WO2023100482A1 - Vehicle control system, vehicle control device, vehicle control method, and vehicle control program - Google Patents
Vehicle control system, vehicle control device, vehicle control method, and vehicle control program Download PDFInfo
- Publication number
- WO2023100482A1 WO2023100482A1 PCT/JP2022/038022 JP2022038022W WO2023100482A1 WO 2023100482 A1 WO2023100482 A1 WO 2023100482A1 JP 2022038022 W JP2022038022 W JP 2022038022W WO 2023100482 A1 WO2023100482 A1 WO 2023100482A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- vehicle
- action plan
- predicted
- control amount
- control
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims description 13
- 230000009471 action Effects 0.000 claims abstract description 104
- 230000004044 response Effects 0.000 claims abstract description 36
- 230000033001 locomotion Effects 0.000 claims abstract description 23
- 230000008859 change Effects 0.000 claims description 23
- 238000004891 communication Methods 0.000 description 29
- 238000012545 processing Methods 0.000 description 13
- 230000001133 acceleration Effects 0.000 description 12
- 238000011156 evaluation Methods 0.000 description 10
- 230000006399 behavior Effects 0.000 description 7
- 230000004043 responsiveness Effects 0.000 description 7
- 230000006866 deterioration Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000001514 detection method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 239000004065 semiconductor Substances 0.000 description 4
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000010391 action planning Effects 0.000 description 2
- 230000001413 cellular effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 230000036461 convulsion Effects 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003534 oscillatory effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W60/00—Drive control systems specially adapted for autonomous road vehicles
Definitions
- the present disclosure relates to vehicle control technology for controlling a host vehicle.
- Patent Document 1 discloses a technique for compensating for the time delay in motion control of a vehicle that automatically runs following a target trajectory. This technology predicts the vehicle behavior when a motion command is given to reduce the deviation between the vehicle position and the target position on the target trajectory, and predicts the vehicle position at the previous time. Then, the vehicle behavior at a time later than the predicted vehicle position is similarly predicted, and the vehicle position at a further time is predicted. In Patent Literature 1, by repeating this process, a command value for vehicle motion a predetermined time ahead is predicted, and the command value is output.
- a first aspect of the present disclosure is a vehicle control system having a processor and controlling a host vehicle, comprising: The processor developing a future action plan including the position and motion state of the host vehicle; Acquiring a predicted control amount in the predicted time ahead based on the delay time of the response regarding travel control in the host vehicle from the action plan; Determining a current output control amount according to the predicted control amount; configured to run
- a second aspect of the present disclosure is a vehicle control device having a processor and controlling a host vehicle,
- the processor developing a future action plan including the position and motion state of the host vehicle; Acquiring a predicted control amount in the predicted time ahead based on the delay time of the response regarding travel control in the host vehicle from the action plan; Determining a current output control amount according to the predicted control amount; configured to run
- a third aspect of the present disclosure is a vehicle control method executed by a processor to control a host vehicle, comprising: developing a future action plan including the position and motion state of the host vehicle; Acquiring a predicted control amount in the predicted time ahead based on the delay time of the response regarding travel control in the host vehicle from the action plan; Determining a current output control amount according to the predicted control amount; including.
- a fourth aspect of the present disclosure is a vehicle control program stored in a storage medium and including instructions to be executed by a processor to control a host vehicle, comprising: the instruction is allowing future action plans to be developed including the position and motion state of the host vehicle; Obtaining from the action plan a predicted control amount in the predicted time ahead based on the response delay time regarding travel control in the host vehicle; determining a current output control amount according to the predicted control amount; including.
- the current output control amount is determined according to the predicted control amount obtained from the action plan including the motion state in addition to the position of the host vehicle. Therefore, the prediction error becomes small and the response delay can be compensated. Therefore, it may be possible to suppress deterioration of controllability and improve responsiveness.
- FIG. 2 is a schematic diagram showing a running environment of a host vehicle to which the first embodiment is applied; 1 is a block diagram showing the functional configuration of a vehicle control system according to a first embodiment; FIG. FIG. 4 is a diagram for explaining response delay in a host vehicle; FIG. 4 is a graph for explaining changes in response depending on the presence or absence of tire deformation.
- 4 is a flowchart showing a vehicle control method according to the first embodiment; 7 is a graph showing vehicle behavior in preceding vehicle follow-up control when it is assumed that there is no response delay; 7 is a graph showing vehicle behavior in preceding vehicle follow-up control when response delay is not compensated; 7 is a graph showing vehicle behavior in preceding vehicle follow-up control when response delay is compensated; It is a figure which shows typically the vehicle control in 2nd embodiment. It is a figure which shows typically the vehicle control in 3rd embodiment.
- a vehicle control system 100 of the first embodiment shown in FIG. 1 controls running of a host vehicle A shown in FIG. From a viewpoint centering on the host vehicle A, the host vehicle A can also be said to be an ego-vehicle. From the viewpoint centered on the host vehicle A, the target vehicle B can also be said to be a user on another road.
- an automatic driving mode is given, which is divided into levels according to the degree of manual intervention of the driver in the driving task.
- Autonomous driving modes may be achieved by autonomous cruise control, such as conditional driving automation, advanced driving automation, or full driving automation, in which the system performs all driving tasks when activated.
- Autonomous driving modes may be provided by advanced driving assistance controls, such as driving assistance or partial driving automation, in which the occupant performs some or all driving tasks.
- the automatic driving mode may be realized by either one, combination, or switching of the autonomous driving control and advanced driving support control.
- the host vehicle A is equipped with a sensor system 10, a communication system 20, a map database (hereinafter referred to as "DB") 30, and a traveling system 40 shown in FIG.
- the sensor system 10 acquires sensor information that can be used by the vehicle control system 100 by detecting the external and internal worlds of the host vehicle A.
- FIG. For this purpose, the sensor system 10 includes an external sensor 11 and an internal sensor 12 .
- the external world sensor 11 acquires external world information that can be used by the vehicle control system 100 from the external world that is the surrounding environment of the host vehicle A.
- the external world sensor 11 may acquire external world information by detecting a target existing in the external world of the host vehicle A.
- the target detection type external sensor 11 is, for example, at least one type of camera, LiDAR (Light Detection and Ranging/Laser Imaging Detection and Ranging), radar, sonar, and the like.
- the external sensor 11 may acquire external world information by receiving positioning signals from satellites of the GNSS (Global Navigation Satellite System) existing in the external world of the host vehicle A.
- the positioning type external sensor 11 is, for example, a GNSS receiver or the like.
- the external world sensor 11 may acquire external world information by transmitting and receiving communication signals to and from a V2X system existing in the external world of the host vehicle A.
- the communication type external sensor 11 is, for example, a DSRC (Dedicated Short Range Communications) communication device, a cellular V2X (C-V2X) communication device, a Bluetooth (registered trademark) device, a Wi-Fi (registered trademark) device, an infrared communication device, or the like. at least one of
- the inner world sensor 12 acquires inner world information that can be used by the vehicle control system 100 from the inner world that is the internal environment of the host vehicle A.
- the inner world sensor 12 may acquire inner world information by detecting a specific kinematic physical quantity in the inner world of the host vehicle A.
- the physical quantity sensing type internal sensor 12 is at least one of, for example, a running speed sensor, an acceleration sensor, a gyro sensor, and the like.
- the communication system 20 acquires communication information that can be used by the vehicle control system 100 by wireless communication.
- the communication system 20 may receive positioning signals from artificial satellites of the GNSS (Global Navigation Satellite System) existing outside the host vehicle A.
- the positioning type communication system 20 is, for example, a GNSS receiver or the like.
- the communication system 20 may transmit and receive communication signals to and from a V2X system existing outside the host vehicle A.
- the V2X type communication system 20 is, for example, at least one of a DSRC (Dedicated Short Range Communications) communication device, a cellular V2X (C-V2X) communication device, and the like.
- the communication system 20 may transmit and receive communication signals to and from terminals existing in the inner world of the host vehicle A.
- the terminal communication type communication system 20 is, for example, at least one of Bluetooth (registered trademark) equipment, Wi-Fi (registered trademark) equipment, infrared communication equipment, and the like.
- the map DB 30 stores map information that can be used by the vehicle control system 100.
- the map DB 30 includes at least one type of non-transitory tangible storage medium, such as semiconductor memory, magnetic medium, and optical medium.
- the map DB 30 may be a database of a locator for estimating the host vehicle A's own state quantity including its own position.
- the map DB 30 may be a database of a navigation unit that navigates the travel route of the host vehicle A.
- the map DB 30 may be configured by combining a plurality of types of these databases.
- the map DB 30 acquires and stores the latest map information through communication with an external center via the V2X type communication system 20, for example.
- the map information is data representing the running environment of the host vehicle A in two or three dimensions.
- the three-dimensional map data digital data of a high-precision map should be adopted.
- the map information may include road information representing at least one of the position, shape, road surface condition, and the like of the road itself.
- the map information may include sign information representing at least one of the position and shape of signs attached to roads and lane markings, for example.
- the map information may include structure information representing at least one of the positions and shapes of buildings facing roads and traffic lights, for example.
- the running system 40 is configured to run the body of the host vehicle A based on commands from the vehicle control system 100 .
- the travel system 40 includes a drive unit that drives the host vehicle A, a braking unit that brakes the host vehicle A, and a steering unit that steers the host vehicle A.
- the vehicle control system 100 is connected to the sensor system 10, the communication system 20, the map DB 30, and the traveling system 40 via at least one of a LAN (Local Area Network) line, a wire harness, an internal bus, a wireless communication line, and the like. It is connected.
- the vehicle control system 100 includes at least one dedicated computer.
- the dedicated computer that configures the vehicle control system 100 may be an operation control ECU (Electronic Control Unit) that controls the operation of the host vehicle A.
- a dedicated computer that configures the vehicle control system 100 may be a navigation ECU that navigates the travel route of the host vehicle A.
- FIG. A dedicated computer that configures the vehicle control system 100 may be a locator ECU that estimates the host vehicle A's self-state quantity.
- the dedicated computer that configures the vehicle control system 100 may be an actuator ECU that controls the travel actuators of the host vehicle A.
- the dedicated computer that configures the vehicle control system 100 may be an HCU (Human Machine Interface) Control Unit (HCU) that controls information presentation in the host vehicle A.
- the dedicated computer that configures the vehicle control system 100 may be a computer other than the host vehicle A that configures an external center or a mobile terminal that can communicate via the V2X type communication system 20, for example.
- the dedicated computer that configures the vehicle control system 100 may be an integrated ECU (Electronic Control Unit) that integrates the operation control of the host vehicle A.
- the dedicated computer that constitutes the vehicle control system 100 may be a judgment ECU that judges the driving task in the driving control of the host vehicle A.
- FIG. A dedicated computer that configures the vehicle control system 100 may be a monitoring ECU that monitors the operation control of the host vehicle A.
- FIG. The dedicated computer that configures the vehicle control system 100 may be an evaluation ECU that evaluates the operation control of the host vehicle A.
- a dedicated computer that constitutes the vehicle control system 100 has at least one memory 101 and at least one processor 102 .
- the memory 101 stores computer-readable programs, data, etc., non-temporarily, and includes at least one type of non-transitory storage medium such as a semiconductor memory, a magnetic medium, and an optical medium. tangible storage medium).
- the processor 102 is, for example, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a RISC (Reduced Instruction Set Computer)-CPU, a DFP (Data Flow Processor), and a GSP (Graph Streaming Processor). as a core.
- the processor 102 executes a plurality of instructions contained in the vehicle control program stored in the memory 101 to control the host vehicle A. Accordingly, the vehicle control system 100 constructs a plurality of functional blocks for controlling the host vehicle A.
