JP2020026188A - Vehicle behavior prediction method and vehicle behavior prediction device - Google Patents

Abstract

To reduce control delay of a vehicle behavior.SOLUTION: In a vehicle behavior prediction method, a future travel plan of a vehicle is determined S10, an initial value of a candidate of controlled variables at a future time is determined S12, a vehicle behavior of a vehicle is predicted by inputting determined future travel plan and candidate of controlled variables into a prediction model obtained by modeling the vehicle behavior generated in the vehicle traveling along the future travel plan S13, cost is calculated by using a prescribed evaluation function based on the predicted vehicle behavior S14, and recalculation is performed until the candidate of the controlled variables is optimized S16.SELECTED DRAWING: Figure 6

Description

  The present invention relates to a vehicle behavior prediction method and a vehicle behavior prediction device.

  Patent Literature 1 proposes a vehicle suspension system that controls a damping coefficient of a shock absorber based on a damper speed, a vertical acceleration, a pitch acceleration, and a roll acceleration according to a control rule learned by a fuzzy neural network.

JP-T-2005-538886

According to the technology described in Patent Document 1, the characteristics of the suspension are controlled based on the current state quantities such as a damper speed, a vertical acceleration, a pitch acceleration, and a roll acceleration.
However, since the state of the vehicle changes dynamically, if control is performed based on the current state amount, control starts after the state of the vehicle changes, so that a control delay occurs.
An object of the present invention is to reduce a control delay of a vehicle behavior.

  In the vehicle behavior prediction method according to one aspect of the present invention, a travel plan of a vehicle is determined, and the determined travel plan is input to a prediction model that models a vehicle behavior occurring in a vehicle traveling along the travel plan. Predicts the vehicle behavior of the vehicle.

  According to the aspect of the present invention, it is possible to predict a vehicle behavior that will occur in the own vehicle from now on according to a future driving scene scheduled in the driving plan. By thus reflecting the influence of the future traveling scene on the vehicle behavior, the prediction accuracy of the future vehicle behavior can be improved. As a result, control can be started based on a more accurate prediction result, so that control delay of vehicle behavior can be reduced.

It is a schematic structure figure of an example of a run support device of an embodiment of the present invention. FIG. 2 is a schematic configuration diagram of an example of an active suspension having the actuator of FIG. 1. FIG. 4 is a characteristic diagram illustrating a relationship between a command current and a control pressure in the pressure control valve. FIG. 2 is a block diagram illustrating an example of a functional configuration of a controller in FIG. 1. 5 is a flowchart illustrating an example of a learning process of the state predictor in FIG. 4. 5 is a flowchart illustrating an example of a control process performed by the controller in FIG. 4. It is a graph which shows the time change of the sprung acceleration when it enters into an irregular road from a flat road. It is a graph which shows a time change of the sprung speed at the time of approaching from a flat road to an irregular road. It is a graph which shows the time change of the sprung displacement when it enters an irregular road from a flat road.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings. Note that the drawings are schematic and may differ from actual ones. The embodiments of the present invention described below exemplify an apparatus and a method for embodying the technical idea of the present invention. Is not specified as: The technical idea of the present invention can be variously modified within the technical scope defined by the claims described in the claims.

(Constitution)
Please refer to FIG. The driving support device 1 controls the vehicle behavior of the host vehicle by predicting the vehicle behavior of the host vehicle and controlling an actuator mounted on the host vehicle based on the predicted vehicle behavior.
The driving support device 1 includes an external environment sensor 2, a vehicle sensor 3, a navigation system 4, a driving control device 5, an actuator 6, and a controller 7.

The external environment sensor 2 is a sensor that detects an external environment outside the host vehicle.
The external environment sensor 2 may be a distance measuring device such as a laser range finder (LRF) or a radar. The distance measuring device detects, for example, an object existing around the own vehicle, a relative position between the own vehicle and the object, and a distance between the own vehicle and the object.
Further, the distance measuring device detects a distance to a road surface ahead of the own vehicle. The road surface roughness can be measured by scanning the road surface ahead of the host vehicle as the host vehicle moves forward.
The ranging device outputs the detected ranging data to the travel control device 5 and the controller 7.

