨迹点规划行驶路径。
在另一个本发明实施例中，步骤还包括：
在所述识别结果为检测到路口车道线的条件下，基于所述出路口车道线确定车道中心线，并根据所述车道中心线进行所述目标车辆的路径规划。
如图3所示，由于路口车道线包括出路口车道线，在本发明实施例中的一个具体实施场景中，当识别结果为存在出路口车道线时，即感知系统可以感知到车辆位于路口中，并识别到了出路口车道线，则为了提高路径规划的准确性，当前执行主体将识别得到的出路口车道线确定为车道中心线，以根据此车道中心线进行目标车辆的路径规划，既避免了车辆的长期跟车而产生的安全隐患，又提高了车辆出路口时的规划效率。
在另一个本发明实施例中，步骤还包括：
在所述识别结果为存在进路口车道线且未搜索到所述待跟车对象的条件下，获取所述进路口车道线的车道中心线，并基于所述车道中心线生成引导行驶路径，以在所述目标车辆按照所述引导行驶路径行驶且识别到出路口车道线的条件下根据所述出路口车道线的车道中心线进行所述目标车辆的路径规划。
如图2所示，由于路口车道线包括进路口车道线，在本发明实施例中的一个具体实施场景中，当前执行主体在确定识别结果为存在进路口车道线，且感知系统未搜索到待跟车对象时，可以通过进路口车道线的车道中心线生成引导行驶路口。此时，引导行驶路口向路口中进行延伸，直至感知系统识别到出路口车道线或者待跟车对象，则执行对应的步骤即可，使车辆在无前方指引情况下能够平稳进入路口，满足行驶安全需求，从而提高车辆进入路口时的规划效率。
本发明实施例通过在目标车辆处于路口行驶的条件下，获取路口车道线的识别结果；在所述识别结果为未检测到路口车道线的条件下，确定所述目标车辆的目标跟车对象，并获取所述目标跟车对象的历史轨迹点；根据所述目标跟车对象的历史轨迹点进行所述目标车辆的路径规划，通过在车辆过路口时以跟车行驶的方式进行路径规划，实现在无地图数据或无路口车道线信息时进行过路口路径规划的目的，从而提高车辆位于路口处行驶的路径规划的有效性，实现无地图数据或无路口车道线信息的过路口功能。
进一步的，作为对上述图1所示方法的实现，本发明实施例提供了一种车辆的路径规划装置，如图5所示，该装置包括：
确定模块21，用于在目标车辆处于路口行驶的条件下，获取路口车道
线的识别结果；
获取模块22，用于在所述识别结果为未检测到路口车道线的条件下，确定所述目标车辆的目标跟车对象，并获取所述目标跟车对象的历史轨迹点；
规划模块23，用于根据所述目标跟车对象的历史轨迹点进行所述目标车辆的路径规划。
进一步地，所述获取模块包括：
搜索单元，用于搜索与所述目标车辆对应的待跟车对象；
确定单元，用于在所述待跟车对象为一个的条件下，将所述待跟车对象确定为目标跟车对象；
获取单元，用于在所述待跟车对象为至少两个的条件下，获取所述待跟车对象的参考轨迹点，并基于所述参考轨迹点与所述目标车辆的行驶轨迹点之间的轨迹差异，从所述待跟车对象中筛选目标跟车对象。
进一步地，所述轨迹差异包括轨迹重合差异、轨迹角度差异、轨迹距离差异中至少一项，所述获取模块还包括：
生成单元，用于基于时间帧单位分别生成与所述参考轨迹点对应的第一轨迹路线以及与所述行驶轨迹点对应的第二轨迹路线；
对比单元，用于通过第一轨迹路线与所述第二轨迹路线进行路线重合对比，得到轨迹重合差异；或，基于所述第一轨迹路线的第一轨迹角度与所述第二轨迹路线的第二轨迹角度进行角度对比，得到轨迹角度差异；或，通过所述第一轨迹路线的第一轨迹长度与所述第二轨迹路线的第二轨迹长度进行长度对比，得到轨迹距离差异。
进一步地，所述获取单元，具体用于在所述轨迹重合差异、所述轨迹角度差异、所述轨迹距离差异中至少一项与预设跟车筛选条件匹配的条件下，将与所述预设跟车筛选条件匹配的所述待跟车对象确定为目标跟车对象，所述预设跟车筛选条件包括按照轨迹重合差异、轨迹角度差异、轨迹距离差异至少一项进行筛选目标跟车对象的最大条件或最小条件。
进一步地，所述装置还包括：
识别模块，用于在所述目标车辆按照路径规划得到的行驶路径进行行驶过程中，识别所述目标车辆的横向偏移距离或行驶角度；
执行模块，用于在所述横向偏移距离大于预设偏移距离或所述行驶角度大于预设行驶角度的条件下，重新执行在所述识别结果为未检测到路口车道线的条件下，确定所述目标车辆的目标跟车对象的步骤。