- FIG. A plurality of functional blocks constructed in the vehicle control system 100 include a recognition block 110, an action plan block 120 and a control amount determination block 130 as shown in FIG.
- the recognition block 110 executes recognition processing for recognizing the environment around the host vehicle A and the state of the host vehicle A based on the external world information from the external sensor 11 and the internal world information from the internal sensor 12 .
- the environment around the host vehicle A includes, for example, at least one type of information such as position and speed information about surrounding moving bodies, position information about features such as road markings, structures along the road, and road edges.
- the state of the host vehicle A includes, for example, at least one of host vehicle A's own position, speed, acceleration, steering angle, yaw rate, and the like.
- the recognition block 110 executes recognition processing using information of the sensors 11 and 12 acquired immediately before recognition processing.
- the recognition block 110 may correct the deviation between the detection time of information in each of the sensors 11 and 12 and the execution time of the recognition process based on the motion model of the recognition target object and the host vehicle A. Alternatively, the recognition block 110 may provide the movement amount of the recognition object or the host vehicle A corresponding to the time lag to the action planning block 120 as an error. Note that the recognition block 110 provides prediction errors to the action planning block 120 even when corrected for deviations.
- the action plan block 120 draws up a future action plan for the host vehicle A.
- the action plan includes the future position and motion state of the host vehicle A as control target values.
- the action plan is chronological information that defines these pieces of information at predetermined times in the future.
- the motion state of the host vehicle A includes at least one or more of speed, acceleration, yaw angle, yaw rate, and the like.
- Motion states may also include pitch angle, pitch rate, pitch acceleration, and the like.
- An action plan including such information can also be expressed as a traveling trajectory of the host vehicle A.
- the action plan block 120 draws up an action plan under the constraint conditions that restrict the action of the host vehicle A.
- Constraint conditions include an area condition under which the host vehicle A can be accommodated within a travelable area.
- the action plan block 120 estimates the travelable area of the host vehicle A based on the surrounding information and the own vehicle information.
- Action plan block 120 generates a plan of action for host vehicle A within this drivable area.
- constraints include vehicle models and obstacle models. Specifically, the constraint conditions include that the control amount of the host vehicle A should be within an allowable range, that the host vehicle should not come into contact with obstacles, and the like.
- Action plan block 120 formulates an action plan under these constraints.
- action plan block 120 optimizes the action plan under constraints. For example, if z is the state variable and the control variable, L(z, k) is the cost function, and N is the prediction point, the evaluation function f(z) of the action plan is given by the following formula (1).
- the evaluation function is a weighted linear combination of mathematical parameters for maintaining a prescribed inter-vehicle distance, maintaining a target vehicle speed, avoiding sudden acceleration and deceleration, traveling along a road, and the like.
- the action plan block 120 satisfies, for example, the following vehicle motion constraint equation (2) and driving environment constraint equation (3), and f(z) is the minimum value over the predicted horizon:
- a variable z is set as a parameter that defines the action plan.
- the prediction horizon is a time interval in which an action plan from the current time to the future time is defined, as shown in FIG.
- the control amount determination block 130 determines the output control amount for the host vehicle A based on the control target value specified in the action plan.
- the output control amount includes at least one of running speed, acceleration, yaw rate (steering angle), jerk, and yaw acceleration.
- the control amount determination block 130 has an FB control block 131, a prediction control block 132, and an output determination block 133 as blocks whose functions are subdivided.
- the FB control block 131 determines a feedback (FB) control amount according to the running state of the host vehicle A.
- the FB control block 131 compensates for disturbances, modeling errors, etc. by feedback.
- the FB control block 131 determines the FB control amount based on the internal world information of the host vehicle A detected by the internal world sensor 12 and the control target value.
- the predictive control block 132 determines the predictive control amount, which is the future control amount, from the action plan. Predictive control block 132 sets the predictive control amount to compensate for the response delay in host vehicle A.
- FIG. The response delay here is the delay time from sensing timing by the sensor system 10 to control response (see FIG. 4). The delay time can also be expressed as dead time.
- the predictive control block 132 acquires the predictive control amount ahead of the predictive time by adding a margin to the dead time from the action plan.
- Margin is a value for dealing with variations in dead time.
- the margin is set as a complementary value for feedback control phase lead compensation.
- the controlled variable in the action plan that is x(k+5) ahead of the predicted time from the current time is obtained as the predicted controlled variable.
- the predictive control block 132 sets the predictive time according to at least one of the presence or absence of downshift control during acceleration, the braking mode, and the degree of tire deformation during curves.
- the delay time differs depending on whether or not shift down control of the transmission occurs. If the downshift control does not occur, the delay time will be short. On the other hand, when downshifting occurs, the delay time is lengthened under the influence of shift control. For example, without downshifting, a response delay of about 150 msec occurs regardless of the current vehicle speed. In this host vehicle A, when downshifting is performed, a response delay of about 300 msec occurs when downshifting to 1st gear, and about 400msec when downshifting to 2nd gear.
- the prediction control block 132 sets a larger prediction time when there is downshift control than when there is no shift down control. Furthermore, the prediction control block 132 sets a larger prediction time as the number of shifts in downshift control increases.
- the prediction control block 132 sets a larger prediction time as the deceleration start speed is lower.
- the predictive control block 132 sets the predictive time constant regardless of the deceleration start speed when the braking mode is foot braking. If the response characteristic is different from this, the predicted time is set according to the response characteristic.
- the prediction control block 132 sets a smaller prediction time when the traveling speed is in the high speed range than when it is in the middle speed range. On the other hand, the prediction control block 132 sets the prediction time shorter than that in the middle speed range when the running speed is in the low speed range.
- the predicted time may be set according to tire characteristics.
- the output determination block 133 determines the current output control amount based on the FB control amount and the predicted control amount. Specifically, the output determination block 133 calculates the output control amount by multiplying the sum of the FB control amount and the predicted control amount by a gain (for example, 0.5). The output determination block 133 commands the travel system 40 to control the host vehicle A according to the calculated output control amount.
- a vehicle control flow which is a flow of a vehicle control method in which the vehicle control system 100 controls the running of the host vehicle A, will be described below with reference to FIG.
- This vehicle control flow is repeatedly executed while the host vehicle A is running.
- Each "S" in the vehicle control flow represents a plurality of steps executed by a plurality of instructions included in the vehicle control program.
- the recognition block 110 acquires data necessary for the action plan from the sensor system 10, etc., and executes recognition processing on the data.
- the action plan block 120 formulates a future action plan including the host vehicle A's position and motion state.
- the prediction control block 132 acquires the prediction control amount from the action plan.
- the FB control block 131 calculates the FB control amount.
- the control amount calculation block calculates the output control amount and outputs it to the traveling system 40.
- the vehicle control system 100 controls the acceleration/deceleration so as to follow the preceding vehicle while not exceeding the ideal inter-vehicle time (eg, 1.4 seconds) and the set vehicle speed (eg, 30 m/s).
- the target acceleration will hunt because the response to the movement of the preceding vehicle is delayed.
- the predictive control amount for the response delay is not calculated, the speed and the inter-vehicle distance become oscillating if control is executed to maintain the set vehicle speed and the ideal inter-vehicle time.
- the response delay is compensated by calculating the predictive control amount as in the present embodiment, the controllability is improved to be equivalent to that of a vehicle with no dead time as shown in FIG.
- a future action plan including the position and motion state of the host vehicle A is drawn up, a future predicted control amount is obtained from the action plan, and the current control amount is calculated based on the predicted control amount. quantity is determined. Therefore, since the motion state of the host vehicle A is included in the action plan, an error is less likely to occur in the predictive control amount, and the response delay can be compensated for by the predictive control amount. Therefore, deterioration of controllability can be suppressed while improving responsiveness.
- response delays may occur due to noise filtering processing in recognition processing and communication processing of recognition results. Furthermore, if filtering processing is performed to prevent malfunctions, a delay occurs even in judgment processing such as an action plan. In this embodiment, it is possible to collectively compensate for the delay from recognition to control request together with the delay from control request to vehicle response.
- the second embodiment is a modification of the first embodiment.
- the action plan block 120 in S20 formulates multiple types of candidate plans as candidates for the action plan P, and selects an action plan from among the candidate plans.
- the action plan block 120 draws up a plurality of types of candidate plans according to the traveling route of the host vehicle A, for example.
- the action plan block 120 draws up a plurality of candidate plans based on higher-order polynomials, for example, in the Fresnet coordinate system.
- the action plan block 120 includes, as shown in FIG. 10, a candidate plan P3 for a straight route, candidate plans PC1 and PC2 for changing lanes to the left of the straight route, and Candidate plans PC4 and PC5 for types of lane changes are drafted.
- the action plan block 120 evaluates each candidate plan of multiple types based on an evaluation function or the like.
- the action plan block 120 selects the highest rated candidate plan as the action plan P to actually execute.
- the left side of FIG. 10 shows an example in which the straight route candidate plan PC3 is selected as the action plan P in a certain cycle.
- the right side of FIG. 10 shows an example in which the action plan P is switched to the candidate plan PC5 for changing lanes to the right in the next cycle.
- the prediction control block 132 in S30 when the candidate plan selected as the action plan P is changed from the previous time, the action plan before change (plan before change) Pp and the action plan after change P Calculates the predictive control amount according to both. Specifically, the predictive control block 132 calculates a predictive control amount based on the pre-change plan Pp (pre-change predictive control amount) and a predictive control amount based on the post-change action plan P (post-change predictive control amount). do. Then, the predictive control block 132 calculates an intermediate predictive control amount of each target value as a predictive control amount corresponding to the pre-change predictive control amount and the post-change predictive control amount.
- the prediction control block 132 may calculate the average value of the pre-change prediction control amount and the post-change prediction control amount as an intermediate prediction control amount.
- the prediction control block 132 may weight at least one of the pre-change prediction control amount and the post-change prediction control amount to calculate an average value.
- the prediction control block 132 provides this intermediate prediction control amount to the output determination block 133 as a parameter for determining the output control amount.
- the pre-change predicted control amount is schematically indicated by a white circle on the pre-change plan Pp
- the post-change predicted control amount is indicated by a white circle on the action plan P after change. It is schematically indicated by a circle.
- An intermediate predictive control amount is schematically shown as a black circle.
- the output control amount is determined based on the predicted control amount from the action plan P after change and the pre-change predicted control amount from the action plan P before change. Therefore, a large change in the predictive control amount according to a change in the selected action plan P can be suppressed. Therefore, it is possible to suppress the vehicle behavior from becoming unstable.
- the third embodiment is a modification of the first embodiment.
- the action plan block 120 in S20 draws up a plurality of candidate plans as candidates for the action plan P, and selects the candidate plan with the highest evaluation as an action to actually execute. Select as Plan P.
- action plan block 120 predicts candidate plans that will be selected in the future, depending on the evaluation results of each candidate plan.
- the action plan block 120 calculates the gradient of the evaluation value over time for each candidate plan.
- the action plan block 120 calculates the predicted evaluation value of the future cycle according to this gradient for each candidate plan.
- the action plan block 120 may calculate the predicted evaluation value up to a predetermined cycle ahead.
- the action plan block 120 predicts action plans to be selected in the future according to this prediction evaluation value.
- a combined plan Ps is generated as an action plan combining Pn.
- a combined plan Ps is generated as the action plan P by combining the current action plan P in which the candidate plan PC3 is selected and the future plan Pn resulting from the selection of the candidate plan PC5. be.
- the predictive control block 132 in S30 acquires the predictive control amount from this combined plan Ps.
- the predictive controlled variable is schematically shown as a black circle.
- the predicted type of candidate plan is combined with the current action plan. Therefore, since the candidate plan selected as the future action plan is combined with the current action plan, the control amount corresponding to the change in the action plan can be obtained as the predictive control amount. Therefore, it is possible to suppress the vehicle behavior from becoming unstable.
