Driving assistance device

Abstract

The present application provides a kind of driving assistance device (200) for assisting the driving of vehicle (101) along target trajectory on predetermined path, with: storage part (52), it stores the first map information of first area including the position information of the dividing line of specified lane and the second map information of second area adjacent to first area;Target trajectory generation unit (551), it generates the first target trajectory of vehicle (101) in first area based on the first map information stored in storage part (52), generates the second target trajectory of vehicle (101) in second area based on second map information;And target trajectory correction unit (552), it corrects the first target trajectory in the boundary portion between first area and second area based on second target trajectory.

Description

TECHNICAL FIELD

[0001] The present application relates to a driving assist device that assists driving of a vehicle. BACKGROUND

[0002] As such a device, a device that sets a target trajectory of an automatically driven vehicle has been known (for example, refer to Patent Literature 1). In the device described in Patent Literature 1, a target trajectory of a vehicle is set in a manner that passes through the center of a lane, based on map information provided in advance.

[0003] However, a vehicle sometimes travels in a boundary region of a plurality of maps that are adjacent to each other. However, since inherent errors are sometimes included in map information of adjacent maps, if a target trajectory is set like the device described in Patent Literature 1, it can be difficult to smoothly set a target trajectory when traveling in a boundary region of a plurality of maps.

[0004] PRIOR ART DOCUMENTS

[0005] PATENT LITERATURE

[0006] Patent Literature 1: Japanese Patent Application Publication No. 2020-66333 (JP 2020-066333 A). SUMMARY

[0007] One aspect of the present application is a driving assist device that assists driving of a vehicle that travels along a target trajectory on a predetermined path, including: a storage unit that stores first map information of a first region and second map information of a second region adjacent to the first region, the first map information of the first region including position information of a division line that defines a lane; a target trajectory generation unit that generates a first target trajectory of the vehicle in the first region based on the first map information stored in the storage unit, and generates a second target trajectory of the vehicle in the second region based on the second map information; and a target trajectory correction unit that corrects the first target trajectory in a boundary portion between the first region and the second region based on the second target trajectory. BRIEF DESCRIPTION OF DRAWINGS

[0008] The objects, features, and advantages of the present application will be further clarified by the following description of embodiments with reference to the attached drawings.

[0009] Figure 1 is a drawing that illustrates an example of a travel scenario of an automatically driven vehicle that applies the driving assist device of an embodiment of the present application.

[0010] Figure 2 is a block diagram that schematically illustrates the overall structure of a vehicle control system of an automatically driven vehicle that applies the driving assist device of an embodiment of the present application.

[0011] Figure 3is a drawing illustrating an example of a travel scenario of an automated vehicle assumed by a driving assist device of an embodiment of the present application.

[0012] Figure 4 is a block diagram illustrating a main part structure of a driving assist device of an embodiment of the present application.

[0013] Figure 5A is a drawing illustrating an example of a target trajectory before and after correction by a driving assist device of an embodiment of the present application.

[0014] Figure 5B is a drawing illustrating another example of a target trajectory before and after correction by a driving assist device of an embodiment of the present application.

[0015] Figure 5C is a drawing illustrating still another example of a target trajectory before and after correction by a driving assist device of an embodiment of the present application.

[0016] Figure 6 is a flowchart illustrating an example of processing performed by a controller of Figure 4 DETAILED DESCRIPTION

[0017] Hereinafter, an embodiment of the present application will be described with reference to Figures 1-6 An embodiment of the present application is described below. The driving assist device of the embodiment of the present application can be applied to a vehicle having an automated driving function (an automated vehicle). The automated vehicle includes not only a vehicle that travels only in an automated driving mode in which a driver's driving operation is not required, but also a vehicle that travels in the automated driving mode and travels in a manual driving mode based on a driver's driving operation.

[0018] Figure 1 is a drawing illustrating an example of a travel scenario of an automated vehicle (hereinafter referred to as a vehicle) 101. Figure 1 An example in which the vehicle 101 keeps traveling in a lane (lane keeping travel) without deviating from a lane LN defined by a division line 102 is illustrated in FIG. 1. Note that the vehicle 101 can be any one of an engine vehicle having an internal combustion engine (engine) as a travel drive source, an electric vehicle having a travel motor as a travel drive source, and a hybrid vehicle having an engine and a travel motor as travel drive sources.

