Travel path generation method, travel support method, travel path generation device, and travel support device

Abstract

To set an optimized target travel trajectory based on travel trajectories when traveling on the same road in the past.SOLUTION: In a travel trajectory generation method, travel trajectories when a vehicle travels in a predetermined section on the same road a plurality of times are acquired (S1), a plurality of candidate travel trajectories when traveling in the predetermined section is generated by extracting, for each of the acquired trave trajectories, pass points that are positions on the travel trajectory and giving reliability to each of the pass points, storing the pass points in a storage device in association with the reliability, and connecting the pass points stored in the storage device (S5), one of the candidate travel trajectories of the plurality of generated candidate travel trajectories is extracted based on the total of the reliability of the pass points belonging to the candidate travel trajectories (S7), and the extracted candidate travel trajectory is generated as a target travel trajectory where the vehicle travels.SELECTED DRAWING: Figure 6

Description

Technical Field

[0001] The present invention relates to a travel trajectory generation method, a travel support method, a travel trajectory generation device, and a travel support device.

Background Art

[0002] The following Patent Document 1 proposes a vehicle travel control device that stores a travel trajectory when traveling manually and sets the travel trajectory as the target trajectory of the host vehicle. The vehicle travel control device recognizes the lane in which the host vehicle is traveling and causes the host vehicle to travel along the target trajectory while maintaining the lane when it is possible to maintain the lane.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, the vehicle travel control device described in Patent Document 1 may not be able to set an appropriate target travel trajectory. For example, when the lane in which the host vehicle is traveling cannot be recognized, the travel trajectory traveled in the past is set as the target travel trajectory as it is, so it is not always the optimal trajectory. An object of the present invention is to set an optimized target travel trajectory based on the travel trajectory when traveling the same road in the past.

Means for Solving the Problems

[0005] In the driving trajectory generation method according to one aspect of the present invention, when a vehicle travels a predetermined section of the same road a plurality of times, driving trajectories are acquired. For each of the acquired driving trajectories, a plurality of passing points that are positions on the driving trajectory are extracted, and a reliability is assigned to each of the plurality of passing points. The passing points and the reliability are associated with each other and stored in a storage device. By connecting the passing points stored in the storage device, a plurality of driving trajectory candidates for traveling in the predetermined section are generated. Among the plurality of generated driving trajectory candidates, one of the driving trajectory candidates is extracted based on the total value of the reliabilities of the passing points belonging to the driving trajectory candidate, and the extracted driving trajectory candidate is generated as the target driving trajectory for the vehicle to travel.

Advantages of the Invention

[0006] According to the present invention, an optimized target driving trajectory can be set based on the driving trajectories when traveling the same road in the past.

Brief Description of the Drawings

[0007]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Best Mode for Carrying Out the Invention

[0008] Hereinafter, embodiments of the present invention will be described with reference to the drawings. In the description of the drawings, the same or similar parts are denoted by the same or similar reference numerals, and redundant descriptions are omitted. Each drawing is schematic and may differ from the actual one. The following embodiments exemplify apparatuses and methods for embodying the technical idea of the present invention, and the technical idea of the present invention is not limited to the apparatuses and methods exemplified in the following embodiments. The technical idea of the present invention can be variously modified within the technical scope described in the claims.

[0009] (Configuration) FIG. 1 shows an example of the schematic configuration of a vehicle equipped with the travel assistance device according to the embodiment. The travel assistance device supports the travel of the host vehicle 1 along a target travel trajectory. The travel assistance control of the host vehicle 1 by the travel assistance device according to the embodiment may include, for example, autonomous driving control for automatically driving the host vehicle 1 along the target travel trajectory without the involvement of an occupant (e.g., a driver). Further, the travel assistance control by the travel assistance device may include, for example, driving assistance control for supporting the travel of the host vehicle 1 along the target travel trajectory by controlling at least the steering angle of the host vehicle 1.