进一步地，所述路口车道线包括出路口车道线，所述装置还包括：
规划模块，用于在所述识别结果为检测到路口车道线的条件下，基于所述出路口车道线确定车道中心线，并根据所述车道中心线进行所述目标车辆的路径规划。
进一步地，所述路口车道线包括进路口车道线，所述装置还包括：
生成模块，用于在所述识别结果为存在进路口车道线且未搜索到所述
待跟车对象的条件下，获取所述进路口车道线的车道中心线，并基于所述车道中心线生成引导行驶路径，以在所述目标车辆按照所述引导行驶路径行驶且识别到出路口车道线的条件下根据所述出路口车道线的车道中心线进行所述目标车辆的路径规划。
本发明实施例通过在目标车辆处于路口行驶的条件下，获取路口车道线的识别结果；在所述识别结果为未检测到路口车道线的条件下，确定所述目标车辆的目标跟车对象，并获取所述目标跟车对象的历史轨迹点；根据所述目标跟车对象的历史轨迹点进行所述目标车辆的路径规划，通过在车辆过路口时以跟车行驶的方式进行路径规划，实现在无地图数据或无路口车道线信息时进行过路口路径规划的目的，从而提高车辆位于路口处行驶的路径规划的有效性，实现无地图数据或无路口车道线信息的过路口功能。
根据本发明一个实施例提供了一种可读存储介质，所述可读存储介质上存储有程序或指令，所述程序或指令被处理器执行时实现如上述车辆的路径规划方法的步骤。
图6示出了根据本发明一个实施例提供的一种计算机设备的结构示意图，包括至少一个处理器，所述处理器和存储器耦合，所述存储器存储有在所述处理器上运行的程序或指令，所述程序或指令被所述处理器执行时实现如上述的车辆的路径规划方法的步骤。本发明具体实施例并不对计算机设备的具体实现做限定。
如图6所示，该计算机设备可以包括：处理器(processor)302、通信接口(Communications Interface)304、存储器(memory)306、以及通信总线308。
其中：处理器302、通信接口304、以及存储器306通过通信总线308完成相互间的通信。
通信接口304，用于与其它设备比如客户端或其它服务器等的网元通信。
处理器302，用于执行程序310，具体可以执行上述车辆的路径规划方法实施例中的相关步骤。
具体地，程序310可以包括程序代码，该程序代码包括计算机操作指令。
处理器302可能是中央处理器CPU，或者是特定集成电路ASIC(Application Specific Integrated Circuit)，或者是被配置成实施本发明实施例的一个或多个集成电路。终端包括的一个或多个处理器，可以是同一类型的处理器，如一个或多个CPU；也可以是不同类型的处理器，如一个或多个CPU以及一个或多个ASIC。
存储器306，用于存放程序310。存储器306可能包含高速RAM存储器，也可能还包括非易失性存储器(non-volatile memory)，例如至少一个磁盘存储器。
程序310具体可以用于使得处理器302执行以下操作：
在目标车辆处于路口行驶的条件下，获取路口车道线的识别结果；
在所述识别结果为未检测到路口车道线的条件下，确定所述目标车辆的目标跟车对象，并获取所述目标跟车对象的历史轨迹点；
根据所述目标跟车对象的历史轨迹点进行所述目标车辆的路径规划。
显然，本领域的技术人员应该明白，上述的本发明的各模块或各步骤可以用通用的计算装置来实现，它们可以集中在单个的计算装置上，或者分布在多个计算装置所组成的网络上，可选地，它们可以用计算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，并且在某些情况下，可以以不同于此处的顺序执行所示出或描述的步骤，或者将它们分别制作成各个集成电路模块，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，本发明不限制于任何特定的硬件和软件结合。
以上所述仅为本发明的优选实施例而已，并不用于限制本发明，对于本领域的技术人员来说，本发明可以有各种更改和变化。凡在本发明的精神和原则之内，所作的任何修改、等同替换、改进等，均应包括在本发明的保护范围之内。
Claims (11)
