WO2020008785A1 - 予測制御装置 - Google Patents

予測制御装置 Download PDF

Info

Publication number
WO2020008785A1
WO2020008785A1 PCT/JP2019/022267 JP2019022267W WO2020008785A1 WO 2020008785 A1 WO2020008785 A1 WO 2020008785A1 JP 2019022267 W JP2019022267 W JP 2019022267W WO 2020008785 A1 WO2020008785 A1 WO 2020008785A1
Authority
WO
WIPO (PCT)
Prior art keywords
vehicle
prediction
unit
control device
initial value
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/JP2019/022267
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
敏明 中村
広津　鉄平
坂本　英之
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hitachi Astemo Ltd
Original Assignee
Hitachi Automotive Systems Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hitachi Automotive Systems Ltd filed Critical Hitachi Automotive Systems Ltd
Priority to CN201980031293.0A priority Critical patent/CN112292717B/zh
Priority to US17/255,748 priority patent/US20210221402A1/en
Publication of WO2020008785A1 publication Critical patent/WO2020008785A1/ja
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

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
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B60W60/001—Planning or execution of driving tasks
    • B60W60/0015—Planning or execution of driving tasks specially adapted for safety
    • 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
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
    • B60W40/04—Traffic conditions
    • 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
    • B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
    • B60W30/095—Predicting travel path or likelihood of collision
    • B60W30/0956—Predicting travel path or likelihood of collision the prediction being responsive to traffic or environmental parameters
    • 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
    • B60W50/0097—Predicting future conditions
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/16—Anti-collision systems
    • 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
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/40—Dynamic objects, e.g. animals, windblown objects
    • B60W2554/404—Characteristics
    • B60W2554/4042—Longitudinal speed
    • 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
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/40—Dynamic objects, e.g. animals, windblown objects
    • B60W2554/404—Characteristics
    • B60W2554/4043—Lateral speed
    • 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
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/40—Dynamic objects, e.g. animals, windblown objects
    • B60W2554/404—Characteristics
    • B60W2554/4044—Direction of movement, e.g. backwards
    • 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
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/40—Dynamic objects, e.g. animals, windblown objects
    • B60W2554/404—Characteristics
    • B60W2554/4049—Relationship among other objects, e.g. converging dynamic objects

