Vehicle motion control device, vehicle-mounted system, and vehicle motion control method

Abstract

The present application provides a kind of vehicle motion control device capable of achieving the track of generating the comfort of the personal hobby and the comfort of obtaining cooperation with low processing load.This vehicle motion control device has: information acquisition unit, which obtains the vehicle information about the vehicle and the environmental information about the surrounding environment of the vehicle;Track generation parameter prediction unit, which inputs the vehicle information and the environmental information obtained by the information acquisition unit into the learned model, and outputs the track generation parameter including the range of physical quantity representing the motion state of the vehicle and the range of the drivable area of the vehicle;And track generation unit, which inputs the track generation parameter, and generates the track of the vehicle driving.

Description

Technical Field

[0001] This invention relates to a vehicle motion control device, an on-board system, and a vehicle motion control method for controlling the movement of a vehicle. Background Technology

[0002] As a type of vehicle motion control technology represented by assisted driving and autonomous driving, the following technologies are known: generating a driving track composed of information such as the driving path and driving speed of the vehicle as the driving target, and controlling the power transmission system, braking system, steering system, etc. to make the vehicle travel along the driving track.

[0003] In addition, as a method for generating driving tracks, for example, Patent Document 1 discloses a method for selecting any one driving track from multiple driving tracks generated using multiple models based on the ease of recognizing the vehicle's surrounding environment.

[0004] Existing technical documents

[0005] Patent documents

[0006] Patent Document 1: Japanese Patent Application Publication No. 2021-160532 Summary of the Invention

[0007] The problem that the invention aims to solve

[0008] However, the method for generating the driving track in Patent Document 1 has the problem of high computational load because it uses multiple models to generate multiple driving tracks.

[0009] In view of this, the object of the present invention is to provide a vehicle motion control device in order to reduce computational load. The vehicle motion control device inputs vehicle information and environmental information about the vehicle's surrounding environment into a prediction model that has learned manual driving, etc., and predicts track generation parameters including the range of physical quantities representing the vehicle's motion state and the range of the vehicle's drivable area, and generates a single driving track based on these parameters.

[0010] Methods for solving problems

[0011] The vehicle motion control device includes: an information acquisition unit that acquires vehicle information and environmental information about the vehicle's surrounding environment; a track generation parameter prediction unit that inputs the vehicle information and environmental information acquired by the information acquisition unit into a learned model and outputs track generation parameters that include the range of physical quantities representing the vehicle's motion state and the range of the vehicle's drivable area; and a track generation unit that inputs the track generation parameters and generates the track for the vehicle to travel on.

[0012] Invention Effects

[0013] According to the present invention, by using a prediction model learned from manual driving, etc., to predict track generation parameters including the range of physical quantities representing the motion state of the vehicle and the range of the vehicle's drivable area, and generating a single driving track based thereon, the processing load when generating the vehicle's driving track can be reduced. Attached Figure Description

[0014] Figure 1 This is a functional block diagram of the vehicle system involved in Embodiment 1.

[0015] Figure 2 This is a hardware configuration diagram of the vehicle motion control device involved in Embodiment 1.

[0016] Figure 3 This is a functional block diagram of the travel track planning unit involved in Embodiment 1.

[0017] Figure 4 This is a flowchart illustrating the processing overview of the travel track planning unit involved in Embodiment 1.

[0018] Figure 5 This is a processing example of the functional module of the travel track planning unit involved in Embodiment 1.

[0019] Figure 6 This is a processing example of the functional module of the travel track planning unit involved in Embodiment 2.

[0020] Figure 7 This is another example of the processing of the functional module of the travel track planning unit involved in Embodiment 2.

[0021] Figure 8 This is a functional block diagram of the operation management unit involved in Embodiment 3.

[0022] Figure 9 This is a functional block diagram of the in-vehicle system and the external system involved in Embodiment 4.

[0023] Figure 10 This is a functional block diagram of the HMI unit involved in Embodiment 5.

[0024] Figure 11 This is a display example of the display involved in Embodiment 5. Detailed Implementation

[0025] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. The following description and drawings are examples for illustrating the present invention; for clarity, appropriate omissions and simplifications have been made. The present invention can also be implemented in a variety of other forms. Unless otherwise specified, the constituent elements can be singular or plural.