[0019] Figure 2 is a block diagram schematically illustrating an overall structure of a vehicle control system 100 of the vehicle 101 to which the driving assist device of the present embodiment is applied. As illustrated in FIG. 5, the vehicle control system 100 includes a vehicle control unit 110, a vehicle state detection unit 120, a vehicle exterior information detection unit 130, a vehicle interior information detection unit 140, a vehicle drive system 150, a vehicle bodywork 160, a vehicle network 170, and a controller 180. Figure 2 ​As shown, the vehicle control system 100 mainly has a controller 50, and an external sensor group 1, an internal sensor group 2, an input / output device 3, a positioning unit 4, a map database 5, a navigation device 6, a communication unit 7, and an actuator AC for running, which are electrically connected to the controller 50, respectively.

[0020] The external sensor group 1 is a collective term of a plurality of sensors (external sensors) that detect an external situation of the periphery of the vehicle 101 as surrounding information. For example, the external sensor group 1 includes a laser radar that measures a distance to an obstacle in the periphery of the vehicle 101 by measuring scattered light of irradiation light in all directions of the vehicle 101, a radar that detects other vehicles, obstacles, and the like in the periphery of the vehicle 101 by irradiating electromagnetic waves and detecting reflected waves, and a camera that is mounted on the vehicle 101 and has a CCD (Charge Coupled Device), a CMOS (Complementary Metal Oxide Semiconductor), or the like as a photographing element to photograph the periphery (front, rear, and side) of the vehicle 101. Figure 1

[0021] The internal sensor group 2 is a collective term of a plurality of sensors (internal sensors) that detect a running state of the vehicle 101. For example, the internal sensor group 2 includes a vehicle speed sensor that detects a vehicle speed of the vehicle 101, an acceleration sensor that detects an acceleration in a front-rear direction and an acceleration in a left-right direction (lateral acceleration) of the vehicle 101, respectively, a rotation speed sensor that detects a rotation speed of a running drive source, and a yaw rate sensor that detects a rotation angular speed of a center of gravity of the vehicle 101 around a vertical axis. A sensor that detects a driving operation of a driver in a manual driving mode, such as an operation on an accelerator pedal, an operation on a brake pedal, an operation on a steering wheel, and the like, is also included in the internal sensor group 2.

[0022] The input / output device 3 is a collective term of devices that input an instruction from a driver and output information to the driver. For example, the input / output device 3 includes various switches through which the driver inputs various instructions by operating operation members, a microphone through which the driver inputs an instruction by voice, a display that provides information to the driver by displaying an image, a speaker that provides information to the driver by voice, and the like.

[0023] The positioning unit (GNSS unit) 4 has a positioning sensor that receives a positioning signal transmitted from a positioning satellite. The positioning satellite is a GPS satellite, a quasi-zenith satellite, or the like. The positioning unit 4 measures a current position (latitude, longitude, and altitude) of the vehicle 101 using positioning information received by the positioning sensor.

[0024] ​The map database 5 is a device that stores general map information for the navigation device 6, for example, constituted by a hard disk, a semiconductor element. The map information includes position information of a road, information of a road shape (curvature, etc.), position information of an intersection or a branch. Note that the map information stored in the map database 5 is different from the high-precision map information stored in the storage section 52 of the controller 50.

[0025] The navigation device 6 is a device that searches for a target route on a road to a destination input by the driver and performs guidance according to the target route. The input of the destination and the guidance according to the target route are performed by the input / output device 3. The target route is calculated based on the current position of the vehicle 101 determined by the positioning unit 4 and the map information stored in the map database 5. It is also possible to determine the current position of the vehicle 101 using the detection values of the external sensor group 1, and it is also possible to calculate the target route based on the current position and the high-precision map information stored in the storage section 52.

[0026] The communication unit 7 communicates with various servers not shown via a network including a wireless communication network typified by the Internet, a mobile phone network, etc., and acquires map information, traffic information, etc. from the servers periodically or at an arbitrary timing. The network includes not only a public wireless communication network but also a closed communication network such as a wireless LAN, Wi-Fi (registered trademark), Bluetooth (registered trademark), etc. provided for each prescribed management area. The acquired map information is output to the map database 5, the storage section 52, and the map information is updated.

