WO2019058460A1 - 走行支援方法及び走行支援装置 - Google Patents
走行支援方法及び走行支援装置 Download PDFInfo
- Publication number
- WO2019058460A1 WO2019058460A1 PCT/JP2017/033920 JP2017033920W WO2019058460A1 WO 2019058460 A1 WO2019058460 A1 WO 2019058460A1 JP 2017033920 W JP2017033920 W JP 2017033920W WO 2019058460 A1 WO2019058460 A1 WO 2019058460A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- driving
- driver
- learning
- support method
- learning result
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 56
- 230000009471 action Effects 0.000 claims description 2
- 238000013500 data storage Methods 0.000 description 32
- 238000005259 measurement Methods 0.000 description 23
- 238000009826 distribution Methods 0.000 description 21
- 238000012545 processing Methods 0.000 description 17
- 238000001514 detection method Methods 0.000 description 12
- 230000008569 process Effects 0.000 description 9
- 238000000611 regression analysis Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 4
- 230000007613 environmental effect Effects 0.000 description 4
- 230000001133 acceleration Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000012353 t test Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000000692 Student's t-test Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000001172 regenerating effect Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 239000000725 suspension Substances 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000009827 uniform distribution 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
- 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
- B60W50/08—Interaction between the driver and the control system
- B60W50/10—Interpretation of driver requests or demands
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
-
- 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
- B60W40/08—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 drivers or passengers
- B60W40/09—Driving style or behaviour
-
- 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
- B60W50/08—Interaction between the driver and the control system
- B60W50/082—Selecting or switching between different modes of propelling
-
- 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
- B60W60/0011—Planning or execution of driving tasks involving control alternatives for a single driving scenario, e.g. planning several paths to avoid obstacles
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/0055—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots with safety arrangements
- G05D1/0061—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots with safety arrangements for transition from automatic pilot to manual pilot and vice versa
-
- 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
- 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
- B60W40/08—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 drivers or passengers
- B60W2040/0809—Driver authorisation; Driver identity check
-
- 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
- B60W2050/0062—Adapting control system settings
- B60W2050/007—Switching between manual and automatic parameter input, and vice versa
-
- 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
- B60W2050/0062—Adapting control system settings
- B60W2050/0075—Automatic parameter input, automatic initialising or calibrating means
-
- 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
- B60W2050/0062—Adapting control system settings
- B60W2050/0075—Automatic parameter input, automatic initialising or calibrating means
- B60W2050/0082—Automatic parameter input, automatic initialising or calibrating means for initialising the control system
-
- 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
- B60W2520/00—Input parameters relating to overall vehicle dynamics
- B60W2520/10—Longitudinal speed
- B60W2520/105—Longitudinal acceleration
-
- 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
- B60W2540/00—Input parameters relating to occupants
- B60W2540/043—Identity of occupants
-
- 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
- B60W2540/00—Input parameters relating to occupants
- B60W2540/30—Driving style
-
- 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
- B60W2554/80—Spatial relation or speed relative to objects
- B60W2554/802—Longitudinal distance
-
- 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
- B60W2556/00—Input parameters relating to data
- B60W2556/10—Historical data
-
- 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
- B60W2556/00—Input parameters relating to data
- B60W2556/45—External transmission of data to or from the vehicle
Definitions
- the present invention relates to a travel support method and a travel support device for a vehicle.
- Patent Document 1 discloses that a driving history for each driver at the time of manual driving is managed, and at the time of automatic driving, a driving style adapted to each individual is provided to a plurality of drivers.
- Patent Document 1 a sensor for performing face recognition, fingerprint recognition, or the like is required in order to specify a driver who is driving at the time of manual driving.
- a sensor for performing face recognition, fingerprint recognition, or the like is required in order to specify a driver who is driving at the time of manual driving.
- the present invention has been made in view of such problems, and the object of the present invention is to specify a driver without requiring a sensor for specifying the driver and an extra operation.
- a driving support method and a driving support device are provided.
- the driving support method and the driving support apparatus correspond to the identified driver by using the driving characteristic of the driver during the manual driving and identifying the driver. Run control.
- FIG. 1 is a block diagram showing a configuration of a driving control system including a driving assistance apparatus according to an embodiment of the present invention.
- FIG. 2 is a flowchart showing a processing procedure of driving characteristic learning by the driving assistance apparatus according to the embodiment of the present invention.
- FIG. 3 is a schematic view showing a comparison of unregistered learning results and registered learning results in the driving support apparatus according to an embodiment of the present invention.
- FIG. 1 is a block diagram showing a configuration of a driving control system 100 including a driving assistance apparatus 11 according to the present embodiment.