[0026] The positions, sizes, shapes, and extents of the various components shown in the accompanying drawings are sometimes not intended to represent actual positions, sizes, shapes, or extents for ease of understanding of the invention. Therefore, the present invention is not necessarily limited to the positions, sizes, shapes, and extents disclosed in the accompanying drawings.

[0027] Example 1

[0028] First, use Figures 1 to 5 Embodiment 1 of the present invention will be described below.

[0029] <Functional Block Diagram of Vehicle System 1>

[0030] Figure 1 This is a functional block diagram of the vehicle system 1 in this embodiment. The vehicle system 1 is installed in the vehicle V1 and is used for performing vehicle motion control functions such as assisted driving and autonomous driving. Figure 1 As shown, the vehicle-mounted system 1 of this embodiment includes an external communication device 11, a GNSS (Global Navigation Satellite System) 12, a map information storage unit 13, a sensor 14, an HMI (Human Machine Interface) unit 15, a vehicle motion control device 2, a powertrain system 3, a braking system 4, and a steering system 5. Furthermore, the vehicle motion control device 2 of this embodiment includes an operation management unit 21, a travel trajectory planning unit 22, and a travel control unit 23. The components will be described sequentially below.

[0031] <Information source group of vehicle motion control device 2>

[0032] The external communication device 11 performs vehicle-to-vehicle communication between the vehicle V1 and other vehicles, or road-to-road communication between the vehicle V1 and the roadside machine, and sends and receives information about vehicles and the surrounding environment, as well as cloud information, through wireless communication.

[0033] GNSS12 receives radio waves transmitted from artificial satellites such as Quasi-Zenith Satellite and GPS (Global Positioning System) satellites, and obtains information such as the position of vehicle V1.

[0034] The map information storage unit 13 stores general road information used by navigation systems, road information including road width and curvature (information about curves), road surface conditions and traffic conditions, and information about vehicles and the surrounding environment, such as the driving status of other vehicles. Furthermore, information about vehicles and the surrounding environment, as well as cloud information, is updated sequentially based on information obtained through vehicle-to-vehicle communication and road-to-road communication via the external communication device 11.

[0035] Sensor 14 is, for example, an external identification sensor that detects information about the vehicle and its surrounding environment, such as an image sensor, millimeter-wave radar, or lidar. It is also a sensor that detects information such as driver actions, vehicle speed, acceleration, jerk, angular velocity, and wheel steering angle. The information about the vehicle and its surrounding environment detected by the external identification sensor in sensor 14 includes, for example, information about various objects present around the vehicle V1, such as obstacles, signs, lane boundary lines, lane outer lines, buildings, pedestrians, bicycles, and other vehicles. Additionally, signs, as a type of environmental element, include, for example, "bicycle lane" signs. Furthermore, sensor 14 identifies lane boundary lines and lane outer lines, for example, based on the difference in brightness between the white lines in image data captured by the image sensor and the road surface.

[0036] The HMI unit 15 displays the information needed by the user on the display screen and provides audio guidance through a speaker, based on information received from user input operations such as driving mode selection and destination setting, information acquired by the external communication device 11, GNSS 12, and sensor 14, and information recorded in the map information storage unit 13. Additionally, the HMI unit 15 generates alarms to attract the user's attention.

[0037] <Vehicle Motion Control Device 2>

[0038] Figure 2 This is a hardware configuration diagram of the vehicle motion control device 2. As shown, the vehicle motion control device 2 is an ECU (Electronic Control Unit) that oversees the control of the vehicle. It includes a computing unit 24 (CPU, etc.), a main storage device 25 and an auxiliary storage device 26 (such as semiconductor memory), and a communication device 27. The computing unit 24 executes programs loaded into the main storage device 25 to achieve various functions, such as the operation management unit 21. In this embodiment, for ease of explanation, the operation management unit 21, the travel trajectory planning unit 22, and the travel control unit 23 have separate configurations. However, separate configurations are not necessarily required. When these units are used in an actual vehicle, the various functions of these units can also be implemented by a higher-level controller.

[0039] The vehicle's driving modes, controlled by the vehicle motion control device 2, include, for example, comfort mode, economy mode, sport mode, shortest time mode (minimum travel time), and shortest distance mode (minimum travel distance). These driving modes can be arbitrarily set by the user, preset by the user, or set by the operation management unit 21 based on driving condition information. Thus, the vehicle motion control device 2 sets the speed, acceleration, jerk of the vehicle V1, and the speed and distance between the vehicle V1 and a preceding vehicle.

