Vehicle controller, method for vehicle control, and computer program
By referring to the lane trajectory distribution information and the reference trajectory change index, a target trajectory far away from the non-ideal trajectory is set, which solves the problem of insufficient safety of vehicle autonomous driving in the prior art and ensures safe driving under non-ideal trajectory conditions.
Patent Information
- Application Number
- CN202410584063.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2023-05-15
- Filing Date
- 2024-05-11
- Publication Date
- 2024-11-15
AI Technical Summary
Existing vehicle autonomous driving control systems are difficult to ensure safety when setting target trajectories, especially when the trajectory recorded during manual driving is not ideal or deviates from the lane, which can lead to safety risks.
By storing and referring to the trajectory distribution information of each lane of the road, the vehicle's target trajectory is set, away from non-ideal trajectories, and a reference trajectory with the lowest change index is selected as the safety target trajectory to ensure that the vehicle is safely driving in the predetermined section.
It realizes setting a very safe target trajectory under non-ideal trajectory conditions, improves the safety of vehicle autonomous driving and avoids the risk of approaching or intrusion with other vehicles.
Smart Images

Figure CN118953382A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to a vehicle controller, a method and a computer program for vehicle control. Background Art
[0002] A technology has been proposed in which a system configured to perform autonomous driving control of a vehicle records the actual trajectory of the vehicle during manual driving and causes the vehicle to travel during autonomous driving by referring to the recorded trajectory (see Japanese Unexamined Patent Publication JP2018-22353A).
[0003] The vehicle driving controller disclosed in JP2018-22353A generates a trajectory of the vehicle based on the position history of the vehicle during manual driving, and sets the generated trajectory as the target trajectory of the vehicle. Summary of the invention
[0004] However, a vehicle under manual driving control does not always travel along an ideal trajectory. Depending on the road section, the vehicle may travel along a trajectory that deviates from the lane in which it is traveling, or the trajectory may differ from vehicle to vehicle. Therefore, even if the trajectory to be traveled (hereinafter referred to as the "target trajectory") is set based on the trajectory of the vehicle under manual driving control, the set target trajectory may not be a safe trajectory.
[0005] An object of the present invention is to provide a vehicle controller capable of setting a very safe target trajectory.
[0006] According to an embodiment, a vehicle controller is provided. The vehicle controller includes: a storage unit that stores trajectory distribution information indicating the trajectory distribution of each lane in a predetermined section of a road; a trajectory setting unit that sets a target trajectory of the vehicle by referring to the trajectory distribution information of a second lane different from a first lane in which the vehicle is traveling when the vehicle is traveling on the predetermined section; and a vehicle control unit that causes the vehicle to travel along the target trajectory.
[0007] For each lane in the predetermined road section, the trajectory distribution information preferably includes multiple trajectories of the lane, and the trajectory setting unit of the vehicle controller preferably sets the target trajectory to be at least a predetermined interval away from any trajectory of the multiple trajectories of the second lane included in the trajectory distribution information.
[0008] Alternatively, the trajectory distribution information preferably includes a reference trajectory and a change index indicating how much the trajectory has changed, and the trajectory setting unit of the vehicle controller preferably sets the target trajectory to be farther away from the reference trajectory of the second lane as the change index of the second lane included in the trajectory distribution information becomes larger.
[0009] In this case, the trajectory setting unit preferably identifies the lane with the lowest variation index in the predetermined section by referring to the reference trajectory distribution information, and sets a target trajectory from the current position of the vehicle to the predetermined section so that the vehicle moves to the identified lane before reaching the predetermined section.
[0010] According to another embodiment, a vehicle controller is provided. The vehicle controller includes: a storage unit that stores a reference track of each lane in a predetermined section of a road; a selection unit that selects a lane whose reference track is the safest among the reference tracks of the lanes in the driving direction of the vehicle when the vehicle is traveling on the predetermined section; and a vehicle control unit that causes the vehicle to travel along the reference track of the selected lane.
[0011] The selection unit of the vehicle controller preferably determines that among the reference trajectories of each lane in the driving direction of the vehicle, a reference trajectory having the same lane position when entering and leaving a predetermined section is safer than a reference trajectory having different lane positions when entering and leaving the predetermined section.
[0012] The vehicle controller preferably further includes: a lane detection unit that detects the host vehicle lane that the vehicle is traveling in. When the host vehicle lane is different from the selected lane, the vehicle control unit preferably controls the vehicle so that the vehicle moves to the selected lane before reaching the predetermined road section.
[0013] According to yet another embodiment, a method for vehicle control is provided. The method includes: when the vehicle is traveling on a predetermined section of a road, setting a target trajectory of the vehicle by referring to trajectory distribution information of a second lane different from a first lane in which the vehicle is traveling; and driving the vehicle along the target trajectory. The trajectory distribution information indicates the trajectory distribution of each lane in the predetermined section.
[0014] According to yet another embodiment, a computer program product for vehicle control is provided. The computer program product includes instructions that cause a processor installed on a vehicle to perform processing, the processing including: when the vehicle is traveling on a predetermined section of a road, setting a target trajectory of the vehicle by referring to trajectory distribution information of a second lane different from a first lane in which the vehicle is traveling; and causing the vehicle to travel along the target trajectory. The trajectory distribution information indicates the trajectory distribution of each lane in the predetermined section.
