JP2022002041A - Environment recognition device, environment recognition method, and environment recognition program - Google Patents

Abstract

To provide an environment recognition device or the like capable of more precisely recognizing an environment by sensor fusion processing.SOLUTION: An environment recognition device 100 recognizes an environment of a vehicle A in which plural types of periphery monitoring sensors 10 whose detection range is at least partially overlapped. The environment recognition device 100 comprises a detection information acquisition part 110 for acquiring detection information from each of the plural types of periphery monitoring sensors 10. The environment recognition device 100 comprises: a weight setting part 130 for setting a weight corresponding to a travel scene of the vehicle for each detection information about an overlapping part in the detection range; and a recognition information generation part 140 for generating environment recognition information by integrating each detection information in which the weight is set.SELECTED DRAWING: Figure 2

Description

The disclosure herein relates to a technique for recognizing the outside world of a vehicle.

Patent Document 1 discloses a device for recognizing an object around a vehicle. This device performs sensor fusion processing on the detection results of the camera, radar device, and LiDAR, and recognizes the position, type, speed, and the like of the object.

JP-A-2019-95875

The apparatus of Patent Document 1 does not consider factors that affect the sensor fusion process. Therefore, there is a risk that the accuracy of the recognition result by the sensor fusion processing will be impaired.

It is an object of the disclosure to provide an outside world recognition device, an outside world recognition method, and an outside world recognition program capable of more accurately recognizing the outside world by sensor fusion processing.

The plurality of embodiments disclosed herein employ different technical means to achieve their respective objectives. Further, the scope of claims and the reference numerals in parentheses described in this section are examples showing the correspondence with the specific means described in the embodiment described later as one embodiment, and limit the technical scope. is not it.

One of the disclosed outside world recognition devices is an outside world recognition device that recognizes the outside world of a vehicle (A) equipped with a plurality of types of sensors (10) having at least a partially overlapping detection range.
An acquisition unit (110) that acquires detection information from multiple types of sensors,
A setting unit (130) that sets weights according to the driving scene of the vehicle for each detection information regarding the overlapping portion of the detection range, and
A generator (140) that integrates each weighted detection information to generate recognition information for the outside world, and
To prepare for.

One of the disclosed external world recognition methods is external world recognition performed by a processor (102) in order to recognize the outside world of a vehicle (A) equipped with a plurality of types of sensors (10) having at least partially overlapping detection ranges. It ’s a method,
The acquisition process (S10) for acquiring detection information from multiple types of sensors,
A setting process (S30) for setting weights according to the driving scene of the vehicle for each detection information regarding the overlapping portion of the detection range, and
A generation process (S40) that integrates each weighted detection information to generate recognition information for the outside world, and
including.

One of the disclosed outside world recognition programs is stored in a storage medium (101) and a processor in order to recognize the outside world of a vehicle (A) equipped with a plurality of types of sensors (10) having at least a partially overlapping detection range. An external recognition program including an instruction to be executed by (102).
The order is
The acquisition process (S10) for acquiring detection information from multiple types of sensors,
A setting process (S30) for setting weights according to the driving scene of the vehicle for each detection information regarding the overlapping portion of the detection range, and
A generation process (S40) that integrates each weighted detection information to generate recognition information of the outside world, and
According to these disclosures including, when the detection information is acquired from a plurality of types of sensors, a weight is set for each detection information regarding the overlapping portion of the detection range according to the driving scene of the vehicle. Then, each detection information for which the weight is set is integrated to generate recognition information. Therefore, the recognition information of the outside world is generated by the sensor fusion processing in consideration of the driving scene. As described above, it is possible to provide an outside world recognition device, an outside world recognition method, and an outside world recognition program capable of more accurately recognizing the outside world by sensor fusion processing.

It is a figure which shows the system including the outside world recognition device. It is a block diagram which shows an example of the function which an outside world recognition device has. It is a figure which shows the detection range of each sensor mounted on a vehicle simply. It is a figure which shows an example of the setting of the weight in each running scene at the time of passing through a tunnel. It is a flowchart which shows an example of the outside world recognition method executed by the outside world recognition apparatus.

