JP7318479B2 - vehicle controller - Google Patents

Description

The present invention relates to a vehicle control device.

In order to use for driving assistance or automatic driving control of a vehicle, it is performed to generate a planned driving route of the vehicle based on the position of the vehicle, the destination of the vehicle, and map data (for example, patent Reference 1).

The planned travel route may be changed when the destination of the vehicle is changed, or when the vehicle deviates from the planned travel route due to road conditions on which the vehicle travels. The vehicle displays the changed planned travel route on the display together with the current position of the vehicle to notify the driver of the latest planned travel route.

In this way, the vehicle displays information about the future route of the vehicle on the display to notify the driver, and the driver sees the position of the vehicle and the planned travel route displayed on the display, and the future route of the vehicle is displayed. Grasp.

Information about the future route of the vehicle, such as whether the vehicle will turn right, turn left, change lanes on the road it is currently traveling on, enter another road to merge from the road it is currently traveling on, and , exiting from the road on which the vehicle is currently traveling to another road at a branch destination.

Here, the lane change includes moving from the lane in which the vehicle is traveling to the lane for entering another road at the merging destination, and moving to the lane for exiting the other road at the branch destination. , and moving into a lane for a right or left turn, it is one of the important pieces of information for the driver regarding the future path of the vehicle.

JP 2017-182521 A

When the autonomous vehicle changes lanes, it controls its driving behavior so that a safe distance is maintained between the autonomous vehicle and other vehicles. If it is unlikely that a safe distance can be secured between the autonomous vehicle and other vehicles, the autonomous vehicle will wait until a safe distance can be secured between the autonomous vehicle and the other vehicles. Continue driving in the current lane without changing lanes.

Since the autonomous vehicle is still driving while it is waiting for a lane change, if it cannot change lanes with automatic control, it will not be able to make a right turn as a result of not being able to change lanes. You may not be able to drive around.

SUMMARY OF THE INVENTION Accordingly, it is an object of the present invention to provide a vehicle control device that enables a driver to recognize that the vehicle cannot change lanes under automatic control.

According to one embodiment, a vehicle controller is provided. This vehicle control device includes a lane change necessity determination unit that determines whether or not it is necessary to change lanes based on map data, a planned travel route toward the vehicle's destination, and the current position of the vehicle; When it is determined that it is necessary to make a change, a vehicle control unit that controls the operation of the vehicle is used within a predetermined distance from the position where the determination was made or within a predetermined time from the time when the determination was made. control the operation of the vehicle so that the lane change is performed by the control, obtain an evaluation value indicating the degree to which the lane change is not possible while the control is being performed, and if the evaluation value is equal to or greater than a predetermined threshold, and a lane change planning unit that notifies the driver via the notification unit of a request to change control of the vehicle from automatic control to manual control.

Advantageous Effects of Invention The vehicle control device according to the present invention has the effect that the driver can grasp that the vehicle cannot change lanes under automatic control.

1 is a schematic configuration diagram of a vehicle control system in which a vehicle control device is implemented; FIG. 1 is a hardware configuration diagram of an electronic control device that is one embodiment of a vehicle control device; FIG. FIG. 4 is a functional block diagram of a processor of the electronic control unit regarding vehicle control processing; It is a figure (1) explaining the process which determines the necessity of changing a lane. It is a figure (part 2) explaining the process which determines the necessity of changing a lane. It is a figure (3) explaining the process which determines the necessity of changing a lane. FIG. 11 is a diagram (part 1) for explaining the process of calculating the degree of expectation; FIG. 12 is a diagram (part 2) for explaining the process of calculating the degree of expectation; 4 is an operation flowchart of a vehicle control system including vehicle control processing;

The vehicle control device will be described below with reference to the drawings. This vehicle control device determines whether or not it is necessary to change lanes based on the vehicle's planned travel route toward the destination and the current position of the vehicle. When the vehicle control device determines that it is necessary to change lanes, the vehicle control device attempts to change lanes within a predetermined distance from the location where this determination was made or within a predetermined time from when this determination was made. A request to control the running operation of the vehicle, obtain an evaluation value indicating the degree to which lane change is not possible, and change the vehicle control from automatic control to manual control when the evaluation value is equal to or greater than a predetermined threshold. (control change request) is notified to the driver via the notification unit. This allows the driver to understand that the vehicle cannot change lanes under automatic control.

A vehicle control system having the vehicle control device of this embodiment has an automatic control driving mode in which the vehicle is driven under automatic control and a manual control driving mode in which the vehicle is driven by the driver. When the driver accepts the control change request, the vehicle control system in the automatic control driving mode switches the driving of the vehicle from the currently applied automatic control driving mode to the manual control driving mode. As a result, when the vehicle cannot change lanes by automatic control, the driver can operate the vehicle by manual control to change lanes. However, the technical scope of the present invention is not limited to those embodiments, but extends to the invention described in the claims and equivalents thereof.

FIG. 1 is a schematic configuration diagram of a vehicle control system in which a vehicle control device is implemented. Also, FIG. 2 is a hardware configuration diagram of an electronic control unit, which is one embodiment of the vehicle control unit.

In this embodiment, a vehicle control system 1 mounted on a vehicle 10 and controlling the vehicle 10 includes a camera 2 that captures an image in front of the vehicle, and lidar sensors 3a to 3d that are arranged on the front, rear, left, and right of the vehicle 10. have The vehicle control system 1 also includes a positioning information receiver 4, a map information storage device 5 for generating map information based on the positioning information output by the positioning information receiver 4, a graphical user interface (GUI) 6, an operation It has a device 7, a navigation device 8, and an electronic control unit (ECU) 9, which is an example of a vehicle control device.

The camera 2, the lidar sensors 3a to 3d, the map information storage device 5, the GUI 6, the operation device 7, the navigation device 8, and the ECU 9 can communicate via an in-vehicle network 11 conforming to a standard such as a controller area network. connected to

The camera 2 is mounted, for example, in the vehicle interior of the vehicle 10 so as to face the front of the vehicle 10 . The camera 2 generates an image representing a predetermined area in front of the vehicle 10 at image information acquisition times set in a predetermined cycle. Features such as lane markings on the road surface included in a predetermined area in front of the vehicle 10 are represented in the generated image. The image produced by camera 2 may be a color image or a gray image. The camera 2 is an example of an imaging unit, and includes a two-dimensional detector composed of an array of photoelectric conversion elements sensitive to visible light, such as a CCD or C-MOS, and an object to be photographed on the two-dimensional detector. It has an imaging optical system that forms an image of the area.

Each time the camera 2 generates an image, the camera 2 outputs the image and the image information acquisition time at which the image was generated to the ECU 9 via the in-vehicle network 11 . The image is used in the ECU 9 for processing for estimating the position of the vehicle and for processing for detecting other objects around the vehicle 10 .

For example, the lidar sensors 3a to 3d are attached to the outer surface of the vehicle 10 so as to face forward, leftward, rearward, and rightward of the vehicle 10, respectively. Each of the lidar sensors 3a to 3d synchronously emits pulsed laser beams toward the front, left, rear, and right sides of the vehicle 10 at distance information acquisition times set in a predetermined cycle, thereby Receives reflected waves reflected by The time required for the reflected wave to return has information about the distance between the vehicle 10 and the feature located in the direction in which the laser was irradiated. Each of the lidar sensors 3a to 3d outputs reflected wave information including the laser irradiation direction and the time required for the reflected wave to return, together with the distance information acquisition time at which the laser was emitted, to the ECU 9 via the in-vehicle network 11. . The reflected wave information is used in processing for detecting other objects around the vehicle 10 in the ECU 9 .