[0015] The vehicle controller according to the present disclosure has the advantageous effect of being able to set a very safe target trajectory. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] Figure 1 The configuration of a vehicle control system equipped with a vehicle controller is schematically shown.
[0017] Figure 2 A hardware configuration of an electronic control unit as an example of a vehicle controller is shown.
[0018] Figure 3 is a functional block diagram of a processor of an electronic control unit related to vehicle control processing according to the first embodiment.
[0019] Figure 4A An example of the relationship between the trajectory distribution in the adjacent lanes and the target trajectory is shown.
[0020] Figure 4B Another example of the relationship between the trajectory distribution in the adjacent lanes and the target trajectory is shown.
[0021] Figure 5 is an operational flowchart of the vehicle control process according to the first embodiment.
[0022] Figure 6 is a functional block diagram of a processor of an electronic control unit related to vehicle control processing according to a second embodiment.
[0023] Figure 7 An example of a safety level for a reference trajectory of a lane is shown.
[0024] Figure 8 is an operational flowchart of the vehicle control process according to the second embodiment. DETAILED DESCRIPTION
[0025] A vehicle controller, a vehicle control method performed by the vehicle controller, and a computer program for vehicle control will be described below in conjunction with the accompanying drawings. The vehicle controller uses trajectory distribution information, which represents the distribution of trajectories of various vehicles along a predetermined section of the road along which they have actually traveled for each lane, to set a target trajectory for the vehicle. For various reasons, the trajectory distribution may include non-ideal trajectories. By setting the target trajectory in this way, the vehicle controller is able to perform automatic driving control of the vehicle while taking into account information about non-ideal trajectories to make the vehicle travel more safely. Alternatively, the vehicle controller selects a lane with the safest reference trajectory by referring to the reference trajectories of each lane, and causes the vehicle to travel along the reference trajectory of the selected lane.
[0026] Figure 1 The configuration of a vehicle control system equipped with a vehicle controller is schematically shown. Figure 2The hardware configuration of an electronic control unit as an embodiment of a vehicle controller is shown. In the present embodiment, a vehicle control system 1 mounted on a vehicle 10 and controlling the vehicle 10 includes a camera 2, a GPS receiver 3, a storage device 4, and an electronic control unit (ECU) 5 as an example of a vehicle controller. The camera 2, the GPS receiver 3, and the storage device 4 are communicatively connected to the ECU 5 via an on-board network conforming to a standard such as a controller area network. The vehicle control system 1 may also include: a distance sensor (not shown) that measures the distance from the vehicle 10 to an object around the vehicle 10 (e.g., a LiDAR or a radar); a wireless communication terminal (not shown) for wirelessly communicating with a device outside the vehicle 10; and a navigation device (not shown) for searching for a planned driving route to a destination.
[0027] The camera 2 is an example of a sensor configured to generate a sensor signal representing the surroundings of the vehicle 10, which includes a two-dimensional detector composed of an array of photoelectric transducers such as CCD or C-MOS that are sensitive to visible light, and a focusing optical system that forms an image of a target area on the two-dimensional detector. The camera 2 is installed, for example, inside the vehicle 10, so as to face the front of the vehicle 10, for example. The camera 2 captures an image of the area in front of the vehicle 10 at intervals of a predetermined capture period (e.g., 1 / 30 second to 1 / 10 second) and generates an image representing the area. Each image acquired by the camera 2 is an example of a sensor signal. The vehicle 10 may include a plurality of cameras that take pictures in different directions or have different focal lengths.
[0028] Every time an image is generated, the camera 2 outputs the generated image to the ECU 5 via the in-vehicle network.
[0029] The GPS receiver 3 receives GPS signals from GPS satellites at predetermined time intervals, and determines the position of the vehicle 10 based on the received GPS signals. The GPS receiver 3 outputs positioning information indicating the result of determining the position of the vehicle 10 based on the GPS signals to the ECU 5 at predetermined time intervals via the in-vehicle network. Instead of the GPS receiver, the vehicle 10 may include a receiver that receives positioning signals from satellites of other satellite positioning systems to determine the position of the vehicle 10.
[0030] The storage device 4 is an example of a storage unit, which includes, for example, a hard disk drive, a non-volatile semiconductor memory, or an optical medium and an access device thereof. The storage device 4 stores a high-precision map for automatic driving control of the vehicle 10. The high-precision map includes, for example, information indicating road markings (such as lane lines or stop lines), and the number of lanes of each road section included in the predetermined area represented in the high-precision map. For each road section, the high-precision map also includes information for determining whether the road section corresponds to a predetermined section, such as the curvature of the road section and whether there are intersections, confluences, branch points, or locations where vehicles enter and exit the road. The high-precision map also includes trajectory distribution information of a predetermined section of each lane of the road section. The trajectory distribution information includes information representing multiple trajectories for each lane. The trajectory distribution information may also include information representing a reference trajectory for each lane and a change index indicating how much the trajectory of each lane changes.