(First Embodiment)
The external world recognition device 100 of the first embodiment will be described with reference to FIGS. 1 to 5. The outside world recognition device 100 is an electronic control device mounted on the vehicle A. The outside world recognition device 100 recognizes the outside world of the vehicle A. The outside world recognition device 100 is connected to the peripheral monitoring sensor 10, the locator 20, the illuminance sensor 30, the body ECU 40, and the automatic driving ECU 50 via a communication bus or the like.

The peripheral monitoring sensor 10 is an autonomous sensor that monitors the surrounding environment of the vehicle A. The peripheral monitoring sensor 10 includes, for example, a camera 11, a LiDAR (Light Detection and Ranging / Laser Imaging Detection and Ranging) 12, and a millimeter-wave radar 13.

The camera 11 outputs image data in which the detection range is captured as detection information. As shown by the dotted line in FIG. 3, for example, a plurality of cameras 11 are provided so as to have the front range, the front side range, and the rear range of the vehicle A as the detection range. The image data includes at least the intensity information of the outside light in the detection range.

The LiDAR 12 is a laser radar that irradiates a laser beam and detects the reflected light. By analyzing the received data of the reflected light, the LiDAR 12 outputs point group data including at least one of the distance to each reflection point where the laser light is reflected and the reflection intensity at each reflection point as detection information. The LiDAR 12 has, for example, the entire circumference of the vehicle A as a detection range, as shown by a broken line in FIG. Therefore, the detection range of LiDAR 12 overlaps at least partially with the detection range of the camera 11 and the millimeter wave radar 13 described later.

The millimeter wave radar 13 is a radio wave radar that irradiates millimeter waves or quasi-millimeter waves and detects reflected waves reflected by an object. The millimeter wave radar 13 analyzes the received data of the reflected wave, and outputs information regarding the position and relative velocity of the object with respect to the vehicle A as detection information. It is assumed that the millimeter wave radar 13 can detect three-dimensional positions of a horizontal position, a depth direction position, and a height direction position. The millimeter-wave radar 13 has, for example, the front side range and the rear side range of the vehicle A as the detection range, as shown by the alternate long and short dash line in FIG. The detection range of the millimeter wave radar 13 overlaps with the detection range of the camera 11 and the LiDAR 12 at least partially.

The locator 20 generates own vehicle position information and the like by compound positioning that combines a plurality of acquired information. The locator 20 includes a GNSS (Global Navigation Satellite System) receiver 21, an inertial sensor 22, a map DB 23, and a locator ECU 24. The GNSS receiver 21 receives positioning signals from a plurality of positioning satellites. The inertial sensor 22 is a sensor that detects the inertial force acting on the vehicle A. The inertial sensor includes, for example, a gyro sensor and an acceleration sensor.

The map DB 23 is a non-volatile memory and stores map data such as link data, node data, road shape, and structures. The map data may be a three-dimensional map composed of point clouds of road shapes and feature points of structures. The three-dimensional map may be generated based on the captured image by REM (Road Experience Management). Further, the map data may include traffic regulation information, road construction information, meteorological information, signal information and the like. The map data stored in the map DB 23 is updated regularly or at any time based on the latest information received by the in-vehicle communication device.

The locator ECU 24 is configured mainly to include a microcomputer provided with a processor, a memory, an input / output interface, a bus connecting them, and the like. The locator ECU 24 sequentially positions the position of the vehicle A (hereinafter referred to as the own vehicle position) by combining the positioning signal received by the GNSS receiver 21, the map data of the map DB 23, and the measurement result of the inertial sensor 22. The position of the own vehicle may be, for example, configured to be represented by the coordinates of latitude and longitude. For the positioning of the own vehicle position, the mileage obtained from the signals sequentially output from the vehicle speed sensor mounted on the vehicle A may be used. When a three-dimensional map consisting of a point cloud of road shapes and feature points of a structure is used as map data, the locator uses the three-dimensional map and the detection result of the peripheral monitoring sensor without using a GNSS receiver. It may be configured to specify the position of the own vehicle by using it.