The positioning information receiver 4 outputs positioning information representing the current position of the vehicle 10 . For example, the positioning information receiver 4 can be a GPS receiver. The positioning information receiver 4 has a positioning information receiving section 4a that receives GPS radio waves, and a processor 4b that outputs positioning information representing the current position of the vehicle 10 based on the GPS radio waves received by the positioning information receiving section 4a. . The processor 4b outputs the positioning information and the positioning information acquisition time at which the positioning information is acquired to the map information storage device 5 every time the positioning information receiving unit 4a acquires the positioning information at a predetermined reception cycle.

The map information storage device 5 has a processor (not shown) and a storage device (not shown) such as a magnetic disk drive or nonvolatile semiconductor memory. It stores wide-area map information of a relatively wide range (for example, a range of 10 to 30 km square) including . This wide-area map information is preferably high-precision map information including features such as lane markings on roads, information representing types and positions of structures, legal speeds of roads, and the like. Note that the positions of features and structures on roads are represented, for example, by a world coordinate system with a predetermined reference position in real space as the origin. The processor of the map information storage device 5 receives and stores wide area map information from an external server via a base station by wireless communication via a wireless communication device (not shown) according to the current position of the vehicle 10 . Store in the device. Each time the positioning information is input from the positioning information receiver 4, the processor of the map information storage device 5 refers to the wide-area map information stored in the storage device to obtain a relative position including the current position represented by the positioning information. map information of a narrow area (for example, a range of 100 m to 10 km square) and the acquisition time of the positioning information are output to the ECU 9 via the in-vehicle network 11 . Further, the processor of the map information storage device 5 outputs the positioning information and the positioning information acquisition time to the navigation device 8 via the in-vehicle network 11 every time the positioning information and the positioning information acquisition time are input from the positioning information receiver 4. do.

GUI 6 is an example of a notification unit. The GUI 6 is controlled by the ECU 9 to notify the driver of driving information of the vehicle 10 and a control change request for changing the control of the vehicle from automatic control to manual control, etc., and inputs operations to the vehicle 10 from the driver. The travel information of the vehicle 10 includes information about the current and future routes of the vehicle, such as the position of the vehicle, the planned travel route, and the plan to change lanes. The GUI 6 has, for example, a liquid crystal display or a touch panel as a notification device for notifying the driver of travel information, control change requests, and the like. Further, the GUI 6 has, for example, a touch panel or operation buttons as an input device for inputting operation information from the driver to the vehicle 10 . The operation information includes, for example, a destination, a waypoint, a vehicle speed, other vehicle control information, a response to a lane change, and a driver's response to a control change request. The GUI 6 outputs the input operation information to the ECU 9 via the in-vehicle network 11 .

The operating device 7 has a steering wheel, an accelerator pedal, a brake pedal, etc. for manually operating the vehicle 10 by the driver in the manual control driving mode of the vehicle 10 . The operation device 7 generates a control signal corresponding to the amount of steering by the driver's steering operation, and outputs the control signal to an actuator (not shown) that controls the steered wheels of the vehicle 10 . The operation device 7 generates a control signal according to the accelerator opening degree by the driver's operation of the accelerator pedal, and outputs the control signal to a fuel injection device (not shown) of the engine of the vehicle 10 . The operating device 7 generates a control signal corresponding to the amount of brake applied by the driver's brake pedal operation, and outputs the control signal to the brake (not shown) of the vehicle 10 .

The navigation device 8 generates a planned travel route from the current position of the vehicle 10 to the destination based on the navigation map information, the destination of the vehicle 10 and the current position of the vehicle 10 . The navigation device 8 has a memory 8a for storing map information for navigation and a processor 8b. The map information for navigation includes location information of links representing roads and location information of nodes connected by the links. The road layout of the planned travel route is represented by links representing roads and nodes connected by the links. The positions of links and nodes are represented, for example, by coordinates in the world coordinate system. Based on the map information for navigation stored in the memory 8a, the destination of the vehicle 10 received from the GUI 6, and the current position of the vehicle received from the map information storage device 5, the processor 8b determines the destination from the current position of the vehicle 10. Generate a planned driving route to the ground. The processor 8b generates the planned travel route of the vehicle 10 using, for example, the Dijkstra method. The planned travel route includes information regarding positions such as right turns, left turns, merging, and branching. The processor 8b newly generates a planned travel route for the vehicle 10 when a new destination is set or when the current position of the vehicle 10 deviates from the planned travel route. The processor 8b outputs the planned travel route to the ECU 9 via the in-vehicle network 11 every time it generates the planned travel route.

The ECU 9 controls the vehicle 10 . In this embodiment, when the ECU 9 determines that it is necessary to change the lane, it notifies the driver via the GUI 6 that the lane will be changed. The ECU 9 generates a driving plan including lane changes, and controls the running operation of the vehicle 10 so that the vehicle 10 is automatically controlled and driven. While the ECU 9 is controlling the vehicle 10 to attempt lane change, the ECU 9 obtains an evaluation value indicating the extent to which the lane change is not possible, and if the evaluation value is equal to or greater than a predetermined threshold value, the vehicle 10 is stopped. A control change request for changing control from automatic control to manual control is notified to the driver via GUI 6 . Therefore, the ECU 9 has a communication interface 21 , a memory 22 and a processor 23 .

A communication interface (I/F) 21 is an example of a communication unit, and has an interface circuit for connecting the ECU 9 to the in-vehicle network 11 . That is, the communication interface 21 is connected to the GUI 6 and the like via the in-vehicle network 11 . The communication interface 21 will transmit the received information to GUI6, if the information which shows a lane change schedule or the information which shows a control change request from ECU9 is received. When the communication interface 21 receives from the GUI 6 the information indicating the response to the driver's lane change or the information indicating the response to the control change request, the communication interface 21 passes the received information to the processor 23 . Also, the communication interface 21 is connected to the camera 2, the map information storage device 5, and the like via the in-vehicle network 11. FIG. For example, every time an image and image information acquisition time are received from the camera 2 , the communication interface 21 passes the received image and image information acquisition time to the processor 23 . Further, the communication interface 21 passes the received positioning information, the positioning information acquisition time and the map information to the processor 23 every time it receives the positioning information, the positioning information acquisition time and the map information from the map information storage device 5 . The communication interface 21 also passes vehicle speed, acceleration and yaw rate received from a vehicle speed sensor, acceleration sensor and yaw rate sensor (not shown) to the processor 23 .

The memory 22 is an example of a storage unit, and has, for example, a volatile semiconductor memory and a nonvolatile semiconductor memory. The memory 22 stores various data used in vehicle control processing executed by the processor 23 of the ECU 9, installation position information such as the optical axis directions and installation positions of the camera 2 and the respective lidar sensors 3a to 3d, focal points of the imaging optical system, and so on. Internal parameters such as distance and angle of view are stored. The memory 22 also stores the planned travel route received from the navigation device 8, the image and the image information acquisition time received from the camera 2, etc., the positioning information received from the map information storage device 5, the positioning information acquisition time, map information, and the like. do.