- the driving control system 100 includes a driving support device 11, a driving condition detection unit 21, a surrounding condition detection unit 22, a driving switch 23, a control state presentation unit 61, and an actuator 31.
- a driving support device 11 includes a driving support device 11, a driving condition detection unit 21, a surrounding condition detection unit 22, a driving switch 23, a control state presentation unit 61, and an actuator 31.
- the driving support apparatus 11 learns the driving characteristic based on predetermined learning target data among the traveling data obtained during the manual driving of the driver in a vehicle capable of switching between the manual driving and the automatic driving by the driver ((1) Driving characteristic learning) is a controller that executes a process of applying the learning result to travel control of automatic driving.
- this embodiment demonstrates the case where the driving assistance apparatus 11 is mounted in a vehicle, a communication apparatus is installed in a vehicle, some driving assistance apparatuses 11 are installed in an external server, and the process of an external server is carried out.
- the driver's driving characteristics may be learned.
- the driving support device 11 is mounted on a vehicle, it is possible to learn the driving characteristics of the driver who owns or uses the vehicle. Then, learning target data for a predetermined period (for example, the latest one month) can be stored, and can be reflected in the automatic driving of a vehicle owned or used by the driver.
- learning target data for a predetermined period for example, the latest one month
- the traveling condition detection unit 21 detects vehicle speed, steering angle, acceleration, inter-vehicle distance with the preceding vehicle, relative velocity with the preceding vehicle, current position, display state of the direction indicator, lighting condition of the headlights, operating condition of the wiper, etc.
- the traveling data indicating the traveling state of the vehicle is detected.
- the traveling condition detection unit 21 may be obtained from sensors provided on a brake pedal or an accelerator pedal, sensors for acquiring the behavior of the vehicle such as wheel side sensors or yaw rate sensors, a laser radar, a camera, or sensors thereof.
- In-vehicle networks and navigation devices such as CAN (Controller Area Network) that communicate the stored data are included.
- the surrounding condition detection unit 22 includes the number of lanes of the road on which the vehicle travels, the speed limit, the road gradient, the road curvature, the display state of traffic light ahead of the vehicle, the distance to the intersection ahead of the vehicle, the number of vehicles traveling in front of the vehicle, Environment information representing an environment in which the vehicle is traveling is detected, such as the planned route of the intersection ahead and the presence or absence of suspension regulation.
- the surrounding situation detection unit 22 includes a camera mounted on a vehicle, a laser radar, and a navigation device. Note that the display state of the traffic signal ahead of the vehicle and the presence or absence of the temporary stop regulation may be detected using the road-vehicle communication.
- the number of vehicles traveling in front of the vehicles may be detected using inter-vehicle communication or a cloud service linked with a smartphone.
- the planned route of the intersection ahead of the vehicle is acquired from the display state of the navigation device and the turn indicator.
- the illuminance around the vehicle, the air temperature, and the weather condition are acquired from the illuminance sensor, the outside air temperature sensor, and the wiper switch, respectively.
- the illuminance may be obtained from the switch of the headlight.
- the driving switching switch 23 is a switch that is mounted on a vehicle and switches between automatic driving and manual driving when operated by an occupant of the vehicle. For example, it is a switch installed in the steering of a vehicle.
- the control state presentation unit 61 displays whether the current control state is the manual operation or the automatic operation on the display screen of the meter display unit, the navigation device, a head-up display, or the like. In addition, a notification sound notifying the start and end of automatic driving is also output, and it is also indicated whether learning of driving characteristics has ended.
- the actuator 31 receives an execution command from the travel support device 11, and drives each part such as an accelerator, a brake, and a steering of the vehicle.
- the driving support apparatus 11 includes a learning target data storage unit 41, a driving characteristic learning unit 42, a driver identification unit 43, and an automatic driving control execution unit 45.
- the learning target data storage unit 41 acquires travel data related to the traveling state of the vehicle and environment information related to the traveling environment around the vehicle from the traveling state detection unit 21, the surrounding state detection unit 22, and the driving switching switch 23.
- predetermined learning target data necessary for learning the driving characteristic of the driver is stored in association with the traveling scene such as the traveling state of the vehicle and the traveling environment.
- the learning target data storage unit 41 stores, for each driver, predetermined learning target data necessary for learning the driving characteristic of the driver. That is, the learning target data storage unit 41 associates the learning target data with the driver, and classifies and stores the learning target data for each driver.
- identification of the driver matched with learning object data is performed by the driver specific part 43 mentioned later.