The illuminance sensor 30 is a sensor that detects the brightness around the vehicle, particularly the illuminance. The illuminance sensor 30 sequentially provides the detected illuminance to the outside world recognition device 100 as brightness information around the vehicle A.

The body ECU 40 is an ECU that integrally controls body-based in-vehicle devices mounted on the vehicle A. The body ECU 40 is communicably connected to the headlight device 41. The headlight device 41 includes a headlight and a control circuit for controlling the headlight, and controls the lighting state of the headlight according to a control signal from the body ECU 40.

The body ECU 40 outputs a control signal for controlling the operation of the headlight device 41 to the headlight device 41 based on the operation of the light switch by the driver's seat occupant, the detection value of the illuminance sensor 30, or the command from the automatic driving ECU. .. For example, when the detection value of the illuminance sensor 30 falls below the threshold value, the body ECU 40 outputs a control signal instructing the lighting of the headlight.

The automatic operation ECU 50 is configured mainly to include a computer including a processor, a memory, an input / output interface, a bus connecting them, and the like. The automatic driving ECU 50 generates a traveling track of the vehicle based on the recognition information from the outside world recognition device 100 and executes the automatic driving of the vehicle A.

The outside world recognition device 100 recognizes the outside world of the vehicle A, that is, the traveling environment, based on the information from the peripheral monitoring sensor 10 described above. The external world recognition device 100 is configured mainly to include a computer including a memory 101, a processor 102, an input / output interface, a bus connecting them, and the like. The processor 102 is hardware for arithmetic processing. The processor 102 includes, for example, at least one of a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a RISC (Reduced Instruction Set Computer) -CPU, and the like as a core.

The memory 101 non-transiently stores or stores a computer-readable program, data, or the like, for example, at least one type of non-transitional substantive storage medium (non-transitional memory, magnetic medium, optical medium, or the like, etc.). transitory tangible storage medium). The memory 101 stores various programs executed by the processor 102, such as an external recognition program described later.

The processor 102 executes a plurality of instructions included in the external recognition program stored in the memory 101. As a result, the outside world recognition device 100 constructs a plurality of functional units for recognizing the outside world. In this way, in the outside world recognition device 100, a plurality of functional units are constructed by causing the processor 102 to execute a plurality of instructions by the program stored in the memory 101. Specifically, as shown in FIG. 2, the external world recognition device 100 is constructed with functional units such as a detection information acquisition unit 110, a traveling scene determination unit 120, a weight setting unit 130, and a recognition information generation unit 140.

The detection information acquisition unit 110 acquires detection information from the peripheral monitoring sensor 10. Specifically, the detection information acquisition unit 110 acquires the captured image of the detection range from the camera 11 as detection information, acquires the point cloud data as detection information from the LiDAR 12, and obtains the relative position and relative speed of the object from the millimeter-wave radar. Acquires the data related to the detection information.

The traveling scene determination unit 120 determines the traveling scene of the vehicle A based on each detection information from the detection information acquisition unit 110, map information from the locator ECU, control information of the headlight device 41 from the body ECU 40, and the like. Specifically, the traveling scene determination unit 120 determines whether or not the current traveling scene corresponds to any of a plurality of specific scenes in which the reliability of the specific sensor is lowered among the peripheral monitoring sensors 10.