The processor 23 is an example of a control unit, and has one or more CPUs (Central Processing Units) and their peripheral circuits. Processor 23 may further comprise other arithmetic circuitry such as a logic arithmetic unit, a math unit or a graphics processing unit. If the processor 23 has multiple CPUs, each CPU may have a memory. Based on the image generated by the camera 2, the processor 23 executes position estimation processing for estimating the position of the vehicle 10 at the image information acquisition time when this image was generated. Further, the processor 23 executes position estimation processing for estimating the position of the vehicle 10 using the estimated position of the vehicle 10 at the image information acquisition time at the position determination time set at a predetermined cycle. Processor 23 controls the traveling motion of vehicle 10 based on the estimated position of vehicle 10 , the destination of vehicle 10 , and the relative positional relationship with other objects around vehicle 10 . Further, the processor 23 determines whether or not the vehicle 10 needs to change lanes, and if it is determined that it is necessary to change lanes, the processor 23 determines whether the vehicle 10 is within a predetermined distance from the position where the determination was made. control the running operation of the vehicle 10 so as to change lanes within a predetermined period of time from the point of time when it is detected, and obtain an evaluation value indicating the extent to which lane changes are not possible while this control is being performed; When this evaluation value is equal to or greater than a predetermined threshold, vehicle control processing is performed to notify the driver via the GUI 6 of a request to change the control of the vehicle 10 from automatic control to manual control.

FIG. 3 is a functional block diagram of the processor 23 of the ECU 9 regarding vehicle control processing including lane change. The processor 23 has a position estimator 31 , an object detector 32 , a lane planner 33 , a driving planner 34 , an expectation calculator 35 , and a vehicle controller 36 . All or part of these units of the processor 23 are, for example, functional modules implemented by computer programs running on the processor 23 . Alternatively, all or part of these units included in processor 23 may be dedicated arithmetic circuits provided in processor 23 . Among these units of the processor 23, the lane planning unit 33, the driving planning unit 34, the degree-of-expectation calculating unit 35, and the vehicle control unit 36 execute vehicle control processing related to lane changes.

A position estimation unit 31 of the processor 23 estimates the position of the vehicle 10 based on the features around the vehicle 10 . The position estimating unit 31 is provided in the image of the camera 2 with a matching area for detecting lane markings, which is an example of a feature around the vehicle 10, and a classifier for identifying the lane markings in the image. to detect lane markings. As the discriminator, for example, a deep neural network (DNN) pre-trained to detect lane markings represented in an input image can be used. Then, assuming the position and orientation of the vehicle 10, the position estimation unit 31 calculates the lane markings represented in the map information received from the map information generation device 5 by the camera 2 generated at the current image information acquisition time. projected onto the image of For example, the position estimating unit 31 determines the position of the vehicle 10 represented by the positioning information received from the positioning information receiver 5 at the current image information acquisition time, and the traveling direction of the vehicle 10 obtained immediately before. The attitude of 10 is assumed to be the assumed position and assumed attitude of the vehicle 10 . The position estimator 31 obtains a conversion formula from the world coordinate system to the camera coordinate system having the position of the camera 2 as the origin and the optical axis direction of the camera 2 as one axis direction, according to the assumed position and assumed orientation. Such a conversion formula is represented by a combination of a rotation matrix representing rotation between coordinate systems and a translation vector representing translation between coordinate systems. Then, the position estimator 31 converts the coordinates of the lane markings on the road around the vehicle 10 represented in the world coordinate system, which are included in the map information, into the coordinates of the camera coordinate system according to the conversion formula. Then, the position estimating unit 31 calculates the lane markings around the vehicle 10 expressed in the camera coordinate system based on the internal parameters of the camera 2 such as the focal length of the camera 2 by the camera generated at the current image information acquisition time. 2 image. Then, the position estimation unit 31 calculates the degree of matching between the lane markings detected from the image of the camera 2 and the lane markings around the vehicle 10 shown on the map. The position estimating unit 31 changes the assumed positions and assumed orientations by a predetermined amount, and executes the same coordinate system conversion, projection, and degree-of-match calculation processes as described above, thereby obtaining a plurality of assumed positions and assumed orientations. , the degree of matching between the lane markings around the vehicle 10 represented in the map information and the lane markings detected from the image is calculated. Then, the position estimator 31 identifies the assumed position and the assumed posture when the degree of matching is maximized, sets the assumed position as the estimated position of the vehicle 10, and estimates the traveling direction of the vehicle 10 based on the assumed posture. Find the azimuth angle.

Further, the position estimating unit 31 detects the position of the vehicle estimated at the image information acquisition time immediately before the position determination time, which is set in a cycle shorter than the cycle of the image information acquisition time at which the camera 2 generates an image. Based on the estimated position and the estimated azimuth angle of the vehicle 10 and the movement amount and movement direction of the vehicle 10 between the image information acquisition time and the position determination time, the estimated position of the vehicle 10 at the position determination time and the estimation of the vehicle 10 Estimate the azimuth. The position estimation unit 31 integrates the vehicle speed of the vehicle 10 to obtain the amount of movement of the vehicle 10 between the image information acquisition time and the position determination time, and integrates the yaw rate of the vehicle 10 to obtain the image information acquisition time and the position estimation unit 31 . The moving direction of the vehicle 10 between the position determination time is obtained. The position estimation unit 31 estimates the driving lane on the road on which the vehicle 10 is located based on the map information and the estimated position and azimuth angle of the vehicle 10 . For example, the position estimating unit 31 determines that the vehicle 10 is traveling in a lane specified by two adjacent lane markings that sandwich the center position of the vehicle 10 in the horizontal direction. Every time the position estimation unit 31 obtains the estimated position, the estimated azimuth angle, and the driving lane of the vehicle 10 at the position determination time, the position estimation unit 31 transmits these information to the object detection unit 32, the driving lane planning unit 33, the driving planning unit 34, and the vehicle. The controller 35 is notified.

The object detection unit 32 of the processor 23 detects other objects and their types around the vehicle 10 based on the image generated by the camera 2 . Other objects include other vehicles driving around vehicle 10 . The object detection unit 32 detects an object represented in the image by, for example, inputting the image generated by the camera 2 into the classifier. As a discriminator, for example, a deep neural network (DNN) pre-trained to detect an object represented in an input image can be used. The object detection unit 32 may use a discriminator other than the DNN. For example, the object detection unit 32 receives, as an identifier, a feature amount (for example, Histograms of Oriented Gradients, HOG) calculated from a window set on an image, and the window represents an object to be detected. A pre-trained support vector machine (SVM) may be used to output the confidence that Alternatively, the object detection unit 32 may detect an object region by performing template matching between a template representing an object to be detected and an image. Further, the object detection unit 32 generates a distance image representing the distance to other objects around the vehicle 10 based on the reflected wave information output by the lidar sensors 3a to 3d, and based on this distance image, the vehicle 10 may detect other objects around the . Further, the object detection unit 32 obtains the orientation of the other object with respect to the vehicle 10 based on the position of the other object in the image generated by the camera 2, and based on the orientation and the distance image, detects the position of the other object. and the vehicle 10 may be determined. Based on the current position of the vehicle 10 and the distance and bearing of the other object with respect to the vehicle 10, the object detection unit 32 estimates the position of the other object expressed, for example, in the world coordinate system. In addition, the object detection unit 32 detects objects from the latest image by associating other objects detected from the latest image generated by the camera 2 with objects detected from past images according to tracking processing based on optical flow. It may track other objects that have been hit. Then, the object detection unit 32 may obtain the trajectory of another object based on the position represented by the world coordinate system of the object in the latest image from the past images. The object detection unit 32 estimates the speed of another object relative to the vehicle 10 based on the change in the position of the other object over time. Also, the object detection unit 32 estimates the acceleration of the other object based on the change in the speed of the other object over time. The object detection unit 32 identifies the lane in which the other object is traveling based on the lane markings represented by the map information and the position of the other object. For example, the object detection unit 32 determines that the other object is traveling in the lane specified by two adjacent lane markings that sandwich the horizontal center position of the other object. The object detection unit 32 notifies the operation planning unit 34 of information indicating the type (for example, vehicle) of the detected other object, information indicating its position, speed, acceleration, and driving lane.