- the new learning target data input to the learning target data storage unit 41 from the traveling state detection unit 21, the surrounding state detection unit 22, and the driving changeover switch 23 is specified as the driver identification corresponding to the learning target data.
- the learning target data storage unit 41 is temporarily stored as unregistered learning target data.
- the learning target data corresponds to the learning target data corresponding to the driver identified by the driver identification unit 43. Is registered in the learning target data storage unit 41.
- the learning target data is the learning target data registered in the learning target data storage unit 41.
- the timing which a driver specifies should just be a timing which can specify a driver, for example, the timing which traveled 3 km, the timing which traveled for 10 minutes, the timing which acquired the data of a predetermined amount (100 plots, 1 kilobyte etc. It may be timing at which a predetermined amount of data is acquired.
- the learning target data storage unit 41 may store the deceleration timing during the manual driving of the driver.
- the learning target data storage unit 41 follows the preceding vehicle in deceleration timing when stopping at a stop position such as a stop line laid at an intersection or the like, deceleration timing when stopping behind a leading vehicle while stopping.
- the timing of deceleration may be stored.
- the learning target data storage unit 41 is a vehicle at the time of the brake operation, such as a brake operation position which is a position for operating the brake with respect to the stop position, a distance to the stop position, a vehicle speed when operating the brake, and acceleration. It may store the behavior of
- the “deceleration timing” includes the timing at which the driver operates the brake (brake pedal) when the vehicle is stopped at the stop position to operate the brake, the timing at which the vehicle is decelerated, the timing at which the accelerator operation is ended, Alternatively, the timing at which the operation of the brake pedal is started is included. Alternatively, the timing at which the driver's operation amount (depression amount) of the brake pedal becomes equal to or more than the predetermined amount set in advance, and the operation amount (depression amount) of the accelerator pedal by the driver are preset in “deceleration timing". It may include the timing when it becomes less than quantitative. Alternatively, the timing includes the timing when the driver operates the brake and the control amount at the time of the brake operation reaches a preset constant value, or the timing at which the speed of increase of the control amount at the time of the brake operation reaches a certain value. May be
- deceleration timing refers to the timing at which the brake was actuated (brake start timing), the accelerator off timing (brake start timing), the timing at which the brake control amount reached a certain value, and the increase speed of the brake control amount. Is a concept that includes the timing when the constant value is reached. In other words, it is the timing at which the driver feels the brake operation.
- the brake in the present embodiment includes a hydraulic brake, an electric brake, and a regenerative brake.
- a hydraulic brake even if the hydraulic brake, the electric control brake, and the regenerative brake are not in operation, the state in which the deceleration is in operation may be included.
- the learning target data storage unit 41 may store an inter-vehicle distance between a vehicle and a preceding vehicle while the driver is driving manually.
- the learning target data storage unit 41 stores, in addition to the inter-vehicle distance, data such as the inter-vehicle distance at a stop, the relative speed with respect to the preceding vehicle, the steering angle, the deceleration, and the continuation time following the preceding vehicle. It may be
- the learning target data storage unit 41 may store the deceleration start speed when the vehicle stops at the intersection, the braking distance when the vehicle stops at the intersection, and the like. In addition, the learning target data storage unit 41 may store data such as the operation amount of the brake pedal and the accelerator pedal of the vehicle, the vehicle speed and the deceleration, the distance to the stop line of the intersection, etc. .
- the learning target data storage unit 41 may also store environmental information in which the vehicle is placed.
- environmental information the number of lanes of the road on which the vehicle travels, road curvature, speed limit, road slope, presence / absence of stop restriction, display condition of traffic light, distance from vehicle to intersection, number of vehicles ahead of vehicle, direction indicator , The weather around the vehicle, the temperature, the illuminance, and the like.
- the driving characteristic learning unit 42 reads the learning target data stored in the learning target data storage unit 41, and learns the driving characteristic of the driver corresponding to the learning target data in consideration of the traveling state and the degree of influence from the traveling environment. Do. The driving characteristic learning unit 42 learns driving characteristics for each learning target data based on the learning target data (unregistered learning target data and registered learning target data) stored in the learning target data storage unit 41. Do. The driving characteristic learning unit 42 associates the learning result thus calculated with the driver, and classifies and stores the learning result for each driver.
- the driver identification part 43 mentioned later performs identification of the driver matched with a learning result.
- the learning result newly calculated by the driving characteristic learning unit 42 is temporarily calculated as an unregistered learning result until the driver identification unit 43 identifies the driver associated with the learning result. It is stored in the learning unit 42. Further, after the driver identification unit 43 identifies the driver associated with the learning result, the learning result corresponds to the driving characteristic as a learning result corresponding to the driver identified by the driver identification unit 43. It is registered in the learning unit 42. As a result, the learning result is a learning result registered in the driving characteristic learning unit 42.