[0027] The actuator AC is an actuator for controlling the running of the vehicle 101. In the case where the running drive source is an engine, the actuator AC includes a throttle valve actuator that adjusts the opening degree of a throttle valve of the engine, and an injector actuator that adjusts the valve opening timing and the valve opening time of an injector. In the case where the running drive source is a running motor, the running motor is included in the actuator AC. A brake actuator that operates a brake device of the vehicle 101 and a steering actuator that drives a steering device are also included in the actuator AC.

[0028] The controller 50 is constituted by an electronic control unit (ECU). More specifically, the controller 50 is constituted by a computer including an arithmetic section 51 having a CPU (microprocessor) or the like, a storage section 52 such as a ROM (read only memory), a RAM (random access memory), and other peripheral circuits such as an I / O (input / output) interface not shown. Note that a plurality of ECUs having different functions such as an engine control ECU, a running motor control ECU, a brake device ECU, etc. can be provided separately, but for the sake of convenience, Figure 2 The controller 50 is shown as a collection of these ECUs.

[0029] The detailed road map information of high precision is stored in the storage section 52. The road map information includes the position information of the road, the information of the shape of the road (curvature, etc.), the information of the slope of the road, the position information of the intersection, the position information of the branch, the information of the number of lanes, the width of the lane, and the position information of each lane (the central position of the lane, the information of the boundary line of the lane position), the position information of the landmark (signal, sign, building, etc.) as the marker on the map, the information of the road surface profile of the concave and convex of the road surface, and the like.

[0030] The map information stored in the storage section 52 includes: the map information acquired from the outside of the vehicle 101 via the communication unit 7, the information of the map (referred to as a cloud map) acquired via a cloud server, and the information of the map (referred to as an environment map) made by the vehicle 101 itself using the detection values of the external sensor group 1, for example, the point cloud data generated by mapping using a technology such as SLAM (Simultaneous Localization and Mapping).

[0031] The cloud map information is general map information generated based on data collected by a dedicated survey vehicle or a general autonomous vehicle traveling on a road and distributed to general autonomous vehicles via a cloud server. The cloud map is generated in a region with a large amount of traffic such as an expressway or a city area, but is not generated in a region with a small amount of traffic such as a residential area or a rural area. On the other hand, the environment map information is dedicated map information generated based on data collected by each autonomous vehicle traveling on a road and used for autonomous driving of the vehicle. Various control programs, threshold values used in the programs, and the like are also stored in the storage section 52.

[0032] The arithmetic section 51 has a vehicle position recognition section 53, an outside recognition section 54, a behavior plan generation section 55, and a travel control section 56 as a functional structure. That is, the CPU (microprocessor) or the like of the controller 50 functions as the vehicle position recognition section 53, the outside recognition section 54, the behavior plan generation section 55, and the travel control section 56.

[0033] The vehicle position recognition section 53 recognizes the position of the vehicle 101 on the map (vehicle position) with high precision based on the detailed road map information of high precision (cloud map information, environment map information) stored in the storage section 52 and the surrounding information of the vehicle 101 detected by the external sensor group 1. Note that when the vehicle position can be measured by an external sensor provided on or beside the road, the vehicle position can also be recognized by communicating with the sensor via the communication unit 7. The position information of the vehicle 101 obtained by the positioning unit 4 can also be used to recognize the vehicle position.

[0034] The outside recognition unit 54 recognizes an outside situation around the vehicle 101 based on a signal from the external sensor group 1 such as a laser radar, a radar, a camera, and the like. For example, a division line 102 of a lane LN in which the vehicle 101 travels, a position, a speed, an acceleration of a surrounding vehicle (a preceding vehicle, a following vehicle) that travels in the periphery of the vehicle 101, a position of a surrounding vehicle that is parked or stopped in the periphery of the vehicle 101, and a position, a state of other objects, and the like. The other objects include a sign, a signal, a road stop line, a building, a guardrail, a utility pole, a billboard, a pedestrian, a bicycle, and the like. The state of the other objects includes a color (red, green, yellow) of the signal, a moving speed, a direction of the pedestrian or the bicycle, and the like.