The specific scene includes a scene (brightness reduction scene) running during the weight adjustment period immediately after entering the dark area from the bright area. Here, the dark area is an area in which the brightness (illuminance) around the vehicle A is estimated to be smaller than the bright area. The dark area includes an area that is presumed to be a dark place due to a light-shielding structure that blocks sunlight, such as inside a tunnel, under an elevated structure, an underpass, and the vicinity of a mountain surface. Further, the weight adjustment period is, for example, a period from entering the dark area to turning on the headlight device 41. The traveling scene determination unit 120 may determine entry into the dark area based on the detection information of the structure by the millimeter wave radar 13. For example, the traveling scene determination unit 120 may determine that the area where the light-shielding structure exists directly above the light-shielding structure is a dark place area, or may consider the structure of the light-shielding structure and the intrusion of sunlight into the dark place area. May be estimated. Further, the traveling scene determination unit 120 may determine whether or not the weight adjustment period is reached based on the control information of the headlight device 41 by the body ECU 40.

Further, the specific scene includes a scene (brightness increase scene) immediately after entering the bright area from the dark area. Similar to the brightness reduction scene, the traveling scene determination unit 120 may determine entry into the bright area based on the detection information of the structure by the millimeter wave radar 13. The brightness increase scene is an example of the "light place approach scene".

Further, the specific scene further includes a side wall curve scene traveling on a curve section on a road provided with a side wall. Here, the road provided with the side wall is a road in a tunnel, an underpass, or the like. The traveling scene determination unit 120 may determine whether or not the scene is a side wall curve scene based on the detection information of the camera 11 or the LiDAR 12 and the map information.

Further, the specific scene includes a snowfall scene. The traveling scene determination unit 120 may determine that it is a snowfall scene when it can be estimated that there is snow, for example, based on the detection information from the LiDAR 12. Specifically, the traveling scene determination unit 120 estimates that there is snow when the traveling division line is no longer detected by the LiDAR 12. The traveling scene determination unit 120 may determine the presence or absence of snow by combining the detection information from other sensors. For example, it may be determined whether or not it is a snowfall scene based on the weather information distributed from the traffic center or the like.

In addition, the specific scene includes a multiple reflection scene in which a specific electromagnetic wave condition relating to the multiple reflection of the electromagnetic wave is satisfied. Here, the electromagnetic wave condition is satisfied when the degree of multiple reflection of the LiDAR 12 and the millimeter wave radar 13 is out of the allowable range. For example, the traveling scene determination unit 120 determines that the electromagnetic wave condition is satisfied when a metal structure such as a guardrail is present on the side of the vehicle A and another vehicle is present in front of the vehicle A.

Further, the specific scene includes a real scene reflection scene in which a specific real scene reflection condition regarding a reflective object reflecting a real scene of the outside world is satisfied. The actual scene reflection condition is satisfied when it is estimated that a reflective object reflecting the actual scene exists in the imaging range of the camera 11. Reflective objects that reflect the actual scene are the glass-walled outer walls of the building. The traveling scene determination unit 120 determines the presence / absence of a reflective object, for example, based on the point cloud data and the map information of the LiDAR 12.

The traveling scene determination unit 120 determines whether or not the current driving scene corresponds to any of the plurality of specific scenes described above, and sequentially provides the determination result to the weight setting unit 130.

The weight setting unit 130 sets weights for each detection information based on the determination result of the traveling scene determination unit 120. When the weight setting unit 130 determines that the traveling scene corresponds to a specific scene, the weight setting unit 130 sets a defined magnitude-related weight for each of the detection information of each peripheral monitoring sensor 10.

More specifically, the weight setting unit 130 sets the weight of the detection information of the LiDAR 12 to be larger than the weight of the detection information of the camera 11 and the millimeter wave radar 13 in the brightness reduction scene (see FIG. 4). Further, the weight setting unit 130 sets the weight of the detection information of the camera 11 to be smaller than the weight of the detection information of the LiDAR 12 and the millimeter wave radar 13 in the brightness increase scene and the snowfall scene (see FIG. 4). In addition, the weight setting unit 130 sets the weight of the detection information of the LiDAR 12 to be larger than the weight of the detection information of the millimeter wave radar 13 in the snowfall scene.