[0010] The travel assistance device according to the embodiment includes a vehicle speed sensor 2, a yaw rate sensor 3, a host vehicle position acquisition device 4, a lane recognition device 5, an actuator 6, and a travel control device 7. The vehicle speed sensor 2 is a vehicle sensor (a sensor for detecting the running state of the host vehicle 1) that detects the wheel speed of the host vehicle 1 and calculates the vehicle speed of the host vehicle 1 based on the wheel speed. The yaw rate sensor 3 is a vehicle sensor that detects the yaw rate generated in the host vehicle 1.

[0011] The own-vehicle position acquisition device 4 measures the current position of the own vehicle 1. The own-vehicle position acquisition device 4 may include, for example, a global navigation satellite system (GNSS) receiver. The GNSS receiver is, for example, a global positioning system (GPS) receiver or the like, and receives radio waves from a plurality of navigation satellites to measure the current position of the own vehicle 1. The own-vehicle position acquisition device 4 may be, for example, an inertial navigation device. The lane recognition device 5 detects lane boundary lines (for example, line marks such as white lines and yellow lines) of the lane in which the own vehicle 1 travels by using object sensors such as a camera, a laser radar, and a LiDAR (Light Detection and Ranging) that detect objects around the own vehicle, and recognizes the lane in which the own vehicle 1 travels.

[0012] The actuator 6 generates the vehicle behavior of the own vehicle 1 by operating the steering device, the drive device, and the braking device of the own vehicle 1 according to a control signal from the travel control device 7. The actuator 6 includes a steering actuator, an accelerator opening actuator, and a brake control actuator. The steering actuator operates the steering device to control the steering direction and the steering amount of the vehicle. The accelerator opening actuator operates the drive device, which is an engine or a drive motor, to control the acceleration of the own vehicle 1. The brake control actuator operates the braking device to control the deceleration of the own vehicle 1.

[0013] The travel control device 7 is an electronic control unit (ECU: Electronic Control Unit) that performs travel support control of the own vehicle 1. For example, when performing autonomous driving control as travel support control, the travel control device 7 automatically controls the travel of the own vehicle 1 by driving the actuator 6 based on the travel environment around the own vehicle 1. Also, for example, when performing driving support control as travel support control, the travel control device 7 controls at least the steering angle of the own vehicle 1 by driving the actuator 6 based on the travel environment around the own vehicle 1. The travel control device 7 includes a processor 10 and peripheral components such as a storage device 11. The processor 10 may be, for example, a CPU (Central Processing Unit) or an MPU (Micro-Processing Unit). The storage device 11 may include a semiconductor storage device, a magnetic storage device, an optical storage device, etc. The functions of the travel control device 7 described below are realized, for example, when the processor 10 executes a computer program stored in the storage device 11. Note that the travel control device 7 may be formed of dedicated hardware for executing each information process described below.

[0014] FIG. 2 is a block diagram of an example of the functional configuration of the travel control device 7. The travel control device 7 includes a travel trajectory storage unit 20, a trajectory optimization unit 21, a reliability calculation unit 22, a map information storage unit 23, a link allocation unit 24, a combination optimization unit 25, a track candidate storage unit 26, a travel road determination unit 27, a road shape estimation unit 28, and a vehicle control unit 29. The travel control device 7 may operate, for example, in at least the following three operation modes. (1) A travel trajectory acquisition mode for accumulating the travel trajectory of the host vehicle 1 during manual driving (2) A track candidate generation mode for optimizing the accumulated travel trajectory to generate travel track candidates (3) A travel support mode for supporting the travel of the host vehicle 1 along the travel track candidates Note that, for example, the processing in the track candidate generation mode may be performed by offline processing. Hereinafter, the processing by the travel control device 7 in the operation mode will be described.

[0015] (Travel Trajectory Acquisition Mode) In the travel trajectory acquisition mode, while the host vehicle 1 is being driven manually by the travel control device 7, the travel control device 7 acquires, from the lane recognition device 5, the positions of the left and right lane boundary lines of the lane in which the host vehicle 1 travels. Also, the travel speed and yaw rate of the host vehicle 1 detected by the vehicle speed sensor 2 and the yaw rate sensor 3 are acquired via the CAN (Controller Area Network) 8. Also, position information of the host vehicle 1 is acquired from the host vehicle position acquisition device 4. The travel control device 7 accumulates, in the travel trajectory storage unit 20, time-series data in which a combination of these data is associated with the time information at the acquisition time.