- the learning performed by the driving characteristic learning unit 42 may be performed in real time simultaneously with storing the learning target data in the learning target data storage unit 41.
- the learning performed by the driving characteristic learning unit 42 may be performed at predetermined time intervals or at timing when accumulation of a predetermined amount of learning target data is performed in the learning target data storage unit 41. Good.
- the driver identification unit 43 identifies the driver based on the unregistered learning result temporarily stored in the learning target data storage unit 41. Specifically, the driver identification unit 43 compares the unregistered learning result stored in the learning target data storage unit 41 with the registered learning result.
- the driver identification unit 43 does not The driver corresponding to the registered learning result is identified as the same person as the registered learning result driver.
- the driver identification unit 43 If, as a result of comparison in the driver identification unit 43, no registered learning result having a driving characteristic within which the difference between the unregistered learning result and the driving characteristic is within the predetermined value is not found, the driver identification unit 43 The driver corresponding to the unregistered learning result is identified as a new driver (a driver who does not correspond to any registered driver).
- an approval act for the driver's registration may be requested. This request may be performed using an in-vehicle display or may be performed using a speaker. After requesting the occupant, the occupant's selection may be received by touch input on the display, or the microphone may recognize and receive the occupant's voice.
- the driver may be requested to input information identifying the driver. This request may be performed using an in-vehicle display or may be performed using a speaker. After requesting the occupant, the occupant's selection may be received by touch input on the display, or the microphone may recognize and receive the occupant's voice.
- a plurality of learned learning results having driving characteristics within a predetermined value of the difference between the unregistered learning results and the driving characteristics are found, a plurality of learning results are found.
- the occupant is requested to select one of a plurality of corresponding drivers. This request may be performed using an in-vehicle display or may be performed using a speaker. After requesting the occupant, the occupant's selection may be received by touch input on the display, or the microphone may recognize and receive the occupant's voice.
- the automatic driving control execution unit 45 executes the automatic driving control when the vehicle travels in the automatic driving section or when the driver selects the automatic driving by the driving switching switch 23. At this time, the automatic driving control execution unit 45 applies the learning result learned by the driving characteristic learning unit 42 to traveling control of automatic driving.
- the driving support device 11 is composed of a microcomputer, a microprocessor, a general-purpose electronic circuit including a CPU, and peripheral devices such as a memory. Then, the specific program is executed to operate as the above-described learning target data storage unit 41, the driving characteristic learning unit 42, the driver specifying unit 43, and the automatic driving control execution unit 45. Each function of such a travel support device 11 can be implemented by one or more processing circuits.
- the processing circuitry comprises a programmed processing device such as, for example, a processing device including an electrical circuit, and an application specific integrated circuit (ASIC) or conventional circuitry arranged to perform the functions described in the embodiments. It also includes devices such as parts.
- step S101 the driving support apparatus 11 determines whether the vehicle is in a manual operation based on the state of the driving switch 23. If the vehicle is in the manual operation, the process proceeds to step S103. If the vehicle is in the automatic operation, the process of the driving characteristic learning is ended and the automatic operation control is executed.
- the learning target data storage unit 41 detects traveling data related to the traveling state of the vehicle and environment information related to the traveling environment around the vehicle from the traveling state detection unit 21, the surrounding state detection unit 22, and the driving switch.
- the travel data to be detected includes vehicle speed, steering angle, acceleration, deceleration, inter-vehicle distance with the preceding vehicle, relative velocity with the preceding vehicle, current position, planned route of the front intersection, operation amount of brake pedal and accelerator pedal, It detects the duration during which the preceding vehicle is following, the lighting state of the headlights, the operating state of the wiper, etc.
- New learning target data including traveling data and environment information is temporarily stored in the learning target data storage unit 41 as unregistered learning target data.
- step S105 the driving characteristic learning unit 42 corresponds to the learning target data in consideration of the traveling state and the influence degree from the traveling environment based on the learning target data stored in the learning target data storage unit 41. Learn the driver's driving characteristics.
- the learning result obtained based on the unregistered learning object data is temporarily stored in the driving characteristic learning unit 42 as the unregistered learning result.
- the driving characteristic learning unit 42 creates a regression model (multiple regression model) to obtain a formula that quantitatively represents the relationship between two or more types of data included in the learning target data, and performs regression analysis (multiple regression). Learning is done by performing analysis.