  The environment sensor 2 outside the vehicle may be a camera such as a stereo camera or a monocular camera. The camera captures image data of objects existing around the vehicle, road markings such as lane boundary lines (for example, white lines), features such as curbs and guardrails, and road surfaces ahead of the vehicle. Output to

The vehicle sensor 3 detects the six-axis movement of the vehicle body on the spring of the own vehicle and the three-axis movement of the unsprung part in the vertical direction, the left-right direction, and the front-back direction as the current state of the own vehicle. Hereinafter, the three-axis movement in the up-down direction, the left-right direction, and the front-back direction is referred to as “bounce”.
For example, the vehicle sensor 3 may detect a bounce acceleration on a spring, a pitch angular velocity, a roll angular velocity, and a yaw angular velocity on a spring, and an unsprung bounce acceleration on a spring.

The vehicle sensor 3 may detect displacement or speed instead of the bounce acceleration.
The vehicle sensor 3 may detect a pitch angular displacement, a roll angular displacement, and a yaw angular displacement instead of the pitch angular velocity, the roll angular velocity, and the yaw angular velocity, and may detect the pitch angular acceleration, the roll angular acceleration, and the yaw angular acceleration. It may be detected.

Further, the vehicle sensor 3 may include a wheel speed sensor that detects a wheel speed of the own vehicle.
Further, the vehicle sensor 3 may include a camera and a pressure sensor for detecting the layout, weight, and movement of the occupant in the vehicle interior, and the arrangement, weight, and movement of the luggage in the vehicle interior, as the state of the interior of the vehicle. Good.
The vehicle sensor 3 outputs a vehicle state signal indicating the current state of the host vehicle to the travel control device 5 and the controller 7.

The navigation system 4 recognizes the current position of the vehicle and road map information at the current position, and sets a traveling route to the destination entered by the occupant.
The navigation system 4 includes a navigation controller, a positioning device, a map database, and a communication unit.
The navigation controller is an electronic control unit (ECU: Electronic Control Unit) that controls the information processing operation of the navigation system 4.

The positioning device measures the current position of the host vehicle. The positioning device is, for example, a GPS receiver that receives radio waves from a plurality of navigation satellites to obtain the current position of the vehicle, or a global positioning system (GNSS) receiver other than the GPS receiver. The positioning device may be an inertial navigation device.
The map database stores map information. The map information includes a road map indicated by nodes and links, information on a road type (for example, a general road or an expressway), road width, road shape, gradient, number of lanes, legal speed (speed limit) in road map coordinates. Is included at least. For example, a road in a road map is identified by a link number for each road, and information on a road type, a road width, a road shape, a gradient, the number of lanes, and a legal speed (speed limit) is associated with each link number. . Further, a link number is set for each lane of each road.

The communication unit performs wireless communication with a communication device outside the own vehicle. The communication method by the communication unit may be, for example, wireless communication using a public mobile phone network, vehicle-to-vehicle communication, road-to-vehicle communication, or satellite communication.
The navigation system 4 may acquire road map data and information on the environment outside the host vehicle from the external device by the communication unit. The navigation system 4 may acquire information on the direction and strength of the wind around the own vehicle, for example, as the environment outside the vehicle.

The navigation system 4 sets a traveling route (scheduled route) from the current position of the vehicle to the destination input by the occupant, and provides route guidance to the occupant according to the traveling route.
Further, the navigation system 4 outputs the information of the set traveling route to the traveling control device 5 and the controller 7 as a future traveling plan of the own vehicle.
For example, the navigation system 4 outputs map information of the set traveling route to the traveling control device 5 and the controller 7.
Further, the navigation system 4 outputs information on the environment outside the vehicle acquired from the external device by the communication unit to the controller 7.

The actuator 6 is a drive device that converts an electrical control signal from the travel control device 5 or the controller 7 into a mechanical motion and controls the behavior of the host vehicle.
For example, the actuator 6 is a steering actuator, an accelerator opening actuator, and a brake control actuator for changing a steering angle, an accelerator opening, and a braking amount of the own vehicle according to a control signal from the traveling control device 5 during automatic driving. You may.

Also, for example, the actuator 6 is a hydraulic cylinder that is provided on an active suspension 8 interposed between a vehicle body-side member and a wheel-side member and that adjusts an operating pressure in accordance with a control signal from a controller 7. Is also good.
Please refer to FIG. Reference numeral 10 indicates a vehicle body side member, and reference numerals 11FL to 11RR indicate front left to rear right wheels, respectively.
The active suspension 8 includes hydraulic cylinders 18FL to 18RR as actuators interposed between the vehicle body-side member 10 and the wheel-side members 14 of the wheels 11FL to 11RR, and the operating pressure of the hydraulic cylinders 18FL to 18RR. The pressure control valves 20FL to 20RR which are individually adjusted are provided.