[0016] (Track candidate generation mode) After the accumulation of the travel trajectory in the travel trajectory acquisition mode has been sufficiently performed, in the track candidate generation mode, the travel control device 7 optimizes the travel trajectory by offline processing to generate a travel track candidate. The travel trajectory accumulated in the travel trajectory acquisition mode is an estimation result obtained by the host vehicle position acquisition device 4 performing an online estimation of the position of the host vehicle 1, and may contain an error in the position information. For example, in a location where the reception condition by the GNSS receiver is poor, an error may occur in the position information. Therefore, the trajectory optimization unit 21 reads the travel trajectory from the travel trajectory storage unit 20, and performs Bundle Adjustment to solve an optimization problem of minimizing the error in the position information based on the position information acquired by the host vehicle position acquisition device 4 and the travel speed and yaw rate acquired from the CAN 8, thereby optimizing the shape of the travel trajectory.

[0017] The trajectory optimization unit 21 samples the points (x, y) on the optimized travel trajectory and the attitude θ of the host vehicle 1 at that point at predetermined intervals (for example, 1 meter). Hereinafter, the points on the sampled travel trajectory (that is, passing points, travel points) are referred to as "nodes". The attitude θ of the host vehicle 1 at each node may be, for example, the traveling direction of the host vehicle 1 at that node or the vehicle body attitude angle.

[0018] The reliability calculation unit 22 calculates the position at the center of the lane in which the host vehicle 1 is traveling, from the recognition result of the lane boundary line stored in the travel trajectory storage unit 20, which is associated with the position information of the travel trajectory according to the time information. For example, the midpoint of the positions of the left and right lane boundary lines represented in the vehicle coordinate system may be calculated as the position at the center of the lane. Now, in the vehicle coordinate system, since the position of the host vehicle 1 is the origin of the coordinate system, the distance between the midpoint of the positions of the left and right lane boundary lines and the origin becomes the lateral deviation of the node from the center of the lane.

[0019] The reliability calculation unit 22 calculates a higher reliability (score) as the lateral deviation of the node from the center of the road lane is smaller. For example, based on this lateral deviation, the reliability calculation unit 22 determines whether or not the host vehicle 1 is traveling substantially in the center of the lane at each node. Here, since a certain amount of deviation in the travel line of the vehicle is generally allowed in a wider lane than in a narrower lane, it may be determined whether or not the position of the host vehicle 1 is substantially at the center according to the lane width. For example, assuming that the detected lane width (the distance between the left and right white lines) is W (m) and the general width of the vehicle is 1.8 m, the threshold value is set to max((W - 1.8) / 2 - 0.4, 0.2), and when the lateral deviation is less than or equal to this threshold value, it may be determined that the host vehicle 1 is traveling substantially in the center of the lane. When it is determined that the host vehicle 1 is traveling substantially in the center of the lane, a reliability of (+1) is given to this node, and when it is determined that the host vehicle 1 is not traveling substantially in the center of the lane, a reliability of (-1) is given. Also, when the lane has not been recognized, a reliability of 0 is given because the position of the lane cannot be known. Through the above processing, each node has information on the position and orientation (x, y, θ) and reliability {-1, 0, +1}. Note that the reliability may be a continuously increasing reliability as the lateral deviation of the node from the center of the road lane becomes smaller, or a stepwise increasing reliability. That is, the reliability may be calculated so as to be higher when the lateral deviation of the node from the center of the road lane is smaller than when it is larger.

[0020] The map information storage unit 23 stores map information having position information for each road. The map information stored in the map information storage unit 23 may be, for example, map information for navigation. FIG. 3 is an explanatory diagram of an example of the map information stored in the map information storage unit 23. The map information stored in the map information storage unit 23 has a graph structure composed of map nodes Nm (represented by black plots in FIGS. 3 and 4) and map links Lm (represented by arrows in FIGS. 3 and 4) that connect the map nodes to each other.