The travel lane planning unit 33 of the processor 23 is an example of a lane change necessity determination unit, and at the travel lane plan generation time set at a predetermined cycle, the most recent driving section (for example, 10 km) selected from the planned travel route ), based on the map information, the planned travel route toward the destination of the vehicle 10, and the current position of the vehicle 10, a lane in the road on which the vehicle 10 travels is selected, and the travel schedule along which the vehicle 10 travels is calculated. Generate a driving lane plan that represents the lanes. In addition, the driving lane planning unit 33 determines whether it is necessary to change lanes in the most recent driving section selected from the planned driving route based on the map information, the planned driving route, and the current position of the vehicle 10. judge. In addition, the driving lane planning unit 33 may further use surrounding environment information or vehicle state information to determine whether a lane change is necessary. The surrounding environment information includes the positions and speeds of other vehicles traveling around the vehicle 10, and the like. The vehicle state information includes the current position of the vehicle 10, vehicle speed, acceleration, traveling direction, and the like. The travel lane planning unit 33 determines whether or not a lane change is necessary within a predetermined section of the planned travel route, and includes the presence or absence of a lane change and, if the lane change is included, the lane before movement and the lane after movement. Generate driving lane plans. The driving lane planning unit 33 notifies the operation planning unit 34 of the driving lane plan each time it generates the driving lane plan. Specifically, the driving lane planning unit 33 selects the nearest driving section from the planned driving route notified from the navigation device 8 at the driving lane plan generation time set at a predetermined cycle, and select lanes in the road on which the vehicle 10 is traveling to generate a travel lane plan. Based on the planned travel route and the current position of the vehicle 10, the travel lane planning unit 33 determines whether the vehicle 10 is to turn right, the vehicle 10 is to turn left, and the road on which the vehicle 10 is currently traveling. The presence or absence of an event position where at least one of entering another road (merging) and exiting from the road on which the vehicle 10 is currently traveling to another road at a branch destination (branching) occurs. judge. The driving lane planning unit 33 determines whether or not it is necessary to change the lane when the driving section includes the event position. Specifically, the driving lane planning unit 33 determines whether or not the lane for executing the event at the event position is the same as the lane in which the vehicle 10 is currently traveling, and changes the lane if they are different. Determining that it is necessary, a driving lane plan is generated that includes the lanes before and after the movement. In addition, if there is another vehicle traveling in the same lane as the lane in which the vehicle 10 is traveling, and the vehicle 10 continues to travel in the same lane, the traveling lane planning unit 33 determines that the vehicle 10 and the other vehicle are traveling in the same lane. When a collision with a vehicle is predicted, it is determined that it is necessary to change lanes, and a driving lane plan including the lane before movement and the lane after movement is generated.

An operation example of the process of generating a driving lane plan by the driving lane planning unit 33 will be described below with reference to FIGS. 4 to 6. FIG.

In the example shown in FIGS. 4 and 5, when the driving section includes the event position, the driving lane planning unit 33 plans the event at the event position based on the map information, the planned driving route, and the current position of the vehicle 10. It is determined whether or not the lane for execution and the lane in which the vehicle 10 is currently traveling are the same. When the lane for executing the event at the event position is different from the lane in which the vehicle 10 is currently traveling, the traveling lane planning unit 33 determines that it is necessary to change the lane, and determines that the vehicle 10 is currently traveling. generate a driving lane plan that includes moving from the lane for executing the event at the event location to the lane for executing the event.

In the example shown in FIG. 4 , the planned travel route 404 of the vehicle 10 includes a route 404 a on the road 401 and a route 404 b on the road 403 branching from the road 401 . A current position 400 of the vehicle 10 is on a route 404a. A route 404b is a route along which the vehicle 10 will travel in the future. Current driving leg 405 includes location 406 where vehicle 10 is currently traveling from road 401 to another road 403 . The travel lane planning unit 33 determines a position 406 where the vehicle 10 exits from the road 401 on which the vehicle 10 is currently traveling to another road 403 that is a branch destination as an event position within the driving section 405 . A road 401 on which the vehicle 10 is traveling has a left lane 401a and a right lane 401b. The travel lane planning unit 33 is notified from the position estimation unit 31 that the current position 400 of the vehicle 10 is on the right lane 401 . Since the driving section 405 includes the event position 406, the driving lane planning unit 33 determines whether it is necessary to change the lane. When exiting from the right lane 401b of the road 401 on which the vehicle 10 is currently traveling to the branch destination road 403 at the event position 406, the vehicle 10 needs to move to the left lane 401a of the road 401. . Therefore, the driving lane planning unit 33 determines that it is necessary to change the lane from the current right lane 401b to the left lane 401a. Then, the driving lane planning unit 33 generates a driving lane plan including a lane change from the right lane 401 b to the left lane 401 a until the vehicle 10 reaches the event position 406 in the driving section 405 .

In the example shown in FIG. 5 , the planned travel route 504 of the vehicle 10 includes a route 504 a on the road 501 and a route 504 b on the road 503 intersecting the road 501 . A current position 500 of the vehicle 10 is on a route 504a. A route 504b is a route along which the vehicle 10 will travel in the future. Current driving leg 505 includes a right turn position 506 from road 501 on which vehicle 10 is currently traveling to another road 503 . The travel lane planning unit 33 determines a position 506 where the vehicle 10 makes a right turn from the road 501 on which the vehicle 10 is currently traveling to another road 503 as an event position within the driving section 505 . The vehicle 10 is traveling on a road 501 from the lower side to the upper side in the figure. A road 501 has a left lane 501a, a center lane 501b, and a right lane 501c on which vehicles can travel from the bottom to the top in the figure. The left lane 501a is a lane in which a vehicle can go straight or turn left at an intersection. The center lane 501b is a lane in which a vehicle can go straight at an intersection. The right lane 501c is a lane in which a vehicle can turn right at an intersection. The travel lane planning unit 33 is notified from the position estimation unit 31 that the current position 500 of the vehicle 10 is on the left lane 501a. In addition, the road 501 has a left lane 501e and a right lane 501d on which vehicles can travel from the upper side to the lower side in the figure. Since the driving section 505 includes the event position 506, the driving lane planning unit 33 determines whether it is necessary to change the lane. When making a right turn at event location 506 from left lane 501a of road 501 on which vehicle 10 is currently traveling, vehicle 10 is required to move to right lane 501c of road 501 . Therefore, the driving lane planning unit 33 determines that it is necessary to change the lane from the current left lane 501a to the right lane 501c. Then, the driving lane planning unit 33 prepares a driving lane plan including changing from the left lane 501a to the right lane 501c via the center lane 501b until the vehicle 10 reaches the event position 506 in the driving section 505. Generate.