  In addition, the active suspension 8 supplies working oil of a predetermined pressure to the pressure control valves 20FL to 20RR through the supply pipe 21S, and collects return oil from the pressure control valves 20FL to 20RR through the return pipe 21R. And a pressure accumulator 24F, 24R interposed in the supply side pipe 21S between the hydraulic source 22 and the pressure control valves 20FL to 20RR.

  Each of the hydraulic cylinders 18FL to 18RR has a cylinder tube 18a, and the cylinder tube 18a is formed with a lower pressure chamber L separated by a piston 18c having a through hole in the axial direction. A thrust is generated according to the pressure receiving area difference between the upper and lower surfaces and the internal pressure. The lower end of the cylinder tube 18a is attached to the wheel side member 14, and the upper end of the piston rod 18b is attached to the vehicle body side member 10.

Each of the pressure chambers L is connected to output ports of the pressure control valves 20FL to 20RR via a hydraulic pipe 38. In addition, each of the pressure chambers L of the hydraulic cylinders 18FL to 18RR is connected to an accumulator 34 for absorbing unsprung vibration via a throttle valve 32. A coil spring 36 having a relatively low spring constant and supporting a static load of the vehicle body is disposed between the upper and lower portions of each of the hydraulic cylinders 18FL to 18RR.
Each of the pressure control valves 20FL to 20RR is constituted by a 3-port proportional electromagnetic pressure reducing valve having a cylindrical valve housing having a spool slidably mounted therein and a proportional solenoid integrally provided therewith.

  By adjusting the command current i (control amount) supplied to the exciting coil of the proportional solenoid, the moving distance of the poppet accommodated in the valve housing, that is, the position of the spool is controlled. Thereby, the working oil flowing between the hydraulic power source 22 and the hydraulic cylinders 18FL to 18RR via the supply port and the output port or the output port and the return port is controlled.

  FIG. 3 shows the relationship between the command current i (: iFL to iRR) applied to the exciting coil and the control pressure P output from the output port of the pressure control valve 20FL (to 20RR). At the time of the minimum current value iMIN in consideration of noise, the control pressure P becomes the minimum control pressure PMIN. When the current value i is increased from this state, the control pressure P increases linearly in proportion to the current value i, When the current value is iMAX, the maximum control pressure PMAX is equivalent to the set line pressure of the hydraulic power source 22. Reference numeral iN indicates a neutral command current, and reference numeral PN indicates a neutral control pressure.

Please refer to FIG. The traveling control device 5 is an electronic control unit that performs automatic driving control of the own vehicle. This “automatic driving” is a concept that includes not only “fully automatic driving” in which all traveling control of the own vehicle is automatically performed, but also “partially automatic driving” and “driving assistance” in which traveling control is partially automatically performed. .
The travel control device 5 is set by the navigation system 4 based on distance measurement data input from the external environment sensor 2, photographing data around the own vehicle, and a vehicle state signal input from the vehicle sensor 3 during automatic driving of the own vehicle. A traveling trajectory (trajectory) for causing the own vehicle to travel along the traveling route is generated.

When generating the traveling trajectory, the traveling control device 5 first determines a driving action plan for automatically causing the own vehicle to travel on the traveling route.
The driving action plan is a plan of driving action at a lane level (lane level) in a medium-long distance range, which defines a lane (lane) for driving the own vehicle and a driving action required for driving the lane. It is. For example, the driving action plan is a plan that defines a driving action such as how many meters before the intersection to change lanes to a right-turn lane in a scene where a right turn is made at an intersection existing ahead.

  Then, the travel control device 5 generates a track candidate for causing the own vehicle to travel according to the driving action plan based on the motion characteristics of the own vehicle. The travel control device 5 evaluates the future risk of each of the track candidates, selects an optimal track, and sets it as a travel track to be driven by the own vehicle. The traveling trajectory includes a target steering angle, a speed plan, and acceleration / deceleration for that purpose.

The traveling control device 5 controls the actuator 6 (for example, a steering actuator, an accelerator opening actuator, and / or a brake control actuator) based on the selected traveling trajectory.
Specifically, the traveling control device 5 calculates a time series of the control amount of the actuator 6 that generates a series of vehicle behaviors following the traveling trajectory, and sequentially outputs the calculated control amount to the actuator 6.
Hereinafter, the control amount of the actuator 6 calculated by the traveling control device 5 is referred to as “ACR control amount”.