[0021] In the intersection areas Ac1 and Ac2 and other areas (single roads), the road classifications are different. The graph structure within the intersection areas Ac1 and Ac2 is divided into a map link for going straight in the intersection area and map links for turning right and / or left. Each of these map links is represented by a plurality of map links. Referring to FIG. 4, for example, in the intersection area Ac1 of an intersection, the map link for going straight in the intersection area is represented by three map links Lm1, Lm2, and Lm3. Also, the map link for turning right is represented by three map links Lm1, Lm4, and Lm5 including the diagonal map link Lm4. The map link for turning left is represented by two map links Lm1 and Lm6.

[0022] In the present embodiment, in order to facilitate the processing described later, a plurality of map links from the entrance to the exit of the intersection areas Ac1 and Ac2 are treated as a single map link. For example, the three map links Lm1, Lm2, and Lm3 are connected and treated as a single map link LS for going straight. Also, the three map links Lm1, Lm4, and Lm5 are connected and treated as a single map link LR for turning right. Also, the two map links Lm1 and Lm6 are connected and treated as a single map link LL for turning left. By treating a plurality of map links connected within the intersection as a single map link in this way, as will be described later, the accuracy in assigning the driving trajectory to the map link is improved.

[0023] Refer to FIG. 2. The link assignment unit 24 assigns the nodes sampled from the travel trajectory to the map link closest to this node. The link assignment unit 24 divides the travel trajectory at the nodes where the assigned map link changes. Thereby, the travel trajectory is divided for each predetermined section corresponding to a single map link. Refer to FIG. 3. The dashed-dotted line indicates a travel trajectory that enters the intersection area Ac1 from below the drawing, turns right, and then turns left in the intersection area Ac2 and heads upward in the drawing. The link assignment unit 24 divides this travel trajectory into a travel trajectory S1 that travels through a single-lane section entering the intersection area Ac1 from below the drawing, a travel trajectory S2 that turns right within the intersection area Ac1, a travel trajectory S3 that travels through a single-lane section exiting the intersection area Ac1 and entering the intersection area Ac2, a travel trajectory S4 that turns left within the intersection area Ac2, and a travel trajectory S5 that travels through a single-lane section exiting the intersection area Ac2.

[0024] Refer to FIG. 2. The combination optimization unit 25 generates a new travel trajectory candidate by reorganizing the connection between the nodes of a plurality of travel trajectories assigned to the same map link. Here, when reorganizing the connection of the nodes, the connected nodes must be smoothly connected spatially. Therefore, the combination optimization unit 25 determines the connectability between the nodes as follows. Refer to FIG. 5. Let the position and orientation of the node N1 be (x1, y1, θ1), and the position and orientation of the node N2 be (x2, y2, θ2). The combination optimization unit 25 determines that it is possible to connect from the node N1 to the node N2 when all of the following connectable conditions (1), (2), and (3) are satisfied.

[0025] (x2 - x1) 2 +(y2 - y1) 2 <D 2 …(1) atan((y2 - y1) / (x2 - x1)) < A …(2) |θ2 - θ1| < B …(3) The connectable conditions (1) and (2) mean that, as seen from node N1, node N2 is located within the shaded area in Fig. 5, and the connectable condition (3) means that the postures of node N1 and node N2 are similar.

[0026] Based on these connectable conditions (1) to (3), the combination optimization unit 25 generates new travel trajectory candidates from a plurality of travel trajectories assigned to the same map link. Referring to Fig. 6, the procedure for the combination optimization unit 25 to generate travel trajectory candidates will be described. In step S1, the combination optimization unit 25 acquires the travel trajectories assigned to the same map link. Let the total number of the acquired travel trajectories be N. In step S2, the combination optimization unit 25 randomly rearranges the order of the acquired travel trajectories and assigns ranks 1 to N. The i-th travel trajectory is denoted as travel trajectory Ti (i: 1 to N).

[0027] In step S3, the combination optimization unit 25 initializes the value of the counter i to "1". In step S4, the combination optimization unit 25 determines the connectability for all combinations of nodes of travel trajectory Ti and travel trajectory T(i + 1). Here, for the combination of travel trajectory Ti and travel trajectory T(i + 1), both the connectability when connecting from the nodes of travel trajectory Ti to the nodes of travel trajectory T(i + 1) and the connectability when connecting from the nodes of travel trajectory T(i + 1) to the nodes of travel trajectory Ti are determined separately.