[0040] <Operation Management Unit 21>

[0041] The operation management unit 21 generates information about the vehicle's behavior, such as the location information of the vehicle V1, information about various objects around the vehicle V1 (such as the position and speed of the vehicle and the surrounding environment), front and rear acceleration, front and rear jerk, lateral acceleration, yaw rate, and lateral jerk, based on information obtained by the external communication device 11, GNSS 12, and sensor 14, and map information recorded in the map information storage unit 13.

[0042] In addition, the operation management unit 21 periodically sends the generated location information of the vehicle V1, information about various objects, and information about the vehicle's behavior to other vehicles and roadside vehicles via the external communication device 11, and simultaneously sends them to the map information storage unit 13. The map information storage unit 13 uses the acquired location information of the vehicle V1, information about various objects, and information about the vehicle's behavior to update the stored map information sequentially.

[0043] Furthermore, based on the location information of the vehicle V1, information about various objects, information about the vehicle's behavior, and information acquired from the HMI unit 15 (e.g., driving mode and destination), the operation management unit 21 sets information about the path from the vehicle's current location to the destination. This path information is displayed in the map described later and is used to determine the vehicle's driving trajectory. The information generated and set by the operation management unit 21 is described below as driving status information.

[0044] <Driving Control Unit 23>

[0045] The driving control unit 23 sets the target driving force, target braking force, target steering angle, etc., so that the vehicle follows the driving trajectory output from the driving trajectory planning unit 22 and controls the power transmission system 3, braking system 4, and steering system 5.

[0046] <Controlled object group of driving control unit 23>

[0047] The powertrain 3 controls the driving force generated by the internal combustion engine and electric motor, etc., based on the operation performed by the driver and the target driving force output from the driving control unit 23.

[0048] The braking system 4 controls the braking force generated by the brake calipers, etc., based on the operation performed by the driver and the target braking force output from the driving control unit 23.

[0049] The steering system 5 controls the steering angle of the wheels based on the operation performed by the driver and the target steering angle output from the driving control unit 23.

[0050] <Traffic Track Planning Unit 22>

[0051] like Figure 3 As shown, the travel trajectory planning unit 22 includes an information acquisition unit 22a, a trajectory generation parameter prediction unit 22b, a trajectory generation unit 22c, and an information output unit 22d. Hereinafter, refer to... Figure 4 The flowchart illustrates the processing of each part.

[0052] <<Step S1>>

[0053] First, in step S1, the information acquisition unit 22a acquires vehicle information such as parameters and location of the vehicle V1, as well as external information about the surrounding environment of the vehicle V1, from the operation management unit 21.

[0054] <<Step S2>>

[0055] Next, in step S2, the track generation parameter prediction unit 22b takes the vehicle information and external information obtained in step S1 as input and uses the learned model M to predict the track generation parameters. Here, the predicted track generation parameters include information on the range of at least one of the physical quantities of the vehicle V1's speed, acceleration, and jerk, as well as the range of the vehicle V1's drivable area. Additionally, for at least one of the external information, including the road shape and surface conditions surrounding the vehicle V1, and obstacles, the range of the predicted physical quantities and the range of the vehicle V1's drivable area are also included.

[0056] The learned model M is a model learned by the occupants of vehicle V1 when manually driving vehicle V1, using data measured by GNSS12 and sensors 14 as input, and outputting track generation parameters. This learned model M is, for example, fully learned based on machine learning. In supervised learning, the teacher data is, for example, a dataset labeled with the range of correct physical quantities of vehicle V1 and the range of the correct drivable area of ​​vehicle V1 that the learned model M should output, based on the behavior of vehicle V1 and its surrounding environment when manually driven by the occupants of vehicle V1. Alternatively, the learned model M can be a DNN (Deep Neural Network), CNN (Convolutional Neural Network), RNN (Recurrent Neural Network), LSTM (Long Short-Term Memory), or even a combination of these.

[0057] <<Step S3>>

[0058] In step S3, the track generation unit 22c calculates the target path W and target speed Ve of the vehicle V1 based on the vehicle information and external information obtained in step S1 and the track generation parameters predicted in step S2.