[0035] The action plan generation unit 55 generates a travel trajectory (a target trajectory) of the vehicle 101 from a current time point to a prescribed time based on, for example, a target path calculated by the navigation device 6, a current position of the vehicle recognized by the current position recognition unit 53, and an outside situation recognized by the outside recognition unit 54. More specifically, based on the high-precision detailed road map information (cloud map information, environment map information) stored in the storage unit 52, the target trajectory of the vehicle 101 is generated on the cloud map or the environment map. When there are a plurality of trajectories that become candidates for the target trajectory on the target path, the action plan generation unit 55 selects the best trajectory that complies with a law and satisfies a criterion such as efficient and safe travel from among them, and sets the selected trajectory as the target trajectory. Then the action plan generation unit 55 generates an action plan corresponding to the generated target trajectory.

[0036] The action plan includes travel plan data set for each unit time (for example, 0.1 seconds) in a period from the current time point to a prescribed time (for example, 5 seconds), that is, travel plan data set in association with each unit time. The travel plan data includes position data of the vehicle 101 for each unit time and data of a vehicle state. The position data is, for example, data that shows a two-dimensional coordinate position on a road, and the data of the vehicle state is vehicle speed data that shows a vehicle speed and direction data that shows an orientation of the vehicle 101, and the like. Therefore, in a case where the vehicle 101 accelerates to a target vehicle speed in the prescribed time, data of the target vehicle speed is included in the action plan. The data of the vehicle state can be derived based on a change in the position data for each unit time. The travel plan is updated every unit time.

[0037] Figure 1 An example of the action plan generated by the action plan generation unit 55, that is, a travel plan of a scenario in which the vehicle 101 travels while not deviating from the lane LN, is shown. Figure 1Each point P in the target trajectory 110 corresponds to position data for each unit time from the current time point until a prescribed time elapses, and the target trajectory 110 is obtained by connecting these points P in time series. The target trajectory 110 is generated, for example, along a center line 103 of a pair of division lines 102 of a prescribed lane LN. The target trajectory 110 can also be generated along a past travel trajectory included in the map information. Note that, in the action plan generation section 55, in addition to lane keeping travel, various action plans corresponding to overtaking travel in which the vehicle 101 changes lanes to overtake a preceding vehicle, lane changing travel in which the vehicle 101 changes lanes, deceleration travel, or acceleration travel, and the like are generated. The action plan generation section 55, when generating the target trajectory 110, first determines a travel mode, and generates the target trajectory 110 based on the travel mode. Information of the target trajectory 110 generated by the action plan generation section 55 is added to the map information and stored in the storage section 52, and is taken into account when the action plan generation section 55 generates an action plan at the next time of travel.

[0038] In the automatic driving mode, the travel control section 56 controls each actuator AC so that the vehicle 101 travels along the target trajectory 110 generated by the action plan generation section 55. More specifically, the travel control section 56 calculates a required driving force for obtaining the target acceleration per unit time calculated by the action plan generation section 55, taking into account the travel resistance determined by the road slope and the like in the automatic driving mode. Also, feedback control is performed on the actuators AC, for example, so that the actual acceleration detected by the internal sensor group 2 becomes the target acceleration. That is, the actuators AC are controlled so that the vehicle 101 travels at the target vehicle speed and the target acceleration. In the manual driving mode, the travel control section 56 controls each actuator AC in accordance with a travel instruction (steering operation or the like) from the driver taken in by the internal sensor group 2.

[0039] The driving assistance device of the present embodiment corrects a target trajectory of an autonomous vehicle traveling in a boundary region of a plurality of maps adjacent to each other. Figure 3 is a diagram illustrating an example of a travel scenario of the vehicle 101 assumed by the driving assistance device of the present embodiment, and Figure 1 is the same as FIG. 1, and illustrates a scenario in which the vehicle 101 performs lane keeping travel without deviating from the lane LN. Note that, hereinafter, a region in the storage section 52 in which an environmental map generated on the vehicle 101 side is stored will be referred to as an environmental map region ARa, and a region in the storage section 52 in which a cloud map generated on the cloud server side is stored will be referred to as a cloud map region ARb.