In the example shown in FIG. 6, when there is another vehicle traveling in the same lane as the lane in which the vehicle 10 is traveling, the travel lane planning unit 33 calculates the current position of the vehicle 10 and information about the other vehicle. Based on the included surrounding environment information and vehicle state information, it is determined whether or not a collision between the vehicle 10 and another vehicle is predicted. When it is predicted that the vehicle 10 will collide with another object, the travel lane planning unit 33 determines that it is necessary to change lanes, and prepares a travel lane plan including the lane before movement and the lane after movement. to generate

In the example shown in FIG. 6 , the planned travel route 604 of the vehicle 10 includes a route that goes straight on the road 601 from the current position 600 of the vehicle 10 on the road 601 . A current position 600 of the vehicle 10 is on a road 601 . The driving lane planning unit 33 determines that the driving section 605 does not include the event position because the planned driving route 604 runs straight on the road 601 in the current driving section 605 . A road 601 on which the vehicle 10 is traveling has a left lane 601a and a right lane 601b. The travel lane planning unit 33 is notified from the position estimation unit 31 that the current position 600 of the vehicle 10 is on the left lane 601a. When notified by the object detection unit 32 that another vehicle is detected around the vehicle 10, the travel lane planning unit 33 determines that the travel lane of the vehicle 10 and the travel lane of the other vehicle are the same. Determine whether or not there is When the driving lanes are the same, the driving lane planning unit 33 determines whether the position of the other vehicle is ahead of or behind the current position 600 of the vehicle 10 in the traveling direction. do. Based on the position 600 and vehicle speed of the vehicle 10 and the positions and speeds of the other vehicles, the driving lane planning unit 33 determines whether the vehicle 10 is ahead of another vehicle within a predetermined time from the current time. It is determined whether or not there is a possibility of collision, or whether or not there is a possibility that another vehicle positioned behind will collide with the vehicle 10 . For example, if the driving lane planning unit 33 estimates that the distance between the vehicle 10 and another vehicle will be within a predetermined distance (for example, 2 m) within a predetermined time from the current time, the vehicle 10 and the other vehicle It is determined that there is a possibility of collision with another vehicle. When there is a possibility that the vehicle 10 will collide with another vehicle located in front, the driving lane planning unit 33 selects a lane for overtaking the other vehicle before the vehicle 10 collides with the other vehicle located in front. Determine that changes need to be made. Further, when there is a possibility that another vehicle located behind collides with the vehicle 10 , the lane planning unit 33 needs to change lanes before the other vehicle located behind collides with the vehicle 10 . Determine that there is. Here, as shown in FIG. 6, the position of the other vehicle 610 is located ahead, so the lane planning unit 33 determines that the vehicle 10 needs to change lanes to overtake the other vehicle 610. Suppose When determining that it is necessary to change lanes, the driving lane planning unit 33 determines whether or not the vehicle 10 can change lanes. The traveling lane planning unit 33 determines that the vehicle 10 can change lanes because the road 601 has a left lane 601a on which the vehicle 10 travels and a right lane 601b adjacent thereto. Then, in the driving section 605, the vehicle 10 changes lanes from the left lane 601a to the right lane 601b and travels in the right lane 601b before the vehicle 10 collides with another vehicle 610 located ahead. and passing by the other vehicle 610, and changing lanes from the right lane 601b to the left lane 601a after passing the other vehicle 610. On the other hand, when the lane planning unit 33 determines that there is no possibility of the vehicle 10 colliding with another vehicle 610, it determines that it is not necessary to change lanes to overtake the other vehicle. Further, if the road 601 has only one lane in which the vehicle 10 can travel, the driving lane planning unit 33 determines that it is not possible to change lanes. In these cases, the driving lane planning unit 33 generates a driving lane plan that does not include lane changes.

When the driving lane plan including the lane change is generated, the driving lane planning unit 33 determines a lane change stop position where the vehicle 10 stops changing the lane by automatic control on the driving lane in which the vehicle 10 is currently driving. do. Specifically, the driving lane planning unit 33 can execute a lane change according to the driving lane plan until the driver who has been notified of the control change request operates the vehicle 10 by manual control and reaches the event position. , the lane change stop position is determined on the lane in which the vehicle 10 is currently traveling. For example, the driving lane planning unit 33 calculates the distance between the lane change stop position and the event position by calculating the travel The distance may be determined so that the time is 4 seconds or longer. Also, the lane change planning unit 33 may determine the lane change stop position at a position ahead of the current position of the vehicle 10 by a predetermined distance (for example, 500 m).

In addition, the driving lane planning unit 33 is within a predetermined distance (lane change completion expected distance) from the position where the lane change is determined, or within a predetermined time (lane change completion expected distance) from the point of time when this determination is made time), the vehicle 10 is controlled to change lanes using the vehicle control unit 36 that controls the vehicle 10 running operation. The driving plan unit 34 generates a driving plan based on the driving lane plan generated by the driving lane planning unit 33, and the vehicle control unit 36 controls the driving operation of the vehicle 10 so as to change lanes based on the driving plan. to control.

The travel lane planning unit 33 may determine the above-described expected lane change completion distance based on the lane change stop position and the current position of the vehicle 10 . For example, the driving lane planning unit 33 determines the expected lane change completion distance as the distance between the current position of the vehicle 10 and the lane change stop position. The driving lane planning unit 33 notifies the driving planning unit 34 of the lane change stop position and the expected lane change completion distance together with the driving lane plan.

The driving plan unit 34 is an example of a lane change planning unit, and at a driving plan generation time set at a predetermined cycle, the map information, the driving lane plan, the current position of the vehicle 10, the surrounding environment information, the vehicle Based on the state information, a driving plan is generated that represents the planned travel locus of the vehicle 10 up to a predetermined time (for example, 5 seconds) ahead. The driving plan is expressed as a set of target positions of the vehicle 10 and target vehicle speeds at the target positions at each time from the current time to a predetermined time ahead. The cycle of the driving plan generation time is preferably shorter than the cycle of the driving lane plan generation time. The operation planning unit 34 may determine the target vehicle speed based on the travel speed input by the driver or the legal speed of the lane in which the vehicle is traveling. The operation planning unit 34 uses a prediction filter such as a Kalman filter to estimate a future trajectory based on the detected recent trajectory of the other vehicle, and the lane in which the detected other vehicle is traveling and the estimated Based on the relative distance calculated from the trajectory obtained, the vehicle 10 travels in a different lane from the other vehicle, or the vehicle 10 is moved so that the relative distance from the vehicle 10 to the other object is equal to or greater than a predetermined distance. Generate an operation plan for The driving plan unit 34 may generate a plurality of driving plans based on the driving lane plan. In this case, the driving plan unit 34 may select the driving plan that minimizes the sum of the absolute values of the acceleration of the vehicle 10 from among the plurality of driving plans. The driving plan unit 34 notifies the vehicle control unit 36 of the driving plan.

When the driving lane plan includes a lane change, the operation planning unit 34 determines the target position of the destination after the lane change on the destination lane, and creates a driving plan including the lane change in which the vehicle 10 moves between lanes. and generate a driving plan that does not include lane changes. The operation planning unit 34 determines the lane line including the target position of the destination after the lane change, the expected lane change completion distance, the lane change stop position, the current position of the vehicle 10, the surrounding environment information, and the vehicle state information. The expectation degree calculation unit 35 is notified of the expectation degree calculation information for calculating the degree of expectation that the change will be successful. The driving plan unit 34 notifies the vehicle control unit 36 of a driving plan that does not include a lane change when the degree of expectation notified from the degree of expectation calculation unit 35 is less than a predetermined threshold value (for example, 0.7 to 0.9). do. In this case, the vehicle 10 continues to travel in the current lane. On the other hand, when the degree of expectation notified from the degree-of-expectation calculating unit 35 is equal to or greater than a predetermined threshold value (for example, 0.7 to 0.9), the driving planning unit 34 executes a driving plan including a lane change by the vehicle control unit. 36. In this case, the vehicle 10 starts to change lanes from the current lane to the destination lane. Processing for calculating the degree of expectation by the degree-of-expectation calculation unit 35 will be described later.