- N measurement results (V 1 , D 1 ), (V 2 , D 2 ),..., (V N , D N ) are obtained for two sets of data such as vehicle speed V and inter-vehicle distance D.
- V ⁇ 1 + ⁇ 2 D (1)
- the error term ⁇ i is defined by the following equation (2), where ⁇ i is the error from the regression model of the ith measurement result.
- the parameters ⁇ 1 and ⁇ 2 when minimizing the sum of squares S of the error terms ⁇ i are estimators of the regression coefficients ⁇ 1 and ⁇ 2 appearing in the equation (1), and the least squares estimator L 1 , L Called 2
- a quantitative relationship between the vehicle speed V and the inter-vehicle distance D can be estimated by determining the least squares estimators L 1 and L 2 .
- a regression residual Ei is defined by the following equation (3).
- the regression residual Ei follows a normal distribution (mean 0, standard deviation ⁇ E ). Therefore, to estimate the standard deviation of the regression residuals E i.
- the estimator of the standard deviation ⁇ E of the regression residual E i is hereinafter referred to as the standard error s E.
- the standard error s E is defined by the following equation (4).
- the least squares estimators L 1 and L 2 are linear functions of the regression residual E i considered to follow the normal distribution
- the least squares estimator L 1 follows the normal distribution (mean ⁇ 1 , standard deviation ⁇ L1 )
- the least squares estimator L 2 is considered to follow a normal distribution (mean ⁇ 2 , standard deviation ⁇ L2 ). Therefore, the standard deviations ⁇ L1 and ⁇ L2 of the least squares estimator L 1 and L 2 can be estimated based on the equation (3) and the standard error s E.
- it represents a standard error s L2 an estimate of the standard deviation sigma L1 least squares estimator L 1 standard error s L1, the estimated amount of the least-squares estimator L 2 standard deviations sigma L2.
- the driving characteristic learning unit 42 learns the driving characteristic based on the learning target data by estimating the least squares estimator [L 1 , L 2 ] and the standard error [s L1 , s L2 ] as described above. .
- the driving characteristic learning unit 42 calculates the driving characteristic of the learning result obtained from the data to be learned, using the least square estimated amount [L 1 , L 2 ] and the standard error [s L1 , s L2 ] obtained as described above. As, remember.
- the driving characteristic learning unit 42 may store the number N of data included in the learning target data used for learning.
- the driving characteristic learning unit 42 may store the traveling frequency of the area in which the vehicle travels, corresponding to the learning target data used for learning.
- regression analysis is performed using not only the vehicle speed V and the inter-vehicle distance D, but also other plural data. Analysis
- regression analysis was performed between two data, so two values L 1 and L 2 were obtained as the least squares estimator, but in general, when performing regression analysis between M data, the minimum M values [L 1 , L 2 ,..., L M ] are obtained as squared estimated quantities.
- M values [s L1 , s L2 ,..., S LM ] are obtained as standard errors corresponding to the least squares estimator.
- linear model linear regression
- any model that can be converted to a linear model by functional conversion or the like It is possible to use the method of linear model described above.
- an elastic model in which the explained variable is proportional to the power of the explanatory variable, or an elastic model (exponential regression) in which the explained variable is proportional to the exponential function of the explanatory variable may be used.
- a combination of a linear model, an elastic model, and an elastic model may be used.
- the regression residuals E i considered as normally distributed generally, not necessarily follow a normal distribution.
- the number N of measurement results is small (for example, when N is less than 30)
- learning of operating characteristics is performed assuming a distribution other than normal distribution according to the nature of the data. Also good.
- learning of operating characteristics may be performed on the assumption of a binomial distribution, a Poisson distribution, and a uniform distribution.
- Non-parametric estimation may be performed to learn driving characteristics.
- an output error is calculated when training data is input to the neural network, and various parameters of the neural network are calculated to minimize the error.
- the learning of the driving characteristic may be performed by performing the adjustment of.
- learning is performed using all the measurement results included in the learning target data, but even if sorting or weighting of measurement results used for learning is performed according to the traveling area in which the vehicle travels Good. For example, the information of the route on which the vehicle travels and the frequency of the place (place of departure, stopover, destination) is determined based on one or more learning target data, and the measurement result included in the learning target data being learned When the measurement is performed in an area where the traveling frequency is high, the contribution of the measurement result to the sum of squares S of the error term ⁇ i used in the regression analysis may be increased.
- the sum of squares S of the error terms ⁇ i may be defined by the following equation (5) with the weighting parameter W i as the parameter W i .
- the weighting parameter W i takes a value of 1 with respect to the measurement results used for learning, and the weighting parameter W for the measurement results not used for learning. i takes the value 0.