- 一种车辆的路径规划方法，其特征在于，包括：在目标车辆处于路口行驶的条件下，获取路口车道线的识别结果；在所述识别结果为未检测到路口车道线的条件下，确定所述目标车辆的目标跟车对象，并获取所述目标跟车对象的历史轨迹点；根据所述目标跟车对象的历史轨迹点进行所述目标车辆的路径规划。
- 根据权利要求1所述的方法，其特征在于，所述在所述识别结果为未检测到路口车道线的条件下，确定所述目标车辆的目标跟车对象包括：搜索与所述目标车辆对应的待跟车对象；在所述待跟车对象为一个的条件下，将所述待跟车对象确定为目标跟车对象；在所述待跟车对象为至少两个的条件下，获取所述待跟车对象的参考轨迹点，并基于所述参考轨迹点与所述目标车辆的行驶轨迹点之间的轨迹差异，从所述待跟车对象中筛选目标跟车对象。
- 根据权利要求2所述的方法，其特征在于，所述轨迹差异包括轨迹重合差异、轨迹角度差异、轨迹距离差异中至少一项，所述基于所述参考轨迹点与所述目标车辆的行驶轨迹点之间的轨迹差异，从所述待跟车对象中筛选目标跟车对象之前，所述方法还包括：基于时间帧单位分别生成与所述参考轨迹点对应的第一轨迹路线以及与所述行驶轨迹点对应的第二轨迹路线；通过第一轨迹路线与所述第二轨迹路线进行路线重合对比，得到轨迹重合差异；或，基于所述第一轨迹路线的第一轨迹角度与所述第二轨迹路线的第二轨迹角度进行角度对比，得到轨迹角度差异；或，通过所述第一轨迹路线的第一轨迹长度与所述第二轨迹路线的第二轨迹长度进行长度对比，得到轨迹距离差异。
- 根据权利要求3所述的方法，其特征在于，所述基于所述参考轨迹点与所述目标车辆的行驶轨迹点之间的轨迹差异，从所述待跟车对象中筛选目标跟车对象包括：在所述轨迹重合差异、所述轨迹角度差异、所述轨迹距离差异中至少一项与预设跟车筛选条件匹配的条件下，将与所述预设跟车筛选条件匹配的所述待跟车对象确定为目标跟车对象，所述预设跟车筛选条件包括按照轨迹重合差异、轨迹角度差异、轨迹距离差异至少一项进行筛选目标跟车对象的最大条件或最小条件。
- 根据权利要求3所述的方法，其特征在于，所述方法还包括：在所述目标车辆按照路径规划得到的行驶路径进行行驶过程中，识别所述目标车辆的横向偏移距离或行驶角度；在所述横向偏移距离大于预设偏移距离或所述行驶角度大于预设行驶 角度的条件下，重新执行在所述识别结果为未检测到路口车道线的条件下，确定所述目标车辆的目标跟车对象的步骤。
- 根据权利要求1-5任一项所述的方法，其特征在于，所述路口车道线包括出路口车道线，所述方法还包括：在所述识别结果为检测到路口车道线的条件下，基于所述出路口车道线确定车道中心线，并根据所述车道中心线进行所述目标车辆的路径规划。
- 根据权利要求1-5任一项所述的方法，其特征在于，所述路口车道线包括进路口车道线，所述方法还包括：在所述识别结果为存在进路口车道线且未搜索到所述待跟车对象的条件下，获取所述进路口车道线的车道中心线，并基于所述车道中心线生成引导行驶路径，以在所述目标车辆按照所述引导行驶路径行驶且识别到出路口车道线的条件下根据所述出路口车道线的车道中心线进行所述目标车辆的路径规划。
- 一种车辆的路径规划装置，其特征在于，包括：确定模块，用于在目标车辆处于路口行驶的条件下，获取路口车道线的识别结果；获取模块，用于在所述识别结果为未检测到路口车道线的条件下，确定所述目标车辆的目标跟车对象，并获取所述目标跟车对象的历史轨迹点；规划模块，用于根据所述目标跟车对象的历史轨迹点进行所述目标车辆的路径规划。
- 一种车辆，其特征在于，包括权利要求8所述的车辆的路径规划装置。
- 一种计算机设备，其特征在于，包括至少一个处理器，所述处理器和存储器耦合，所述存储器存储有在所述处理器上运行的程序或指令，所述程序或指令被所述处理器执行时实现如权利要求1至7中任一项所述的车辆的路径规划方法的步骤。
- 一种可读存储介质，其上存储有程序或指令，其特征在于，所述程序或指令被处理器执行时实现如权利要求1至7中任一项所述的车辆的路径规划方法的步骤。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310426222.9A CN118816914A (zh) | 2023-04-20 | 2023-04-20 | 车辆的路径规划方法及装置、车辆 |