[0040] Due to ranging errors and the like at the time of generating the maps, an inherent error is included in each map information. Therefore, as illustrated in Figure 3As shown, the target trajectory 110a of vehicle 101 generated on the environmental map and the target trajectory 110b generated on the cloud map are sometimes inconsistent. When driving in autonomous driving mode in the boundary region Arc, which is the boundary area between the environmental map region ARa and the cloud map region ARb, with a deviation between the target trajectories 110a and 110b, the target trajectory 110 of vehicle 101 may not be set smoothly. More specifically, the target trajectory 110 may not be set smoothly when switching the map information used by the vehicle position recognition unit 53 to recognize the vehicle's position. Therefore, in this embodiment, the driving assistance device is configured as follows to eliminate the deviation of the target trajectory generated on multiple maps and to smoothly set the target trajectory when driving in the boundary area.

[0041] Figure 4 This is a block diagram showing the main structural components of a driving assistance device 200 according to an embodiment of the present invention. The driving assistance device 200 assists the driving actions of the vehicle 101 in automatic driving mode, constituting... Figure 2 It is part of the vehicle control system 100. For example... Figure 4 As shown, the driving assistance device 200 includes a controller 50, an external sensor group 1, and a positioning unit 4.

[0042] The controller 50 includes a target trajectory generation unit 551, a target trajectory correction unit 552, and a road information correction unit 553, which serve as the calculation unit 51. Figure 2 The functional structure undertaken by the controller 50 is as follows: Specifically, the CPU (microprocessor) and other arithmetic unit 51 of the controller 50 functions as the target trajectory generation unit 551, the target trajectory correction unit 552, and the road information correction unit 553. The target trajectory generation unit 551, the target trajectory correction unit 552, and the road information correction unit 553 are, for example, composed of… Figure 2 The action plan generation department consists of 55 components. Figure 4 The storage unit 52 pre-stores environmental map information for the environmental map region ARa and cloud map information for the cloud map region ARb.

[0043] The target trajectory generation unit 551 generates a target trajectory 110a of the vehicle 101 on the environmental map based on the surrounding information of the vehicle 101 detected by the external sensor group 1, the current position of the vehicle 101 determined by the positioning unit 4, and the environmental map information stored in the storage unit 52. Figure 3 Additionally, a target trajectory 110b for vehicle 101 is generated on the cloud map based on cloud map information. The information of target trajectories 110a and 110b generated by the target trajectory generation unit 551 is added to the environmental map information and the cloud map information, respectively, and stored in the storage unit 52.

[0044] The target trajectory correction section 552 corrects the target trajectory 110a on the environment map in the boundary section ARc based on the target trajectory 110b on the cloud map Figure 3 ). That is, since the map information common to a plurality of automated vehicles including the vehicle 101, that is, the cloud map information cannot be rewritten on the vehicle 101 side, the environment map information on the vehicle 101 side is corrected based on the cloud map information.

[0045] The target trajectory correction section 552 acquires information of the target trajectories 110a, 110b in the boundary section ARc generated by the target trajectory generation section 551, and associates the information of each lane LN in the case where a plurality of lanes LN exist. More specifically, the information of the division lines 102a, 102b, the center lines 103a, 103b, and the target trajectories 110a, 110b corresponding to each lane LN are associated, respectively. In addition, in the case where the data formats of the division lines 102a, 102b, the center lines 103a, 103b, and the target trajectories 110a, 110b are different, they are unified. For example, in the case where one target trajectory 110a is expressed by coordinate values and the other target trajectory 110b is expressed by a function, they are unified to coordinate values.

[0046] Figures 5A-5C is a drawing illustrating an example of the target trajectory 110 before and after correction by the target trajectory correction section 552, and illustrates the target trajectories 110a, 110b before correction expressed by coordinate values and the target trajectory 110c after correction expressed by a function.

[0047] As shown in Figure 5A , the target trajectory correction section 552 corrects a part (dotted line part in the drawing) of the target trajectory 110a on the environment map to an approximate curve passing through a point Pa on the target trajectory 110a and a point Pb on the target trajectory 110b on the cloud map. In other words, an approximate curve that starts from the point Pa on the target trajectory 110a and ends at the point Pb on the target trajectory 110b is generated as the target trajectory 110c after correction. The approximate curve is expressed by a function such as a Bezier curve or a B-spline curve using a point cloud between the point Pa and the point Pb as control points. Thereby, the target trajectory 110a on the environment map and the target trajectory 110b on the cloud map are smoothly connected without interruption by the target trajectory 110c after correction.