- the weighting parameter W i takes a larger value as the traveling frequency of the area corresponding to the measurement results is higher.
- sorting or weighting the measurement results used for learning allows the driving characteristic of the driver in the area to be driven manually as the traveling frequency of the area where the vehicle travels increases. Can be learned with high priority. As the traveling frequency of the area where the vehicle travels is higher, the driver is considered to be more accustomed to driving in the area, and the driving characteristic of the driver is considered to appear more strongly in the learning target data.
- the driving characteristics and the standard error are estimated from the learning object data by regression analysis, but based on the frequency distribution (the horizontal axis is the deceleration timing and the vertical axis is the frequency) related to the deceleration timing obtained from the measurement result
- the mean value and the standard deviation of the deceleration timing may be estimated as the operating characteristic and the standard error, respectively.
- the average value and standard deviation of the inter-vehicle distance may be estimated as standard error.
- the average value and standard deviation of the vehicle speed during deceleration operation are the operating characteristics and standard error, respectively. It may be estimated as
- step S107 the driver specifying unit 43 specifies the driver based on the unregistered learning result temporarily stored in the learning target data storage unit 41. Specifically, the driver identification unit 43 compares the unregistered learning result stored in the learning target data storage unit 41 with the registered learning result.
- unregistered learning results (the least squares estimator L U and standard error s U as driving characteristics) are obtained, and as the registered learning results, the driver A's learning results (driving As the characteristics, the least squares estimator L A , the standard error s A ), the learning results of the driver B (as the driving characteristics, the least square estimator L B , the standard errors s B ), the learning results of the driver C (as the driving characteristics , Least squares estimator L c , standard error s c ) are already registered.
- the driver identification unit 43 compares the learning results with each other by performing t-test on the driving characteristic.
- T UA ⁇ L U ⁇ L A ⁇ / ⁇ s U 2 + s A 2 ⁇ 1/2 (6)
- the least squares estimator L U and the least squares estimator L A follows a normal distribution, two-sample t-statistic T UA between the learning result of unregistered learned result that the driver A follows the t-distribution.
- the t distribution has a degree of freedom depending on the learning target data corresponding to the unregistered learning result, the learning target data corresponding to the learning result of the driver A, and the like.
- the significance level ⁇ may be changed based on the number of measurement results included in the learning target data.
- the driver identification unit 43 calculates a two-sample t statistic T UB between the unregistered learning result and the driver B's learning result, and further, the unregistered learning result and the driver C's learning Calculate the two-sample t statistic T UC between the results.
- the driver identification unit 43 calculates a two-sample t statistic between the unregistered learning result and the registered learning result.
- the driver specifying unit 43 does not compare the above-described learning results.
- step S109 the driver identification unit 43 determines whether there is a registered learning result that matches the unregistered learning result.
- the driver identification unit 43 determines that the calculated two-sample t statistic T UA is a value largely deviated from 0, and in particular, the percentage point T in the t distribution in which the absolute value of the two-sample t statistic T UA is determined by the significance level ⁇ . If the value is larger than ⁇ / 2 , the null hypothesis is rejected.
- the percentage point T ⁇ / 2 refers to the value of a two-sample t statistic such that the upper probability in the t distribution is ⁇ / 2.
- the set of statistic values to which the null hypothesis should be rejected (rejected area) includes both a positive area outside of zero and a negative area outside of zero, and it is necessary to perform a two-sided test Therefore, the upper probability is set to half the value of the significance level ⁇ .
- the driver identification unit 43 determines that the unregistered learning result and the driver A's learning result do not match. Furthermore, the driver corresponding to the unregistered learning result is specified as not the driver A.
- the driver identification unit 43 determines that the unregistered learning result matches the learning result of the driver A. Further, the driver corresponding to the unregistered learning result is specified as the driver A.
- the driver identification unit 43 compares L U representing the driving characteristic of the unregistered learning result with L A representing the driving characteristic of the driver A's learning result, and the difference between L U and L A is a predetermined value. If it is the following, driver specific part 43 specifies that a driver corresponding to an unregistered study result is driver A of a registered study result.
- the driver identification unit 43 determines whether the unregistered learning result matches the learning result of the driver B based on the two-sample t statistic TUB , and the unregistered learning result is used as the unregistered learning result. It is specified whether the corresponding driver is the driver B or not. In addition, the driver identification unit 43 determines whether the unregistered learning result matches the driver C's learning result based on the two-sample t statistic value UC , and corresponds to the unregistered learning result. It is specified whether the driver is the driver C or not.