| CN202310426222.9 | 2023-04-20 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2024216768A1 true WO2024216768A1 (zh) | 2024-10-24 |
Family
ID=93079396
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2023/107129 WO2024216768A1 (zh) | 2023-04-20 | 2023-07-13 | 车辆的路径规划方法及装置、车辆 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN118816914A (zh) |
| WO (1) | WO2024216768A1 (zh) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110626349A (zh) * | 2019-09-20 | 2019-12-31 | 中国第一汽车股份有限公司 | 自动驾驶车辆的控制方法、装置、汽车控制器及存储介质 |
| CN111209361A (zh) * | 2019-12-31 | 2020-05-29 | 深圳安智杰科技有限公司 | 跟车目标选择方法、装置、电子设备及可读存储介质 |
| CN112498367A (zh) * | 2020-11-25 | 2021-03-16 | 重庆长安汽车股份有限公司 | 一种行驶轨迹规划方法、装置、汽车、控制器及计算机可读存储介质 |
| CN112665590A (zh) * | 2020-12-11 | 2021-04-16 | 国汽(北京)智能网联汽车研究院有限公司 | 车辆的轨迹确定方法、装置、电子设备及计算机存储介质 |
| CN113353078A (zh) * | 2021-06-24 | 2021-09-07 | 中汽创智科技有限公司 | 一种无车道线自动跟车轨迹确定方法及装置 |
| KR20210153998A (ko) * | 2020-06-11 | 2021-12-20 | 현대자동차주식회사 | 차량 및 그 제어방법 |
| CN114763996A (zh) * | 2022-04-27 | 2022-07-19 | 重庆长安汽车股份有限公司 | 一种基于多传感器融合的复杂场景路径规划方法 |
| CN115431970A (zh) * | 2021-12-07 | 2022-12-06 | 北京罗克维尔斯科技有限公司 | 用于车辆的驾驶方法和装置 |
-
2023
- 2023-04-20 CN CN202310426222.9A patent/CN118816914A/zh active Pending
- 2023-07-13 WO PCT/CN2023/107129 patent/WO2024216768A1/zh unknown
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110626349A (zh) * | 2019-09-20 | 2019-12-31 | 中国第一汽车股份有限公司 | 自动驾驶车辆的控制方法、装置、汽车控制器及存储介质 |
| CN111209361A (zh) * | 2019-12-31 | 2020-05-29 | 深圳安智杰科技有限公司 | 跟车目标选择方法、装置、电子设备及可读存储介质 |
| KR20210153998A (ko) * | 2020-06-11 | 2021-12-20 | 현대자동차주식회사 | 차량 및 그 제어방법 |
| CN112498367A (zh) * | 2020-11-25 | 2021-03-16 | 重庆长安汽车股份有限公司 | 一种行驶轨迹规划方法、装置、汽车、控制器及计算机可读存储介质 |
| CN112665590A (zh) * | 2020-12-11 | 2021-04-16 | 国汽(北京)智能网联汽车研究院有限公司 | 车辆的轨迹确定方法、装置、电子设备及计算机存储介质 |