[0048] As shown in Figure 5AAs shown, when vehicle 101 travels from environmental map region ARa to cloud map region ARb, for example, the current position (vehicle position) of vehicle 101 is set as the starting point of the corrected target trajectory 110c. Thus, the target trajectory 110a on the environmental map is pre-corrected to target trajectory 110c before vehicle 101 actually travels, and is connected to the target trajectory 110b on the cloud map, thereby appropriately assisting vehicle 101 in its driving actions at the boundary region ARc.

[0049] Furthermore, any point included in the overlapping area ARd between the environmental map area ARa and the cloud map area ARb, such as point Pb on the target trajectory 110b, a predetermined distance forward from the end of the cloud map area ARb, is set as the endpoint of the corrected target trajectory 110c. Based on the vehicle speed of 101, the predetermined distance is set to a distance that allows for stable identification of the vehicle's position after the map information used by the vehicle position identification unit 53 to identify the vehicle's position is switched to cloud map information.

[0050] It should be noted that, as Figure 5B As shown, when vehicle 101 travels from cloud map region ARb to environment map region ARa, for example, point Pa on target trajectory 110a, a predetermined distance forward from the end of cloud map region ARb, is set as the endpoint of the corrected target trajectory 110c. In this case, the predetermined distance is set to be sufficient to eliminate deviations from the envisioned target trajectories 110a and 110b and smoothly set the distance of the corrected target trajectory 110c. The predetermined distance can also be set according to the vehicle speed of vehicle 101, etc. Furthermore, point Pb on target trajectory 110b, which is included in the overlapping region ARd, is set as the starting point of the corrected target trajectory 110c.

[0051] like Figure 5C As shown, the target trajectory correction unit 552 can correct the target trajectory 110a within the overlapping region ARd. In this case, the target trajectory correction unit 552 generates the corrected target trajectory 110c by taking point Pa at the end of the cloud map region ARb on the target trajectory 110a as the starting point and point Pb at the end of the environment map region ARa on the target trajectory 110b as the ending point. Thus, the corrected target trajectory 110c can be smoothly set using the overlapping region ARd.

[0052] The road information correction unit 553 corrects the position information of the dividing line 102a and the center line 103a contained in the environmental map information stored in the storage unit 52 based on the correction result of the target trajectory correction unit 552. More specifically, the position information of the dividing line 102a and the center line 103a in the boundary section ARc is corrected using the same function as the corrected target trajectory 110c generated by the target trajectory correction unit 552. This prevents malfunctions of off-road deviation suppression functions and other functions implemented based on the position information of the dividing line 102a and the center line 103a.

[0053] Figure 6 It is shown by Figure 4 The flowchart illustrates an example of the processing performed by the controller 50. The processing shown in the flowchart begins, for example, when the autonomous driving mode of the vehicle 101 is activated, and repeats at a predetermined cycle until the autonomous driving mode is deactivated. First, in S1 (S: processing step), a target trajectory 110 is generated on the target path. Next, in S2, it is determined whether multiple map boundary regions ARc exist on the target trajectory 110 generated in S1. If S2 is affirmative (S2: yes), the process proceeds to S3; if it is negative (S2: no), the processing ends.

[0054] In S3, the information of target trajectories 110a, 110b, dividing lines 102a, 102b, and centerlines 103a, 103b on each map corresponding to each lane LN in the boundary section ARc is associated. Next, in S4, it is determined whether the target trajectories 110a, 110b, dividing lines 102a, 102b, and centerlines 103a, 103b are represented by functions. If S4 is affirmative (S4: Yes), proceed to S5, transform the target trajectories 110a, 110b, dividing lines 102a, 102b, and centerlines 103a, 103b into coordinate values, and proceed to S6. On the other hand, if S4 is negative (S4: No), skip S5 and proceed directly to S6.

[0055] In S6, the target trajectory 110a of one side in the boundary section ARc is corrected based on the target trajectory 110b of the other side. Next, in S7, using the same correction method as in S6, the dividing line 102a and center line 103a of one side in the boundary section ARc are corrected based on the dividing line 102b and center line 103b of the other side. Next, in S8, the information of the target trajectory 110a, dividing line 102a, and center line 103a of one side, which were corrected in S6 and S7, is stored in the storage unit 52, the map information of one side is updated, and the processing ends.