[0059] The trajectory generation unit 22c is, for example, a model that uses an optimization method to calculate the operation amount in order to get as close as possible to the target for the problem of becoming an object. Alternatively, the trajectory generation unit 22c may also use a rule-based, Bayesian estimation, or maximum likelihood estimation model, or even a combination of these.

[0060] <<Step S4>>

[0061] In step S4, the information output unit 22d outputs information about the travel trajectory of the vehicle V1, including the target path W and target speed Ve generated in step S3, to the driving control unit 23. Thus, the driving control unit 23 can control the vehicle V1 based on a suitable target path W and target speed Ve that takes into account the relationship between moving bodies and environmental factors surrounding the vehicle.

[0062] <Processing Example of Track Planning Unit 22>

[0063] Here, use Figure 5 The processing steps S2 to S3 are explained when there is a pedestrian P in the direction of travel of the vehicle V1.

[0064] Figure 5The diagram illustrates the drivable area A of vehicle V1 when it is traveling on a straight road between lane lines Lm1 and Lm2, and pedestrian P is walking in the direction of arrow D near lane line Lm2 in front of vehicle V1. v A graph showing the target path W and target velocity Ve within the target area.

[0065] Here, drivable area A v When the center of gravity of the vehicle (V1) is in the drivable area A v When driving on the boundary line, the permitted driving area is the area where the vehicle can travel without veering off the outer lane lines Lm1 and Lm2 and without colliding with pedestrian P. Additionally, the permitted driving area A... v The size and shape, in addition to what has been learned by the model M, are determined by the conditions that the vehicle V1 can avoid collisions with obstacles and comply with regulations. If these conditions are met, it can also be expanded to a size greater than... Figure 5 The range shown can be wider, or it can be narrowed down.

[0066] In this environment, the track generation unit 22c is in the drivable area A. v The target path W, which is far away from pedestrian P, is generated internally. The target speed Ve is determined based on the speed learned by the learned model M. For example, if the learning process is to keep the speed constant when avoiding pedestrian P, the trajectory generation parameter prediction unit 22b outputs a prediction with the speed set to Lim1, and the trajectory generation unit 22c generates the target speed Ve1 based on this prediction.

[0067] In addition, if the learning process is performed to set the speed of the pedestrian P's vicinity (specifically, from distance Tr1 to distance Tr2) to a speed Lim2 that is lower than speed Lim1 when avoiding pedestrian P, then the trajectory generation parameter prediction unit 22b outputs a prediction that the speed from distance Tr1 to distance Tr2 will be set to Lim2, and the trajectory generation unit 22c generates the target speed Ve2 based on the prediction.

[0068] When using parameters that are optimized only for specific scenarios, it can only generate target speeds with speed limits set to Lim1 or Lim2. However, by generating driving tracks that conform to human senses based on the driver's usual driving learning results, it not only does not compromise the comfort of the occupants of the vehicle V1 in a variety of scenarios, but also achieves highly safe driving that does not easily cause a sense of danger to pedestrians P when generating a low target speed Ve2.

[0069] In addition, in emergency situations such as avoiding collisions with pedestrians who run off the road, there may be situations where the driver brakes or turns suddenly. However, if such obviously abnormal driving is also included as a learning object, the quality of the learned model M will deteriorate. Therefore, it is preferable to exclude obviously abnormal driving from the learning object data to prevent the quality of the learned model M from deteriorating.

[0070] As described above, according to this embodiment, when both environmental elements such as the outer lane line and moving objects such as pedestrians are detected, the speed, acceleration, jerk, and other track generation parameters output by the learned model M, which is learned from measurement data obtained when using manual driving, can generate a suitable driving track that matches the preferences of the vehicle's occupants while with low processing load.

[0071] Example 2

[0072] Next, use Figures 6 to 7 The travel track planning unit 22 of Embodiment 2 of the present invention will be described below. Furthermore, the commonalities with Embodiment 1 will be omitted from repeated descriptions.

[0073] <<First example( Figure 6 )>>

[0074] Figure 6 This diagram illustrates the handling of the vehicle V1 when it is traveling on an S-shaped curve surrounded by the outer lane lines Lm1 and Lm2. Figure 6 The diagram illustrates the drivable area A of vehicle V1 when deceleration is required upon entering a curve. v The acceleration before and after is obtained by differentiating the target velocity Ve with respect to time.