Definitions

  • the present invention relates to a predictive control device applied to automatic driving of a vehicle.
  • Patent Document 1 As a predictive control technique in automatic driving of a vehicle, a technique described in Patent Document 1 is disclosed.
  • Patent Literature 1 observes a change in a time constant of a control target and controls a sampling time, a prediction section, and a control in accordance with the change amount.
  • a technique for changing at least one setting of a section and stabilizing control according to a control target is disclosed.
  • Patent Literature 1 the processing is speeded up by mainly observing a change in a time constant of a control target and a target control amount and adjusting a control parameter of the prediction control. Situation changes every moment.
  • Patent Document 1 does not take into account changes in the surrounding conditions while the vehicle is running, and does not perform control corresponding to the surrounding conditions while the host vehicle is running.
  • the present invention is configured as follows.
  • the prediction control device includes means for detecting a change amount and a change direction of the surroundings and the vehicle, and means for setting an initial value and a prediction period of a solution search operation in the prediction control means based on the detection result.
  • a predictive control device capable of responding to a change in surrounding conditions during traveling of the host vehicle and capable of performing quick operations during normal traveling and during an emergency so that a person drives.
  • FIG. 1 is a diagram illustrating an example of a block configuration of an automatic driving control system for a vehicle, which is a prediction control device according to a first embodiment of the present invention. It is a figure showing the example of block composition of the operation command value generation part in a model prediction control part. It is a figure showing the example of block composition of the output prediction part in a model prediction control part. It is a figure showing the example of block composition of the evaluation function operation part in a model prediction control part. It is a figure showing the example of block composition of a situation recognition part.
  • FIG. 4 is a diagram illustrating an example of a block configuration of a change amount detection unit.
  • FIG. 7 is a diagram illustrating a method of determining an initial value for a weight Wa of a control condition adjustment unit.
  • FIG. 9 is a diagram illustrating a method of determining a prediction period for a weight Wb of a control condition adjustment unit.
  • FIG. 3 is a diagram illustrating a block configuration example of a control condition adjusting unit. It is a figure showing the example of block composition of other examples of a control condition adjustment part.
  • FIG. 3 is a diagram illustrating a block configuration example of an initial value setting unit. It is a figure which shows the number of times of operation until the evaluation function output of predictive control converges when the present invention is not used.
  • FIG. 7 is a diagram illustrating the number of calculations performed until the evaluation function output of predictive control converges when the previous optimal solution is included in the initial value candidate in the first embodiment of the present invention.
  • FIG. 3 is a diagram illustrating a block configuration example of a control condition adjusting unit. It is a figure showing the example of block composition of other examples of a control condition adjustment part.
  • FIG. 3 is a diagram illustrating a block configuration example of an initial value setting unit. It
  • FIG. 9 is a diagram illustrating the number of calculations performed until the evaluation function output of the prediction control converges when the prediction period is shortened in the first embodiment of the present invention.
  • FIG. 2 is a diagram illustrating a trajectory of automatic driving of a vehicle by predictive control according to the first embodiment of the present invention.
  • FIG. 1 is a diagram illustrating an example of a block configuration of an automatic driving control system for a vehicle that is a predictive control device according to a first embodiment of the present invention.
  • the model prediction control unit 101 predicts the speed and direction of the vehicle in the future several seconds, for example, every several milliseconds based on information about the surroundings of the vehicle. Processing (solution search operation) for obtaining the operation amount several milliseconds later is performed.
  • Some input model predictive control unit 101 is at ambient information, some of the output steering, an accelerator operation, a manipulated variable u 0 for the actuator 102, such as a brake operation.
  • the model prediction control unit 101 includes an operation command value generation unit 106, an output prediction unit 107, and an evaluation function calculation unit 108.
  • the operation command value generation unit 106 operates the actuator 102 with, for example, a current operation amount u 0 and an operation amount candidate (predicted value for n seconds in the future every several milliseconds from the next operation amount u 1 ). u 1 to u n ).
  • the operation command value generation unit 106 will be described later with reference to FIG.
  • Output prediction unit 107 for example, an operation amount candidate (u 1 ⁇ u n), receives a control quantity x 0 of the vehicle at the present time outputted from the actuator 102 to the state equation representing the operation model of the vehicle in the formula, This is a means for outputting a corresponding control amount (speed, position, direction, etc.) as a control amount candidate (x 1 to x n ) as a predicted value corresponding to the output of the actuator 102.
  • the output prediction unit 107 will be described later with reference to FIG.
  • the evaluation function calculation unit 108 expresses the constraint conditions necessary for the automatic driving with a plurality of functions, inputs control amount candidates (x 1 to x n ) from the output prediction unit 107, and outputs the sum F of the outputs of the respective functions for the constraint conditions. Is output to the operation command value generation unit 106.
  • the evaluation function calculation unit 108 will be described later with reference to FIG.
  • the situation recognizing unit 103 uses the information on the surrounding situation of the own vehicle during traveling to detect moving objects (dynamic obstacles) such as other vehicles, bicycles, and pedestrians on the traveling road, and stationary objects such as guardrails and stopped vehicles. This is means for recognizing and outputting a static obstacle), route information to the destination of the own vehicle, and the position of the own vehicle.