[0028] In step S5, the combination optimization unit 25 randomly connects the connectable nodes (that is, randomly rearranges the connections between the nodes of travel trajectory Ti and travel trajectory T(i + 1)) to generate a plurality of travel trajectory candidates. Refer to Fig. 7. The driving trajectories T1 and T2 are driving trajectories obtained when driving on a two-lane road. The white plots with reference signs N1, N2, … N8 indicate the nodes on the driving trajectory T1, and the white plots with reference signs Na, Nb, … Ng indicate the nodes on the driving trajectory T2. Since these driving trajectories T1 and T2 intersect at two locations, they can be connected at these intersection points.

[0029] Fig. 8 schematically shows the connectability between these nodes N1~N8, Na~Ng. In Fig. 8, two nodes connected by an arrow indicate that they can be connected in the direction indicated by the arrow. For example, it is possible to connect from node Nc of driving trajectory T2 to node N4 of driving trajectory T1, from node N4 of driving trajectory T1 to node Nd of driving trajectory T2, and from node Nf of driving trajectory T2 to node N7 of driving trajectory T1. In this case, for example, the combination optimization unit 25 may generate a candidate driving trajectory of a combination that starts from node N1, proceeds from node N4 to node Nd, and then returns from node Nf to node N7. A candidate driving trajectory that proceeds from node Nf to node Ng without returning to node N7 may also be generated. Also, for example, a candidate driving trajectory that starts from node N2, proceeds from node Nc to node N4, and then proceeds from node N4 to node N8 may be generated. The combination optimization unit 25 may randomly generate a plurality of other candidate driving trajectories as well.

[0030] Refer to Fig. 6. In step S6, the combination optimization unit 25 calculates the reliability of all the nodes belonging to these trajectory candidates and the driving trajectories Ti, T(i + 1) for each of the generated driving trajectory candidates, and obtains an evaluation value by summing them up. For example, the combination optimization unit 25 may calculate the total value of the reliability of all the nodes as the evaluation value, or may calculate the average value as the evaluation value. In step S7, the combination optimization unit 25 selects any one of these driving trajectory candidates and driving trajectories Ti and T(i + 1) based on the evaluation value. For example, a driving trajectory candidate or a driving trajectory having the largest evaluation value may be selected, or any one of the driving trajectory candidates or driving trajectories having an evaluation value equal to or greater than the threshold value may be selected. The combination optimization unit 25 replaces (overwrites and updates) the driving trajectory Ti with the selected driving trajectory candidate or driving trajectory.

[0031] In step S8, the combination optimization unit 25 increments (increments) the value of the counter i by one. In step S9, the combination optimization unit 25 determines whether the value of the counter i has become N or more. If the value of the counter i has become N or more (step S9: Y), the process proceeds to step S10. If the value of the counter i is less than N (step S9: N), the process returns to step S4.

[0032] In step S10, the combination optimization unit 25 determines whether the processes of steps S2 to S9 have been repeated a predetermined number of times. If the processes of steps S2 to S9 have not yet been repeated a predetermined number of times (step S10: N), the process returns to step S2. When the processes have been repeated a predetermined number of times (step S10: Y), the combination optimization unit 25 ends the process. Through the above processes, a set of driving trajectory candidates having better evaluation values (that is, driving trajectory candidates that travel on a driving line closer to the center of the lane) than the original driving trajectory obtained by manually driving the host vehicle 1 is obtained. However, these driving trajectory candidates include a plurality of driving trajectory candidates traveling in the same lane and are redundant.

[0033] ​Here, the driving trajectories traveling in the same lane, for example, on a multi-lane road as shown in FIG. 7, in addition to the case where two driving trajectories both travel only in the right lane or both travel only in the left lane, also include the case where both are trajectories that change lanes from the right lane to the left lane or both are trajectories that change lanes from the left lane to the right lane.