[0056] The operation of the driving assistance device 200 in this embodiment is summarized as follows. For example... Figure 5AAs shown, when the vehicle 101 in travel on the target path from the environment map region ARa to the cloud map region ARb in the automatic driving mode reaches the boundary portion Arc, the target trajectory 110a is corrected to a target trajectory 110c Figure 6 S1-S6, S8). Thereby, the vehicle 101 can travel smoothly along the target trajectories 110a, 110b connected smoothly by the corrected target trajectory 110c at the boundary portion Arc. In addition, the division line 102a and the center line 103a are also corrected in accordance with the target trajectory 110a Figure 3 Figure 6 S7, S8), so that erroneous operation of the off-road deviation suppression function and the like based on these position information can be prevented.

[0057] With the present embodiment, the following effects can be achieved.

[0058] (1) The driving assistance device 200 assists the driving of the vehicle 101 traveling along the target trajectory 110 on the predetermined target path Figure 1 ). The driving assistance device 200 has a storage section 52 that stores environment map information of an environment map region ARa and cloud map information of a cloud map region ARb adjacent to the environment map region ARa, the environment map information of the environment map region ARa including position information of a division line 102 of a lane LN, a target trajectory generation section 551 that generates a target trajectory 110a of the vehicle 101 in the environment map region ARa based on the environment map information stored in the storage section 52, and a target trajectory 110b of the vehicle 101 in the cloud map region ARb based on the cloud map information, and a target trajectory correction section 552 that corrects the target trajectory 110a in a boundary portion Arc between the environment map region ARa and the cloud map region ARb based on the target trajectory 110b Figure 4 ).

[0059] Thereby, when the vehicle 101 travels on the boundary portion Arc, the plurality of target trajectories 110a, 110b respectively generated in the plurality of maps are connected to each other in advance in the boundary portion Arc, so that the target trajectory 110 when traveling on the boundary portion Arc can be set smoothly.

[0060] (2) The precision of the cloud map information is higher than that of the environment map information. For example, the target trajectory 110a of the environment map information generated based on the driving data of each vehicle 101 is corrected based on the cloud map information of higher precision generated based on the driving data of more vehicles. Therefore, the target trajectory 110 when traveling on the boundary portion Arc can be set appropriately.

[0061] ​(3) The environmental map information is exclusive map information that can be used only by the vehicle 101, and the cloud map information is common map information that can be used by the vehicle 101 and other vehicles. That is, the cloud map is common map information used by a plurality of autonomous vehicles including the vehicle 101, and cannot be rewritten at each vehicle 101 side. Based on the cloud map, the target trajectory 110a of the exclusive map information, that is, the environmental map information, for each vehicle 101 is corrected.

[0062] (4) The target trajectory correction section 552 corrects a part of the target trajectory 110a to an approximate curve (corrected target trajectory 110c) passing through a point Pa on the target trajectory 110a and a point Pb on the target trajectory 110b. Figures 5A-5C ). Thereby, the target trajectory 110a and the target trajectory 110b can be smoothly connected without interruption.

[0063] (5) Either of the point Pa and the point Pb is included in an overlap region ARd between the environmental map region ARa and the cloud map region ARb. Figures 5A-5C ). For example, the end point of the corrected target trajectory 110c when entering the cloud map region ARb from the environmental map region ARa is set to the point Pb on the target trajectory 110b at a predetermined distance forward from the end portion of the cloud map region ARb. In this case, the own vehicle position can be stably recognized after the map information for recognizing the own vehicle position is switched to the cloud map information.

[0064] (6) The point Pa is a point at the end portion of the cloud map region, and the point Pb is a point at the end portion of the environmental map region. Figure 5C ). Thereby, since the approximate curve (corrected target trajectory 110c) is generated using the overlap region ARd between the environmental map region ARa and the cloud map region ARb, it is possible to set a gentle target trajectory 110.

[0065] (7) The driving assistance device 200 further has a road information correction section 553 Figure 4 ) that corrects the position information of the division line 102a stored in the storage section 52 according to the correction result of the target trajectory correction section 552. Thereby, it is possible to prevent erroneous operation of the off-road deviation suppression function and the like based on the position information of the division line 102a, and to assist smooth travel operation of the vehicle 101 at the boundary portion ARc.