For example, when the driving lane plan includes a lane change, the driving plan unit 34 generates a driving plan that does not include the lane change so that the vehicle 10 does not run side by side with other vehicles traveling in the destination lane. Also, a driving plan including a lane change is generated so that the vehicle 10 moves from the center line of the lane of the movement source to the center line of the lane of the movement destination, and the relative distance is equal to or greater than a predetermined distance.

The operation planning unit 34 may not be able to complete the lane change because a predetermined distance cannot be secured between the vehicle 10 and another vehicle after the vehicle 10 has started traveling to change lanes, or When notified of the degree of expectation less than the predetermined threshold value from the degree of expectation calculation unit 35, the lane change is stopped. As described above, the driving plan unit 34 repeats generating a driving plan that does not include a lane change and a driving plan that includes a lane change. Then, if the travel distance of the vehicle 10 is within the lane change expected completion distance or the time is within the lane change expected completion time, the operation planning unit 34 determines that the expected degree notified from the expected degree calculation unit 35 is When it reaches or exceeds a predetermined threshold (for example, 0.7 to 0.9), the vehicle controller 36 is notified of the driving plan including the lane change, and the vehicle 10 starts lane change again.

Below, based on the driving lane plan generated by the driving lane planning unit 33, the driving planning unit 34 uses the vehicle control unit 36 to move within the expected lane change completion distance from the position where the lane change is determined. An example of generating a driving plan including a lane change so as to perform a lane change is described below.

First, the operation planning unit 34 determines the destination target position after the lane change on the destination lane. The operation planning unit 34 uses a prediction filter such as a Kalman filter to predict the future trajectories of other vehicles traveling on the destination lane based on the most recent trajectories of other vehicles traveling on the destination lane. A space is estimated and a destination space is selected so that a safe distance is secured between the vehicle 10 in front and behind, and the movement of the vehicle 10 is set to a predetermined constraint so that the vehicle 10 moves into this space. Generate a driving plan that includes one or more lane changes to satisfy Predetermined restrictions include that the amount of change in acceleration per unit time, the amount of change in speed per unit time, or the amount of change in yaw rate per unit time is equal to or less than an upper limit value. When driving plans including a plurality of lane changes are generated, the driving plan unit 34 may select a driving plan that secures the most distances to vehicles ahead and behind.

When the driving lane plan includes a lane change, the driving plan unit 34 generates the above-described driving plan and obtains an evaluation value indicating the extent to which the lane change is impracticable. The operation planning unit 34 notifies the driver via the GUI 6 of a control change request for changing the control of the vehicle 10 from automatic control to manual control when the evaluation value is equal to or greater than a predetermined threshold. The operation planning unit 34 determines whether the lane change cannot be completed because a predetermined distance cannot be secured between the vehicle 10 and another vehicle after the vehicle 10 starts changing lanes, or when the expected degree calculation unit 35, the lane change is cancelled. When the lane change is canceled, the operation planning unit 34 determines that the lane change is unsuccessful, and counts the number of unsuccessful times as an evaluation value. For example, if the lane change is canceled twice, the evaluation value is 2. Even after determining that the lane change is unsuccessful, the driving plan unit 34 continues to generate a new driving plan including the lane change until the vehicle 10 reaches the lane change stop position. However, when the evaluation value becomes equal to or greater than a predetermined threshold value (for example, 2 to 4), the operation planning unit 34 sends a control change request to the driver via the GUI 6 to change the control of the vehicle from automatic control to manual control. Notice. The threshold value of the evaluation value is determined so that the evaluation value reaches the threshold value before the vehicle 10 travels the expected lane change completion distance and reaches the lane change stop position. It is preferable from the viewpoint of notifying the driver with In addition, regardless of the value of the evaluation value, when the vehicle 10 reaches the lane change stop position, the operation planning unit 34 sends a control change request to change the control of the vehicle from automatic control to manual control via the GUI 6. Notify the driver. The GUI 6 displays that automatic control cannot change lanes and a control change request. The GUI 6 also receives the driver's response to the control change request and outputs it to the ECU 9 via the in-vehicle network 11 . When the driver approves the control change request, the operation planning unit 34 switches the operation of the vehicle 10 from the applied automatic control operation mode to the manual control operation mode. Preferably, in the manual control driving mode, at least the steering is manually controlled. Alternatively, in the manual control driving mode, steering, acceleration and braking may be manually controlled. The driver who approves the control change request operates the vehicle 10 in the manual control driving mode to perform the notified lane change. On the other hand, if the driver does not approve the control change request, the driving planning unit 34 continues driving the vehicle 10 in the automatic control driving mode.

Hereinafter, with reference to FIG. 7, a process of generating a driving plan including a lane change by the driving planning unit 34 will be described. As shown in FIG. 7, vehicle 10 is traveling on road 701 . Road 701 has a left lane 701a and a right lane 701b. The vehicle 10 is traveling on the left lane 701a. The driving lane plan involves vehicle 10 changing lanes from left lane 701 a to right lane 701 b by the time vehicle 10 reaches lane change stop position 703 . The lane change stop position 703 is determined to be ahead of the current position 700 of the vehicle 10 in the direction of travel on the lane 701a on which the vehicle 10 travels. In addition, the expected lane change completion distance D is determined as the distance between the current position 700 of the vehicle 10 and the lane change stop position 703 . The operation planning unit 34 determines the destination target position after the lane change based on the driving lane plan, the current position 700 of the vehicle 10, and the surrounding environment information including information on other vehicles. Based on the surrounding environment information including the information of the other vehicles notified from the object detection unit 32, the driving planning unit 34 detects other vehicles 710 and 711 on the destination right lane 701b. , and another vehicle 712 are notified that they are running in turn. There is a space S1 on the traveling direction side of another vehicle 710 , a space S2 between another vehicle 710 and another vehicle 711 , and a space S3 between another vehicle 711 and another vehicle 712 . The operation planning unit 34 uses a prediction filter such as a Kalman filter to drive on the right lane 701b of the destination based on the most recent trajectories of other vehicles 710, 711, and 712 traveling on the right lane 701b of the destination. By estimating the future trajectories of other vehicles 710, 711, 712, the vehicle 10 is large enough to move, and a safe distance is secured between the vehicles ahead and behind. , selects a destination space and generates a driving plan including one or more lane changes to move into this space and to satisfy predetermined constraints on the behavior of the vehicle 10 . The driving plan unit 34 selects a lane change to move to a target position in the space S2 between the other vehicle 710 and the other vehicle 711 as a driving plan that ensures the most distance between the vehicles ahead and behind. Generate a driving plan including

Next, the process of calculating the degree of expectation that the lane change will be successful, performed by the degree-of-expectation calculation unit 35, will be described below. When the expectation calculation information is notified from the operation planning unit 34, the expectation calculation unit 35 calculates the operation plan, the current position of the vehicle 10, and the positions of the other vehicles at the expectation calculation time set at a predetermined cycle. An expectation E(t) for a successful lane change is calculated based on surrounding environment information including information and vehicle state information. It is preferable that the cycle of the expected degree calculation time is shorter than the cycle of the operation plan generation time. The expectation degree calculation unit 35 calculates the degree of expectation E(t) for a successful lane change from the first lane change success degree Q1 (D( t)), the second lane change success rate Q2 (bth) calculated based on the vehicle behind the destination position (corresponding to the other vehicle 711 in FIG. 7), and the vehicle ahead of the destination position ( 7 corresponding to the other vehicle 710). The expectation calculation unit 35 notifies the operation planning unit 34 of the expectation E(t) each time it obtains the expectation E(t).