[0075] In this environment, the track generation unit 22c generates a track that can pass through the drivable area A. v The target path W is within the drivable area. Additionally, target path W passes through drivable area A. v The position within is determined by what the learned model M has learned, not only Figure 6 Driving area A shown v The center can also be a straight line with a smaller curvature.

[0076] The target speed Ve at this time is determined according to the timing of the deceleration start learned by the learned model M. For example, if the learning has been performed many times to start deceleration from a distance Tr3 near the entrance of the curve, the track generation parameter prediction unit 22b outputs a prediction that sets the acceleration before and after deceleration from a distance Tr3 to Lg3 as the behavior pattern, and the track generation unit 22c generates the target speed based on the prediction.

[0077] In addition, if the learning process involves decelerating from a distance Tr4 that is closer to the vehicle V1 than the distance Tr3, the track generation parameter prediction unit 22b outputs a prediction that sets the acceleration before and after deceleration from the distance Tr4 to Lg4 as the behavior pattern, and the track generation unit 22c generates the target speed based on this prediction.

[0078] By generating such a driving track, it is possible to create a driving track that provides a high level of comfort and meets the preferences of the vehicle's occupants.

[0079] <<Second example ( Figure 7 )>>

[0080] Figure 7 This diagram illustrates the handling of a situation where vehicle V1 is traveling on the right lane of a road with two lanes on one side, having lane outer line Lm1, lane boundary line Lm3, and lane center line Lm4, and a vehicle V2 is traveling in front of vehicle V1. Figure 7 The diagram illustrates the drivable area A of vehicle V1 when it changes lanes from the right lane to the left lane and overtakes the preceding vehicle V2. v A graph of the target path within.

[0081] Here, drivable area A v When the center of gravity of the vehicle (V1) is in the drivable area A v When driving on the boundary line, the area that can be driven without veering off to the outside of the outer lane line Lm1 and the center lane line Lm4, and without colliding with the preceding vehicle V2.

[0082] In this environment, the track generation unit 22c generates a track in the drivable area A. v The target path is to overtake the preceding vehicle V2. As the target path, for example, after learning from the vicinity of the preceding vehicle V2 multiple times, the track generation parameter prediction unit 22b outputs a path through the drivable area A. v The prediction of turns near the boundary line is used as a behavior pattern, and the track generation unit 22c generates the target path W1 based on this prediction. Additionally, for example, after learning multiple times about locations away from the preceding vehicle V2, the track generation parameter prediction unit 22b outputs a path away from the drivable area A. v The prediction of the turning position of the boundary line is used as a behavior pattern, and the track generation unit 22c generates the target path W2 based on the prediction.

[0083] By generating such driving tracks, it is possible to create driving tracks that provide a high level of comfort and cater to the preferences of the vehicle's occupants.

[0084] Example 3

[0085] Next, use Figure 8The operation management unit 21 of Embodiment 3 of the present invention will be described. Furthermore, the commonalities with Embodiment 1 will be omitted from repeated descriptions.

[0086] like Figure 8 As shown, the operation management unit 21 in this embodiment includes an information acquisition unit 21a, a vehicle control unit 21b, and an information output unit 21c. Based on the information acquired by the information acquisition unit 21a, the operation management unit 21 selects a vehicle control method in the vehicle control unit 21b and outputs the information from the information output unit 21c to the driving control unit 23.

[0087] The information acquired by the information acquisition unit 21a may include, for example, the driving mode, which may include automatic driving control of the vehicle V1, or switching control between automatic driving and manual driving of the vehicle V1, or manual driving assistance control performed by the occupants of the vehicle V1.

[0088] In the vehicle control unit 21b, appropriate vehicle control is selected based on the information acquired by the information acquisition unit 21a. For example, if the occupant selects automatic driving control in the HMI unit 15 and the conditions of the vehicle V1 and the surrounding environment are suitable for automatic driving, automatic driving control is selected; otherwise, manual driving or manual driving assistance control is selected.

[0089] Subsequently, in the driving control unit 23, the vehicle is controlled based on the vehicle control selected in the vehicle control unit 21b and the driving track generated by the track generation unit 22c.