[0031] Unless there are special reasons, the reference trajectory of each lane is the standard trajectory along which the vehicle travels in the lane. For example, the reference trajectory is set by averaging multiple trajectories of vehicles that have actually traveled through the lane. Alternatively, the reference trajectory can be set along the center of the lane. The variation index can be the variance value of multiple trajectories in a single lane with respect to the width direction of the lane. Alternatively, the variation index can be the maximum value of the difference in position between multiple trajectories in the width direction of the lane, or the distance in the width direction of the lane between the reference trajectory and the trajectory farthest from the reference trajectory among the multiple trajectories.
[0032] In some cases, a vehicle 10 entering a predetermined section from one side may select one of the multiple exits of the predetermined section, such as when the predetermined section includes an intersection. In this case, a reference trajectory and a variation index are set for each exit. For example, it is assumed that the predetermined section includes an intersection, and at one end of the predetermined section, there are lanes that allow straight and left turns, lanes that only allow straight, and lanes that allow straight and right turns. In this case, for lanes that allow straight and left turns, the high-precision map includes information representing the reference trajectory of straight vehicles, information representing the reference trajectory of left-turning vehicles, and variation indices corresponding to these trajectories. For lanes that only allow straight, the high-precision map includes information representing the reference trajectory of straight vehicles and a variation index. For lanes that allow straight and right turns, the high-precision map includes information representing the reference trajectory of straight vehicles, information representing the reference trajectory of right-turning vehicles, and variation indices corresponding to these trajectories. Similarly, when the predetermined section includes a branch point, the high-precision map includes: for each lane, information and variation indices representing the reference trajectory of the drivable direction at the branch point.
[0033] The storage device 4 may also include a processor for performing, for example, processing for updating a high-precision map and processing related to a request from the ECU 5 to read a high-precision map. For example, each time the vehicle 10 moves a predetermined distance, the storage device 4 may transmit a request to obtain a high-precision map together with the current position of the vehicle 10 to a map server (not shown) via a wireless communication terminal (not shown). The storage device 4 may receive a high-precision map of a predetermined area around the current position of the vehicle 10 from the map server via a wireless communication terminal. When receiving a request from the ECU 5 to read a high-precision map, the storage device 4 extracts a portion of the high-precision map stored therein that includes the current position of the vehicle 10 and represents an area smaller than the predetermined area, and outputs the extracted portion to the ECU 5 via the vehicle network.
[0034] The ECU 5 performs automatic driving control of the vehicle 10. In the present embodiment, the ECU 5 sets a target trajectory by referring to trajectory distribution information of a predetermined section in the traveling direction of the vehicle 10, and causes the vehicle 10 to travel along the set target trajectory.
[0035] like Figure 2 As shown in FIG, the ECU 5 includes a communication interface 21, a memory 22, and a processor 23. The communication interface 21, the memory 22, and the processor 23 may be configured as separate circuits or a single integrated circuit.
[0036] The communication interface 21 includes an interface circuit for connecting the ECU 5 to the vehicle network. Each time an image is received from the camera 2, the communication interface 21 transmits the received image to the processor 23. Each time positioning information is received from the GPS receiver 3, the communication interface 21 transmits the positioning information to the processor 23. In addition, the communication interface 21 transmits the high-precision map read from the storage device 4 to the processor 23.
[0037] The memory 22 is another example of a storage unit, which includes, for example, volatile and nonvolatile semiconductor memories, and which stores various data used in the vehicle control processing performed by the processor 23. For example, the memory 22 stores parameters of the camera 2, including focal length, orientation, installation position of the camera 2, and various parameters for specifying an object detection classifier for detecting, for example, features. The memory 22 also stores positioning information of the vehicle 10, images around the vehicle 10, and high-precision maps. Further, the memory 22 temporarily stores various types of data generated during the vehicle control processing.
[0038] The processor 23 includes one or more central processing units (CPUs) and their peripheral circuits. The processor 23 may also include other computing circuits such as a logic arithmetic unit, an arithmetic unit, or a graphics processing unit. The processor 23 performs vehicle control processing for the vehicle 10 at predetermined time intervals.
[0039] (First embodiment) Next, the vehicle control process according to the first embodiment will be described. In the vehicle control process according to the first embodiment, the processor 23 sets the target trajectory by referring to the trajectory distribution information of other lanes different from the host vehicle lane in which the vehicle 10 is traveling (the host vehicle lane may be referred to as the "first lane" below, and the other lanes will be referred to as the "second lane" below). More specifically, the processor 23 sets the target trajectory away from the second lane based on the trajectory distribution information of the second lane, assuming that other vehicles traveling in the second lane are approaching or intruding into the host vehicle lane.
[0040] Figure 3 2 is a functional block diagram of the processor 23 related to the vehicle control process according to the first embodiment. The processor 23 includes a lane detection unit 31, a trajectory setting unit 32, and a vehicle control unit 33. The units included in the processor 23 are functional modules, such as implemented by a computer program executed by the processor 23, or they may also be dedicated operation circuits provided in the processor 23.