  • moving objects dynamic obstacles
  • stationary objects such as guardrails and stopped vehicles.
  • the change amount detection unit 104 calculates the amount of change in the relative position of the recognized object and the traveling path of the own vehicle with respect to the own vehicle per unit time (from the relative position and relative speed of the dynamic obstacle and the static obstacle with respect to the own vehicle). This is a means for detecting the obtained change amount and the change direction of the surroundings and the own vehicle, obtaining a weight coefficient, and outputting the weight coefficient to the control condition adjusting unit 105.
  • the change amount detection unit 104 will be described later with reference to FIG.
  • the situation recognition unit 103 and the change amount detection unit 104 form a unit that detects a change amount and a change direction of the surroundings and the own vehicle.
  • the control condition adjusting unit 105 is a unit that adjusts and sets an initial value and a prediction period for performing the calculation of the model prediction control based on the weight coefficient input from the change amount detection unit 104. In other words, it is a means for setting the initial value and the prediction period of the optimal value search operation (solution search operation) performed by the operation command value generation unit 106 and outputting the prediction period to the operation command value generation unit 106.
  • the control condition adjusting unit 105 will be described later with reference to FIG.
  • the loop processing from the operation command value generation unit 106 to the output prediction unit 107 and the evaluation function calculation unit 108 is repeated a plurality of times, for example, every several milliseconds, and the total sum F of the evaluation functions is minimized.
  • the operation command value 106 selects an operation amount candidate (u 1 to u n ). Then, the operation amount u 1 at the next time is output to the actuator 102.
  • the actuator 102 converts the operation amount u into a control amount x, and executes a brake, an accelerator, a steering wheel operation, and the like.
  • FIG. 2 is a diagram illustrating a block configuration example of the operation command value generation unit 106 in the model prediction control unit 101.
  • the operation command value generating unit 106 inputs the evaluation function F which is output from the evaluation function calculating unit 108, the operation amount u 0 and the operation amount candidates for the actuator 102 (u 1 ⁇ u n) accordingly Generate and output.
  • the comparison unit 202 in the operation command value generation unit 106 compares the operation result (output of the evaluation function F) output from the evaluation function operation unit 108 with the value stored in the minimum value storage unit 203. If the value input from the evaluation function calculation unit 108 to the comparison unit 202 is smaller than the value stored in the minimum value storage unit 203, a save command signal is output to the minimum value storage unit 203.
  • the minimum value storage unit 203 stores the calculation result of the evaluation function according to the storage command signal from the comparison unit 202. A series of processing up to this means that a value that minimizes the output F of the evaluation function operation 108 has been obtained.
  • Manipulated variable generating unit 201 is a means for generating a manipulated variable candidates from the operation amount candidates u 1 of the following time until the operation amount candidates u n future time n (u 1 ⁇ u n).
  • an operation amount candidate value is generated by generating a random number as an initial value, and thereafter, a calculation for gradually changing the value is repeated to obtain a convergence solution.
  • Specific methods include particle swarm optimization, ant colony optimization, and artificial bee colony algorithm.
  • the operation amount storage unit 204 stores operation command value candidates (u 1 to u n ) corresponding to the evaluation function values stored in the minimum value storage unit 203, and sets the current operation amount u 0 to the brake, accelerator, front wheel.
  • the steering angle is output to the actuator 102. Further, it outputs the operation amount candidates (u 1 to u n ) to the output prediction unit 107 shown in FIG.
  • operation amount u 0 in the current time can be calculated by using the operation amount candidates u 1 of the following time points obtained in the previous processing cycle.
  • operation amount candidates (u 1 to u n ) which are time-series operation amounts that minimize the evaluation function F. This means that the trajectory indicated by the solid line in FIG.
  • FIG. 3 is a diagram showing an example of a block configuration of the output prediction unit 107 in the model prediction control unit 101.
  • a state equation calculation unit 301 is means for expressing an operation model of a vehicle by mathematical expressions. For example, when the acceleration and the angle of the traveling direction are input, the state equation calculation unit 301 converts the acceleration and the physical quantity such as the position coordinate, the speed, and the direction of the own vehicle.
  • the storage unit 302 is a unit for temporarily storing the output of the state equation calculation unit 301 and using the output for the prediction process at the next time point. For example, by storing the current position coordinates and speed, a predicted value of the next position coordinates can be calculated.
  • the state equation calculation unit 301 receives time-series predicted operation amounts (u 1 to u n ) from within the operation command value generation unit 106 in order to represent the operation model of the vehicle by mathematical expressions. . Further, a control amount corresponding to the output of the actuator 102 is calculated as a time-series predicted control amount (x 1 to x n ), output to the evaluation function calculation unit 108, and used for calculation of the evaluation function.
  • the storage unit 302 is used to determine the reference position. However, this may be determined based on the current position indicated by the actuator 102 as shown in FIG.
  • FIG. 4 is a diagram illustrating an example of a block configuration of the evaluation function calculation unit 108 in the model prediction control unit 101.
  • an evaluation function calculation unit 108 includes a plurality of constraint condition function units (risk degree calculation unit 401, speed error calculation unit 402, acceleration calculation unit 403, jerk speed) in which constraints necessary for automatic driving are expressed by functions.
  • the value of the evaluation function F to be output to the operation command value generation unit 106 is generated using the calculation unit 404).