The traveling control device 5 outputs the driving action plan and the traveling trajectory to the controller 7 as the traveling plan of the own vehicle.
The travel control device 5 outputs the time series of the ACR control amount to the controller 7 as a travel plan of the own vehicle.
Further, the travel control device 5 outputs the automatic operation level of the automatic operation control scheduled to be performed by the travel control device 5 to the controller 7 as a travel plan.

The automatic driving level may include, for example, a level that does not require the driver to monitor the traveling state and a level that requires the driver to monitor the traveling state. The automatic driving level may include, for example, “fully automatic driving”, “partial automatic driving”, and “driving assistance”.
As an example, according to the automatic driving level according to the standards established by the National Highway Traffic Safety Administration (NHTSA), the level that does not require the driver to monitor the driving state is the automatic driving level 3 or more, The level at which the driver needs to monitor the driving state is automatic driving level 2 or lower, fully automatic driving is automatic driving level 3 or higher, partial automatic driving is automatic driving level 2 and driving support is automatic driving level 1 It is.

  The controller 7 includes distance measurement data input from the external environment sensor 2 and photographing data around the own vehicle, a vehicle state signal input from the vehicle sensor 3, travel plan and external environment information input from the navigation system 4, and a travel control device 5 This is an electronic control unit that drives the actuator 6 based on the travel plan input from the vehicle and controls the behavior of the host vehicle.

The controller 7 includes a processor such as a CPU (Central Processing Unit) and an MPU (Micro-Processing Unit), and peripheral components such as a storage device.
The storage device may include any of a semiconductor storage device, a magnetic storage device, and an optical storage device. The storage device may include a register, a cache memory, and a memory such as a ROM (Read Only Memory) and a RAM (Random Access Memory) used as a main storage device.

The processor realizes functions of the controller 7 described below by executing a computer program stored in the storage device.
The controller 7 may be realized by a functional logic circuit set in a general-purpose semiconductor integrated circuit. For example, the controller 7 may include a programmable logic device (PLD: Programmable Logic Device) such as a field-programmable gate array (FPGA).

In the present embodiment, an example will be described in which the controller 7 adjusts the operating pressure of the hydraulic cylinders 18FL to 18RR of the active suspension 8 as an actuator for controlling the vehicle behavior of the host vehicle, and changes the characteristics of the active suspension 8.
Specifically, the controller 7 controls the vehicle body behavior of the own vehicle by adjusting the command current i (control amount) of the pressure control valves 20FL to 20RR to control the thrust generated by the hydraulic cylinders 18FL to 18RR. . For example, the vehicle body behavior of the own vehicle is controlled so as to suppress the vertical vibration of the vehicle body.

The functional configuration of the controller 7 will be described with reference to FIG. The controller 7 constitutes the vehicle behavior prediction device 40 of the embodiment. The vehicle behavior prediction device 40 includes a vehicle information acquisition unit 41, an outside-of-vehicle information acquisition unit 42, a travel plan acquisition unit 43, and a model prediction control unit 44.
The vehicle information acquisition unit 41 acquires vehicle state information indicating the state of the vehicle based on the vehicle state signal output from the vehicle sensor 3.

The vehicle state information may include, for example, lateral acceleration, and information on displacement, velocity, and acceleration around the roll axis and the yaw axis.
When the vehicle state signal is displacement information, the vehicle information acquisition unit 41 can acquire speed information and acceleration information by differentiating the displacement information.
When the vehicle state signal is speed information, the vehicle information obtaining unit 41 can obtain displacement information by integrating the speed information, and can obtain acceleration information by differentiating the speed information.
When the vehicle state signal is acceleration information, the vehicle information acquisition unit 41 can acquire displacement information and speed information by integrating the acceleration information.

Further, the vehicle information acquisition unit 41 may acquire the current value of the ACR control amount from the travel control device 5 as vehicle state information.
Further, the vehicle information acquisition unit 41 acquires, as the vehicle state information, in-vehicle information indicating the layout, weight, and movement of the occupant in the vehicle interior, and the state of the vehicle interior such as the layout, weight, and movement of the vehicle interior.
The vehicle information acquisition unit 41 outputs the acquired vehicle state information and the in-vehicle information to the model prediction control unit 44.