[0041] The lane detection unit 31 detects the lane of the vehicle by comparing an image generated by the camera 2 representing the surroundings of the vehicle 10 (hereinafter referred to as the "image") with a high-precision map. For example, assuming the position and orientation of the vehicle 10, the lane detection unit 31 projects features on or around the road detected from the image onto the high-precision map, or projects features on or around the road near the vehicle 10 represented in the high-precision map onto the image. The features on or around the road can be, for example, road markings such as lane lines or stop lines, or curbs. The lane detection unit 31 estimates the position of the vehicle 10 as the position and orientation of the vehicle 10 when the features detected from the image best match the features represented in the high-precision map.
[0042] The lane detection unit 31 uses the initial values of the position and orientation of the assumed vehicle 10 and the parameters of the camera 2 (such as focal length, height of the installation position, and orientation) to determine the position of the feature projected into the high-precision map or image. As the initial values of the position and orientation of the vehicle 10, the position of the vehicle 10 determined by the GPS receiver 3 or the position obtained by correcting the position and orientation of the vehicle 10 estimated when the lane of the vehicle was last detected using the odometer information is used. Then, the lane detection unit 31 calculates the degree of match between the features on or around the road detected from the image and the corresponding features represented in the high-precision map (for example, the inverse of the sum of the squares of the distances between these features).
[0043] The lane detection unit 31 repeats the above process while changing the assumed position and orientation of the vehicle 10. The lane detection unit 31 estimates the actual position of the vehicle 10 as the position and orientation in the case where the matching degree is the largest. Then, the lane detection unit 31 identifies the lane including the position of the vehicle 10 as the host vehicle lane in which the vehicle 10 is traveling by referring to the high-precision map.
[0044] For example, the lane detection unit 31 inputs the image into a classifier trained to detect the detection target features from the image, thereby detecting these features. As such a classifier, the lane detection unit 31 can use, for example, a deep neural network (DNN) having a convolutional neural network (CNN) type architecture, such as a single shot multibox detector or Faster R-CNN. Alternatively, as such a classifier, the lane detection unit 31 can use a DNN having a self-attention network (SAN) type architecture, such as a Vision Transformer.
[0045] The lane detection unit 31 notifies the trajectory setting unit 32 of information indicating the detected lane of the host vehicle.
[0046] The trajectory setting unit 32 sets a target trajectory by referring to trajectory distribution information of a predetermined road section between the current position of the vehicle 10 and a position away by a predetermined distance (eg, several hundred meters to several kilometers) in the traveling direction of the vehicle 10 .
[0047] The predetermined road section may be, for example, a curved road section having a curvature not less than a predetermined degree or a road section including an intersection. Alternatively, the predetermined road section may be a road section including a junction with other roads, or a road section facing a vehicle entrance and exit, such as an entrance and exit of a parking lot. The predetermined road section is not limited to these road sections, and may be a simple straight road section. Alternatively, the predetermined road section may be a road section having trajectory distribution information in a high-precision map.
[0048] The trajectory setting unit 32 identifies a predetermined section between the current position of the vehicle 10 and a position away from a predetermined distance along the driving direction of the vehicle 10 by referring to a high-precision map. In the trajectory distribution information of the predetermined section included in the high-precision map, the trajectory setting unit 32 refers to the trajectory distribution information of a second lane other than the lane of the vehicle (in particular, a lane adjacent to the lane of the vehicle). The adjacent lane is not limited to a parallel lane along which other vehicles can travel in the same direction as the vehicle 10, but can also be an oncoming lane. The trajectory setting unit 32 sets the target trajectory to be at least a predetermined interval away from any of the multiple trajectories on the second lane included in the trajectory distribution information. The trajectory setting unit 32 sets the target trajectory so that the deviation of the target trajectory from the center of the lane of the vehicle or the reference trajectory is minimized, as long as the target trajectory is at least a predetermined interval away from any of the multiple trajectories on the second lane.
[0049] When the trajectory distribution information of the second lane includes an abnormal trajectory approaching or invading the lane of the host vehicle, it is assumed that a vehicle traveling in the second lane may approach or invading the lane of the host vehicle. The vehicle 10 can maintain a certain distance from such a vehicle by setting the target trajectory as described above.
[0050] Figure 4A and Figure 4B An example of the relationship between the trajectory distribution in the adjacent lanes and the target trajectory is shown. Figure 4A and Figure 4B In the example shown in , the vehicle 10 is traveling in the right lane 402 of the two lanes 401 and 402 of the road 400. In other words, the lane 402 is the host vehicle lane. Therefore, in order to set the target trajectory, the trajectory distribution information of the left lane 401 is referred to.
[0051] exist Figure 4A In the example shown in , the variation of the plurality of trajectories 410 included in the trajectory distribution information of the lane 401 is relatively small, and any trajectory is close to the center of the lane 401. Therefore, a target trajectory 420 is also set near the center of the host vehicle lane 402, and the target trajectory 420 is set to be at least a predetermined interval away from each trajectory.
[0052] exist Figure 4BIn the example shown in , a track 410a among the multiple tracks 410 included in the track distribution information of the lane 401 passes through a position close to the boundary between the host vehicle lane 402 and the lane 401. Therefore, the target track 430 is set so that as the track 410a gets closer to the host vehicle lane 402, the position passed by the target track 430 becomes farther away from the lane 401 than the center of the host vehicle lane 402.