E(t)=Q1(D(t))*Q2(bth)*Q3 (1)

FIG. 8 is a diagram for explaining the first lane change success rate Q1(D(t)) calculated based on the position of the vehicle 10. As shown in FIG. The expectation calculation unit 35 determines the first lane change success rate Q1 (D(t)) based on the distance D(t) between the position of the vehicle 10 and the lane change stop position. The first lane change success rate Q1(D(t)) decreases as the vehicle 10 approaches the lane change stop position, and becomes zero when the vehicle 10 reaches the lane change stop position. On the other hand, the first lane change success rate Q1(D(t)) increases as the vehicle 10 moves away from the lane change stop position. For example, a sigmoid function can be used as the first lane change success rate Q1(D(t)).

The degree-of-expectation calculator 35 obtains the position K(t) of the vehicle 10 at time t using the following formula (2).

Here, K(t0) is the position of the vehicle 10 at time t0 when the operation planning unit 34 starts counting the lane change trial time allowed for each lane change trial. v(t) is the vehicle speed of the vehicle 10 at time t. a(t) is the acceleration of the vehicle 10 at time t. When the vehicle speed is increased, the acceleration value is positive, and when the vehicle speed is decreased, the acceleration value is negative. K(t) is, for example, a position vector expressed in the world coordinate system. v(t) and a(t) are expressed in vector quantities. Decreasing the speed of the vehicle is actually done using braking, but the change in speed due to braking is expressed using acceleration.

The degree-of-expectation calculation unit 35 obtains the distance D(t) between the position of the vehicle 10 and the lane change stop position using the following formula (3).

D(t)=|SK(t)| (3)

Here, S represents the lane change stop position on the lane in which the vehicle 10 is traveling, and is a position vector represented by the world coordinate system, for example.

The second lane change success rate Q2 calculated based on the vehicle behind in the destination space S2 is the probability that the vehicle 10 will overtake the vehicle behind in the space S2 and move to the space S2. The degree-of-expectation calculation unit 35 obtains the second lane change success degree Q2 using the following formula (4).

Here, PB(b) represents the probability distribution function that the vehicle behind is in the state of acceleration b. bth represents the acceleration at which the vehicle 10 can overtake the rear vehicle. The second lane change success rate Q2 is normalized so that the integral of the acceleration b from -∞ to ∞ becomes 1.

As PB(b), the expectation calculation unit 35 obtains the average value of acceleration and the dispersion of acceleration based on, for example, the temporal change in the acceleration of the rear vehicle obtained by the operation planning unit 34 during the most recent fixed period. , to generate a Gaussian distribution function. Further, the expectation calculation unit 35 may obtain a polynomial approximation using multivariate analysis based on the acceleration of the rear vehicle obtained by the operation planning unit 34 as PB(b). In addition, the expectation calculation unit 35 calculates, as PB, changes over time in the acceleration b of the rear vehicle obtained by the operation planning unit 34 during the most recent fixed period, and A function representing PB(b,c) may be determined using a Gaussian distribution function or multivariate analysis based on the change in distance c over time. Furthermore, the expectation calculation unit 35 calculates, as PB, changes over time in the acceleration b of the rear vehicle obtained by the operation planning unit 34 during the most recent fixed period, and the relationship between the rear vehicle and the front vehicle positioned ahead of the rear vehicle. A function representing PB(b, c, d) may be obtained using a Gaussian distribution function or multivariate analysis based on changes over time in the distance c between the .

Further, the expectation calculation unit 35 can obtain bth as follows. First, the degree-of-expectation calculator 35 determines a movement target position in the space S2 where the vehicle 10 moves, on the destination lane 701b, and obtains the distance S between this movement target position and the vehicle 10 . The movement target position is a position ahead of the lane change stop position. can do. Assume that the vehicle 10 catches up with the vehicle behind after time T. The expectation calculation unit 35 uses the distance S, the time T, the acceleration b of the rear vehicle (constant), and the acceleration a of the vehicle 10 (a is a constant greater than b) to calculate the following: Acceleration a of the vehicle 10 that satisfies Equation (5) is obtained. The expectation calculation unit 35 can use the average value of the probability distribution function PB(b) of the acceleration of the rear vehicle as the acceleration b of the rear vehicle. An initial value of the time T can be set to 10 seconds, for example.

The degree-of-expectation calculating unit 35 finds the acceleration a of the vehicle 10 that satisfies the above equation (5) while changing the time T to increase by a predetermined amount while the movement target position is fixed. If the obtained acceleration a of the vehicle 10 is equal to or less than a predetermined threshold value, the expectation calculation unit 35 sets the acceleration a as bth. The predetermined threshold value is preferably an acceleration that does not make the driver feel uncomfortable, and can be, for example, 0.1 to 0.3 m/s ² . In the state where the movement target position is fixed, the expectation calculation unit 35 increases the movement target position by a predetermined amount and then increases the time T by a predetermined amount when the acceleration a that is equal to or less than the predetermined threshold value cannot be obtained. The process of finding the acceleration a of the vehicle 10 that satisfies the above equation (5) is repeated while changing the acceleration a by one. The expectation calculation unit 35 sets the second lane change success rate Q2 to zero when the movement target position is before the lane change stop position and the acceleration a equal to or less than the predetermined threshold is not obtained.

The third lane change success rate Q3 calculated based on the forward vehicle at the destination position represents the probability that the forward vehicle accelerates and the space S2 expands. The degree-of-expectation calculator 35 obtains the success degree Q3 of changing the third lane using the following formula (6).

Here, the probability distribution function PC(c) represents the probability distribution function when the forward vehicle is in the state of acceleration c. The third lane change success rate Q3 is normalized so that the acceleration c is integrated to 1 in the interval from -∞ to ∞.

The expectation calculation unit 35 can obtain, for example, the probability distribution function PC(c) in the same manner as the probability distribution function PC(b) described above.

Here, when there is no other vehicle on the right lane 701b around the vehicle 10, both the second lane change success rate Q2 and the third lane change success rate Q3 are close to 1. is substantially determined by the first lane change success rate Q1.

The vehicle control unit 36 causes the vehicle 10 to travel along the planned travel route based on the position of the vehicle 10 at the position determination time, the vehicle speed and yaw rate, and the notified driving plan (including the lane change plan). Each part of the vehicle 10 is controlled as follows. For example, the vehicle control unit 36 obtains the steering angle, acceleration, and angular acceleration of the vehicle 10 according to the notified driving plan and the current vehicle speed and yaw rate of the vehicle 10, and obtains the steering angle, acceleration, and angular acceleration. The steering amount, accelerator opening, or brake amount is set as follows. The vehicle control unit 36 then outputs a control signal corresponding to the set steering amount to an actuator (not shown) that controls the steered wheels of the vehicle 10 . Further, the vehicle control unit 36 obtains the fuel injection amount according to the set accelerator opening, and outputs a control signal corresponding to the fuel injection amount to the fuel injection device (not shown) of the engine of the vehicle 10 . Alternatively, the vehicle control unit 36 outputs a control signal corresponding to the set brake amount to the brake (not shown) of the vehicle 10 .

When the driving plan includes a set of target trajectories and target vehicle speeds for changing lanes, the vehicle control unit 36 controls the traveling operation of the vehicle 10 to change lanes.

FIG. 9 is an operation flowchart of vehicle control processing including lane change executed by the processor 23 . In the operation flowchart shown below, the processing of steps S904 to S907 corresponds to the vehicle control processing when it is determined that it is necessary to change lanes.