The outside-of-vehicle information acquisition unit 42 indicates the outside environment of the host vehicle based on the distance measurement data output from the external environment sensor 2 and the photographing data around the host vehicle, and the vehicle state signal output from the vehicle sensor 3. Acquire outside environment information.
The external environment information may include, for example, the road surface roughness of the road surface ahead of the host vehicle, the road surface vibration occurring on the road surface, and the road surface friction coefficient of the road surface ahead of the host vehicle.

The outside-of-vehicle information acquisition unit 42 acquires the road surface roughness of the road surface ahead of the host vehicle and the road surface vibration occurring on the road surface based on the distance measurement data output from the external environment sensor 2 and the photographing data around the host vehicle. .
The external information acquisition unit 42 calculates the acceleration of the vehicle and the slip ratio of the tire from the wheel speed of the vehicle, and acquires the road surface friction coefficient based on the regression coefficient of the acceleration and the slip ratio.

In addition, the outside-of-vehicle information acquisition unit 42 may acquire outside-of-vehicle environment information from an external device by the communication unit of the navigation system 4. For example, the outside-of-vehicle information acquiring unit 42 may acquire outside-of-vehicle environment information indicating the direction and strength of wind around the own vehicle from an external device.
The outside-of-vehicle information acquisition unit 42 outputs the acquired outside-of-vehicle environment information to the model prediction control unit 44.

The travel plan acquisition unit 43 acquires the set route set by the navigation system 4 and its map information as a travel plan.
Further, the traveling plan acquisition unit 43 acquires the driving action plan determined by the traveling control device 5 and the traveling trajectory as the traveling plan.

Further, the travel plan acquisition unit 43 acquires a time series of the ACR control amount calculated by the travel control device 5 as a travel plan.
In addition, the travel plan obtaining unit 43 obtains, as the travel plan, the automatic driving level of the automatic driving control scheduled to be performed by the driving control device 5.

Further, the travel plan acquisition unit 43 calculates, as the travel plan, a predicted value of the lateral acceleration that is predicted to occur when the host vehicle travels on the travel track determined by the travel control device 5.
The travel plan acquisition unit 43 outputs the acquired travel plan to the model prediction control unit 44.

  The model prediction control unit 44 performs model prediction control based on the vehicle state information, the in-vehicle information, the out-of-vehicle environment information, and the travel plan, and controls the control amounts of the pressure control valves 20FL to 20RR of the active suspension 8. Hereinafter, the control amount of the pressure control valves 20FL to 20RR controlled by the model prediction control unit 44 will be simply referred to as “control amount”.

In the model predictive control, the state of the control target over a finite section (prediction section) from the current time to the future is predicted.
Specifically, assuming that the length of the prediction section is Tp, based on the input to the control target at times t0, t0 + 1,. The state of the control target in is predicted.
Then, based on the predicted states at times t0 + 1, t0 + 2,..., T0 + Tp + 1, an evaluation function indicating the control performance in the prediction section is calculated, and a control amount that minimizes the evaluation function is searched for using an optimization problem or the like. I do.

The model prediction control unit 44 includes a state predictor 50, an evaluation unit 51, and an optimization unit 52.
The state predictor 50 inputs the state of the own vehicle at the current time t0 and the outside environment around the own vehicle, and the candidates of the travel plan and the control amount of the own vehicle at times t0, t0 + 1,..., T0 + Tp, and inputs the time t0 + 1. , T0 + 2,..., T0 + Tp + 1 are predicted as the vehicle behavior.
For this reason, the state predictor 50 calculates the vehicle behavior of the own vehicle generated according to the travel plan (future travel plan) in which the own vehicle is to be run, the control amount, the current state of the own vehicle, and the environment outside the vehicle. Has a modeled prediction model.

The prediction model is, for example, a driving plan in which the host vehicle is scheduled to run, a control amount, and a vehicle behavior of the host vehicle generated according to the state of the host vehicle and the environment outside the vehicle at the current time, and a model in which a differential equation is expressed. It may be.
Further, the prediction model is based on, for example, actually driving the own vehicle in accordance with the running plan, according to the running plan in which the own vehicle is to run, the control amount, the state of the own vehicle at the current time, and the environment outside the vehicle. It may be a deep neural network (DNN: Deep Neural Network) that learns the behavior of the vehicle that has occurred in the own vehicle.