  • a constraint condition function unit is provided for the risk degree R output from the situation recognition unit 103 and the time-series prediction control amounts (x 0 to x n ) obtained by the output prediction unit 107. .
  • the evaluation function operation unit 108 includes a plurality of constraint condition function operation units (401 to 404).
  • the evaluation function F is defined by a plurality of constraint condition function units (401 to 404).
  • the plurality of constraint condition functions include a function f1 for the risk degree of the own vehicle obtained by the risk degree calculation unit 401, a function f2 for the speed error obtained by the speed error calculation unit 402, a function f3 for the acceleration obtained by the acceleration calculation unit 403, This is a function f4 regarding jerk speed obtained by jerk calculation section 404.
  • the evaluation function F is a function composed of five elements in which a function f5 regarding the responsiveness obtained by the output prediction unit 107 is further added. The numerical value determined by these five elements is determined to be the smallest.
  • the adder 405 adds the output results of the respective constraint condition functions obtained by the constraint function calculators (401 to 404) to each other and outputs the result to the operation command value generator 106.
  • the evaluation function calculation unit 108 is configured as described above, but as described above, the prediction control device controls the vehicle with the operation amount u when the output of the evaluation function F is minimized.
  • the four constraint functions that determine the output of the evaluation function F that is, the constraint function f1 for the degree of risk, the constraint function f2 for the speed error, the constraint function f3 for the acceleration, and the constraint function f4 for the jerk, It reflects the current driving conditions.
  • FIG. 5 is a diagram illustrating an example of a block configuration of the situation recognition unit 103.
  • a camera 501 captures surroundings of the vehicle in front, rear, left and right.
  • the LiDAR 502 detects a situation around the own vehicle using a laser beam.
  • the millimeter-wave radar 503 detects the surrounding situation by the reflected light of the radio wave.
  • the GPS 504 detects the longitude and latitude where the vehicle is located.
  • the map 505 outputs route information from the departure point of the vehicle to the expected arrival point.
  • the object recognition unit 506 recognizes an object such as another vehicle, bicycle, or pedestrian based on data input from the camera 501, the LiDAR 502, and the millimeter wave radar 503, and outputs object information.
  • the own vehicle route detecting unit 507 detects the current position on the map of the own vehicle based on input information from the GPS 504 and the map 505, and outputs map information around a local point on the route.
  • FIG. 6 is a diagram illustrating a block configuration example of the change amount detection unit 104.
  • the weight calculation unit 601 for normal time sets a value obtained by multiplying the change amounts on the time axis of the object information and the route information input from the situation recognition unit 103 by the coefficients k 0 and k 1 as the weight Wa.
  • Coefficients k 2 and k 3 are output as weights Wb.
  • the failure-time weight calculation unit 602 calculates a value obtained by multiplying the amount of change on the time axis between the object information and the route information input from the situation recognition unit 103 by coefficients k 4 and k 5 , respectively.
  • the selection unit 603 determines that the vehicle is normal based on the diagnosis information of the vehicle input from the ECU or the like mounted on the vehicle, the selection unit 603 selects the output of the weight calculation unit 601 for normal time, and outputs information indicating that the vehicle is faulty When a failure notification signal from the actuator) is input, the output of the weight calculation unit for failure 602 is selected and output. Therefore, the change amount of the own vehicle includes a travel route of the own vehicle and a signal input of a failure notification from the actuator of each unit belonging to the own vehicle.
  • FIG. 7A is a diagram illustrating a method of determining an initial value for the weight Wa by the control condition adjustment unit 105.
  • FIG. 7B is a diagram illustrating a method of determining a prediction period for the weight Wb by the control condition adjusting unit 105.
  • FIG. 8 is a diagram showing an example of a block configuration of the control condition adjusting unit 105.
  • an initial value setting unit 801 determines a candidate value of an initial value for an optimal value search operation to be output to the operation command value generation unit 106 according to the value of the weight Wa input from the change amount detection unit 104.
  • the prediction period setting unit 802 determines (adjusts) a prediction period for performing an optimal value search operation to be output to the operation command value generation unit 106 according to the value of the weight Wb input from the change amount detection unit 104.
  • FIG. 9 is a diagram illustrating an example of a block configuration of the control condition adjustment unit 105 different from the configuration illustrated in FIG. 8, which is an example of adjusting a prediction interval in addition to an initial value and a prediction period of prediction control.
  • an initial value setting unit 801 and a prediction period setting unit 802 have the same functions as those of the block configuration example in FIG.
  • the control condition adjusting unit 105 initializes the solution search operation in the model prediction control unit 101 (prediction control unit) based on the detection results of the means (103, 104) for detecting the amount of change and the direction of change of the surroundings and the vehicle. This is an example of a means for setting a prediction period.
  • FIG. 10 is a diagram illustrating an example of a block configuration of the initial value setting unit 801 illustrated in FIGS. 8 and 9.
  • the random number range adjustment unit 1002 determines the range of the random number to be added to each value based on the previously employed operation amount. The random number range adjustment unit 1002 determines that the closer the value of Wa is to 1, the higher the dependence on the previously adopted operation amount, and narrows the range of values that the random number can take.
  • the previous operation amount dependent generation unit 1003 generates an initial value by adding the random number generated by the random number range adjustment unit 1002 to the previous operation amount.