The weight setting unit 130 determines the change timing of the traveling scene to the brightness decrease scene or the brightness increase scene based on the detection information from the millimeter wave radar 13. Specifically, the weight setting unit 130 sets the change timing to the brightness reduction scene as the entry timing of the light-shielding structure into the light-shielding range based on the position information of the light-shielding structure detected by the millimeter-wave radar 13. do. The weight setting unit 130 may simply set the light-shielding range as the existing area of the light-shielding structure, or may determine the light-shielding range in combination with other information such as illuminance information. Then, the weight setting unit 130 sets the change timing to the brightness increase scene as the exit timing from the light-shielding range of the light-shielding structure. The weight setting unit 130 changes the weight applied to each detection information at the determined change timing.

Further, the weight setting unit 130 determines the change of the traveling scene to the snowfall scene based on the detection information from the LiDAR 12. Specifically, the weight setting unit 130 estimates that the non-detection range of the traveling lane marking by LiDAR 12 is the snow covering range where the traveling lane marking is buried by the snow cover, and changes the approach timing to the snow cover range to the snowfall scene. The timing. The weight setting unit 130 changes the weight applied to each detection information at the determined change timing.

The weight setting unit 130 determines the magnitude of the weight of each detection information in the brightness decrease scene and the brightness increase scene based on the illuminance information from the illuminance sensor 30. Specifically, the weight setting unit 130 weights the detection information of the LiDAR 12 as the difference in illuminance between the bright area and the dark area increases in the brightness reduction scene, the camera 11 and the millimeter wave radar 13. Set larger than the weight of the detection information of. Further, the weight setting unit 130 sets the weight of the detection information of the camera 11 as the detection information of the LiDAR 12 and the millimeter wave radar 13 as the difference in illuminance between the bright area and the dark area becomes larger in the brightness increase scene. Set smaller than the weight of.

Further, the weight setting unit 130 sets the weights of the detected information in the side wall curve scene as LiDAR 12, the camera 11, and the millimeter wave radar 13 in descending order. That is, in the side wall curve scene, the weight of the detection information of the millimeter wave radar 13 is set to be smaller than the weight of the detection information of the camera 11 and the LiDAR 12 (see FIG. 4).

The weight setting unit 130 sets the weight of the detection information of the camera 11 to be larger than the weight of the detection information of the LiDAR 12 and the millimeter wave radar 13 in the multiple reflection scene. In addition, the weight setting unit 130 sets the weight of the detection information of the LiDAR 12 to be larger than the weight of the detection information of the millimeter wave radar 13 in the multiple reflection scene.

Further, the weight setting unit 130 sets the weight of the detection information of the camera 11 to be smaller than the weight of the detection information of the LiDAR 12 and the millimeter wave radar 13 in the actual scene reflection scene.

If it is determined that the current driving scene does not correspond to any of the scenes in which the reliability of the specific sensor is lowered, the weight setting unit 130 cancels the weight setting for any of the detection information. ..

The recognition information generation unit 140 generates recognition information of the outside world by a sensor fusion process that integrates each detection information for which weights are set. The recognition information generation unit 140 generates, for example, the type, position, shape, size, relative speed, etc. of each detected object as recognition information. The recognition information generation unit 140 sequentially provides the generated recognition information to the automatic operation ECU 50.

Next, the flow of the external world recognition method executed by the external world recognition device 100 jointly by the functional blocks will be described below with reference to FIG. In the flow described later, "S" means a plurality of steps of the flow executed by a plurality of instructions included in the program.

First, in S10, the detection information acquisition unit 110 acquires the detection information from each peripheral monitoring sensor 10. Next, in S20, the traveling scene determination unit 120 determines whether or not the current traveling scene corresponds to any of the specific scenes. In the following S30, the weight setting unit 130 sets the weight of each detection information based on the determination result. Further, in S40, the recognition information generation unit 140 integrates the weighted detection information to generate and output the recognition information, and then ends a series of processes.

The above-mentioned S10 is an example of the "acquisition process", S30 is an example of the "setting process", S20 is an example of the "determination process", and S40 is an example of the "generation process".

Next, the action and effect brought about by the first embodiment will be described.