- the action plan block 120 may use MDP (Markov decision process) or DP (dynamic programming) as an action plan estimation method.
- MDP Markov decision process
- DP dynamic programming
- control amount determination block 130 may be a target value filter type two-degree-of-freedom control system instead of the two-degree-of-freedom control system of feedforward control and feedback control.
- the dedicated computer that configures the vehicle control system 100 may have at least one of digital circuits and analog circuits as a processor.
- Digital circuits here include, for example, ASIC (Application Specific Integrated Circuit), FPGA (Field Programmable Gate Array), SOC (System on a Chip), PGA (Programmable Gate Array), and CPLD (Complex Programmable Logic Device).
- ASIC Application Specific Integrated Circuit
- FPGA Field Programmable Gate Array
- SOC System on a Chip
- PGA Programmable Gate Array
- CPLD Complex Programmable Logic Device
- the vehicle control system 100 may be implemented as a vehicle control apparatus that is a processing apparatus (eg, processing ECU, etc.) mounted on the host vehicle A.
- a processing apparatus eg, processing ECU, etc.
- the above-described embodiments and variations may be implemented as a semiconductor device (for example, a semiconductor chip or the like) having at least one processor 102 and at least one memory 101 of the vehicle control system 100 .
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Human Computer Interaction (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
Abstract
This vehicle control system has a processor and controls a host vehicle. The processor of the vehicle control system is configured to establish a future action plan that includes the position and motion state of the host vehicle. The processor is configured to execute acquisition of a predicted control amount at a future predicted time based on a delay time of a response relating to traveling control in the host vehicle from the action plan. The processor is configured to execute determination of a current output control amount corresponding to the predicted control amount.
Description
この出願は、2021年11月30日に日本に出願された特許出願第2021-194047号を基礎としており、基礎の出願の内容を、全体的に、参照により援用している。
This application is based on Patent Application No. 2021-194047 filed in Japan on November 30, 2021, and the content of the underlying application is incorporated by reference in its entirety.
本開示は、ホスト車両を制御する車両制御技術に、関する。
The present disclosure relates to vehicle control technology for controlling a host vehicle.
特許文献1には、目標軌道に追従して自動走行する車両の運動の制御における時間遅れを補償する技術が開示されている。この技術では、自車位置と目標軌道における目標位置との偏差を減らすための運動指令を与えたときの車両挙動を予測し、先の時刻における自車位置を予測する。そして、予測した自車位置からさらに先の時刻における車両挙動を同様に予測し、さらに先の時刻における自車位置を予測する。特許文献1では、この処理を繰り返すことで、所定時間先の車両運動の指令値を予測し、当該指令値を出力させる。
Patent Document 1 discloses a technique for compensating for the time delay in motion control of a vehicle that automatically runs following a target trajectory. This technology predicts the vehicle behavior when a motion command is given to reduce the deviation between the vehicle position and the target position on the target trajectory, and predicts the vehicle position at the previous time. Then, the vehicle behavior at a time later than the predicted vehicle position is similarly predicted, and the vehicle position at a further time is predicted. In Patent Literature 1, by repeating this process, a command value for vehicle motion a predetermined time ahead is predicted, and the command value is output.
特許文献1の技術では、目標軌道における目標位置との偏差を減らすための指令値をサンプリング時間ごとに順次予測するため、予測誤差が累積し、制御性が悪化する虞がある。
With the technique of Patent Document 1, the command value for reducing the deviation from the target position on the target trajectory is sequentially predicted for each sampling time, so there is a risk that prediction errors will accumulate and controllability will deteriorate.
本開示の課題は、制御性の悪化を抑制し、且つ応答性を向上させることが可能な車両制御システムを、提供することにある。本開示の別の課題は、制御性の悪化を抑制し、且つ応答性を向上させることが可能な車両制御装置を提供することにある。本開示のさらに別の課題は、制御性の悪化を抑制し、且つ応答性を向上させることが可能な車両制御方法を、提供することにある。本開示のさらに別の課題は、制御性の悪化を抑制し、且つ応答性を向上させることが可能な車両制御プログラムを、提供することにある。
An object of the present disclosure is to provide a vehicle control system capable of suppressing deterioration of controllability and improving responsiveness. Another object of the present disclosure is to provide a vehicle control device capable of suppressing deterioration of controllability and improving responsiveness. Still another object of the present disclosure is to provide a vehicle control method capable of suppressing deterioration of controllability and improving responsiveness. Yet another object of the present disclosure is to provide a vehicle control program capable of suppressing deterioration of controllability and improving responsiveness.
以下、課題を解決するための本開示の技術的手段について、説明する。尚、請求の範囲及び本欄に記載された括弧内の符号は、後に詳述する実施形態に記載された具体的手段との対応関係を示すものであり、本開示の技術的範囲を限定するものではない。
The technical means of the present disclosure for solving the problems will be described below. It should be noted that the symbols in parentheses described in the claims and this column indicate the correspondence with specific means described in the embodiments described in detail later, and limit the technical scope of the present disclosure. not a thing
本開示の第一態様は、プロセッサを有し、ホスト車両を制御する車両制御システムであって、
プロセッサは、
ホスト車両の位置及び運動状態を含む将来の行動計画を立案することと、
行動計画から、ホスト車両における走行制御に関する応答の遅れ時間に基づく予測時間先での予測制御量を取得することと、
予測制御量に応じた現在の出力制御量を決定することと、
を実行するように構成される。 A first aspect of the present disclosure is a vehicle control system having a processor and controlling a host vehicle, comprising:
The processor
developing a future action plan including the position and motion state of the host vehicle;
Acquiring a predicted control amount in the predicted time ahead based on the delay time of the response regarding travel control in the host vehicle from the action plan;
Determining a current output control amount according to the predicted control amount;
configured to run
プロセッサは、
ホスト車両の位置及び運動状態を含む将来の行動計画を立案することと、
行動計画から、ホスト車両における走行制御に関する応答の遅れ時間に基づく予測時間先での予測制御量を取得することと、
予測制御量に応じた現在の出力制御量を決定することと、
を実行するように構成される。 A first aspect of the present disclosure is a vehicle control system having a processor and controlling a host vehicle, comprising:
The processor
developing a future action plan including the position and motion state of the host vehicle;
Acquiring a predicted control amount in the predicted time ahead based on the delay time of the response regarding travel control in the host vehicle from the action plan;
Determining a current output control amount according to the predicted control amount;
configured to run
本開示の第二態様は、プロセッサを有し、ホスト車両を制御する車両制御装置であって、
プロセッサは、
ホスト車両の位置及び運動状態を含む将来の行動計画を立案することと、
行動計画から、ホスト車両における走行制御に関する応答の遅れ時間に基づく予測時間先での予測制御量を取得することと、
予測制御量に応じた現在の出力制御量を決定することと、
を実行するように構成される。 A second aspect of the present disclosure is a vehicle control device having a processor and controlling a host vehicle,
The processor
developing a future action plan including the position and motion state of the host vehicle;
Acquiring a predicted control amount in the predicted time ahead based on the delay time of the response regarding travel control in the host vehicle from the action plan;
Determining a current output control amount according to the predicted control amount;
configured to run
プロセッサは、
ホスト車両の位置及び運動状態を含む将来の行動計画を立案することと、
行動計画から、ホスト車両における走行制御に関する応答の遅れ時間に基づく予測時間先での予測制御量を取得することと、
予測制御量に応じた現在の出力制御量を決定することと、
を実行するように構成される。 A second aspect of the present disclosure is a vehicle control device having a processor and controlling a host vehicle,
The processor
developing a future action plan including the position and motion state of the host vehicle;
Acquiring a predicted control amount in the predicted time ahead based on the delay time of the response regarding travel control in the host vehicle from the action plan;
Determining a current output control amount according to the predicted control amount;
configured to run
本開示の第三態様は、ホスト車両を制御するために、プロセッサにより実行される車両制御方法であって、
ホスト車両の位置及び運動状態を含む将来の行動計画を立案することと、
行動計画から、ホスト車両における走行制御に関する応答の遅れ時間に基づく予測時間先での予測制御量を取得することと、
予測制御量に応じた現在の出力制御量を決定することと、
を含む。 A third aspect of the present disclosure is a vehicle control method executed by a processor to control a host vehicle, comprising:
developing a future action plan including the position and motion state of the host vehicle;
Acquiring a predicted control amount in the predicted time ahead based on the delay time of the response regarding travel control in the host vehicle from the action plan;
Determining a current output control amount according to the predicted control amount;
including.
ホスト車両の位置及び運動状態を含む将来の行動計画を立案することと、
行動計画から、ホスト車両における走行制御に関する応答の遅れ時間に基づく予測時間先での予測制御量を取得することと、
予測制御量に応じた現在の出力制御量を決定することと、
を含む。 A third aspect of the present disclosure is a vehicle control method executed by a processor to control a host vehicle, comprising:
developing a future action plan including the position and motion state of the host vehicle;
Acquiring a predicted control amount in the predicted time ahead based on the delay time of the response regarding travel control in the host vehicle from the action plan;
Determining a current output control amount according to the predicted control amount;
including.
本開示の第四態様は、ホスト車両を制御するために記憶媒体に記憶され、プロセッサに実行させる命令を含む車両制御プログラムであって、
命令は、
ホスト車両の位置及び運動状態を含む将来の行動計画を立案させることと、
行動計画から、ホスト車両における走行制御に関する応答の遅れ時間に基づく予測時間先での予測制御量を取得させることと、
予測制御量に応じた現在の出力制御量を決定させることと、
を含む。 A fourth aspect of the present disclosure is a vehicle control program stored in a storage medium and including instructions to be executed by a processor to control a host vehicle, comprising:
the instruction is
allowing future action plans to be developed including the position and motion state of the host vehicle;
Obtaining from the action plan a predicted control amount in the predicted time ahead based on the response delay time regarding travel control in the host vehicle;
determining a current output control amount according to the predicted control amount;
including.
命令は、
ホスト車両の位置及び運動状態を含む将来の行動計画を立案させることと、
行動計画から、ホスト車両における走行制御に関する応答の遅れ時間に基づく予測時間先での予測制御量を取得させることと、
予測制御量に応じた現在の出力制御量を決定させることと、
を含む。 A fourth aspect of the present disclosure is a vehicle control program stored in a storage medium and including instructions to be executed by a processor to control a host vehicle, comprising:
the instruction is
allowing future action plans to be developed including the position and motion state of the host vehicle;
Obtaining from the action plan a predicted control amount in the predicted time ahead based on the response delay time regarding travel control in the host vehicle;
determining a current output control amount according to the predicted control amount;
including.
これら第一~第四態様によると、ホスト車両の位置に加えて運動状態を含む行動計画から取得された予測制御量に応じて、現在の出力制御量が決定される。故に、予測誤差が小さくなり、且つ応答遅れが補償され得る。したがって、制御性の悪化を抑制し、且つ応答性を向上させることが可能となり得る。
According to these first to fourth aspects, the current output control amount is determined according to the predicted control amount obtained from the action plan including the motion state in addition to the position of the host vehicle. Therefore, the prediction error becomes small and the response delay can be compensated. Therefore, it may be possible to suppress deterioration of controllability and improve responsiveness.
以下、本開示の実施形態を図面に基づき複数説明する。尚、各実施形態において対応する構成要素には同一の符号を付すことで、重複する説明を省略する場合がある。また、各実施形態において構成の一部分のみを説明している場合、当該構成の他の部分については、先行して説明した他の実施形態の構成を適用することができる。さらに、各実施形態の説明において明示している構成の組み合わせばかりではなく、特に組み合わせに支障が生じなければ、明示していなくても複数の実施形態の構成同士を部分的に組み合わせることができる。
A plurality of embodiments of the present disclosure will be described below based on the drawings. Note that redundant description may be omitted by assigning the same reference numerals to corresponding components in each embodiment. Moreover, when only a part of the configuration is described in each embodiment, the configurations of the other embodiments previously described can be applied to the other portions of the configuration. Furthermore, not only the combinations of the configurations explicitly specified in the description of each embodiment, but also the configurations of the multiple embodiments can be partially combined even if they are not explicitly specified unless there is a particular problem with the combination.