  • the normal random number generation unit 1004 generates random numbers within a preset range and generates an initial value.
  • FIG. 11A is a graph showing the characteristics of the evaluation function output value with respect to the number of operations when the present invention is not used.
  • the vertical axis indicates the evaluation function output
  • the horizontal axis indicates the number of calculations
  • (1), (2), and (3) indicate the first, second, and third calculations, respectively.
  • the number of calculations required to converge to the minimum value differs each time, and the number of calculations that can be determined to have converged to the minimum value for all three times is 2150.
  • FIG. 11B is a graph showing the characteristics when the previous optimal solution is included in the initial value in the first embodiment of the present invention.
  • the vertical axis represents the evaluation function output
  • the horizontal axis represents the number of calculations.
  • the first calculation (1) requires 3000 calculations to converge to the minimum value because all values generated by random numbers are used as initial values.
  • the second calculation (2) and the third calculation (3) the convergence to the minimum value is completed by 900 calculations because the initial value includes the previous optimal solution.
  • FIG. 11C is a graph showing characteristics when the prediction period in the present invention is shortened from 128 points to 16 points.
  • the vertical axis represents the output of the evaluation function
  • the horizontal axis represents the number of operations.
  • the prediction period is as short as 16 points compared to 128 points in FIG. 11B, so that the number of calculations until all three convergences is 1000 times.
  • FIG. 12 is a diagram showing an operation example of automatic driving by model predictive control.
  • the vehicle 1201 by automatic driving while traveling in the traveling lane of the highway runs behind the vehicle 1202 traveling in the same traveling lane.
  • the driving lanes are indicated by broken lines.
  • FIG. 12A is a diagram in which the own vehicle 1201 is traveling behind another vehicle 1202 on the highway. To perform the operation this time the vehicle 1201 is efficient, sequential control quantity u 0 ⁇ u n (FIG time indicated by a thick solid arrow from the candidates of a plurality of controlled variables x (indicated by a plurality of solid lines) In the example of FIG. 12A, u 0 to u 127 ) are selected, and u 1 is determined as the control amount at the next time point.
  • FIG. 12 shows an embodiment in which the previously selected trajectory is included in the initial value and the prediction control calculation is performed.
  • the selected predicted trajectory is also the same as the example shown in FIG. .
  • the vehicle diagnostic information input to the selection unit 603 is a signal indicating “failure”
  • the same trajectory as the previous time is maintained, thereby contributing to quick fail-operational control (fail-operational). Control contribution mode).
  • ((C) of FIG. 12 is a diagram showing a predicted trajectory obtained by shortening the prediction period.
  • the other vehicle 1202 stops at the shoulder of the road as compared to the example illustrated in FIG. Is shortened to find the predicted trajectory for this time.
  • the time until the optimum trajectory is determined is shortened, so that it is possible to cope with a sudden change in the surrounding situation.
  • the prediction period can be shortened and the trajectory to retreat to the road shoulder can be immediately generated, which contributes to quick fail-safe control (fail-safe control contribution mode). ).
  • the amount of change in the surrounding conditions of the own vehicle is detected, and the initial value and the prediction period of the prediction control are changed according to the detected amount of change.
  • a predictive control device capable of realizing both the riding comfort in normal driving and the quick operation in emergency.
  • the prediction control is performed by including the previously selected trajectory in the initial value, or the prediction period is shortened and the initial value is changed according to the magnitude of the change of the own vehicle and the surrounding conditions of the own vehicle. Is generated by random numbers, and control to switch or perform prediction control is performed. Therefore, it is possible to appropriately control the operation of the vehicle according to the change in the surrounding conditions of the own vehicle.
  • the mode that switches between a mode that contributes to fail operational control and a mode that contributes to rapid fail-safe control is switched.
  • the second embodiment is similar to the first embodiment in that the initial value and the prediction period of the prediction control are changed according to the surrounding conditions of the own vehicle and changes in the own vehicle, but the fail-safe control contribution mode is provided. I haven't. That is, in the second embodiment, the control condition adjustment unit 105 that sets the initial value and the prediction period calculates the initial value and the prediction period to be set according to the surrounding conditions of the vehicle and the amount of change in the vehicle. Has only the fail operational control mode in which the previous calculation result (operation amount) is included in the initial value and set as the operation amount.
  • the difference between the second embodiment and the first embodiment is that, in the second embodiment, the initial value setting unit 801 and the prediction period setting unit 802 of the control condition adjustment unit 105 shown in FIGS. In the mode, the previous operation amount is set.
  • the second embodiment it is possible to realize a predictive control device in which the riding comfort during normal running is improved.
  • the calculation load can be reduced. For example, even when a failure of the own vehicle occurs when driving on a highway, The orbit can be maintained quickly.
  • 101 Model prediction control unit
  • 102 Actuator
  • 103 Situation recognition unit
  • 104 Change amount detection unit
  • 105 Control condition adjustment unit
  • 106 Operation command value generation unit
  • 107 output prediction unit
  • 108 evaluation function calculation unit
  • 201 operation amount generation unit
  • 202 comparison unit
  • 203 minimum value storage unit
  • 204 operation amount storage Unit
  • 301 state equation calculation unit 302 storage unit
  • 401 risk degree calculation unit 402 speed error calculation unit
  • 403 acceleration calculation unit 403 acceleration calculation unit
  • 404 addition Speed calculation section 405 addition section
  • 501 camera 502 LiDAR, 503 millimeter wave radar
  • 504 GPS
  • 505 map information section 506 object Recognition unit
  • 507 ...