The state predictor 50 inputs the vehicle state information and the in-vehicle information at the current time t0 from the vehicle information acquisition unit 41. The state predictor 50 inputs the outside environment information at the current time t0 from the outside information acquisition unit 42.
Further, the state predictor 50 inputs the travel plan of the own vehicle at times t0, t0 + 1,..., T0 + Tp from the travel plan acquisition unit 43.
The travel plan of the own vehicle includes, for example, a speed plan of the own vehicle, a scheduled acceleration / deceleration of the own vehicle, a planned lateral acceleration generated in the own vehicle traveling along the traveling track, a time series of the ACR control amount, and a travel of the own vehicle. The planned route to be performed, and the planned automatic driving level.

For example, the speed plan and the scheduled acceleration / deceleration of the own vehicle are respective speeds and acceleration / deceleration at times t0, t0 + 1,..., T0 + Tp determined by the traveling trajectory determined by the traveling control device 5.
For example, the lateral acceleration scheduled to occur in the own vehicle is each lateral acceleration predicted to occur at time t0, t0 + 1,..., T0 + Tp in the own vehicle traveling on the traveling trajectory determined by the traveling control device 5.

For example, the time series of the ACR control amount is an ACR control amount to be output to the actuator 6 at times t0, t0 + 1,..., T0 + Tp.
For example, the scheduled route on which the host vehicle travels is a position at which the host vehicle traveling on the set route set by the navigation system 4 reaches times t0, t0 + 1,..., T0 + Tp, and map information thereof.
For example, the scheduled automatic operation levels are the respective automatic operation levels scheduled to be performed by the travel control device 5 at times t0, t0 + 1,..., T0 + Tp.

Further, the state predictor 50 inputs the respective control amount candidates at the times t0, t0 + 1,..., T0 + Tp from the optimization unit 52.
Based on the vehicle state information, the in-vehicle information, and the out-of-vehicle environment information at the current time t0, and the candidates for the travel plan and the control amount of the own vehicle at the times t0, t0 + 1,. , And the state quantities of the vehicle body at t0 + Tp + 1 are predicted. For example, the state predictor 50 predicts the displacement, speed and acceleration of the bounce on the spring, and the displacement, speed and acceleration around the pitch axis, the roll axis and the yaw axis, and the displacement, speed and acceleration of the bounce under the spring. Good.
The state predictor 50 outputs to the evaluator 51 the state quantities of the vehicle body at the predicted times t0 + 1, t0 + 2,..., T0 + Tp + 1.

  The evaluator 51 evaluates the control performance of the control amount candidates at each time t0, t0 + 1,..., T0 + Tp by calculating a cost using a predetermined evaluation function based on the state quantity predicted by the state predictor 50. I do. Here, for example, acceleration on a spring or speed on a spring may be calculated as an evaluation function (cost) in order to suppress the vehicle body behavior. The evaluation unit 51 outputs the calculated cost to the optimization unit 52.

The optimization unit 52 optimizes each control amount candidate at time t0, t0 + 1,..., T0 + Tp so as to minimize the cost calculated by the evaluation unit 51.
The optimization unit 52 may optimize the control amount candidate based on, for example, an iterative method using a differential value of the evaluation function.
Further, for example, the optimization unit 52 may optimize the control amount candidate based on a heuristic method of directly searching for an optimal solution by trial and error. As a heuristic, for example, a genetic algorithm, particle swarm optimization, artificial bee colony algorithm may be used.
The optimization unit 52 outputs the control amount at time t0 among the control amounts at times t0, t0 + 1,..., T0 + Tp optimized by the search to the pressure control valves 20FL to 20RR of the active suspension 8.

(motion)
With reference to FIGS. 5 and 6, an operation of the driving support device according to the embodiment will be described. FIG. 5 is a flowchart illustrating an example of a learning process of the state predictor 50 in FIG.
In step S1, a travel plan of the host vehicle is determined. The travel plan may be determined using, for example, the navigation system 4 and the travel control device 5, or may be determined offline.
In step S2, the vehicle sensor 3 and the outside environment sensor 2 detect the state of the own vehicle when the vehicle actually travels according to the travel plan and the outside environment outside the own vehicle.

In step S3, the control amount of control actually performed on the pressure control valves 20FL to 20RR of the active suspension 8 when traveling according to the traveling plan is detected.
In step S4, each data of the travel plan determined in step S1, the state of the own vehicle detected in step S2, the environment outside the own vehicle, and the control amount detected in step S3 is stored.