(第一実施形態)
図1に示す第一実施形態の車両制御システム100は、図2に示すホスト車両Aの走行を制御する。ホスト車両Aを中心とする視点において、ホスト車両Aは自車両(ego-vehicle)であるともいえる。ホスト車両Aを中心とする視点において、ターゲット車両Bは他道路ユーザであるともいえる。 (First embodiment)
Avehicle control system 100 of the first embodiment shown in FIG. 1 controls running of a host vehicle A shown in FIG. From a viewpoint centering on the host vehicle A, the host vehicle A can also be said to be an ego-vehicle. From the viewpoint centered on the host vehicle A, the target vehicle B can also be said to be a user on another road.
図1に示す第一実施形態の車両制御システム100は、図2に示すホスト車両Aの走行を制御する。ホスト車両Aを中心とする視点において、ホスト車両Aは自車両(ego-vehicle)であるともいえる。ホスト車両Aを中心とする視点において、ターゲット車両Bは他道路ユーザであるともいえる。 (First embodiment)
A
ホスト車両Aにおいては、運転タスクにおける乗員の手動介入度に応じてレベル分けされる、自動運転モードが与えられる。自動運転モードは、条件付運転自動化、高度運転自動化、又は完全運転自動化といった、作動時のシステムが全ての運転タスクを実行する自律走行制御により、実現されてもよい。自動運転モードは、運転支援、又は部分運転自動化といった、乗員が一部若しくは全ての運転タスクを実行する高度運転支援制御により、実現されてもよい。自動運転モードは、それら自律走行制御と高度運転支援制御とのいずれか一方、組み合わせ、又は切り替えにより実現されてもよい。
In the host vehicle A, an automatic driving mode is given, which is divided into levels according to the degree of manual intervention of the driver in the driving task. Autonomous driving modes may be achieved by autonomous cruise control, such as conditional driving automation, advanced driving automation, or full driving automation, in which the system performs all driving tasks when activated. Autonomous driving modes may be provided by advanced driving assistance controls, such as driving assistance or partial driving automation, in which the occupant performs some or all driving tasks. The automatic driving mode may be realized by either one, combination, or switching of the autonomous driving control and advanced driving support control.
ホスト車両Aには、図3に示すセンサ系10、通信系20、地図データベース(以下、「DB」)30、及び走行系40が搭載される。センサ系10は、車両制御システム100により利用可能なセンサ情報を、ホスト車両Aの外界及び内界の検出により取得する。そのためにセンサ系10は、外界センサ11及び内界センサ12を含んで構成されている。
The host vehicle A is equipped with a sensor system 10, a communication system 20, a map database (hereinafter referred to as "DB") 30, and a traveling system 40 shown in FIG. The sensor system 10 acquires sensor information that can be used by the vehicle control system 100 by detecting the external and internal worlds of the host vehicle A. FIG. For this purpose, the sensor system 10 includes an external sensor 11 and an internal sensor 12 .
外界センサ11は、ホスト車両Aの周辺環境となる外界から、車両制御システム100により利用可能な外界情報を取得する。外界センサ11は、ホスト車両Aの外界に存在する物標を検知することで、外界情報を取得してもよい。物標検知タイプの外界センサ11は、例えばカメラ、LiDAR(Light Detection and Ranging / Laser Imaging Detection and Ranging)、レーダ、及びソナー等のうち、少なくとも一種類である。
The external world sensor 11 acquires external world information that can be used by the vehicle control system 100 from the external world that is the surrounding environment of the host vehicle A. The external world sensor 11 may acquire external world information by detecting a target existing in the external world of the host vehicle A. The target detection type external sensor 11 is, for example, at least one type of camera, LiDAR (Light Detection and Ranging/Laser Imaging Detection and Ranging), radar, sonar, and the like.
外界センサ11は、ホスト車両Aの外界に存在するGNSS(Global Navigation Satellite System)の人工衛星から測位信号を受信することで、外界情報を取得してもよい。測位タイプの外界センサ11は、例えばGNSS受信機等である。外界センサ11は、ホスト車両Aの外界に存在するV2Xシステムとの間において通信信号を送受信することで、外界情報を取得してもよい。通信タイプの外界センサ11は、例えばDSRC(Dedicated Short Range Communications)通信機、セルラV2X(C-V2X)通信機、Bluetooth(登録商標)機器、Wi-Fi(登録商標)機器、及び赤外線通信機器等のうち、少なくとも一種類である。
The external sensor 11 may acquire external world information by receiving positioning signals from satellites of the GNSS (Global Navigation Satellite System) existing in the external world of the host vehicle A. The positioning type external sensor 11 is, for example, a GNSS receiver or the like. The external world sensor 11 may acquire external world information by transmitting and receiving communication signals to and from a V2X system existing in the external world of the host vehicle A. The communication type external sensor 11 is, for example, a DSRC (Dedicated Short Range Communications) communication device, a cellular V2X (C-V2X) communication device, a Bluetooth (registered trademark) device, a Wi-Fi (registered trademark) device, an infrared communication device, or the like. at least one of
内界センサ12は、ホスト車両Aの内部環境となる内界から、車両制御システム100により利用可能な内界情報を取得する。内界センサ12は、ホスト車両Aの内界において特定の運動物理量を検知することで、内界情報を取得してもよい。物理量検知タイプの内界センサ12は、例えば走行速度センサ、加速度センサ、及びジャイロセンサ等のうち、少なくとも一種類である。
The inner world sensor 12 acquires inner world information that can be used by the vehicle control system 100 from the inner world that is the internal environment of the host vehicle A. The inner world sensor 12 may acquire inner world information by detecting a specific kinematic physical quantity in the inner world of the host vehicle A. FIG. The physical quantity sensing type internal sensor 12 is at least one of, for example, a running speed sensor, an acceleration sensor, a gyro sensor, and the like.
通信系20は、車両制御システム100により利用可能な通信情報を、無線通信により取得する。通信系20は、ホスト車両Aの外界に存在するGNSS(Global Navigation Satellite System)の人工衛星から、測位信号を受信してもよい。測位タイプの通信系20は、例えばGNSS受信機等である。通信系20は、ホスト車両Aの外界に存在するV2Xシステムとの間において、通信信号を送受信してもよい。V2Xタイプの通信系20は、例えばDSRC(Dedicated Short Range Communications)通信機、及びセルラV2X(C-V2X)通信機等のうち、少なくとも一種類である。通信系20は、ホスト車両Aの内界に存在する端末との間において、通信信号を送受信してもよい。端末通信タイプの通信系20は、例えばBluetooth(登録商標)機器、Wi-Fi(登録商標)機器、及び赤外線通信機器等のうち、少なくとも一種類である。
The communication system 20 acquires communication information that can be used by the vehicle control system 100 by wireless communication. The communication system 20 may receive positioning signals from artificial satellites of the GNSS (Global Navigation Satellite System) existing outside the host vehicle A. The positioning type communication system 20 is, for example, a GNSS receiver or the like. The communication system 20 may transmit and receive communication signals to and from a V2X system existing outside the host vehicle A. The V2X type communication system 20 is, for example, at least one of a DSRC (Dedicated Short Range Communications) communication device, a cellular V2X (C-V2X) communication device, and the like. The communication system 20 may transmit and receive communication signals to and from terminals existing in the inner world of the host vehicle A. FIG. The terminal communication type communication system 20 is, for example, at least one of Bluetooth (registered trademark) equipment, Wi-Fi (registered trademark) equipment, infrared communication equipment, and the like.
地図DB30は、車両制御システム100により利用可能な地図情報を、記憶する。地図DB30は、例えば半導体メモリ、磁気媒体、及び光学媒体等のうち、少なくとも一種類の非遷移的実体的記憶媒体(non-transitory tangible storage medium)を含んで構成される。地図DB30は、ホスト車両Aの自己位置を含む自己状態量を推定するロケータの、データベースであってもよい。地図DB30は、ホスト車両Aの走行経路をナビゲートするナビゲーションユニットの、データベースであってもよい。地図DB30は、これらのデータベース等のうち複数種類の組み合わせにより、構成されていてもよい。
The map DB 30 stores map information that can be used by the vehicle control system 100. The map DB 30 includes at least one type of non-transitory tangible storage medium, such as semiconductor memory, magnetic medium, and optical medium. The map DB 30 may be a database of a locator for estimating the host vehicle A's own state quantity including its own position. The map DB 30 may be a database of a navigation unit that navigates the travel route of the host vehicle A. FIG. The map DB 30 may be configured by combining a plurality of types of these databases.
地図DB30は、例えばV2Xタイプの通信系20を介した外部センタとの通信等により、最新の地図情報を取得して記憶する。ここで地図情報は、ホスト車両Aの走行環境を表す情報として、二次元又は三次元にデータ化されている。特に三次元の地図データとしては、高精度地図のデジタルデータが採用されるとよい。地図情報は、例えば道路自体の位置、形状、及び路面状態等のうち、少なくとも一種類を表した道路情報を含んでいてもよい。地図情報は、例えば道路に付属する標識及び区画線の位置並びに形状等のうち、少なくとも一種類を表した標示情報を含んでいてもよい。地図情報は、例えば道路に面する建造物及び信号機の位置並びに形状等のうち、少なくとも一種類を表した構造物情報を含んでいてもよい。
The map DB 30 acquires and stores the latest map information through communication with an external center via the V2X type communication system 20, for example. Here, the map information is data representing the running environment of the host vehicle A in two or three dimensions. In particular, as the three-dimensional map data, digital data of a high-precision map should be adopted. The map information may include road information representing at least one of the position, shape, road surface condition, and the like of the road itself. The map information may include sign information representing at least one of the position and shape of signs attached to roads and lane markings, for example. The map information may include structure information representing at least one of the positions and shapes of buildings facing roads and traffic lights, for example.
走行系40は、車両制御システム100からの指令に基づきホスト車両Aの車体を走行させる構成である。走行系40は、ホスト車両Aを駆動させる駆動ユニット、ホスト車両Aを制動する制動ユニット及びホスト車両Aを操舵する操舵ユニットを含む。
The running system 40 is configured to run the body of the host vehicle A based on commands from the vehicle control system 100 . The travel system 40 includes a drive unit that drives the host vehicle A, a braking unit that brakes the host vehicle A, and a steering unit that steers the host vehicle A. FIG.
車両制御システム100は、例えばLAN(Local Area Network)回線、ワイヤハーネス、内部バス、及び無線通信回線等のうち、少なくとも一種類を介してセンサ系10、通信系20、地図DB30及び走行系40に接続されている。車両制御システム100は、少なくとも一つの専用コンピュータを含んで構成されている。
The vehicle control system 100 is connected to the sensor system 10, the communication system 20, the map DB 30, and the traveling system 40 via at least one of a LAN (Local Area Network) line, a wire harness, an internal bus, a wireless communication line, and the like. It is connected. The vehicle control system 100 includes at least one dedicated computer.