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Physics & Mathematics (AREA)
  • Human Computer Interaction (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Traffic Control Systems (AREA)
  • Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
PCT/JP2019/022267 2018-07-02 2019-06-05 予測制御装置 Ceased WO2020008785A1 (ja)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201980031293.0A CN112292717B (zh) 2018-07-02 2019-06-05 预测控制装置
US17/255,748 US20210221402A1 (en) 2018-07-02 2019-06-05 Prediction control device

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2018126250A JP7046740B2 (ja) 2018-07-02 2018-07-02 予測制御装置
JP2018-126250 2018-07-02

Publications (1)

Publication Number Publication Date
WO2020008785A1 true WO2020008785A1 (ja) 2020-01-09

Family

ID=69059938

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2019/022267 Ceased WO2020008785A1 (ja) 2018-07-02 2019-06-05 予測制御装置

Country Status (4)

Country Link
US (1) US20210221402A1 (enExample)
JP (1) JP7046740B2 (enExample)
CN (1) CN112292717B (enExample)
WO (1) WO2020008785A1 (enExample)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114516342A (zh) * 2020-11-19 2022-05-20 上海汽车集团股份有限公司 一种车辆控制方法、装置及车辆

Families Citing this family (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11416171B2 (en) * 2020-01-07 2022-08-16 Western Digital Technologies, Inc. Dynamic predictive latency attributes
JP7122494B2 (ja) * 2020-05-22 2022-08-19 三菱電機株式会社 車両制御システム、車両統合制御装置、電子制御装置、ネットワーク通信装置、車両制御方法、および、車両制御プログラム
JP7342828B2 (ja) * 2020-09-24 2023-09-12 いすゞ自動車株式会社 自動運転装置
US20230365144A1 (en) * 2020-11-27 2023-11-16 Mitsubishi Electric Corporation Control arithmetic device
WO2022172337A1 (ja) * 2021-02-09 2022-08-18 三菱電機株式会社 制御演算装置および制御演算方法
JP7387061B2 (ja) * 2021-04-08 2023-11-27 三菱電機株式会社 シーケンス自動生成装置、シーケンス自動生成方法およびプログラム
JP7195369B2 (ja) * 2021-04-26 2022-12-23 三菱電機株式会社 車両のモデル予測制御装置
JP7241800B2 (ja) * 2021-05-12 2023-03-17 三菱電機株式会社 車両制御装置及び車両制御方法
JP7466796B2 (ja) * 2021-11-19 2024-04-12 三菱電機株式会社 最適演算装置
CN118556239A (zh) * 2022-01-17 2024-08-27 株式会社电装 最优解运算装置
KR102784102B1 (ko) * 2022-08-02 2025-03-21 포티투닷 주식회사 차량의 궤적을 최적화하는 방법 및 장치
US12472981B2 (en) * 2023-06-30 2025-11-18 Mitsubishi Electric Research Laboratories, Inc. Systems and methods for decision making for autonomous vehicles