In step S5, a prediction model provided in the state predictor 50 is learned based on each data stored in step S4.
For example, for each time ti within a period of traveling in accordance with the travel plan, the state of the own vehicle at time ti and the environment outside the own vehicle, the travel plan of the own vehicle at times ti, ti + 1,. The control amount is input to the prediction model, and the state of the host vehicle at times ti + 1, ti + 2,..., Ti + Tp + 1 is predicted. Then, a solution that minimizes the error function between the prediction result and the actually detected state (teacher data) of the own vehicle is searched for, and the prediction model is learned.

FIG. 6 is a flowchart illustrating an example of a control process of the active suspension 8 performed by the controller 7 of FIG.
In step S10, the navigation system 4 and the travel control device 5 determine a travel plan of the own vehicle.
In step S11, the vehicle sensor 3 and the outside environment sensor 2 detect the state of the own vehicle and the outside environment outside the own vehicle.

In step S12, the optimization unit 52 determines the initial values of the control amount candidates at times t0, t0 + 1,..., T0 + Tp.
In step S13, the state predictor 50 determines the time t0 + 1 based on the vehicle state information, the in-vehicle information, and the outside environment information at the current time t0, and the candidate for the travel plan and the control amount of the own vehicle at the times t0, t0 + 1,. , T0 + 2,..., T0 + Tp + 1, respectively.

In step S14, the evaluation unit 51 calculates a cost using a predetermined evaluation function based on the state quantity predicted by the state predictor 50, thereby controlling the control performance of the control amount candidate at time t0, t0 + 1,..., T0 + Tp. To evaluate.
In step S15, the optimization unit 52 determines whether or not the control amount candidates at the times t0, t0 + 1,..., T0 + Tp have been optimized based on the cost calculated by the evaluation unit 51. For example, the optimization unit 52 may determine that the candidate for the control amount has been optimized when the cost has become equal to or less than the threshold value or when the cost has reached the minimum value.

When the control amount candidate is not optimized (step S15: N), the process proceeds to step S16.
In step S16, the optimization unit 52 recalculates the control amount candidates according to a predetermined optimization algorithm. Thereafter, the process returns to step S13.
When the candidate for the control amount is optimized (step S15: Y), the optimization unit 52 outputs the control amount at time t0 to the pressure control valves 20FL to 20RR of the active suspension 8. Thereafter, the process ends.

(Effects of the embodiment)
(1) The navigation system 4 and the travel control device 5 determine a future travel plan of the vehicle. The model prediction control unit 44 sends a future prediction determined by the navigation system 4 and the travel control device 5 to the state predictor 50 having a prediction model that models a vehicle behavior occurring in the vehicle traveling along the future travel plan. By inputting a travel plan, the vehicle behavior of the own vehicle is predicted.

By using a future traveling plan in which the own vehicle will travel, a vehicle behavior occurring in the own vehicle can be predicted according to a future traveling scene scheduled in the traveling plan.
By reflecting the influence of the future running scene on the vehicle behavior, the prediction accuracy of the future vehicle behavior can be improved. As a result, control can be started based on a more accurate prediction result, so that control delay of vehicle behavior can be reduced.
For this reason, the optimal vehicle behavior according to the travel plan can be realized. For example, when controlling the hydraulic cylinders 18 FL to 18 RR of the active suspension 8, it is possible to obtain optimal suspension characteristics according to the traveling plan.

7A to 7C are graphs showing sprung acceleration, sprung speed, and sprung displacement over time when the vehicle turns at an intersection and enters an irregular road from a flat road.
The broken line shows a waveform when the active suspension is controlled without using the travel plan.
The external environment sensor 2 for measuring the road surface roughness detects a road surface displacement at a position ahead of the own vehicle position by a predetermined foreseeable distance. Therefore, when the vehicle turns at an intersection and enters an irregular road, information on the road surface roughness cannot be used during a period (T1 to T2) until the vehicle travels for the foreseeable distance. For this reason, the control of the active suspension is delayed, and the motion on the spring increases.

The solid line shows a waveform when the active suspension is controlled using a prediction model that receives a travel plan as an input.
In this case, entry into the irregular road is scheduled in the traveling plan, and the vehicle behavior that occurs in the own vehicle that has traveled on the irregular road has been learned. It is possible to predict the behavior of the own vehicle traveling. For this reason, the error of the control of the active suspension can be reduced from time T1 immediately after entering the irregular road, and the movement on the sprung can be suppressed.