車両制御システム100を構成する専用コンピュータは、ホスト車両Aの運転を制御する、運転制御ECU(Electronic Control Unit)であってもよい。車両制御システム100を構成する専用コンピュータは、ホスト車両Aの走行経路をナビゲートする、ナビゲーションECUであってもよい。車両制御システム100を構成する専用コンピュータは、ホスト車両Aの自己状態量を推定する、ロケータECUであってもよい。車両制御システム100を構成する専用コンピュータは、ホスト車両Aの走行アクチュエータを制御する、アクチュエータECUであってもよい。車両制御システム100を構成する専用コンピュータは、ホスト車両Aにおける情報提示を制御する、HCU(HMI(Human Machine Interface) Control Unit)であってもよい。車両制御システム100を構成する専用コンピュータは、例えばV2Xタイプの通信系20を介して通信可能な外部センタ又はモバイル端末等を構成する、ホスト車両A以外のコンピュータであってもよい。
The dedicated computer that configures the vehicle control system 100 may be an operation control ECU (Electronic Control Unit) that controls the operation of the host vehicle A. A dedicated computer that configures the vehicle control system 100 may be a navigation ECU that navigates the travel route of the host vehicle A. FIG. A dedicated computer that configures the vehicle control system 100 may be a locator ECU that estimates the host vehicle A's self-state quantity. The dedicated computer that configures the vehicle control system 100 may be an actuator ECU that controls the travel actuators of the host vehicle A. FIG. The dedicated computer that configures the vehicle control system 100 may be an HCU (Human Machine Interface) Control Unit (HCU) that controls information presentation in the host vehicle A. The dedicated computer that configures the vehicle control system 100 may be a computer other than the host vehicle A that configures an external center or a mobile terminal that can communicate via the V2X type communication system 20, for example.
車両制御システム100を構成する専用コンピュータは、ホスト車両Aの運転制御を統合する、統合ECU(Electronic Control Unit)であってもよい。車両制御システム100を構成する専用コンピュータは、ホスト車両Aの運転制御における運転タスクを判断する、判断ECUであってもよい。車両制御システム100を構成する専用コンピュータは、ホスト車両Aの運転制御を監視する、監視ECUであってもよい。車両制御システム100を構成する専用コンピュータは、ホスト車両Aの運転制御を評価する、評価ECUであってもよい。
The dedicated computer that configures the vehicle control system 100 may be an integrated ECU (Electronic Control Unit) that integrates the operation control of the host vehicle A. The dedicated computer that constitutes the vehicle control system 100 may be a judgment ECU that judges the driving task in the driving control of the host vehicle A. FIG. A dedicated computer that configures the vehicle control system 100 may be a monitoring ECU that monitors the operation control of the host vehicle A. FIG. The dedicated computer that configures the vehicle control system 100 may be an evaluation ECU that evaluates the operation control of the host vehicle A. FIG.
車両制御システム100を構成する専用コンピュータは、メモリ101及びプロセッサ102を、少なくとも一つずつ有している。メモリ101は、コンピュータにより読み取り可能なプログラム及びデータ等を非一時的に記憶する、例えば半導体メモリ、磁気媒体、及び光学媒体等のうち、少なくとも一種類の非遷移的実体的記憶媒体(non-transitory tangible storage medium)である。プロセッサ102は、例えばCPU(Central Processing Unit)、GPU(Graphics Processing Unit)、RISC(Reduced Instruction Set Computer)-CPU、DFP(Data Flow Processor)、及びGSP(Graph Streaming Processor)等のうち、少なくとも一種類をコアとして含んでいる。
A dedicated computer that constitutes the vehicle control system 100 has at least one memory 101 and at least one processor 102 . The memory 101 stores computer-readable programs, data, etc., non-temporarily, and includes at least one type of non-transitory storage medium such as a semiconductor memory, a magnetic medium, and an optical medium. tangible storage medium). The processor 102 is, for example, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a RISC (Reduced Instruction Set Computer)-CPU, a DFP (Data Flow Processor), and a GSP (Graph Streaming Processor). as a core.
車両制御システム100においてプロセッサ102は、ホスト車両Aを制御するためにメモリ101に記憶された、車両制御プログラムに含まれる複数の命令を実行する。これにより車両制御システム100は、ホスト車両Aを制御するための機能ブロックを、複数構築する。車両制御システム100において構築される複数の機能ブロックには、図3に示すように認識ブロック110、行動計画ブロック120及び制御量決定ブロック130が含まれている。
In the vehicle control system 100, the processor 102 executes a plurality of instructions contained in the vehicle control program stored in the memory 101 to control the host vehicle A. Accordingly, the vehicle control system 100 constructs a plurality of functional blocks for controlling the host vehicle A. FIG. A plurality of functional blocks constructed in the vehicle control system 100 include a recognition block 110, an action plan block 120 and a control amount determination block 130 as shown in FIG.
認識ブロック110は、外界センサ11による外界情報、及び内界センサ12による内界情報に基づいて、ホスト車両A周辺の環境、及びホスト車両Aの状態を認識する認識処理を実行する。ホスト車両A周辺の環境は、例えば、周辺の移動体に関する位置及び速度情報、路面標示や道路沿いの構造物、道路端等の地物に関する位置情報等の少なくとも一種類を含む。ホスト車両Aの状態は、例えば、ホスト車両Aの自己位置、速度、加速度、操舵角、及びヨーレート等のうち少なくとも一種類を含む。認識ブロック110は、認識処理の直前に取得された各センサ11,12の情報を用いて、認識処理を実行する。
The recognition block 110 executes recognition processing for recognizing the environment around the host vehicle A and the state of the host vehicle A based on the external world information from the external sensor 11 and the internal world information from the internal sensor 12 . The environment around the host vehicle A includes, for example, at least one type of information such as position and speed information about surrounding moving bodies, position information about features such as road markings, structures along the road, and road edges. The state of the host vehicle A includes, for example, at least one of host vehicle A's own position, speed, acceleration, steering angle, yaw rate, and the like. The recognition block 110 executes recognition processing using information of the sensors 11 and 12 acquired immediately before recognition processing.
認識ブロック110は、各センサ11,12における情報の検出時刻と、認識処理の実行時刻とのずれを、認識対象物及びホスト車両Aの動きモデルに基づいて補正してもよい。又は、認識ブロック110は、時刻のずれ分に相当する認識対象物又はホスト車両Aの移動量を、誤差として行動計画ブロック120に提供してもよい。尚、認識ブロック110は、ずれを補正した場合でも、予測誤差を行動計画ブロック120に提供する。
The recognition block 110 may correct the deviation between the detection time of information in each of the sensors 11 and 12 and the execution time of the recognition process based on the motion model of the recognition target object and the host vehicle A. Alternatively, the recognition block 110 may provide the movement amount of the recognition object or the host vehicle A corresponding to the time lag to the action planning block 120 as an error. Note that the recognition block 110 provides prediction errors to the action planning block 120 even when corrected for deviations.
行動計画ブロック120は、ホスト車両Aの将来の行動計画を立案する。行動計画は、ホスト車両Aの将来の位置及び運動状態を制御目標値として含んでいる。行動計画は、これらの情報を将来の所定の時間ごとに規定する時系列情報である。ここでホスト車両Aの運動状態は、速度、加速度、ヨー角、及びヨーレート等の少なくとも一種類以上を含んでいる。運動状態は、さらに、ピッチ角、ピッチレート及びピッチ加速度等を含んでいてもよい。こうした情報を含む行動計画は、ホスト車両Aの走行軌道と表現することもできる。
The action plan block 120 draws up a future action plan for the host vehicle A. The action plan includes the future position and motion state of the host vehicle A as control target values. The action plan is chronological information that defines these pieces of information at predetermined times in the future. Here, the motion state of the host vehicle A includes at least one or more of speed, acceleration, yaw angle, yaw rate, and the like. Motion states may also include pitch angle, pitch rate, pitch acceleration, and the like. An action plan including such information can also be expressed as a traveling trajectory of the host vehicle A. FIG.
行動計画ブロック120は、ホスト車両Aの行動を制約する制約条件下にて、行動計画を立案する。制約条件には、ホスト車両Aが走行可能な走行可能領域に収まる領域条件が含まれる。行動計画ブロック120は、周辺情報及び自車情報に基づいて、ホスト車両Aの走行可能領域を推定する。行動計画ブロック120は、この走行可能領域内でホスト車両Aの行動計画を生成する。加えて、制約条件には、車両モデル及び障害物モデルが含まれる。具体的には、制約条件には、ホスト車両Aの制御量が許容範囲内に収まること、障害物と接触しないこと等が含まれる。行動計画ブロック120は、これらの制約条件下にて、行動計画を立案する。
The action plan block 120 draws up an action plan under the constraint conditions that restrict the action of the host vehicle A. Constraint conditions include an area condition under which the host vehicle A can be accommodated within a travelable area. The action plan block 120 estimates the travelable area of the host vehicle A based on the surrounding information and the own vehicle information. Action plan block 120 generates a plan of action for host vehicle A within this drivable area. In addition, constraints include vehicle models and obstacle models. Specifically, the constraint conditions include that the control amount of the host vehicle A should be within an allowable range, that the host vehicle should not come into contact with obstacles, and the like. Action plan block 120 formulates an action plan under these constraints.
詳記すると、行動計画ブロック120は、制約条件の下で、行動計画を最適化する。例えば、状態変数及び制御変数をz、コスト関数をL(z,k)、予測点をNとすると、行動計画の評価関数f(z)は、以下の数式(1)で与えられる。評価関数は、例えば規定車間距離の維持、目標車速の維持、急加減速の回避、走路に沿った走行等について数式化したパラメータを、重み付け線形結合したものとされる。
Specifically, action plan block 120 optimizes the action plan under constraints. For example, if z is the state variable and the control variable, L(z, k) is the cost function, and N is the prediction point, the evaluation function f(z) of the action plan is given by the following formula (1). The evaluation function is a weighted linear combination of mathematical parameters for maintaining a prescribed inter-vehicle distance, maintaining a target vehicle speed, avoiding sudden acceleration and deceleration, traveling along a road, and the like.
行動計画ブロック120は、例えば、以下の車両運動に関する制約条件を示す数式(2)及び走行環境に関する制約条件を示す数式(3)を満たし、且つf(z)が予測ホライズンにわたって最小の値となる変数zを、行動計画を規定するパラメータとして設定する。ここで予測ホライズンは、図2に示すような、現在時刻から将来時刻までの行動計画が規定される時間区間である。
The action plan block 120 satisfies, for example, the following vehicle motion constraint equation (2) and driving environment constraint equation (3), and f(z) is the minimum value over the predicted horizon: A variable z is set as a parameter that defines the action plan. Here, the prediction horizon is a time interval in which an action plan from the current time to the future time is defined, as shown in FIG.
制御量決定ブロック130は、行動計画において規定された制御目標値に基づいてホスト車両Aにおける出力制御量を決定する。出力制御量は、走行速度、加速度、ヨーレート(操舵角)、ジャーク及びヨー加速度等の少なくとも一種類を含んでいる。制御量決定ブロック130は、より機能を細分化したブロックとして、FB制御ブロック131、予測制御ブロック132、及び出力決定ブロック133を有する。
The control amount determination block 130 determines the output control amount for the host vehicle A based on the control target value specified in the action plan. The output control amount includes at least one of running speed, acceleration, yaw rate (steering angle), jerk, and yaw acceleration. The control amount determination block 130 has an FB control block 131, a prediction control block 132, and an output determination block 133 as blocks whose functions are subdivided.
FB制御ブロック131は、ホスト車両Aの走行状態に応じたフィードバック(FB)制御量を決定する。FB制御ブロック131は、外乱及びモデル化誤差等を、フィードバックにより補償する。FB制御ブロック131は、内界センサ12によって検出されたホスト車両Aの内界情報等と、制御目標値に基づき、FB制御量を決定する。
The FB control block 131 determines a feedback (FB) control amount according to the running state of the host vehicle A. The FB control block 131 compensates for disturbances, modeling errors, etc. by feedback. The FB control block 131 determines the FB control amount based on the internal world information of the host vehicle A detected by the internal world sensor 12 and the control target value.