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006315489A (ja) * 2005-05-11 2006-11-24 Toyota Motor Corp 車両周囲警報装置
JP2007233646A (ja) * 2006-02-28 2007-09-13 Toyota Motor Corp 物体進路予測方法、装置、およびプログラム
JP2012118909A (ja) * 2010-12-03 2012-06-21 Nissan Motor Co Ltd 走行支援装置
WO2012172632A1 (ja) * 2011-06-13 2012-12-20 トヨタ自動車株式会社 運転支援装置及び運転支援方法

Family Cites Families (30)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2762711B2 (ja) * 1990-07-02 1998-06-04 日産自動車株式会社 車両の制動挙動補償装置
JP3481046B2 (ja) * 1996-06-13 2003-12-22 本田技研工業株式会社 車両のアクティブマウント用制御システムにおける故障診断方法及び装置
JP3430832B2 (ja) * 1997-01-27 2003-07-28 日産自動車株式会社 道路曲率推定装置
JP4385392B2 (ja) * 2000-06-15 2009-12-16 マツダ株式会社 車両用情報提供装置
JP4069754B2 (ja) * 2003-02-07 2008-04-02 日産自動車株式会社 車両運動制御装置
JP4055653B2 (ja) * 2003-05-27 2008-03-05 株式会社デンソー 車速制御装置およびプログラム
JP2005339241A (ja) * 2004-05-27 2005-12-08 Nissan Motor Co Ltd モデル予測制御装置および車両用推奨操作量生成装置
WO2007018188A1 (ja) * 2005-08-05 2007-02-15 Honda Motor Co., Ltd. 車両の制御装置
JP4899550B2 (ja) * 2006-03-15 2012-03-21 株式会社豊田中央研究所 フェールセーフ装置及びフェールセーフシステム
JP4797948B2 (ja) * 2006-11-22 2011-10-19 株式会社デンソー 運転行動推定方法および装置
JP4586795B2 (ja) * 2006-12-07 2010-11-24 トヨタ自動車株式会社 車両用制御装置
JP5359459B2 (ja) * 2009-03-27 2013-12-04 トヨタ自動車株式会社 車両のシフト制御装置
JP5351814B2 (ja) * 2010-03-31 2013-11-27 本田技研工業株式会社 車両の運動制御装置
JP5601878B2 (ja) * 2010-05-12 2014-10-08 三菱電機株式会社 経路予測装置
JP5672971B2 (ja) * 2010-10-29 2015-02-18 株式会社アドヴィックス 車両運動制御装置
DE102013213169A1 (de) * 2013-07-04 2015-01-08 Robert Bosch Gmbh Verfahren und Vorrichtung zum Betreiben eines Kraftfahrzeugs in einem automatisierten Fahrbetrieb
JP6109257B2 (ja) * 2015-07-21 2017-04-05 三菱電機株式会社 駆動装置
JP6409744B2 (ja) * 2015-11-06 2018-10-24 株式会社アドヴィックス 車両の走行支援装置
JP2017124659A (ja) * 2016-01-12 2017-07-20 三菱重工業株式会社 駐車支援システム、駐車支援方法及びプログラム
DE102016117438A1 (de) * 2016-09-16 2018-03-22 Knorr-Bremse Systeme für Nutzfahrzeuge GmbH Verfahren und Vorrichtung zum Steuern einer Bewegung eines Fahrzeugs und Fahrzeugbewegungssteuersystem
JP6636218B2 (ja) * 2017-06-20 2020-01-29 三菱電機株式会社 経路予測装置および経路予測方法
JP6939273B2 (ja) * 2017-08-31 2021-09-22 株式会社アドヴィックス ブレーキ制御装置
CN107702716B (zh) * 2017-08-31 2021-04-13 广州小鹏汽车科技有限公司 一种无人驾驶路径规划方法、系统和装置
US10635109B2 (en) * 2017-10-17 2020-04-28 Nio Usa, Inc. Vehicle path-planner monitor and controller
JP6760331B2 (ja) * 2017-11-17 2020-09-23 株式会社デンソー 車両制御装置
GB201720266D0 (en) * 2017-12-05 2018-01-17 Trw Ltd Controlling the operation of a vehicle
EP3726329A4 (en) * 2017-12-12 2021-01-27 Sony Corporation INFORMATION PROCESSING DEVICE, MOVING BODY, CONTROL SYSTEM, INFORMATION PROCESSING METHOD AND PROGRAM
JP2019144691A (ja) * 2018-02-16 2019-08-29 本田技研工業株式会社 車両制御装置
WO2019203022A1 (ja) * 2018-04-20 2019-10-24 ソニー株式会社 移動体、情報処理装置、情報処理方法、及びプログラム
WO2019218097A1 (zh) * 2018-05-14 2019-11-21 Lu Shan 汽车爆胎安全稳定控制系统