[0053] As described above, the trajectory distribution information may include: for each lane, the reference trajectory of the lane and the change index indicating how much the trajectory changes. In this case, the trajectory setting unit 32 may set the target trajectory to a reference trajectory that is further away from the second lane as the change index of the second lane increases. For example, when the change index of the adjacent lane is not greater than a predetermined change threshold, the trajectory setting unit 32 sets the reference trajectory of the lane of the vehicle as the target trajectory. When the change index of the adjacent lane exceeds the predetermined change threshold, the trajectory setting unit 32 sets the target trajectory so that the target trajectory passes through a position offset from the reference trajectory of the lane of the vehicle in a direction away from the adjacent lane by an offset distance, and the offset distance depends on the change index of the adjacent lane. In this way, the target trajectory is set to a reference trajectory away from the adjacent lane with a high change index. In this case, the trajectory setting unit 32 may also set the target trajectory so that the vehicle 10 can maintain a certain distance from other vehicles approaching or invading the lane of the vehicle on the second lane, as described in the above example.
[0054] In some cases, the vehicle may travel in multiple directions from the host vehicle lane and the second lane, such as in the case where the predetermined road section includes an intersection. In this case, the trajectory setting unit 32 performs the above processing by referring to the reference trajectory and change index for the same direction as the driving direction of the vehicle 10 in the host vehicle lane (in the case of a parallel lane) or the opposite direction (in the case of an opposite lane) among the reference trajectory and change index set for the second lane. The trajectory setting unit 32 identifies the direction in which the vehicle 10 is moving in the predetermined road section by referring to the planned driving route of the vehicle 10 received from the navigation device (not shown).
[0055] When the target trajectory is set, the trajectory setting unit 32 notifies the vehicle control unit 33 of the set target trajectory.
[0056] The vehicle control unit 33 controls the components of the vehicle 10 so that the vehicle 10 travels along the target trajectory received from the trajectory setting unit 32. To achieve this, the vehicle control unit 33 measures the position of the vehicle 10 at predetermined intervals and compares the measured position of the vehicle 10 with the target trajectory. The vehicle control unit 33 measures the correct position of the vehicle 10 by comparing the image acquired by the camera 2 with the high-precision map in a manner similar to that described with respect to the lane detection unit 31. When the measured position of the vehicle 10 is on the target trajectory, the vehicle control unit 33 determines the steering angle of the vehicle 10 so that the vehicle 10 travels along the target trajectory, and controls the steering of the vehicle 10 so that the steering angle is the same as determined. When the measured position of the vehicle 10 is away from the target trajectory, the vehicle control unit 33 determines the steering angle of the vehicle 10 so that the vehicle 10 approaches the target trajectory, and controls the steering of the vehicle 10 so that the steering angle is the same as determined.
[0057] Further, the vehicle control unit 33 sets the acceleration or deceleration of the vehicle 10 so as to keep the distance between the vehicle 10 and other vehicles traveling in front (hereinafter referred to as "front vehicles") at a distance greater than a certain distance. To achieve this, the vehicle control unit 33 detects the front vehicle by inputting an image acquired by the camera 2 or a ranging signal acquired by a distance sensor (not shown) into a classifier trained to detect vehicles. Then, the vehicle control unit 33 estimates the distance between the vehicle 10 and the front vehicle based on the size of the front vehicle in the image or the bottom position of the area representing the front vehicle, or based on the distance in the direction toward the detected front vehicle indicated by the ranging signal. When the distance between the vehicle 10 and the front vehicle decreases below a predetermined distance threshold, the vehicle control unit 33 sets the acceleration or deceleration of the vehicle 10 to decelerate the vehicle 10. When the distance between the vehicle 10 and the front vehicle is not less than the predetermined distance threshold, the vehicle control unit 33 sets the acceleration or deceleration of the vehicle 10 so that the speed of the vehicle 10 remains constant or approaches the speed limit of the road on which the vehicle 10 is traveling or the target speed set by the driver. Then, the vehicle control unit 33 sets the accelerator opening or the braking amount according to the set acceleration or deceleration. The vehicle control unit 33 determines the fuel injection amount according to the set accelerator opening, and outputs a control signal to the fuel injector of the engine of the vehicle 10 according to the fuel injection amount. Alternatively, the vehicle control unit 33 determines the power to be supplied to the motor according to the set accelerator opening, and controls the drive circuit of the motor to supply the determined power to the motor. Alternatively, the vehicle control unit 33 outputs a control signal to the brake of the vehicle 10 according to the set braking amount.
[0058] Figure 5is an operation flowchart of the vehicle control process according to the first embodiment executed by the processor 23. The processor 23 executes the vehicle control process at predetermined time intervals according to the operation flowchart described below.
[0059] The lane detection unit 31 of the processor 23 detects a host vehicle lane in which the vehicle 10 is traveling (step S101 ).
[0060] The trajectory setting unit 32 of the processor 23 sets a target trajectory on the lane of the vehicle in a predetermined section closer than a position away from a predetermined distance in the driving direction of the vehicle 10 by referring to the trajectory distribution information of the second lane other than the lane of the vehicle, so that the target trajectory is away from any trajectory on the second lane by at least a predetermined interval (step S102). As described above, the trajectory setting unit 32 can set the target trajectory so that as the change index of the second lane increases, it moves away from the reference trajectory of the second lane.