予測制御ブロック132は、行動計画から将来の制御量である予測制御量を決定する。予測制御ブロック132は、ホスト車両Aにおける応答遅れを補償するように予測制御量を設定する。ここでの応答遅れは、センサ系10によるセンシングタイミングから制御応答までの遅れ時間である(図4参照)。遅れ時間は、むだ時間と表現することもできる。
The predictive control block 132 determines the predictive control amount, which is the future control amount, from the action plan. Predictive control block 132 sets the predictive control amount to compensate for the response delay in host vehicle A. FIG. The response delay here is the delay time from sensing timing by the sensor system 10 to control response (see FIG. 4). The delay time can also be expressed as dead time.
予測制御ブロック132は、むだ時間にマージンを加えた予測時間先における予測制御量を、行動計画から取得する。マージンは、むだ時間の変動に対処するための値である。マージンは、フィードバック制御の位相進み補償を補完する値として設定される。図2に示す例では、現在時刻からx(k+5)の分だけ予測時間先の行動計画における制御量が、予測制御量として取得される。
The predictive control block 132 acquires the predictive control amount ahead of the predictive time by adding a margin to the dead time from the action plan. Margin is a value for dealing with variations in dead time. The margin is set as a complementary value for feedback control phase lead compensation. In the example shown in FIG. 2, the controlled variable in the action plan that is x(k+5) ahead of the predicted time from the current time is obtained as the predicted controlled variable.
予測制御ブロック132は、加速時におけるシフトダウン制御の発生有無、制動態様、及びカーブ時におけるタイヤ変形度合の少なくとも一種類に応じて、予測時間を設定する。
The predictive control block 132 sets the predictive time according to at least one of the presence or absence of downshift control during acceleration, the braking mode, and the degree of tire deformation during curves.
目標加速度で車両制御する場合を考える。目標加速度が大きい時は、スロットルの制御量が大きくなる。この場合、トランスミッションのシフトダウン制御が発生するかしないかによって、遅れ時間が異なる。シフトダウン制御が発生しない場合は、遅れ時間は短くなる。一方で、シフトダウンが発生する場合は、シフト制御の影響を受けて遅れ時間が長くなる。例えば、シフトダウン無しの場合は、現在車速によらず、約150msecの応答遅れが発生する。このホスト車両Aにおいて、シフトダウン有りの場合は1速シフトダウンする場合は、約300msec、2速シフトダウンする場合は、約400msecの応答遅れが発生する。
Consider the case of vehicle control with a target acceleration. When the target acceleration is large, the control amount of the throttle becomes large. In this case, the delay time differs depending on whether or not shift down control of the transmission occurs. If the downshift control does not occur, the delay time will be short. On the other hand, when downshifting occurs, the delay time is lengthened under the influence of shift control. For example, without downshifting, a response delay of about 150 msec occurs regardless of the current vehicle speed. In this host vehicle A, when downshifting is performed, a response delay of about 300 msec occurs when downshifting to 1st gear, and about 400msec when downshifting to 2nd gear.
したがって、予測制御ブロック132は、シフトダウン制御がある場合には、ない場合よりも予測時間を大きく設定する。さらに、予測制御ブロック132は、シフトダウン制御におけるシフト数が大きいほど、予測時間を大きく設定する。
Therefore, the prediction control block 132 sets a larger prediction time when there is downshift control than when there is no shift down control. Furthermore, the prediction control block 132 sets a larger prediction time as the number of shifts in downshift control increases.
目標減速度で車両制御する場合を考える。スロットルオフによるエンジンブレーキの利き具合は、現車速によって若干異なる。車速が高い時は遅れが小さく、車速が低い時は遅れが大きい。例えば、高速域(例えば80km/h~)には、200msec、中速域(例えば40~80km/h)には、約250msec、低速域(例えば~40km/h)には、約300msecの遅れが発生する。フットブレーキによる減速は、ブレーキ油圧の応答遅れが主要因のため、車速によって遅れ時間に大きな変化は無い。アクチュエータの応答特性は加圧量によらずほぼ一定なので、目標減速量にも応答性は依存せず、約300msecで一定である。
Consider the case of vehicle control with a target deceleration. The effect of engine braking by throttle off varies slightly depending on the current vehicle speed. When the vehicle speed is high, the delay is small, and when the vehicle speed is low, the delay is large. For example, there is a delay of 200msec in the high speed range (eg 80km/h), about 250msec in the medium speed range (eg 40-80km/h), and about 300msec in the low speed range (eg ~40km/h). Occur. Since the deceleration by the footbrake is mainly caused by the response delay of the brake hydraulic pressure, the delay time does not change significantly depending on the vehicle speed. Since the response characteristic of the actuator is substantially constant regardless of the amount of pressurization, the response does not depend on the target deceleration amount and is constant at about 300 msec.
したがって、予測制御ブロック132は、制動態様がエンジンブレーキである場合には、減速開始速度が小さいほど、予測時間を大きく設定する。一方で、予測制御ブロック132は、制動態様がフットブレーキである場合には、減速開始速度に関わらず、予測時間を一定に設定する。これとは異なる応答特性である場合は、その応答特性に応じて、予測時間を設定する。
Therefore, when the braking mode is engine braking, the prediction control block 132 sets a larger prediction time as the deceleration start speed is lower. On the other hand, the predictive control block 132 sets the predictive time constant regardless of the deceleration start speed when the braking mode is foot braking. If the response characteristic is different from this, the predicted time is set according to the response characteristic.
目標ヨーレートで車両制御する場合を考える。操舵による応答遅れは、アクチュエータの遅れに加えて、タイヤの変形の影響を受ける。このため、目標ヨーレートへの応答特性が車速によって大きく異なる。例えば、低速域(例えば~40km/h)には、タイヤの変形が小さく、応答遅れが約100~200msecとなる。中速域(例えば40~70km/h)には、タイヤ変形が小さいため、応答遅れが約200msec~300msecとなる。さらに、高速域(例えば70km/h~)には、応答遅れが約100~200msecとなる。タイヤ変形が小さい場合は、ホスト車両Aのヨーレートは目標に追従するように応答するが、タイヤ変形がある場合は、ヨーレートが振動的になる。車両特性が変化しているため、応答性が良くなっているように見える(図5参照)。
Consider the case of controlling the vehicle at the target yaw rate. Response delay due to steering is affected by tire deformation in addition to actuator delay. Therefore, the response characteristics to the target yaw rate differ greatly depending on the vehicle speed. For example, in a low speed range (eg, up to 40 km/h), tire deformation is small and response delay is about 100 to 200 msec. In the middle speed range (for example, 40 to 70 km/h), the tire deformation is small, so the response delay is about 200 msec to 300 msec. Furthermore, in a high speed range (for example, from 70 km/h), the response delay is about 100-200 msec. When the tire deformation is small, the yaw rate of the host vehicle A responds to follow the target, but when there is tire deformation, the yaw rate becomes oscillatory. Since the vehicle characteristics have changed, it seems that the responsiveness has improved (see FIG. 5).
したがって、予測制御ブロック132は、走行速度が高速域である場合には、中速域である場合よりも予測時間を小さく設定する。一方で、予測制御ブロック132は、走行速度が低速域である場合には、中速域よりも予測時間を小さく設定する。予測時間は、タイヤ特性に応じて設定されてもよい。
Therefore, the prediction control block 132 sets a smaller prediction time when the traveling speed is in the high speed range than when it is in the middle speed range. On the other hand, the prediction control block 132 sets the prediction time shorter than that in the middle speed range when the running speed is in the low speed range. The predicted time may be set according to tire characteristics.
出力決定ブロック133は、FB制御量と予測制御量とに基づき、現在の出力制御量を決定する。具体的には、出力決定ブロック133は、FB制御量と予測制御量との加算値にゲイン(例えば0.5)をかけることで、出力制御量を算出する。出力決定ブロック133は算出した出力制御量によるホスト車両Aの制御を走行系40に指令する。
The output determination block 133 determines the current output control amount based on the FB control amount and the predicted control amount. Specifically, the output determination block 133 calculates the output control amount by multiplying the sum of the FB control amount and the predicted control amount by a gain (for example, 0.5). The output determination block 133 commands the travel system 40 to control the host vehicle A according to the calculated output control amount.
ここまで説明したブロック110,120,130の共同により、車両制御システム100がホスト車両Aの走行を制御する車両制御方法のフローである車両制御フローを、図6に従って以下に説明する。本車両制御フローは、ホスト車両Aの起動中に繰り返し実行される。尚、本車両制御フローにおける各「S」は、車両制御プログラムに含まれた複数命令によって実行される複数ステップを、それぞれ意味している。
A vehicle control flow, which is a flow of a vehicle control method in which the vehicle control system 100 controls the running of the host vehicle A, will be described below with reference to FIG. This vehicle control flow is repeatedly executed while the host vehicle A is running. Each "S" in the vehicle control flow represents a plurality of steps executed by a plurality of instructions included in the vehicle control program.
まず、S10では、認識ブロック110が、センサ系10等から行動計画に必要なデータを取得し、当該データに対する認識処理を実行する。続くS20では、行動計画ブロック120が、ホスト車両Aの位置及び運動状態を含む将来の行動計画を立案する。続くS30では、予測制御ブロック132が、行動計画から予測制御量を取得する。続くS40では、FB制御ブロック131がFB制御量を算出する。さらに、S50では、制御量算出ブロックが、出力制御量し、走行系40へと出力する。
First, in S10, the recognition block 110 acquires data necessary for the action plan from the sensor system 10, etc., and executes recognition processing on the data. At S20, the action plan block 120 formulates a future action plan including the host vehicle A's position and motion state. In subsequent S30, the prediction control block 132 acquires the prediction control amount from the action plan. In subsequent S40, the FB control block 131 calculates the FB control amount. Furthermore, in S50, the control amount calculation block calculates the output control amount and outputs it to the traveling system 40. FIG.
次に、ホスト車両Aにむだ時間が無いと想定した場合の先行車追従動作例を説明する(図7参照)。この例では、ホスト車両Aは、正弦波のように加減速している先行車に追従するものとする。先行追従制御において、車両制御システム100は、理想車間時間(例えば1.4秒)及び設定車速(例えば30m/s)を超えない状態で先行車に追従するように、加減速度を制御する。
Next, an example of the preceding vehicle following operation will be described assuming that the host vehicle A has no dead time (see FIG. 7). In this example, host vehicle A follows a preceding vehicle that accelerates and decelerates like a sine wave. In the follow-up control, the vehicle control system 100 controls the acceleration/deceleration so as to follow the preceding vehicle while not exceeding the ideal inter-vehicle time (eg, 1.4 seconds) and the set vehicle speed (eg, 30 m/s).
図8に示すように、むだ時間が1秒ある場合、先行車の動きに対して応答が遅れるため、目標加速度がハンチングする。このように、応答遅れに対する予測制御量を算出しない場合、設定車速、理想車間時間を保つような制御を実行すると、速度、車間距離が振動的になってしまう。一方で、本実施形態のように予測制御量を算出することにより応答遅れを補償すると、図9のようにむだ時間が無い車両と同等の制御性に改善される。
As shown in Fig. 8, if there is a dead time of 1 second, the target acceleration will hunt because the response to the movement of the preceding vehicle is delayed. As described above, when the predictive control amount for the response delay is not calculated, the speed and the inter-vehicle distance become oscillating if control is executed to maintain the set vehicle speed and the ideal inter-vehicle time. On the other hand, if the response delay is compensated by calculating the predictive control amount as in the present embodiment, the controllability is improved to be equivalent to that of a vehicle with no dead time as shown in FIG.