According to the first embodiment, when the detection information is acquired from the plurality of types of peripheral monitoring sensors 10, weights corresponding to the traveling scene of the vehicle A are set for each detection information regarding the overlapping portion of the detection range. Then, each detection information for which the weight is set is integrated to generate recognition information. Therefore, the recognition information of the outside world is generated by the sensor fusion processing in consideration of the driving scene. As a result, the outside world can be recognized more accurately by the sensor fusion process.

Further, according to the first embodiment, the weight of the detection information by the LiDAR 12 is set to be larger than the weight of the detection information by the camera 11 in the weight adjustment period immediately after entering the dark region from the bright region. Therefore, immediately after entering the dark area from the bright area, the detection information of the LiDAR 12 is more important in the generation of the recognition information than the detection information of the camera 11 whose reliability may decrease due to the change in brightness. Can be done. Therefore, the sensor fusion process makes it possible to recognize the outside world more accurately.

Further, according to the first embodiment, in the scene immediately after entering the bright area from the dark area, the weight of the detection information by the camera 11 is set smaller than the weight of the detection information by the LiDAR 12. Even in this case, the detection information of LiDAR12 is more important in the generation of recognition information than the detection information of the camera 11 whose reliability may be lowered due to the change in brightness, and the external recognition by the sensor fusion processing is more accurate. Can be.

Further, according to the first embodiment, the weight of the detection information by the millimeter wave radar 13 is set to be the smallest in the side wall curve scene traveling on the curve section on the road provided with the side wall. Therefore, in the side wall curve scene where the millimeter wave radar 13 can erroneously detect the side wall as a moving body, the outside world recognition can be more accurate.

In addition, according to the first embodiment, in the case of a traveling scene in which a specific electromagnetic wave condition relating to multiple reflection of electromagnetic waves is satisfied, the weight of the detection information by the camera 11 is the detection information by the LiDAR 12 and the millimeter wave radar 13. It is set larger than the weight. Therefore, in the traveling scene where the electromagnetic wave condition is satisfied, the detection information of the camera 11 can be given more importance than the detection information of the LiDAR 12 and the millimeter wave radar 13 that detect by the reflected wave of the irradiated electromagnetic wave. This makes it possible to recognize the outside world more accurately by the sensor fusion process.

Further, according to the first embodiment, in the case of a traveling scene in which a specific actual scene reflection condition regarding a reflecting object reflecting a real scene of the outside world is satisfied, the weight of the detection information by the camera 11 is determined by the LiDAR and the millimeter wave radar 13. It is set smaller than the weight of the detection information. Therefore, in a traveling scene where the actual scene reflection condition is satisfied, the detection information of the LiDAR and the millimeter wave radar 13 can be given more importance than the detection information of the camera 11 in which erroneous detection may occur due to the reflection of the actual scene to be imaged. Therefore, the outside world can be recognized more accurately in the driving scene where the actual scene reflection condition is satisfied.

(Other embodiments)
The disclosure herein is not limited to the exemplary embodiments. Disclosures include exemplary embodiments and modifications by those skilled in the art based on them. For example, the disclosure is not limited to the parts and / or combinations of elements shown in the embodiments. Disclosure can be carried out in various combinations. The disclosure can have additional parts that can be added to the embodiment. Disclosures include those in which the parts and / or elements of the embodiment are omitted. Disclosures include the replacement or combination of parts and / or elements between one embodiment and another. The technical scope disclosed is not limited to the description of the embodiments. Some technical scopes disclosed are indicated by the description of the scope of claims and should be understood to include all modifications within the meaning and scope equivalent to the description of the scope of claims. ..

In the above-described embodiment, the detection information acquisition unit 110 is supposed to acquire detection information from three types of peripheral monitoring sensors 10, that is, a camera 11, a LiDAR 12, and a millimeter-wave radar 13. Instead of this, the detection information acquisition unit 110 may be configured to acquire only the two types of detection information described above.