[0034] Therefore, the combination optimization unit 25 identifies a plurality of driving trajectory candidates that travel in the same lane. For example, the combination optimization unit 25 may compare any two driving trajectory candidates among the plurality of driving trajectory candidates and determine whether these two driving trajectory candidates are spatially independent. When two driving trajectory candidates are spatially independent, it may be determined that they are not driving trajectory candidates traveling in the same lane, and when they are not independent, it may be determined that they are driving trajectory candidates traveling in the same lane.

[0035] For example, the combination optimization unit 25 may determine whether two driving trajectory candidates are spatially independent based on the distance between the start nodes of the two driving trajectory candidates and the distance between the end nodes of the two driving trajectory candidates. Referring to FIG. 9. For example, the combination optimization unit 25 calculates the distance DS between the start node 1S of the driving trajectory candidate T1 and the start node 2S of the driving trajectory candidate T2, and the distance DE between the end node 1E of the driving trajectory candidate T1 and the end node 2E of the driving trajectory candidate T2. When at least one of the distance DS or the distance DE is greater than the threshold value, the combination optimization unit 25 determines that the driving trajectory candidates T1 and T2 are spatially independent. That is, it is determined that the driving trajectory candidates T1 and T2 are not driving trajectory candidates traveling in the same lane. On the other hand, when both the distance DS and the distance DE are less than or equal to the threshold value, the combination optimization unit 25 determines that the driving trajectory candidates T1 and T2 are not spatially independent. That is, it is determined that the driving trajectory candidates T1 and T2 are driving trajectory candidates traveling in the same lane.

[0036] The combination optimization unit 25 selects one of a plurality of driving trajectory candidates identified as driving trajectories on the same lane. For example, the combination optimization unit 25 may hold (extract) one of the identified plurality of driving trajectory candidates and delete (discard) the rest from the trajectory candidate storage unit 26. The combination optimization unit 25 may select a driving trajectory candidate based on, for example, an evaluation value. For example, the driving trajectory candidate with the highest evaluation value may be selected, or any of the driving trajectory candidates having an evaluation value equal to or greater than a predetermined value may be selected.

[0037] Referring to FIG. 10, when at least one of the distance DS between the node 1S at the start point of the driving trajectory candidate T1 and the node 2S at the start point of the driving trajectory candidate T2 and the distance DE between the node 1E at the end point of the driving trajectory candidate T1 and the node 2E at the end point of the driving trajectory candidate T2 is greater than the threshold value, it is determined that the driving trajectory candidates T1 and T2 are not driving trajectory candidates for driving on the same lane. Therefore, the combination optimization unit 25 does not perform the process of selecting one of the driving trajectory candidates T1 and T2. That is, both the driving trajectory candidates T1 and T2 are held. On the other hand, when both the distance DS and the distance DE are equal to or less than the threshold value, it is determined that the driving trajectory candidates T1 and T2 are driving trajectory candidates for driving on the same lane. Therefore, the combination optimization unit 25 holds the candidate with the higher evaluation value among the driving trajectory candidates T1 and T2 and deletes the other with the lower evaluation value from the trajectory candidate storage unit 26.

[0038] (Driving support mode) Referring to FIG. 2, in the driving support mode, the driving control device 7 supports the driving of the host vehicle 1 along the driving trajectory candidates generated in the trajectory candidate generation mode. The driving road determination unit 27 identifies the map link of the road on which the host vehicle 1 is traveling based on the self-position acquired by the self-vehicle position acquisition device 4. The road shape estimation unit 28 acquires, from the trajectory candidate storage unit 26, the driving trajectory candidates assigned to the map link of the road during driving, selects one driving trajectory candidate having the node closest to the current position of the host vehicle 1, and sets it as the target driving trajectory.

[0039] The vehicle control unit 29 controls the actuator 6 so as to assist the running of the host vehicle 1 along the target travel trajectory. For example, when performing autonomous driving control as the driving assistance control, the actuator 6 is controlled so that the host vehicle 1 automatically runs along the target travel trajectory. Also, for example, when performing driving assistance control as the driving assistance control, the actuator 6 is controlled so that the steering angle becomes such that the host vehicle 1 runs along the target travel trajectory. For example, a steering assist force may be applied so that the host vehicle 1 runs along the target travel trajectory.