以上の第一実施形態によれば、ホスト車両Aの位置及び運動状態を含む将来の行動計画が立案され、行動計画から将来の予測制御量が取得され、予測制御量に基づいて、現在の制御量が決定される。故に、行動計画においてホスト車両Aの運動状態が含まれているため、予測制御量において誤差が生じにくくなり、さらに予測制御量により応答遅れが補償され得る。故に、応答性を改善しつつ、制御性の悪化を抑制可能となり得る。
According to the first embodiment described above, a future action plan including the position and motion state of the host vehicle A is drawn up, a future predicted control amount is obtained from the action plan, and the current control amount is calculated based on the predicted control amount. quantity is determined. Therefore, since the motion state of the host vehicle A is included in the action plan, an error is less likely to occur in the predictive control amount, and the response delay can be compensated for by the predictive control amount. Therefore, deterioration of controllability can be suppressed while improving responsiveness.
また、車両制御において、認識処理におけるノイズのフィルタリング処理や、認識結果の通信処理による応答遅れが生じ得る。さらに、行動計画等の判断処理でも誤動作防止のためにフィルタリング処理を実施すると、遅れが生じる。本実施形態において、認識から制御要求までの遅れを制御要求から車両応答までの遅れとともにまとめて補償可能となる。
Also, in vehicle control, response delays may occur due to noise filtering processing in recognition processing and communication processing of recognition results. Furthermore, if filtering processing is performed to prevent malfunctions, a delay occurs even in judgment processing such as an action plan. In this embodiment, it is possible to collectively compensate for the delay from recognition to control request together with the delay from control request to vehicle response.
(第二実施形態)
図10に示すように第二実施形態は、第一実施形態の変形例である。 (Second embodiment)
As shown in FIG. 10, the second embodiment is a modification of the first embodiment.
図10に示すように第二実施形態は、第一実施形態の変形例である。 (Second embodiment)
As shown in FIG. 10, the second embodiment is a modification of the first embodiment.
第二実施形態において、S20での行動計画ブロック120は、行動計画Pの候補として複数種別の候補計画を立案し、候補計画の中から行動計画を選択する。行動計画ブロック120は、例えばホスト車両Aの進行経路に応じた複数種別の候補計画を立案する。行動計画ブロック120は、例えばフレネ座標系にて高次多項式による候補計画を、複数立案する。一例として、行動計画ブロック120は、図10に示すように、直進経路の候補計画P3と、直進経路に対して左側に車線変更する種別の候補計画PC1,PC2と、直進経路に対して右側に車線変更する種別の候補計画PC4,PC5と、を立案する。
In the second embodiment, the action plan block 120 in S20 formulates multiple types of candidate plans as candidates for the action plan P, and selects an action plan from among the candidate plans. The action plan block 120 draws up a plurality of types of candidate plans according to the traveling route of the host vehicle A, for example. The action plan block 120 draws up a plurality of candidate plans based on higher-order polynomials, for example, in the Fresnet coordinate system. As an example, the action plan block 120 includes, as shown in FIG. 10, a candidate plan P3 for a straight route, candidate plans PC1 and PC2 for changing lanes to the left of the straight route, and Candidate plans PC4 and PC5 for types of lane changes are drafted.
行動計画ブロック120は、複数種別の各候補計画を評価関数等に基づき評価する。行動計画ブロック120は、最も評価の高い候補計画を、実際に実行する行動計画Pとして選択する。図10の紙面左側には、ある周期において、直進経路の候補計画PC3が行動計画Pとして選択された例を示している。また、図10の紙面右側には、次の周期にて右側へ車線変更する候補計画PC5へと行動計画Pが切り替わった例を示している。
The action plan block 120 evaluates each candidate plan of multiple types based on an evaluation function or the like. The action plan block 120 selects the highest rated candidate plan as the action plan P to actually execute. The left side of FIG. 10 shows an example in which the straight route candidate plan PC3 is selected as the action plan P in a certain cycle. The right side of FIG. 10 shows an example in which the action plan P is switched to the candidate plan PC5 for changing lanes to the right in the next cycle.
第二実施形態において、S30での予測制御ブロック132は、行動計画Pとして選択される候補計画が前回から変更された場合、変更前の行動計画(変更前計画)Pp及び変更後の行動計画Pの両方に応じた予測制御量を算出する。詳記すると、予測制御ブロック132は、変更前計画Ppに基づく予測制御量(変更前予測制御量)と、変更後の行動計画Pに基づく予測制御量(変更後予測制御量)と、を算出する。そして、予測制御ブロック132は、変更前予測制御量と変更後予測制御量とに応じた予測制御量として、各目標値の中間的な予測制御量を算出する。
In the second embodiment, the prediction control block 132 in S30, when the candidate plan selected as the action plan P is changed from the previous time, the action plan before change (plan before change) Pp and the action plan after change P Calculates the predictive control amount according to both. Specifically, the predictive control block 132 calculates a predictive control amount based on the pre-change plan Pp (pre-change predictive control amount) and a predictive control amount based on the post-change action plan P (post-change predictive control amount). do. Then, the predictive control block 132 calculates an intermediate predictive control amount of each target value as a predictive control amount corresponding to the pre-change predictive control amount and the post-change predictive control amount.
例えば、予測制御ブロック132は、変更前予測制御量と変更後予測制御量との平均値を、中間的な予測制御量として算出すればよい。尚、予測制御ブロック132は、変更前予測制御量及び変更後予測制御量の少なくとも一方に重みづけを行って平均値を算出してもよい。予測制御ブロック132は、この中間的な予測制御量を、出力制御量を決定するパラメータとして出力決定ブロック133に提供する。尚、図10に示す例では、変更前予測制御量を変更前計画Pp上における白抜きの丸で模式的に示しており、変更後予測制御量を変更後の行動計画P上における白抜きの丸で模式的に示している。そして、中間的な予測制御量を黒塗りの丸として模式的に示している。
For example, the prediction control block 132 may calculate the average value of the pre-change prediction control amount and the post-change prediction control amount as an intermediate prediction control amount. Note that the prediction control block 132 may weight at least one of the pre-change prediction control amount and the post-change prediction control amount to calculate an average value. The prediction control block 132 provides this intermediate prediction control amount to the output determination block 133 as a parameter for determining the output control amount. In the example shown in FIG. 10, the pre-change predicted control amount is schematically indicated by a white circle on the pre-change plan Pp, and the post-change predicted control amount is indicated by a white circle on the action plan P after change. It is schematically indicated by a circle. An intermediate predictive control amount is schematically shown as a black circle.
以上の第二実施形態によれば、変更後の行動計画Pからの予測制御量及び変更前の行動計画Pからの変更前予測制御量に基づいて出力制御量が決定される。故に、選択される行動計画Pの変更に応じた予測制御量の大きな変化が抑制され得る。したがって、車両挙動が不安定になることを抑制できる。
According to the second embodiment described above, the output control amount is determined based on the predicted control amount from the action plan P after change and the pre-change predicted control amount from the action plan P before change. Therefore, a large change in the predictive control amount according to a change in the selected action plan P can be suppressed. Therefore, it is possible to suppress the vehicle behavior from becoming unstable.
(第三実施形態)
図11に示すように第三実施形態は、第一実施形態の変形例である。 (Third embodiment)
As shown in FIG. 11, the third embodiment is a modification of the first embodiment.
図11に示すように第三実施形態は、第一実施形態の変形例である。 (Third embodiment)
As shown in FIG. 11, the third embodiment is a modification of the first embodiment.
第三実施形態において、S20での行動計画ブロック120は、第二実施形態と同様に、行動計画Pの候補として複数の候補計画を立案し、最も評価の高い候補計画を、実際に実行する行動計画Pとして選択する。加えて、行動計画ブロック120は、各候補計画の評価結果に応じて、将来選択される候補計画を予測する。
In the third embodiment, as in the second embodiment, the action plan block 120 in S20 draws up a plurality of candidate plans as candidates for the action plan P, and selects the candidate plan with the highest evaluation as an action to actually execute. Select as Plan P. In addition, action plan block 120 predicts candidate plans that will be selected in the future, depending on the evaluation results of each candidate plan.
例えば、行動計画ブロック120は、各候補計画に対して、評価値の時間変化の勾配を算出する。行動計画ブロック120は、この勾配に応じた将来周期の予測評価値を、候補計画毎に算出する。行動計画ブロック120は、規定の周期先まで予測評価値を算出すればよい。行動計画ブロック120は、この予測評価値に応じて、将来選択される行動計画を予測する。
For example, the action plan block 120 calculates the gradient of the evaluation value over time for each candidate plan. The action plan block 120 calculates the predicted evaluation value of the future cycle according to this gradient for each candidate plan. The action plan block 120 may calculate the predicted evaluation value up to a predetermined cycle ahead. The action plan block 120 predicts action plans to be selected in the future according to this prediction evaluation value.
そして、行動計画ブロック120は、将来選択される行動計画の種別が現在の行動計画と異なる場合、すなわち行動計画が規定の周期先までに切り替わる場合に、現在の行動計画Pと、将来の行動計画(将来計画)Pnとを合成した行動計画として合成計画Psを生成する。図11に示す例では、候補計画PC3が選択された現在の行動計画Pに対して、候補計画PC5が選択されることによる将来計画Pnが合成された合成計画Psが、行動計画Pとして生成される。
When the type of action plan to be selected in the future is different from the current action plan, that is, when the action plan is switched before the prescribed cycle, the action plan block 120 sets the current action plan P and the future action plan. (Future plan) A combined plan Ps is generated as an action plan combining Pn. In the example shown in FIG. 11, a combined plan Ps is generated as the action plan P by combining the current action plan P in which the candidate plan PC3 is selected and the future plan Pn resulting from the selection of the candidate plan PC5. be.
この場合、S30での予測制御ブロック132は、この合成計画Psから予測制御量を取得する。図11に示す例では、予測制御量を黒塗りの丸として模式的に示している。
In this case, the predictive control block 132 in S30 acquires the predictive control amount from this combined plan Ps. In the example shown in FIG. 11, the predictive controlled variable is schematically shown as a black circle.
以上の第三実施形態によれば、将来において行動計画として選択される候補計画の種別変更が予測される場合に、現在の行動計画に予測される種別の候補計画が合成される。故に、将来行動計画として選択される候補計画が現在の行動計画に合成されるため、予測制御量として行動計画の変化に対応した制御量が取得され得る。したがって、車両挙動が不安定になることを抑制できる。
According to the third embodiment described above, when a change in the type of a candidate plan to be selected as an action plan in the future is predicted, the predicted type of candidate plan is combined with the current action plan. Therefore, since the candidate plan selected as the future action plan is combined with the current action plan, the control amount corresponding to the change in the action plan can be obtained as the predictive control amount. Therefore, it is possible to suppress the vehicle behavior from becoming unstable.
(他の実施形態)
以上、複数の実施形態について説明したが、本開示は、当該説明の実施形態に限定して解釈されるものではなく、本開示の要旨を逸脱しない範囲内において種々の実施形態に適用することができる。 (Other embodiments)
Although a plurality of embodiments have been described above, the present disclosure should not be construed as being limited to the described embodiments, and can be applied to various embodiments within the scope of the present disclosure. can.
以上、複数の実施形態について説明したが、本開示は、当該説明の実施形態に限定して解釈されるものではなく、本開示の要旨を逸脱しない範囲内において種々の実施形態に適用することができる。 (Other embodiments)
Although a plurality of embodiments have been described above, the present disclosure should not be construed as being limited to the described embodiments, and can be applied to various embodiments within the scope of the present disclosure. can.
変形例において、行動計画ブロック120は、行動計画の推定方法として、MDP(マルコフ決定過程)又はDP(動的計画法)等を用いてもよい。
In a modified example, the action plan block 120 may use MDP (Markov decision process) or DP (dynamic programming) as an action plan estimation method.