In the above-described embodiment, the traveling scene determination unit 120 determines whether or not the traveling scene is a brightness decreasing scene or a brightness increasing scene based on the detection information of the light-shielding structure detected by the millimeter-wave radar 13. I decided to judge. Instead of this, the traveling scene determination unit 120 may determine whether or not the traveling scene is a brightness decreasing scene or a brightness increasing scene based on the illuminance detected by the illuminance sensor 30. For example, the traveling scene determination unit 120 may determine that the traveling scene is a brightness-reduced scene when the illuminance drops from within the permissible range to a value below the permissible range. Further, the traveling scene determination unit 120 may determine that the traveling scene is a brightness increasing scene when the illuminance rises from below the allowable range to within the allowable range.

The external world recognition device 100 may be a dedicated computer configured to include at least one of a digital circuit and an analog circuit as a processor. Here, particularly digital circuits include, for example, ASIC (Application Specific Integrated Circuit), FPGA (Field Programmable Gate Array), SOC (System on a Chip), PGA (Programmable Gate Array), CPLD (Complex Programmable Logic Device) and the like. Of these, at least one. Further, such a digital circuit may include a memory for storing a program.

The external recognition device 100 may be provided by one computer, or a set of computer resources linked by a data communication device. For example, a part of the functions provided by the outside world recognition device 100 in the above-described embodiment may be realized by another ECU.

10 Peripheral monitoring sensor (sensor), 100 External recognition device, 101 Memory (storage medium), 102 processor, 110 Detection information acquisition unit (acquisition unit), 120 Driving scene determination unit (judgment unit), 130 Weight setting unit (setting unit) ), 140 recognition information generation unit (generation unit), A vehicle, S10 acquisition process, S30 setting process, S40 generation process.

Claims (25)