[0040] (Modification example) In the above description, the driving assistance device generates a target travel trajectory for running the host vehicle 1 based on the travel trajectory that the host vehicle 1 has traveled in the past. Instead of this, a target travel trajectory for running a vehicle other than the host vehicle 1 may be generated. Further, a target travel trajectory for running the host vehicle 1 may be generated based on the travel trajectory that a vehicle other than the host vehicle 1 has traveled in the past, and a target travel trajectory for running the other vehicle or still another vehicle may be generated.

[0041] (Effects of the embodiment) (1) The travel control device 7 acquires the travel trajectories when the vehicle has traveled a plurality of times in a predetermined section of the same road, and for each of the acquired travel trajectories, extracts a plurality of passing points that are positions on the travel trajectory and assigns a reliability to each of the plurality of passing points, associates the passing points with the reliability, and stores them in the storage device. By connecting the passing points stored in the storage device, a plurality of travel trajectory candidates for traveling in the predetermined section are generated, and among the plurality of generated travel trajectory candidates, one of the travel trajectory candidates is extracted based on the total value of the reliabilities of the passing points belonging to the travel trajectory candidate, and the extracted travel trajectory candidate is generated as the target travel trajectory for the vehicle to travel. Thereby, an optimized target travel trajectory can be set based on the travel trajectories when the same road section has been traveled a plurality of times in the past.

[0042] (2) The travel control device 7 may calculate the distance of the passing point from the center of the road lane, and assign a higher reliability when the calculated distance is small than when it is large. Thereby, a target travel trajectory optimized to travel near the center of the lane can be set. (3) The travel control device 7 may estimate the center of the lane from the position of the lane boundary line of the road lane. Thereby, the center of the lane can be estimated based on the recognition result of the lane boundary line, and the reliability of the passing point can be calculated.

[0043] (4) The travel control device 7 may extract a travel trajectory candidate whose total value is equal to or greater than a predetermined value. Thereby, a target travel trajectory optimized to travel near the center of the lane can be set. (5) The travel control device 7 may determine whether the passing points stored in the storage device are connectable, and generate a plurality of travel trajectory candidates by connecting the passing points determined to be connectable. For example, when the distance between two passing points is equal to or less than a distance threshold and the difference in the vehicle's attitude angle or traveling direction at the two passing points is equal to or less than an angle threshold, it may be determined that the two passing points are connectable. Thereby, a travel trajectory candidate in which the passing points are smoothly connected can be generated.

[0044] (6) The travel control device 7 may generate a plurality of travel trajectory candidates by connecting the passing points belonging to different travel trajectories among the acquired travel trajectories. Thereby, a more optimized travel trajectory candidate can be generated than a travel trajectory obtained by traveling a predetermined section of the same road. (7) The travel control device 7 may repeatedly perform a process of extracting any two travel trajectories from the acquired travel trajectories, and a process of generating a travel trajectory candidate by connecting a passing point belonging to one of the two travel trajectories and a passing point connecting to the other travel trajectory a plurality of times, to generate a plurality of travel trajectory candidates. Thereby, by generating a larger number of travel trajectory candidates, a more optimized target travel trajectory can be set.

[0045] (8) The travel control device 7 may compare any two of the plurality of travel route candidates, extract both of the two travel route candidates when the two travel route candidates are spatially independent, and extract one of the two travel route candidates and discard the other when the extracted travel route candidates are not spatially independent. For example, it may be determined whether the two travel route candidates are spatially independent based on the distance between the passing points of the starting points of the two travel route candidates and the distance between the passing points of the end points. This can delete redundant travel route candidates, thereby reducing the storage capacity for storing travel route candidates and the processing load for selecting a target travel route from the travel route candidates. (9) The travel of the vehicle along the target travel route generated by the above (1) to (11) may be supported. Thereby, the travel of the vehicle can be supported based on the optimized target travel route.