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006315489A (ja) * 2005-05-11 2006-11-24 Toyota Motor Corp 車両周囲警報装置
JP2007233646A (ja) * 2006-02-28 2007-09-13 Toyota Motor Corp 物体進路予測方法、装置、およびプログラム
JP2012118909A (ja) * 2010-12-03 2012-06-21 Nissan Motor Co Ltd 走行支援装置
WO2012172632A1 (ja) * 2011-06-13 2012-12-20 トヨタ自動車株式会社 運転支援装置及び運転支援方法

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114516342A (zh) * 2020-11-19 2022-05-20 上海汽车集团股份有限公司 一种车辆控制方法、装置及车辆
CN114516342B (zh) * 2020-11-19 2024-05-03 上海汽车集团股份有限公司 一种车辆控制方法、装置及车辆

Also Published As

Publication number Publication date
CN112292717A (zh) 2021-01-29
JP2020008889A (ja) 2020-01-16
US20210221402A1 (en) 2021-07-22
CN112292717B (zh) 2022-10-04
JP7046740B2 (ja) 2022-04-04

Similar Documents

Publication Publication Date Title
WO2020008785A1 (ja) 予測制御装置
US11794748B2 (en) Vehicle system for recognizing objects
JP6822752B2 (ja) アクティブ車両制御のための運転支援技術
US12187313B2 (en) Methods and systems for vehicle path planning
US12366863B2 (en) Driver-centric model predictive controller
US11392093B2 (en) Prediction control device and method
CN110874642B (zh) 学习装置、学习方法及存储介质
US11372417B2 (en) Method for predicting exiting intersection of moving obstacles for autonomous driving vehicles
CN114212086B (zh) 车辆控制装置、车辆控制方法及存储介质
WO2021089608A1 (en) Adaptive cruise control
JP5577126B2 (ja) 走行支援装置
US12208813B2 (en) Arithmetic operation device for automobiles
JP7019885B2 (ja) 車両制御値決定装置、車両制御値決定方法、およびプログラム
US20220227391A1 (en) Systems and methods for scenario dependent trajectory scoring
KR20200044169A (ko) 자율주행 차량의 충돌 회피 시스템 및 충돌 회피 방법
US20200307586A1 (en) Situational complexity quantification for autonomous systems
CN119370125B (zh) 一种基于模型预测控制的智能车变道轨迹规划方法
Kim et al. Design of an adaptive cruise control/collision avoidance with lane change support for vehicle autonomous driving
US11320820B2 (en) Hyperassociation in episode memory
CN114595913A (zh) 基于人类推理的自主车辆表现评分系统和方法
EP4219259B1 (en) Method, computer system and non-transitory computer readable medium for target selection in the vicinity of a vehicle
JP2012030659A (ja) 状況適合型運転支援装置
US11634133B1 (en) Adaptive automatic preventative braking (APB) distance
US11618460B1 (en) Predictive planning
JP2021163452A (ja) 汎用ナビゲーションシステムを有する車両のための目標指向型ナビゲーションシステム、方法、および非一時的コンピュータ可読媒体

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: 19831232

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19831232

Country of ref document: EP

Kind code of ref document: A1