| CN113353078A (zh) * | 2021-06-24 | 2021-09-07 | 中汽创智科技有限公司 | 一种无车道线自动跟车轨迹确定方法及装置 |
| CN115431970A (zh) * | 2021-12-07 | 2022-12-06 | 北京罗克维尔斯科技有限公司 | 用于车辆的驾驶方法和装置 |
| CN114763996A (zh) * | 2022-04-27 | 2022-07-19 | 重庆长安汽车股份有限公司 | 一种基于多传感器融合的复杂场景路径规划方法 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118816914A (zh) | 2024-10-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11377096B2 (en) | Automatic parking method and device | |
| US20200265710A1 (en) | Travelling track prediction method and device for vehicle | |
| US20200269874A1 (en) | Track prediction method and device for obstacle at junction | |
| US11520340B2 (en) | Traffic lane information management method, running control method, and traffic lane information management device | |
| CN111301409A (zh) | 一种泊车路径规划方法、装置、车辆和存储介质 | |
| CN113353103A (zh) | 一种弯道车速控制方法、装置、设备及介质 | |
| US10909377B2 (en) | Tracking objects with multiple cues | |
| CN108171967B (zh) | 一种交通控制方法及装置 | |
| JP2023009531A (ja) | 走行軌道生成方法、走行支援方法、走行軌道生成装置および走行支援装置 | |
| CN113419546B (zh) | 一种无人车的控制方法、装置、介质及电子设备 | |
| CN114684111A (zh) | 一种车头先入的泊车方法、装置和系统 | |
| CN112327826A (zh) | 一种路径规划方法、装置、设备和介质 | |
| CN118235180A (zh) | 预测可行驶车道的方法和装置 | |
| CN115489516A (zh) | 一种泊车速度规划方法、系统及存储介质 | |
| CN112785072A (zh) | 路线规划和模型训练方法、装置、设备及存储介质 | |
| WO2024216768A1 (zh) | 车辆的路径规划方法及装置、车辆 | |
| CN113899378A (zh) | 一种变道处理方法、装置、存储介质及电子设备 | |
| EP4151487B1 (en) | Method and apparatus for controlling lane changing, electronic device and storage medium | |
| JP5682302B2 (ja) | 走行道路推定装置、方法およびプログラム | |
| CN115497322A (zh) | 一种窄路会车方法、装置、设备及存储介质 | |
| CN115583258A (zh) | 自动驾驶车辆会车控制方法、装置、车辆控制设备和介质 | |
| CN115469669A (zh) | 一种窄路会车方法、装置、设备及存储介质 | |
| CN114355932A (zh) | 一种机器人控制方法、装置及机器人 | |
| CN117508232A (zh) | 车辆周边障碍物的轨迹预测方法、装置、设备及介质 | |
| WO2024178799A1 (zh) | 车辆通行效率的确定方法及装置、车辆 |