[0061] The vehicle control unit 33 of the processor 23 controls the components of the vehicle 10 so that the vehicle 10 travels along the target trajectory (step S103). Then, the processor 23 terminates the vehicle control process.
[0062] As described above, the vehicle controller uses the trajectory distribution information of the second lane to set the target trajectory of the vehicle. Therefore, the vehicle controller can set a very safe target trajectory in consideration of the possible trajectories of other vehicles traveling in the second lane.
[0063] In the road section where the trajectory distribution information indicates that the trajectory on the second lane has a large change, it is assumed that other vehicles traveling in the second lane may accidentally approach the lane of the host vehicle. Therefore, according to the modified example, the vehicle control unit 33 can notify the driver of a warning that other vehicles may approach the vehicle 10 via a display (not shown) or a speaker (not shown) provided inside the vehicle in the road section where the change index of the second lane other than the lane of the host vehicle is not less than a predetermined threshold.
[0064] In the road section where the trajectory distribution information indicates that the trajectory on the lane of the host vehicle has a large change, it is also assumed that some interference may occur during the driving of the vehicle 10. Therefore, the vehicle control unit 33 can also notify the driver of a warning to call attention to the driving of the vehicle 10 via a display or a speaker provided inside the vehicle in the road section where the change index of the lane of the host vehicle is not less than a predetermined threshold.
[0065] According to another variation example, the trajectory setting unit 32 may give a higher priority to the lane with a lower change index among the lanes in the driving direction of the vehicle 10 in the predetermined section to set the target trajectory. For example, the trajectory setting unit 32 identifies the lane with the lowest change index among the lanes to which the vehicle 10 can move before reaching the predetermined section. Then, the trajectory setting unit 32 sets the target trajectory from the current position of the vehicle 10 indicated by the latest positioning information to the predetermined section, so that the vehicle 10 moves to the identified lane before reaching the predetermined section. For the predetermined section, the trajectory setting unit 32 sets the target trajectory according to the above embodiment or variation example. The distance required for a single lane change (hereinafter referred to as "lane change distance") can be pre-stored in the memory 22. The trajectory setting unit 32 determines the distance from the current position of the vehicle 10 to the predetermined section by referring to the high-precision map, and divides the distance by the lane change distance to determine the maximum number of lane changes that the vehicle 10 can make before reaching the predetermined section. The trajectory setting unit 32 determines the lanes that the vehicle 10 can move to before reaching the predetermined road section from each lane that the host vehicle can reach through the maximum number of lane changes. According to this modified example, the trajectory setting unit 32 can set the target trajectory so that the vehicle 10 can travel while avoiding lanes that may interfere.
[0066] (First embodiment) Next, the vehicle control process according to the second embodiment will be described. In the vehicle control process according to the second embodiment, the processor 23 selects the lane with the safest reference trajectory as the target lane by referring to the reference trajectory of each lane, and drives the vehicle 10 along the reference trajectory of the selected target lane.
[0067] The vehicle control process according to the second embodiment is different from the vehicle control process according to the first embodiment in part of the processing executed by the processor 23. Therefore, the differences from the first embodiment are described below.
[0068] In a second embodiment, the high-precision map includes information representing a reference trajectory of each lane in a predetermined section. The predetermined section in the second embodiment may be a road section similar to the predetermined section in the first embodiment. In a second embodiment, the predetermined section may be a road section having information representing a reference trajectory of a lane in the high-precision map.
[0069] Figure 62 is a functional block diagram of the processor 23 related to the vehicle control process according to the second embodiment. The processor 23 includes a lane detection unit 31, a selection unit 34, and a vehicle control unit 33. The units included in the processor 23 are functional modules, such as implemented by a computer program executed by the processor 23, or they may also be dedicated operation circuits provided in the processor 23.
[0070] The lane detection unit 31 detects the host vehicle lane in which the vehicle 10 is traveling, as in the first embodiment. The lane detection unit 31 notifies the selection unit 34 of the detected host vehicle lane.
[0071] The selection unit 34 identifies a predetermined section between the current position of the vehicle 10 and a position away from a predetermined distance along the driving direction of the vehicle 10 by referring to a high-precision map. The selection unit 34 sets a target trajectory based on the reference trajectory of each lane in the predetermined section. In the present embodiment, the selection unit 34 selects a lane whose reference trajectory is the safest reference trajectory among the reference trajectories of each lane in the driving direction of the vehicle 10 when the vehicle 10 is traveling on the predetermined section. To this end, the selection unit 34 may determine a lane to which the vehicle 10 can move before reaching the predetermined section as a candidate lane, as in the above-mentioned variant example. Alternatively, when the predetermined section includes an intersection or a branch point, the selection unit 34 may determine a lane to which the vehicle 10 can go to the destination from among a plurality of lanes of the predetermined section as a candidate lane by referring to the planned driving route of the vehicle 10 received from a navigation device (not shown).
[0072] For example, the selection unit 34 determines that the lane among the candidate lanes is safer as the deviation of the reference trajectory from the center of the lane is smaller. Alternatively, the selection unit 34 may determine that the lane is safer as the maximum value of the change per unit distance of the angle of the driving direction of the reference trajectory of the lane is smaller.