First, the navigation device 8 generates a planned travel route from the current position of the vehicle 10 to the destination based on the navigation map information, the destination of the vehicle 10, and the current position of the vehicle 10 (step S901). .

Next, the position estimation unit 31 of the processor 23 obtains the estimated position and the estimated azimuth angle of the vehicle 10 at each position determination time (step S902).

Next, the object detection unit 32 of the processor 23 detects other objects around the vehicle 10 based on the image generated by the camera 2 and the range image (step S903).

Next, the travel lane planning unit 33 of the processor 23 selects a lane in the road on which the vehicle 10 travels in the driving section of the planned travel route and generates a travel lane plan. In addition, the driving lane planning unit 33 changes lanes in the driving section of the planned driving route based on the map information, the planned driving route, the current position of the vehicle 10, the surrounding environment information, and the vehicle state information. determine whether or not it is necessary. When the driving lane planning unit 33 determines that the lane change is necessary, the driving lane planning unit 33 generates the driving lane plan so as to include the lane change (step S904).

Next, the operation planning unit 34 of the processor 23 determines the lane in which the vehicle 10 travels within a predetermined section based on the driving lane plan, the current position of the vehicle 10, the surrounding environment information, and the vehicle state information. A driving plan is generated (step S905). The driving plan unit 34 generates a driving plan including the lane change when it is determined that it is necessary to change the lane.

Next, when it is determined that it is necessary to change lanes, the operation planning unit 34 of the processor 23 moves the vehicle control unit that controls the running operation of the vehicle 10 within a predetermined distance from the position where the determination is made. In addition to obtaining an evaluation value indicating the extent to which lane change is not possible, if the evaluation value is equal to or greater than a predetermined threshold, the vehicle 10 A request to change control from automatic control to manual control is sent to the driver via GUI 6 (step S906).

As described above, when the vehicle control device determines that it is necessary to change lanes, it controls the operation of the vehicle so as to attempt to change lanes within a predetermined distance or within a predetermined time. When the vehicle control device determines that the lane cannot be changed, the vehicle control device notifies the driver of a control change request for changing the control of the vehicle from automatic control to manual control via the notification unit. This allows the driver to understand that the vehicle cannot change lanes under automatic control. If desired, the driver can steer the vehicle under manual control to make scheduled lane changes. In addition, since the vehicle control device determines that the lane cannot be changed within a predetermined distance or within a predetermined time, the driver should manually operate the vehicle with enough time to change the lane. You can receive notifications from your device.

Next, modified examples of the above-described embodiment will be described below. In this modification, based on the driving lane plan generated by the driving lane planning unit 33 of the processor 23, the operation planning unit 34 determines that the lane change is necessary from the position at which the lane change completion scheduled time ( A driving plan including a lane change is generated so that the vehicle control unit 36 is used to change the lane within a predetermined time.

First, the driving lane planning unit 33 determines a lane change stop position where the vehicle 10 stops changing lanes by automatic control on the lane in which the vehicle 10 travels.

The travel lane planning unit 33 may determine the lane change completion scheduled time based on the lane change stop position, the current position of the vehicle 10 and the vehicle speed of the vehicle 10 . For example, the lane change planning unit 33 may set the estimated lane change completion time to a value obtained by dividing the distance between the current position of the vehicle 10 and the lane change stop position by the vehicle speed of the vehicle 10 . The driving lane planning unit 33 may obtain the vehicle speed of the vehicle 10 as an average speed over a recent predetermined time period (for example, 1 to 3 seconds).

The operation planning unit 34 obtains the elapsed time from the point at which it is determined that it is necessary to change the lane as an evaluation value, and when the elapsed time exceeds the lane change completion scheduled time, automatically controls the vehicle. The user is notified via the GUI 6 of a control change request to change from control to manual control.

Further, when the driving lane planning unit 33 of the processor 23 determines that it is necessary to change the lane, it may notify the driver via the GUI 6 that the lane change is scheduled. For example, the driving lane planning unit 33 notifies the driver that the lane change is scheduled by displaying the driving lane plan including the lane changes shown in FIGS. 4 to 6 on the GUI 6 . As a result, the driver, as information about the future route of the vehicle 10, is planning to change lanes in order to exit the road on which the vehicle 10 is currently traveling to another road at the branch destination (example in FIG. 4). ), that the vehicle 10 is scheduled to change lanes to make a right turn (example in FIG. 5), or that the vehicle 10 is scheduled to change lanes to overtake another vehicle (example in FIG. 6). etc. can be understood. Note that the lane planning unit 33 may notify the driver of the planned lane change by voice using an audio output device (an example of the notification unit) such as a speaker (not shown).

In addition, the driving lane planning unit 33 of the processor 23 notifies the driver that the lane change is scheduled, and displays on the GUI 6 to ask the driver whether or not to approve the lane change. good too. The driving lane planning unit 33 inputs the driver's answer by operating the GUI 6 by the driver. The driving lane plan unit 33 generates a driving lane plan including the lane change when the driver approves the lane change, and generates a driving lane plan not including the lane change when the driver does not approve the lane change. do.

In the present invention, the vehicle control device of the embodiment described above can be modified as appropriate without departing from the gist of the present invention.

For example, in the above-described embodiment, the expected lane change completion distance is obtained based on the vehicle position and the lane change stop position, but the method of obtaining the expected lane change completion distance is not particularly limited. In addition, although the lane change completion time is obtained based on the lane change stop position, the position of the vehicle, and the vehicle speed, the method of obtaining the lane change completion time is not particularly limited.

Also, the method of calculating the degree of expectation that the lane change will be successful is not limited to the above-described embodiment. For example, the degree-of-expectation calculation unit may further use an average inter-vehicle distance in the immediate vicinity (for example, several minutes) of the destination lane in order to calculate the degree of expectation. In addition, in order to calculate the degree of expectation, the degree-of-expectation calculation unit may further use the relationship between the speed distribution of other vehicles traveling in the destination lane in the immediate vicinity (for example, several minutes) and the speed of the vehicle. .

1 Vehicle Control System 2 Cameras 3a to 3d Lidar Sensor 4 Positioning Information Receiver 4a Positioning Information Receiver 4b Processor 5 Map Information Storage Device 6 Graphical User Interface (GUI)
7 operating device 8 navigation device 8a memory 8b processor 9 electronic control unit (ECU)
REFERENCE SIGNS LIST 10 vehicle 11 in-vehicle network 21 communication interface 22 memory 23 processor 31 position estimation unit 32 object detection unit 33 traveling lane planning unit 34 operation planning unit 35 expectation calculation unit 36 vehicle control unit

Claims (1)

a lane change necessity determination unit that determines whether or not it is necessary to change lanes based on map data, the planned travel route toward the destination of the vehicle, and the current position of the vehicle;
If it is determined that it is necessary to change lanes in order to head for the vehicle's destination , the vehicle will move within a predetermined distance from the location where the determination was made or within a predetermined time from the time when the determination was made. Controlling the operation of the vehicle to change lanes using a vehicle control unit that controls the operation, obtaining an evaluation value indicating the extent to which the lane change is not feasible, and determining the evaluation value as a predetermined first threshold. In the above cases, a lane change planning unit that notifies the driver via the notification unit of a request to change vehicle control from automatic control to manual control;
has
The lane change planning unit determines that the lane change is to be executed when the expected degree of success of the lane change within the predetermined distance or within the predetermined time is equal to or greater than a second threshold, and the expected degree is the second threshold value. A vehicle control device that repeatedly determines that a lane change is unsuccessful if the threshold is less than the threshold, and obtains the number of unsuccessful determinations as the evaluation value.

Images