[0090] In this way, the vehicle control unit 21b of the operation management unit 21 can achieve safe and low-impact vehicle control by selecting appropriate vehicle control that corresponds to the conditions of the vehicle V1 and the surrounding environment.

[0091] Example 4

[0092] Next, use Figure 9 The in-vehicle system 1 and the external system of Embodiment 4 of the present invention will be described. Furthermore, the commonalities with Embodiment 1 will be omitted from repeated descriptions.

[0093] Figure 9 Is Figure 1 The figure shows an external learning processing device 6, which serves as an external system, added to the front of the external communication device 11 of the vehicle system 1.

[0094] The external learning processing device 6 is a server or cloud-based device that communicates with the vehicle motion control device 2 via the external communication device 11. This external learning processing device 6 acquires information about the vehicle V1 and its surrounding environment via the external communication device 11, and outputs information related to the learned model M, which has been learned based on this information, to the vehicle motion control device 2. Furthermore, for areas not acquired or learned in the onboard system 1, which is the communication target, the external learning processing device 6 outputs a learned model M interpolated using information acquired and learned from the onboard system 1 of another vehicle.

[0095] Furthermore, when using information obtained from other vehicles to interpolate the learned model M, it is preferable to utilize driving information from other drivers whose driving habits and preferences match those of the driver of vehicle V1. This allows the interpolated learned model M to become a model that matches the driver and driving habits of vehicle V1. In this case, to determine other drivers whose driving habits match, for example, one can select from the drivers registered in the external learning processing device 6 other drivers whose driving characteristics, represented by the upper limit of physical quantities (e.g., speed, acceleration, jerk) observed while driving the vehicle, are similar to those of the driver of this vehicle.

[0096] In this way, by placing the learning process, which has a high processing load, outside the vehicle system 1, the external learning processing device 6 can reduce the performance required for the ECU of the vehicle system 1, thus achieving cost reduction. Furthermore, by interpolating the unlearned regions, the range of conditions suitable for automated driving control can be expanded.

[0097] Example 5

[0098] Next, use Figure 10 The HMI unit 15 of Embodiment 5 of the present invention will be described below. Furthermore, the commonalities with Embodiment 1 will be omitted from the description.

[0099] like Figure 10 As shown, the HMI unit 15 includes an information acquisition unit 15a, an information selection unit 15b, and an information output unit 15c. Based on the information acquired in the information acquisition unit 15a, the occupants of the vehicle V1 select information in the information selection unit 15b, and output the information from the information output unit 15c to the travel track planning unit 22.

[0100] The information acquired by the information acquisition unit 15a and displayed on the display includes, for example, information related to the update content based on the learning results of the learned model M, and preferably, information that can be understood by the occupants, such as changes in travel time to the destination, increases or decreases in acceleration, or changes in driving position before and after the update.

[0101] In the information selection unit 15b, at least two learned models, before and after the update, can be selected. The occupants of vehicle V1 then decide whether to grant permission to update the selected learned model M based on the information before and after the update.

[0102] Figure 11 This is an example of the display used in this embodiment. As shown in the figure, the features of the learned model M before and after the update are displayed on the display, so that the occupant can select the preferred model and use it for future vehicle control.

[0103] In this way, the travel track planning unit 22 generates a travel track based on the track generation parameters predicted by the learned model M selected by the occupants of the vehicle V1 in the information selection unit 15b of the HMI unit 15, thereby achieving vehicle control with high comfort and reassurance that meets the preferences of the occupants of the vehicle.

[0104] Furthermore, the present invention is not limited to the embodiments described above, and various modifications and other configurations can be combined without departing from its spirit. Additionally, the present invention is not limited to devices having all the configurations described in the above embodiments, but also includes devices that have removed a portion of their configuration, devices that have added a portion of other configurations, and devices that have replaced a portion of other configurations.