- the driver identification unit 43 does not A driver corresponding to the learning result of registration is specified as a new driver (a driver who does not correspond to any registered driver).
- step S109 As a result of comparison in the driver identification unit 43, if there is no registered learning result that matches the unregistered learning result (in the case of NO at step S109), the process proceeds to step S111, and matches with the unregistered learning result. If there is a registered learning result (YES in step S109), the process proceeds to step S113.
- step S111 the learning target data storage unit 41 registers the unregistered learning target data as learning target data corresponding to a new driver. Further, the driving characteristic learning unit 42 registers an unregistered learning result as a learning result corresponding to a new driver.
- step S113 as a result of comparison in driver identification unit 43, when there is only one registered learning result that matches the unregistered learning result (YES in step S113), the process proceeds to step S115, and automatic The operation control execution unit 45 applies the registered learning result that matches the unregistered learning result to the automatic driving.
- step S113 if there are a plurality of registered learning results that match the unregistered learning results (in the case of NO in step S113), the process proceeds to step S117, and the control state presentation unit 61 matches the registered ones. A plurality of driver candidates corresponding to the learning result are displayed.
- the automatic driving control execution unit 45 Is a registered learning result that matches the unregistered learning result, and applies the learning result of the selected driver to automatic driving.
- one driving characteristic (one least square estimator) was taken, and the t test for the driving characteristic was performed, but two or more driving characteristics are It may be combined to perform t-test on the operating characteristic. More accurate comparison of learning results and identification of a driver are possible by combining a larger number of driving characteristics than using only one driving characteristic.
- the unregistered learning result is applied instead of applying the registered learning result to the automatic driving in steps S115 and S119.
- the learning result obtained by performing learning using both the target data and the learning result corresponding to the specified driver may be applied to automatic driving.
- step S115 and step S119 the unregistered learning target data is merged with the learning target data of the specified driver, and the learning result based on the newly obtained learning target data is applied to automatic driving. May be By this process, the data size of the learning target data can be increased, and the learning result in which the driving characteristic of the specified driver is more strongly reflected can be applied to the automatic driving.
- the two-sample t statistic on the assumption that the t distribution is followed may be determined, and a test amount corresponding to the distribution may be calculated.
- nonparametric estimation may be performed based on learning target data, and learning results may be compared.
- the learning results may be compared by deep learning (deep learning, machine learning) using a neural network.
- the comparison between learning results includes various methods as described above.
- a predetermined probability is calculated based on two or more learning results to be compared, and it is possible to reject or adopt the null hypothesis that “the learning results match” by comparing the probability and the significance level. Any method can be used as a method of comparing learning results in the present invention.
- the driver in the vehicle capable of switching between the manual driving and the automatic driving by the driver, the driver can The driving control is performed based on the learning result corresponding to the identified driver. As a result, the driver can be identified without requiring a sensor for identifying the driver or an extra operation, and appropriate driving support suitable for the driver can be performed.
- the driver can be identified based on the driving characteristics during manual driving.
- the cost can be reduced compared to products equipped with sensors for For example, it is possible to reduce the price of a fingerprint authentication sensor of about 5,000 yen on a mass-produced basis from the manufacturing cost.
- the driving support method compares the driving characteristic during manual driving with the learning result corresponding to the driver, and is between the driving characteristic during manual driving and the driving characteristic of the learning result.
- the difference is larger than the predetermined value
- the driving characteristic during the manual driving may be registered as a learning result of the new driver.
- the driver can be accurately identified based on the driver's inherent driving characteristics.
- a new driver not registered can be registered automatically without the need for a driver's special operation.
- the travel support method according to the present embodiment may require an approval action for registration with the occupant when registering a new driver's learning result.
- an approval action for registration with the occupant when registering a new driver's learning result.
- the travel support method may require the occupant to input information for identifying the driver when registering a new driver's learning result. This makes it possible to set a driver corresponding to the learning result. Therefore, when using the learning result after setting, for example, when requesting the driver to select the driver, the passenger can select an appropriate learning result.
- the input of attributes such as age and gender may be requested.
- the driving support method compares the driving characteristic during the manual driving with the learning result corresponding to the driver, and is between the driving characteristic during the manual driving and the driving characteristic of the learning result.
- the driver may be required to select one of a plurality of drivers corresponding to the plurality of learning results found.
- the user can select whether to perform travel control of automatic driving based on which of a plurality of drivers corresponding to the plurality of learning results found. Furthermore, it is possible to suppress the use of learning results not intended by the user.
- the driving support method according to the present embodiment may be preferentially used as the driving characteristic during manual driving when specifying the driver as the traveling frequency of the area in which the vehicle travels is higher.