[0073] When the predetermined road section includes an intersection, the lane position of the reference trajectory at the intersection relative to the road edge may be different when entering and leaving the intersection. For example, when entering an intersection with more than three lanes in each direction, the reference trajectory of the second lane from the center may move to the leftmost lane when leaving the intersection after turning right at the intersection. In this case, a vehicle turning right at the intersection along the reference trajectory of the second lane from the center may travel in the same lane as other vehicles entering the intersection from the opposite lane and turning left at the intersection when leaving the intersection. However, if the reference trajectory of the centermost lane remains in the rightmost lane after turning right, it is presumed that the possibility of the above-mentioned similar situation occurring is small. Further, if at an intersection with multiple lanes that allow left turns, the reference trajectory of one of the lanes moves to the right lane when leaving the intersection, it is assumed that the vehicle 10 traveling along one of the lanes needs to move to the right lane after turning left. However, if the reference trajectory of the rightmost lane among these lanes that allow left turns remains in the rightmost lane after leaving the intersection, it is assumed that the vehicle 10 traveling along the rightmost lane does not need to make a lane change after turning left. Therefore, the selection unit 34 determines that the reference trajectory in which the position of the lane including the entry point of the predetermined road section is the same as the position of the lane including the exit point of the predetermined road section is safer than the reference trajectory in which the position of the lane including the entry point of the predetermined road section is different from the position of the lane including the exit point of the predetermined road section. Since this gives priority to the lane with the reference trajectory remaining in the lane, the selection unit 34 can select the target lane to prevent inadvertent lane changes.
[0074] The selection unit 34 selects the target lane according to one or more of the above-mentioned criteria for lane selection. When multiple selection criteria are used, the selection unit 34 gives the highest priority to the lane of the vehicle, for example, whose reference trajectory remains in a predetermined section. When there are multiple such lanes, for each of these lanes, the selection unit 34 secondly evaluates the maximum value of the per unit distance change of the reference trajectory from the center of the lane or the angle in the driving direction, and thirdly evaluates another lane mentioned above, thereby selecting the target lane. Alternatively, when multiple lanes are given priority according to one of the above-mentioned selection criteria, the selection unit 34 can select the lane closest to the lane of the vehicle among these lanes as the target lane.
[0075] The selection unit 34 sets the reference trajectory of the target lane determined to be the safest in the predetermined section as the target trajectory. When the target lane is different from the host vehicle lane, the selection unit 34 also sets the target trajectory in the section from the current position of the vehicle 10 to the predetermined section so that the vehicle 10 moves from the host vehicle lane to the target lane before reaching the predetermined section.
[0076] Figure 7 An example of the safety level of the reference trajectory of the lane is shown. Figure 7 In the example shown in , the predetermined road section includes an intersection 700. On two lanes 711 and 712 among lanes included in a road 710 (as one of the roads entering the intersection 700), a left turn is allowed at the intersection 700. In addition, a road 720 located on the left side with respect to the road 710 includes three lanes 721, 722, and 723 leaving from the intersection 700.
[0077] The reference track 711a for turning left from the leftmost lane 711 in the road 710 passes along the leftmost lane 721 after leaving from the intersection 700. In other words, the lane position of the reference track 711a does not change relative to the edge of the road between entering the predetermined section and leaving from the predetermined section. In contrast, the reference track 712a for turning left from the second lane 712 in the road 710 passes along the most central lane 723 in the road 720 after leaving from the intersection 700. In other words, the lane position of the reference track 712a changes relative to the edge of the road between entering the predetermined section and leaving from the predetermined section. Therefore, it is determined that the reference track 711a of the lane 711 is safer than the reference track 712a of the lane 712. Therefore, when the vehicle 10 enters the intersection 700 from the road 710 and turns left at the intersection 700, the lane 711 is selected as the target lane.
[0078] When setting a target trajectory from the current position of the vehicle 10 to the end of the predetermined road section, the selection unit 34 notifies the vehicle control unit 33 of the set target trajectory.
[0079] Similar to the vehicle control unit 33 according to the first embodiment, the vehicle control unit 33 controls the components of the vehicle 10 so that the vehicle 10 travels along the target trajectory. When the target lane is different from the host vehicle lane, the vehicle control unit 33 controls the components of the vehicle 10 so that the vehicle 10 moves from the host vehicle lane to the target lane along the target trajectory before reaching the predetermined road section.
[0080] Figure 8 is an operation flowchart of the vehicle control process according to the second embodiment. The processor 23 executes the vehicle control process at predetermined time intervals according to the operation flowchart described below.
[0081] The lane detection unit 31 of the processor 23 detects a host vehicle lane in which the vehicle 10 is traveling (step S201 ).
[0082] The selection unit 34 of the processor 23 selects a lane having a reference trajectory that is the safest reference trajectory from the reference trajectory of each lane in the predetermined section ahead of the vehicle 10 as the target lane (step S202). The selection unit 34 sets the target trajectory so that the vehicle 10 moves from the vehicle lane to the target lane in the section from the current position of the vehicle 10 to the predetermined section (step S203). For the predetermined section, the selection unit 34 also sets the reference trajectory of the target lane as the target trajectory (step S204).