[0105] Symbol Explanation

[0106] 1. Vehicle system

[0107] 2 Vehicle motion control device

[0108] 21 Operation Management Unit

[0109] 21a Information Acquisition Department

[0110] 21b Vehicle Control Department

[0111] 21c Information Output Department

[0112] 22. Track Planning Unit

[0113] 22a Information Acquisition Department

[0114] 22b Orbit Generation Parameter Prediction Unit

[0115] 22c Orbit Generation Unit

[0116] 22d Information Output Department

[0117] 23 Driving Control Unit

[0118] 24. Computing device

[0119] 25. Main storage device

[0120] 26. Auxiliary storage device

[0121] 27 Communication devices

[0122] 3. Powertrain System

[0123] 4. Braking System

[0124] 5. Steering System

[0125] 6. External learning processing device

[0126] 11. External communication device

[0127] 12 GNSS

[0128] 13. Map Information Storage Department

[0129] 14 Sensors

[0130] 15 HMI units

[0131] 15a Information Acquisition Department

[0132] 15b Information Selection Department

[0133] 15c Information Output Department

[0134] V1 This car

[0135] V2 advance vehicle

[0136] A v Driving area

[0137] W1, W2, W3 This vehicle's target path

[0138] Ve1, Ve2 Target Speed ​​of this vehicle

[0139] Lg3, Lg4 Target front-rear acceleration of this vehicle

[0140] P pedestrian

[0141] D. The direction of pedestrian movement.

Claims

1. A vehicle motion control device, characterized in that, have: The information acquisition unit acquires information about the vehicle itself and environmental information about the vehicle's surrounding environment. The track generation parameter prediction unit inputs the vehicle information and the environmental information obtained by the information acquisition unit into the learned model, and outputs track generation parameters that include the range of physical quantities representing the motion state of the vehicle and the range of the vehicle's drivable area. as well as The track generation unit takes into account the track generation parameters and generates the track on which the vehicle travels.

2. The vehicle motion control device as described in claim 1, characterized in that, The orbit generation unit has a model based on at least one method, such as rule-based, machine learning, optimization method, Bayesian estimation, or maximum likelihood estimation.

3. The vehicle motion control device as described in claim 1, characterized in that, The learned model is generated by learning the vehicle information and the environmental information obtained during manual driving of the vehicle.

4. The vehicle motion control device as described in claim 1, characterized in that, The track generation parameter prediction unit outputs the range of the physical quantities of the vehicle and the range of the drivable area for at least one of the road shape, road surface condition, and obstacles obtained by the information acquisition unit.

5. The vehicle motion control device as described in claim 1, characterized in that, The track generation parameter prediction unit outputs a behavior pattern representing the vehicle's motion based on at least one of the road shape, road surface conditions, and obstacles acquired by the information acquisition unit. The track generation unit takes the behavior pattern as input and generates the track.

6. The vehicle motion control device as described in claim 5, characterized in that, The behavior pattern refers to at least one of the vehicle's acceleration, deceleration, and turning.

7. The vehicle motion control device as described in claim 1, characterized in that, The physical quantity of the vehicle includes at least one of the vehicle's speed, acceleration, and jerk.

8. The vehicle motion control device as described in claim 1, characterized in that, The vehicle is equipped with a vehicle control unit that performs at least one of the following functions based on the track generated by the track generation unit: automatic driving control of the vehicle, switching control between automatic driving and manual driving of the vehicle, and manual driving assistance control performed by the driver of the vehicle.

9. The vehicle motion control device as described in claim 1, characterized in that, The information acquisition unit communicates with an external learning processing device, which outputs the learned model after interpolating the unlearned areas of the learned model using information from other drivers' manual driving.

10. The vehicle motion control device as described in claim 1, characterized in that, The vehicle is equipped with an information selection unit that displays information related to updates based on the learning results of the learned model, and the occupants of the vehicle can select whether or not to allow updates to the learned model.

11. A vehicle-mounted system, characterized in that, have: The vehicle motion control device as described in claim 1; The power transmission system that controls the driving force of the vehicle; A braking system that controls the braking force of the vehicle; and The steering system that controls the steering angle of the wheels of the vehicle. The vehicle motion control device controls the power transmission system, the braking system, and the steering system so that the vehicle travels along the track generated by the track generation unit.

12. A vehicle motion control method, characterized in that, have: The information acquisition steps involve acquiring information about the vehicle itself and environmental information about the vehicle's surrounding environment. The track generation parameter prediction step inputs the acquired vehicle information and environmental information into the learned model and outputs track generation parameters that include the range of physical quantities representing the vehicle's motion state and the range of the vehicle's drivable area; and The track generation step involves inputting the track generation parameters and generating the track for the vehicle to travel on.

Images