変形例において、制御量決定ブロック130は、フィードフォワード制御とフィードバック制御の2自由度制御系の代わりに、目標値フィルタ型の2自由度制御系であってもよい。
In a modified example, the control amount determination block 130 may be a target value filter type two-degree-of-freedom control system instead of the two-degree-of-freedom control system of feedforward control and feedback control.
変形例において車両制御システム100を構成する専用コンピュータは、デジタル回路及びアナログ回路のうち、少なくとも一方をプロセッサとして有していてもよい。ここでデジタル回路とは、例えばASIC(Application Specific Integrated Circuit)、FPGA(Field Programmable Gate Array)、SOC(System on a Chip)、PGA(Programmable Gate Array)、及びCPLD(Complex Programmable Logic Device)等のうち、少なくとも一種類である。またこうしたデジタル回路は、プログラムを記憶したメモリを、有していてもよい。
In a modified example, the dedicated computer that configures the vehicle control system 100 may have at least one of digital circuits and analog circuits as a processor. Digital circuits here include, for example, ASIC (Application Specific Integrated Circuit), FPGA (Field Programmable Gate Array), SOC (System on a Chip), PGA (Programmable Gate Array), and CPLD (Complex Programmable Logic Device). , at least one Such digital circuits may also have a memory that stores the program.
ここまでの説明形態の他、上述の実施形態及び変化例による車両制御システム100は、ホスト車両Aに搭載の処理装置(例えば処理ECU等)である車両制御装置として、実施されてもよい。また、上述の実施形態及び変化例は、車両制御システム100のプロセッサ102及びメモリ101を少なくとも一つずつ有した半導体装置(例えば半導体チップ等)として、実施されてもよい。
In addition to the forms described so far, the vehicle control system 100 according to the above-described embodiments and modifications may be implemented as a vehicle control apparatus that is a processing apparatus (eg, processing ECU, etc.) mounted on the host vehicle A. Also, the above-described embodiments and variations may be implemented as a semiconductor device (for example, a semiconductor chip or the like) having at least one processor 102 and at least one memory 101 of the vehicle control system 100 .
Claims (11)
- プロセッサ(102)を有し、ホスト車両(A)を制御する車両制御システムであって、
前記プロセッサは、
前記ホスト車両の位置及び運動状態を含む将来の行動計画を立案することと、
前記行動計画から、前記ホスト車両における走行制御に関する応答の遅れ時間に基づく予測時間先での予測制御量を取得することと、
前記予測制御量に応じた現在の出力制御量を決定することと、
を実行するように構成される車両制御システム。 A vehicle control system having a processor (102) and controlling a host vehicle (A), comprising:
The processor
formulating a future action plan including the position and motion state of the host vehicle;
Acquiring a predicted control amount ahead of a predicted time based on a response delay time regarding travel control in the host vehicle from the action plan;
Determining a current output control amount according to the predicted control amount;
a vehicle control system configured to perform - 前記予測時間は、シフトダウン制御の有無に応じて決定されることを含む請求項1に記載の車両制御システム。 The vehicle control system according to claim 1, wherein the predicted time is determined according to the presence or absence of shift down control.
- 前記予測時間は、シフトダウン制御のシフト数に応じて決定されることを含む請求項2に記載の車両制御システム。 The vehicle control system according to claim 2, wherein the predicted time is determined according to the number of shifts in shift down control.
- 前記予測時間は、制動態様に応じて決定されることを含む請求項1から請求項3のいずれか1項に記載の車両制御システム。 The vehicle control system according to any one of claims 1 to 3, wherein the predicted time is determined according to a braking mode.
- 前記予測時間は、タイヤの変形度合に応じて決定されることを含む請求項1から請求項4のいずれか1項に記載の車両制御システム。 The vehicle control system according to any one of claims 1 to 4, wherein the predicted time is determined according to the degree of tire deformation.
- 前記予測時間は、走行速度に応じて決定されることを含む請求項1から請求項5のいずれか1項に記載の車両制御システム。 The vehicle control system according to any one of claims 1 to 5, wherein the predicted time is determined according to the running speed.
- 前記行動計画を立案することは、
複数種別の候補計画から前記行動計画を選択することを含み、
前記予測制御量を取得することは、
前記行動計画として選択される前記候補計画の種別が変更された場合には、変更前の前記行動計画からの前記予測制御量である変更前予測制御量をさらに取得することを含み、
前記出力制御量を決定することは、
変更後の前記行動計画からの前記予測制御量及び前記変更前予測制御量に応じて前記出力制御量を決定することを含む請求項1から請求項6のいずれか1項に記載の車両制御システム。 Drafting the action plan includes:
selecting the action plan from multiple types of candidate plans;
Acquiring the predictive control amount includes:
further acquiring a pre-change predictive control amount that is the predictive control amount from the action plan before change, when the type of the candidate plan selected as the action plan is changed;
Determining the output control amount includes:
7. The vehicle control system according to any one of claims 1 to 6, further comprising determining the output control amount according to the predicted control amount from the changed action plan and the pre-change predicted control amount. . - 前記行動計画を立案することは、
複数種別の候補計画から前記行動計画を選択することと、
将来において前記行動計画として選択される前記候補計画の種別変更が予測される場合に、現在の前記行動計画に予測される種別の前記候補計画を合成することと、
を含む請求項1から請求項6のいずれか1項に記載の車両制御システム。 Drafting the action plan includes:
selecting the action plan from multiple types of candidate plans;
when a change in type of the candidate plan selected as the action plan is predicted in the future, combining the candidate plan of the predicted type with the current action plan;
7. The vehicle control system according to any one of claims 1 to 6, comprising: - プロセッサ(102)を有し、ホスト車両(A)を制御する車両制御装置であって、
前記プロセッサは、
前記ホスト車両の位置及び運動状態を含む将来の行動計画を立案することと、
前記行動計画から、前記ホスト車両における走行制御に関する応答の遅れ時間に基づく予測時間先での予測制御量を取得することと、
前記予測制御量に応じた現在の出力制御量を決定することと、
を実行するように構成される車両制御装置。 A vehicle control device having a processor (102) and controlling a host vehicle (A),
The processor
formulating a future action plan including the position and motion state of the host vehicle;
Acquiring a predicted control amount ahead of a predicted time based on a response delay time regarding travel control in the host vehicle from the action plan;
Determining a current output control amount according to the predicted control amount;
A vehicle controller configured to perform - ホスト車両(A)を制御するために、プロセッサ(102)により実行される車両制御方法であって、
前記ホスト車両の位置及び運動状態を含む将来の行動計画を立案することと、
前記行動計画から、前記ホスト車両における走行制御に関する応答の遅れ時間に基づく予測時間先での予測制御量を取得することと、
前記予測制御量に応じた現在の出力制御量を決定することと、
を含む車両制御方法。 A vehicle control method executed by a processor (102) for controlling a host vehicle (A), comprising:
formulating a future action plan including the position and motion state of the host vehicle;
Acquiring a predicted control amount ahead of a predicted time based on a response delay time regarding travel control in the host vehicle from the action plan;
Determining a current output control amount according to the predicted control amount;
vehicle control methods including; - ホスト車両(A)を制御するために記憶媒体(101)に記憶され、プロセッサ(102)に実行させる命令を含む車両制御プログラムであって、
前記命令は、
前記ホスト車両の位置及び運動状態を含む将来の行動計画を立案させることと、
前記行動計画から、前記ホスト車両における走行制御に関する応答の遅れ時間に基づく予測時間先での予測制御量を取得させることと、
前記予測制御量に応じた現在の出力制御量を決定させることと、
を含む車両制御プログラム。 A vehicle control program stored in a storage medium (101) and containing instructions to be executed by a processor (102) for controlling a host vehicle (A), comprising:
Said instruction
Developing a future action plan including the position and motion state of the host vehicle;
Acquiring from the action plan a predicted control amount at a predicted time ahead based on a response delay time regarding travel control in the host vehicle;
Determining a current output control amount according to the predicted control amount;
Vehicle control program including.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2023564770A JPWO2023100482A1 (en) | 2021-11-30 | 2022-10-12 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2021194047 | 2021-11-30 | ||
JP2021-194047 | 2021-11-30 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2023100482A1 true WO2023100482A1 (en) | 2023-06-08 |
Family
ID=86611924
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2022/038022 WO2023100482A1 (en) | 2021-11-30 | 2022-10-12 | Vehicle control system, vehicle control device, vehicle control method, and vehicle control program |
Country Status (2)
Country | Link |
---|---|
JP (1) | JPWO2023100482A1 (en) |
WO (1) | WO2023100482A1 (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007062654A (en) * | 2005-09-01 | 2007-03-15 | Nissan Motor Co Ltd | Vehicle behavior control device |
JP2018016225A (en) * | 2016-07-29 | 2018-02-01 | 日立オートモティブシステムズ株式会社 | Vehicle motion control device |
WO2020152977A1 (en) * | 2019-01-21 | 2020-07-30 | 日立オートモティブシステムズ株式会社 | Vehicle control device, vehicle control method, and vehicle control system |
-
2022
- 2022-10-12 WO PCT/JP2022/038022 patent/WO2023100482A1/en active Application Filing
- 2022-10-12 JP JP2023564770A patent/JPWO2023100482A1/ja active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007062654A (en) * | 2005-09-01 | 2007-03-15 | Nissan Motor Co Ltd | Vehicle behavior control device |
JP2018016225A (en) * | 2016-07-29 | 2018-02-01 | 日立オートモティブシステムズ株式会社 | Vehicle motion control device |
WO2020152977A1 (en) * | 2019-01-21 | 2020-07-30 | 日立オートモティブシステムズ株式会社 | Vehicle control device, vehicle control method, and vehicle control system |
Also Published As
Publication number | Publication date |
---|---|
JPWO2023100482A1 (en) | 2023-06-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20220063611A1 (en) | Autonomous driving system | |
CN111688663B (en) | Motor vehicle and method for controlling automatic driving operation thereof | |
CN109557912B (en) | Decision planning method for automatically driving special operation vehicle | |
JP7036545B2 (en) | Online learning method and vehicle control method based on reinforcement learning without active search | |
US10800427B2 (en) | Systems and methods for a vehicle controller robust to time delays | |
US9796390B2 (en) | Vehicle sensing grid having dynamic sensing cell size | |
Guvenc et al. | Connected and autonomous vehicles | |
CN112612287A (en) | System, method, medium and device for planning local path of automatic driving automobile | |
US11745760B2 (en) | Parallel obstacle buffer system for path planning | |
CN111301392A (en) | Vehicle routing | |
CN115701295A (en) | Method and system for vehicle path planning | |
CN111415511A (en) | Vehicle monitoring and control infrastructure | |
US20210200231A1 (en) | Speed planning guidance line for mild slow down | |
US11120566B2 (en) | Determining vanishing points based on feature maps | |
CN112149484B (en) | Determining vanishing points based on lane lines | |
JP2020111300A (en) | Vehicle driving support system and method | |
CN114088094A (en) | Intelligent route planning method and system for unmanned ship | |
CN115042816A (en) | Path tracking method, device, apparatus, medium, and program | |
JP7206970B2 (en) | VEHICLE MOTION CONTROL METHOD AND VEHICLE MOTION CONTROL DEVICE | |
JP2020111302A (en) | Vehicle driving support system and method | |
WO2023100482A1 (en) | Vehicle control system, vehicle control device, vehicle control method, and vehicle control program | |
CN115685992B (en) | Automatic driving vehicle path planning method and device, vehicle and medium | |
US20230391356A1 (en) | Dynamic scenario parameters for an autonomous driving vehicle | |
EP3838697A1 (en) | Speed planning using a speed planning guideline for idle speed of autonomous driving vehicles | |
CN115098821A (en) | Trajectory reference curvature determination method, apparatus, device, medium, and program |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 22900916 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2023564770 Country of ref document: JP |