An outside world recognition device that recognizes the outside world of a vehicle (A) equipped with a plurality of types of sensors (10) having at least a partially overlapping detection range.
An acquisition unit (110) that acquires detection information from each of the plurality of types of sensors, and
A setting unit (130) for setting a weight according to a driving scene of the vehicle for each detection information regarding the overlapping portion of the detection range, and a setting unit (130).
A generation unit (140) that integrates each of the weighted detection information to generate the recognition information of the outside world, and
External recognition device equipped with. The external world recognition device according to claim 1, wherein the acquisition unit acquires the detection information from a camera, a laser radar, and a radio wave radar. The setting unit sets the weight of the detection information by the laser radar to the detection information by the camera in the weight adjustment period after entering the dark area having a brightness smaller than that of the bright area from the bright area. The external world recognition device according to claim 2, which is set to be larger than the weight of. The external world recognition device according to claim 3, wherein the setting unit is a period from entering the dark area to turning on the headlights of the vehicle. In the bright place approach scene immediately after entering the bright place area having a higher brightness than the dark place area, the setting unit sets the weight of the detection information by the camera as the detection information by the laser radar. The external world recognition device according to any one of claims 3 and 4, which is set to be smaller than the weight of the above. A determination unit that determines the timing at which the traveling scene changes to the bright spot approach scene based on the detection information about the structure around the vehicle detected by the radio wave radar capable of detecting information in the height direction. The external world recognition device according to claim 5, further comprising (120). The setting unit according to any one of claims 2 to 6, wherein the setting unit sets the weight of the detection information by the radio wave radar to the minimum in a side wall curve scene traveling in a curve section on a road provided with a side wall. External recognition device. The external world recognition device according to claim 7, wherein the setting unit sets the weight of the detection information by the laser radar to be larger than the weight of the detection information by the camera in the side wall curve scene. The external world recognition device according to any one of claims 2 to 8, wherein the setting unit sets the weight of the detection information by the camera to be smaller than the weight of the detection information by the laser radar in a snowfall scene. .. The external world recognition device according to claim 9, wherein the setting unit sets the weight of the detection information by the camera to be smaller than the weight of the detection information by the laser radar in the snowfall scene. In the case of a traveling scene in which a specific electromagnetic wave condition relating to multiple reflection of electromagnetic waves is satisfied, the setting unit sets the weight of the detected information by the camera to be larger than the weight of the detected information by the laser radar and the radio wave radar. The external world recognition device according to any one of claims 2 to 10, which is largely set. The setting unit detects the weight of the detection information by the camera by the laser radar and the radio wave radar when the traveling scene satisfies the specific actual reflection condition regarding the reflective object reflecting the actual view of the outside world. The external world recognition device according to any one of claims 2 to 11, which is set to be smaller than the weight of information. An outside world recognition method executed by a processor (102) in order to recognize the outside world of a vehicle (A) equipped with a plurality of types of sensors (10) having at least a partially overlapping detection range.
The acquisition process (S10) for acquiring detection information from each of the plurality of types of sensors,
A setting process (S30) for setting a weight according to a driving scene of the vehicle for each detection information regarding the overlapping portion of the detection range.
A generation process (S40) that integrates each of the weighted detection information to generate the recognition information of the outside world, and
External recognition methods including. The external world recognition method according to claim 13, wherein in the acquisition process, the detection information from a camera, a laser radar, and a radio wave radar is acquired. In the setting process, in the weight adjustment period after entering the dark area having a brightness smaller than that of the bright area from the bright area, the weight of the detected information by the laser radar is changed to the detected information by the camera. The external world recognition method according to claim 14, which is set to be larger than the weight of. The external world recognition method according to claim 15, wherein in the setting process, the weight adjustment period is a period from entering the dark area to turning on the headlights of the vehicle. In the setting process, in the bright place approach scene immediately after entering the bright place area having a brightness higher than the dark place area from the dark place area, the weight of the detection information by the camera is weighted by the detection information by the laser radar. The external world recognition method according to any one of claims 14 to 16, which is set to be smaller than the weight of the above. A determination process for determining the timing at which the traveling scene changes to the bright spot approach scene based on the detection information regarding the structure around the vehicle detected by the radio wave radar capable of detecting information in the height direction. The external world recognition method according to claim 17, further comprising (S20). In the setting process, any one of claims 14 to 18 in which the setting unit sets the weight of the detection information by the radio wave radar to the minimum in the side wall curve scene traveling in the curve section on the road provided with the side wall. The method for recognizing the outside world according to item 1. The external world recognition method according to claim 19, wherein in the setting process, the weight of the detection information by the laser radar is set to be larger than the weight of the detection information by the camera in the side wall curve scene. The external world recognition method according to any one of claims 14 to 20, wherein in the setting process, the weight of the detection information by the camera is set to be smaller than the weight of the detection information by the laser radar in a snowfall scene. .. The external world recognition method according to claim 21, wherein in the setting process, the weight of the detection information by the camera is set to be smaller than the weight of the detection information by the laser radar in the snowfall scene. In the setting process, in the case of a traveling scene in which a specific electromagnetic wave condition relating to multiple reflection of electromagnetic waves is satisfied, the weight of the detected information by the camera is larger than the weight of the detected information by the laser radar and the radio wave radar. The external world recognition method according to any one of claims 14 to 22, which is largely set. In the setting process, when the traveling scene satisfies the specific actual reflection condition regarding the reflective object reflecting the actual view of the outside world, the weight of the detection information by the camera is detected by the laser radar and the radio wave radar. The external world recognition method according to any one of claims 14 to 23, which is set to be smaller than the weight of information. The outside world including an instruction stored in a storage medium (101) and executed by a processor (102) in order to recognize the outside world of a vehicle (A) equipped with a plurality of types of sensors (10) having at least a partially overlapping detection range. It ’s a recognition program,
The command is
The acquisition process (S10) for acquiring detection information from each of the plurality of types of sensors,
A setting process (S30) for setting a weight according to a driving scene of the vehicle for each detection information regarding the overlapping portion of the detection range.
A generation process (S40) that integrates each of the weighted detection information to generate the recognition information of the outside world.
External recognition program including.

Images