[0066] The above-described embodiments can be modified in various ways. Hereinafter, several modified examples will be described. In the above-described embodiments, an example in which the deviation of the target trajectories 110a, 110b generated between the environmental map information on the vehicle 101 side and the cloud map information on the cloud server side is eliminated was described, but the first map information and the second map information are not limited thereto. For example, the deviation of the target trajectories generated between the environmental map information on the vehicle 101 side and the environmental map information acquired from other automated driving vehicles through inter-vehicle communication can also be eliminated. The deviation of the target trajectories generated between a plurality of cloud map information can also be eliminated.

[0067] In the above-described embodiments, an example in which the driving assistance device 200 constitutes a part of the vehicle control system 100 was described, but the driving assistance device can be a device that assists the travel action of an automated driving vehicle, and is not limited to a device mounted on an automated driving vehicle. For example, it can be a device that constitutes a part of a running management server or a traffic control server or the like provided outside the automated driving vehicle.

[0068] In the above-described embodiments, an example in which the target trajectory generation section 551 generates the target trajectories 110a, 110b from the current time point to a prescribed time was described, but the target trajectory generation section is not limited thereto. For example, the target trajectories in the boundary region can be generated every time each map information is updated, regardless of the timing at which the automated driving vehicle travels in the boundary region.

[0069] In the above-described embodiments, in Figure 4 In the above-described embodiments, the driving assistance device 200 was described as having a road information correction section 553 in addition to the target trajectory correction section 552, but the driving assistance device can have only the target trajectory correction section. The driving assistance device can have a road information correction section that corrects road information other than the division line, the center line, and the like of the road in the vicinity of the road.

[0070] In the above-described embodiments, an example in which the target trajectory correction section 552 corrects the target trajectory 110a using a function such as a Bezier curve or a B-spline curve was described, but the target trajectory correction section that corrects the first target trajectory based on the second target trajectory is not limited thereto. Correction can be performed using other functions, or correction can also be performed through geometric correction.

[0071] In the above-described embodiments, in Figure 3 , Figures 5A-5C In the above-described embodiments, an example in which the deviation of the target trajectories generated on a plurality of maps occurs in the vehicle width direction of the vehicle 101 was described, but the deviation occurring in the advancing direction or the height direction of the vehicle 101 can also be eliminated by the same method.

[0072] One or more of the above-described embodiments and modifications can be combined with each other, or with the modifications.

[0073] According to the present application, the target trajectory can be smoothly set when traveling in a boundary region of a plurality of maps.

[0074] The present application has been described above with reference to the preferred embodiments thereof. However, it should be understood by those skilled in the art that various modifications and changes can be made thereto without departing from the scope disclosed in the following claims.

Claims

1. A driving assistance device (200) that is a driving assistance device (200) that assists driving of a vehicle (101) that travels on a predetermined path along a target trajectory, characterized by, Possessing: a storage section (52) that stores first map information of a first region and second map information of a second region adjacent to the first region, the first map information of the first region including position information of a division line that defines a lane; a target trajectory generation section (551) that generates a first target trajectory of the vehicle (101) in the first region based on the first map information stored in the storage section (52), and generates a second target trajectory of the vehicle (101) in the second region based on the second map information; a target trajectory correction section (552) that corrects the first target trajectory in a boundary section between the first region and the second region based on the second target trajectory; and a road information correction section (553) that corrects the position information of the division line stored in the storage section (52) according to a correction result of the target trajectory correction section (552); the second map information cannot be rewritten, the road information correction section (553) corrects the position information of the division line included in the first map information.

2. The driving assistance device (200) according to claim 1, characterized in that the second map information has higher precision than the first map information.

3. The driving assistance device (200) according to claim 1, characterized in that the first map information is exclusive map information that only the vehicle (101) can use, the second map information is common map information that the vehicle (101) and other vehicles can use.

4. The driving assistance device (200) according to claim 1, characterized in that the target trajectory correction section (552) corrects a part of the first target trajectory to an approximate curve that passes through a first point on the first target trajectory and a second point on the second target trajectory.

5. The driving assistance device (200) according to claim 4, characterized in that either one of the first point and the second point is included in an overlap section between the first region and the second region.

6. The driving assistance device (200) according to claim 4, characterized in that the first point is a point of an end portion of the second region, the second point is a point of an end portion of the first region.

Images