  (2) The travel plan input to the state predictor 50 may include a route on which the host vehicle is to travel. As a result, the vehicle behavior can be controlled in accordance with the route on which the host vehicle will travel.

  (3) The travel plan input to the state predictor 50 may include a speed plan of the own vehicle. Thereby, the vehicle behavior can be controlled in accordance with the vehicle speed plan of the own vehicle.

(Modification)
(1) In the above embodiment, the controller 7 adjusts the operating pressure of the hydraulic cylinders 18FL to 18RR of the active suspension 8 as an actuator for controlling the vehicle behavior of the host vehicle.
Instead, the controller 7 may control any of the control amounts of the steering actuator, the accelerator opening actuator, and the brake control actuator. In this case, the controller 7 may control the control amounts of these actuators instead of the travel control device 5.

(2) The vehicle state information, the outside-of-vehicle environment information, and the data of the travel plan used for the prediction of the state of the own vehicle by the model prediction control unit 44 may have different priorities.
For example, the priority of the vehicle state information may be set to the highest, the priority of the travel plan may be set to the second highest, and the priority of the environment information outside the vehicle may be set to the lowest.

  The state predictor 50 may more strongly reflect the influence of data having a higher priority on the prediction result than the influence of data having a lower priority. For example, when the state predictor 50 has a prediction model using a deep neural network, data having higher priority than a coupling coefficient between a node to which low priority data is input and an intermediate layer is input. The coupling coefficient between the node and the intermediate layer may be made larger.

This makes it possible to provide superiority or inferiority in the influence of data used for the state prediction of the own vehicle on the prediction result.
For example, by setting the priority of data with high likelihood higher than the priority of data with low likelihood, the accuracy of the prediction result can be improved.
Further, for example, when there is a likelihood difference between the outside environment information, the priority of the outside environment information having a high likelihood may be set higher than the priority of the outside environment information having a low likelihood. Thus, when there is a difference in the likelihood of the sensor detecting the environment outside the vehicle or when the likelihood of the sensor fluctuates, it is possible to adjust the influence of the sensor signal on the prediction result according to the likelihood.

  (3) In the above embodiment, the state predictor 50 predicts the state of the own vehicle using the travel plan used for automatic driving. Alternatively, the state predictor 50 may predict the state of the host vehicle using a travel plan used for route guidance to the driver during manual driving.

  DESCRIPTION OF SYMBOLS 1 ... Driving assistance device, 2 ... Outside environment sensor, 3 ... Vehicle sensor, 4 ... Navigation system, 5 ... Driving control device, 6 ... Active suspension, 7 ... Controller, 8 ... Active suspension, 10 ... Body side member, 11FL: Wheel, 11RR: Wheel, 14: Wheel side member, 18a: Cylinder tube, 18b: Piston rod, 18c: Piston, 18FL: Hydraulic cylinder, 18RR: Hydraulic cylinder, 20FL: Pressure control valve, 20RR: Pressure control valve, 21R: Side pipe, 21S: Supply side pipe, 22: Hydraulic source, 24F: Accumulator, 24R: Accumulator, 32: Valve, 34: Accumulator, 36: Coil spring, 38: Hydraulic pipe, 40: Vehicle behavior prediction device, 41 ... Vehicle information acquisition unit, 42 ... Outside vehicle information acquisition unit, 43 ... Driving plan acquisition units 43, 44 Model predictive control unit, 50 ... state predictor, 51 ... evaluation unit, 52 ... optimization section

Claims (4)

Determine the future driving plan of the vehicle,
Predict the vehicle behavior of the vehicle by inputting the determined future travel plan to a prediction model that models the vehicle behavior occurring in the vehicle traveling along the future travel plan,
A vehicle behavior prediction method characterized by the above-mentioned.   The vehicle behavior prediction method according to claim 1, wherein the travel plan is a route on which the vehicle is to travel.   The method according to claim 1, wherein the travel plan is a speed plan of the vehicle.   By determining the future travel plan of the vehicle and inputting the determined future travel plan to a prediction model that models a vehicle behavior occurring in the vehicle traveling along the future travel plan, the vehicle A vehicle behavior prediction device comprising a controller for predicting a vehicle behavior of the vehicle.

Images