Explanation of Reference Numerals

[0046] 1... own vehicle, 2... vehicle speed sensor, 3... yaw rate sensor, 4... own vehicle position acquisition device, 5... lane recognition device, 6... actuator, 7... travel control device, 10... processor, 11... storage device, 20... travel locus storage unit, 21... locus optimization unit, 22... reliability calculation unit, 23... map information storage unit, 24... link assignment unit, 25... optimization unit, 26... track candidate storage unit, 27... travel road determination unit, 28... road shape estimation unit, 29... vehicle control unit

Claims

1. Obtain the driving trajectories when a vehicle travels a plurality of times in a predetermined section of the same road, For each of the obtained driving trajectories, extract a plurality of passing points that are positions on the driving trajectory and assign a reliability to each of the plurality of passing points, Associate the passing points with the reliability and store them in a storage device, By connecting the passing points stored in the storage device, generate a plurality of driving trajectory candidates for traveling in the predetermined section, Among the plurality of generated driving trajectory candidates, extract any one of the driving trajectory candidates based on the total value of the reliability of the passing points belonging to the driving trajectory candidate, Generate the extracted driving trajectory candidate as the target driving trajectory for the vehicle to travel, Calculate the distance of the passing point from the center of the lane of the road, and when the calculated distance is small, assign a higher reliability than when it is large, A driving trajectory generation method characterized by the above.

2. The driving trajectory generation method according to claim 1, characterized in that the center of the lane is estimated from the position of the lane boundary line of the lane of the road.

3. The driving trajectory generation method according to claim 1 or 2, characterized in that the driving trajectory candidate with the total value being equal to or more than a predetermined value is extracted.

4. Determine whether the passing points stored in the storage device are connectable, and generate the plurality of driving trajectory candidates by connecting the passing points determined to be connectable. The driving trajectory generation method according to any one of claims 1 to 3.

5. The driving trajectory generation method according to claim 4, characterized in that when the distance between two passing points is equal to or less than a distance threshold and the difference in the attitude angle or traveling direction of the vehicle at the two passing points is equal to or less than an angle threshold, it is determined that the two passing points are connectable.

6. The driving trajectory generation method according to any one of claims 1 to 5, characterized in that the plurality of driving trajectory candidates are generated by connecting the passing points belonging to different driving trajectories among the obtained driving trajectories.

7. The process of extracting any two of the obtained driving trajectories, The process of generating the driving trajectory candidate by connecting the passing points belonging to one of the two driving trajectories and the passing points connected to the other driving trajectory, The driving trajectory generation method according to claim 6, characterized in that the plurality of driving trajectory candidates are generated by repeating the above two processes a plurality of times.

8. Compare any two of the plurality of candidate travel trajectories, and if at least one of a first distance between the passing points of the starting points of the two candidate travel trajectories or a second distance between the passing points of the ending points is greater than a threshold value, extract both of the two candidate travel trajectories, and if both the first distance and the second distance are equal to or less than the threshold value, extract one of the two candidate travel trajectories and discard the other. The travel trajectory generation method according to any one of claims 1 to 7, characterized by this.

9. A travel support method, characterized by supporting the travel of the vehicle along the target travel trajectory generated by the travel trajectory generation method according to any one of claims 1 to 8.

10. A positioning device for measuring the current position of the vehicle, A vehicle sensor for detecting the running state of the vehicle, A storage device, Based on the positioning result of the positioning device and the detection result of the vehicle sensor, obtain the travel trajectory when the vehicle travels a plurality of times in a predetermined section of the same road, and for each of the obtained travel trajectories, extract a plurality of passing points that are positions on the travel trajectory and assign a reliability to each of the plurality of passing points, associate the passing points with the reliability and store them in the storage device, and generate a plurality of candidate travel trajectories for traveling in the predetermined section by connecting the passing points stored in the storage device, and among the plurality of generated candidate travel trajectories, extract any candidate travel trajectory based on the total value of the reliabilities of the passing points belonging to the candidate travel trajectory, and generate the extracted candidate travel trajectory as the target travel trajectory for the vehicle to travel, calculate the distance of the passing point from the center of the lane of the road, and assign a higher reliability when the calculated distance is small than when it is large. A controller, A travel trajectory generation device, characterized by comprising.

11. A travel support device, characterized by supporting the travel of the vehicle along the target travel trajectory generated by the travel trajectory generation device according to claim 10.

Images