[0083] The vehicle control unit 33 of the processor 23 controls the components of the vehicle 10 so that the vehicle 10 travels along the target trajectory (step S205). Then, the processor 23 terminates the vehicle control process.
[0084] As described above, the vehicle controller according to the second embodiment selects the lane with the safest reference trajectory as the target lane in the predetermined section ahead of the vehicle by referring to the reference trajectory of each lane, and causes the vehicle to travel along the reference trajectory of the selected lane. Therefore, the vehicle controller can guide the vehicle to a safer lane.
[0085] According to a modified example, the vehicle control unit 33 can perform following control to control the vehicle 10 so that the vehicle 10 follows the vehicle traveling in front of the vehicle 10. In this case, when the predetermined section includes an intersection, and the reference trajectory of the lane of the vehicle moves to the adjacent lane after turning right or left at the intersection, the front vehicle is likely to move to the adjacent lane after turning right or left at the intersection. Therefore, when the following control is applied to the vehicle 10 in the predetermined section including such an intersection, the vehicle control unit 33 can reduce the priority of the following control. For example, the vehicle control unit 33 can control various components of the vehicle 10 so that the vehicle 10 keeps traveling in the lane of the vehicle without following the front vehicle even when the front vehicle moves to the adjacent lane.
[0086] Further, the processor 23 may be capable of performing both the vehicle control according to the first embodiment and the vehicle control according to the second embodiment. For example, the processor 23 may perform the vehicle control processing according to the second embodiment to select a target lane in a predetermined section and set a target trajectory from the current position of the vehicle 10 to the predetermined section. Then, the processor 23 may perform the vehicle control processing according to the first embodiment to set the target trajectory in the predetermined section.
[0087] The computer program that realizes the functions of the processor 23 of the ECU 5 according to the above-described embodiment or modified example may be provided in a form recorded on a computer-readable portable storage medium such as a semiconductor memory, a magnetic medium, or an optical medium.
[0088] As described above, those skilled in the art can make various modifications according to the embodiments within the scope of the present invention.
Claims
1. Vehicle controller, including: a storage unit storing trajectory distribution information representing a trajectory distribution of each lane in a predetermined section of a road; a trajectory setting unit, which sets a target trajectory of the vehicle by referring to trajectory distribution information of a second lane different from a first lane on which the vehicle is traveling when the vehicle is traveling on the predetermined road section; and A vehicle control unit causes the vehicle to travel along the target trajectory.
2. The vehicle controller according to claim 1, wherein: For each lane in the predetermined road section, the trajectory distribution information includes a plurality of trajectories of the lane, and The trajectory setting unit sets the target trajectory to be away from any trajectory of a plurality of trajectories of the second lane included in the trajectory distribution information by at least a predetermined interval.
3. The vehicle controller according to claim 1, wherein: The trajectory distribution information includes a reference trajectory and a change index indicating how much the trajectory changes, and The trajectory setting unit sets the target trajectory to be farther away from a reference trajectory of the second lane as a change index of the second lane included in the trajectory distribution information increases.
4. The vehicle controller according to claim 3, wherein: The trajectory setting unit identifies a lane having a lowest variation index in the predetermined section by referring to the reference trajectory distribution information, and sets a target trajectory from a current position of the vehicle to the predetermined section so that the vehicle moves to the identified lane before reaching the predetermined section.
5. Vehicle controller, including: a storage unit that stores a reference trajectory for each lane in a predetermined section of the road; a selection unit, which, when the vehicle is traveling on the predetermined road section, selects a lane having a reference trajectory that is the safest lane among reference trajectories of lanes in the traveling direction of the vehicle; as well as A vehicle control unit causes the vehicle to travel along a reference trajectory of the selected lane.
6. The vehicle controller according to claim 5, wherein: The selection unit determines that among the reference trajectories of each lane in the driving direction of the vehicle, a reference trajectory having the same lane position at entering and leaving the predetermined section is safer than a reference trajectory having different lane positions at entering and leaving the predetermined section.
7. The vehicle controller according to claim 5 or 6, further comprising: A lane detection unit detects a lane of the vehicle in which the vehicle is traveling, wherein When the host vehicle lane is different from the selected lane, the vehicle control unit controls the vehicle so that the vehicle moves to the selected lane before reaching the predetermined road section.
8. A method for vehicle control, comprising: When a vehicle is traveling on a predetermined section of a road, a target trajectory of the vehicle is set by referring to trajectory distribution information of a second lane different from a first lane on which the vehicle is traveling, the trajectory distribution information indicating trajectory distribution of each lane in the predetermined section; as well as The vehicle is caused to travel along the target trajectory.
9. A computer program product for vehicle control, the computer program causing a processor installed in the vehicle to perform a process comprising: When the vehicle is traveling on a predetermined section of a road, setting a target trajectory of the vehicle by referring to trajectory distribution information of a second lane different from a first lane on which the vehicle is traveling, the trajectory distribution information indicating trajectory distribution of each lane in the predetermined section; as well as The vehicle is caused to travel along the target trajectory.
Citation Information
Patent Citations
Vehicle travel control device, vehicle travel control system, and vehicle travel control method
JP2018022353A