- the traveling frequency of the area where the vehicle travels is higher, the driver is considered to be more accustomed to driving in the area, and the driving characteristic of the driver is considered to appear more strongly in the learning target data. Therefore, the driver can be specified more accurately by setting the priority based on the traveling frequency of the area.
- the driving support method uses the deceleration timing during manual operation, the distance between the vehicle and the preceding vehicle, the vehicle speed during deceleration operation, or a combination of these as the driving characteristic during manual operation. It may be Among the driving characteristics that appear in the travel data of the vehicle, the driving characteristics such as the deceleration timing during manual driving, the distance between the vehicle and the preceding vehicle, and the vehicle speed during deceleration operation are driver characteristics even compared to other driving characteristics. It is a driving characteristic that tends to appear. Therefore, the driver can be specified more accurately by using these driving characteristics.
- the driver identification based on the learning result may not be performed. Therefore, the processing time required to identify the driver can be reduced, and the speed of the entire system can be increased.
- the driving support method according to the present embodiment may be one in which driving characteristics for each driver are learned by an external server provided outside the vehicle. Thereby, the processing load on the vehicle can be reduced.
- the external server integrates and manages the learning results from the plurality of vehicles, and the vehicle for which traveling control by automatic driving is necessary is required from the external server By distributing the learning result, the learning result can be taken over among a plurality of vehicles. This makes it possible to execute appropriate driving support suited to the driver. Performing processing on an external server is particularly useful when it is assumed that a driver uses a plurality of vehicles, such as in car shelling.
- the processing circuitry comprises a programmed processing device, such as a processing device that includes an electrical circuit.
- the processing device also includes devices such as application specific integrated circuits (ASICs) and conventional circuit components arranged to perform the functions described in the embodiments.
- ASICs application specific integrated circuits
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- Mechanical Engineering (AREA)
- Transportation (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Aviation & Aerospace Engineering (AREA)
- Mathematical Physics (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
- Traffic Control Systems (AREA)
- Regulating Braking Force (AREA)
Abstract
Description
図1は、本実施形態に係る走行支援装置11を含む運転制御システム100の構成を示すブロック図である。図1に示すように、本実施形態に係る運転制御システム100は、走行支援装置11、走行状況検出部21、周囲状況検出部22、運転切替スイッチ23、制御状態提示部61、及びアクチュエータ31を備えている。
次に、本実施形態に係る走行支援装置11による運転特性学習の処理手順を図2のフローチャートを参照して説明する。図2に示す運転特性学習の処理は、車両のイグニッションがオンされると開始する。
以上詳細に説明したように、本実施形態に係る走行支援方法では、運転者による手動運転と自動運転とを切り替え可能な車両において、運転者の手動運転中の運転特性を用いて、運転者を特定し、特定した運転者に対応した学習結果に基づいて走行制御を行う。これにより、運転者の特定のためのセンサや余分な操作を必要とせずに運転者の特定ができ、運転者に合った適切な走行支援を実行できる。
21 走行状況検出部
22 周囲状況検出部
23 運転切替スイッチ
31 アクチュエータ
41 学習対象データ記憶部
42 運転特性学習部
43 運転者特定部
45 自動運転制御実行部
61 制御状態提示部
Claims (12)
- 運転者による手動運転と自動運転とを切り替え可能な車両において、運転者の手動運転中の走行データから運転者ごとの運転特性を学習し、この学習結果を自動運転の走行制御に適用する走行支援方法であって、
運転者の手動運転中の運転特性を用いて、前記運転者を特定し、
特定した前記運転者に対応した前記学習結果に基づいて前記走行制御を行う走行支援方法。 - 請求項1に記載の走行支援方法であって、
前記手動運転中の運転特性と、運転者に対応した前記学習結果とを比較し、
前記手動運転中の運転特性と、前記学習結果の運転特性との間にある差が所定値よりも大きい場合に、前記手動運転中の運転特性を新規の運転者の学習結果として登録すること
を特徴とする走行支援方法。 - 請求項2に対する走行支援方法であって、
新規の運転者の学習結果を登録する場合に、乗員に登録する事に対する承認行為を要求すること
を特徴とする走行支援方法。 - 請求項2又は3に対する走行支援方法であって、
新規の運転者の学習結果を登録する場合に、乗員に前記運転者を特定する情報の入力を要求すること
を特徴とする走行支援方法。 - 請求項1~4のいずれか一項に記載の走行支援方法であって、
前記手動運転中の運転特性と、運転者に対応した前記学習結果とを比較し、
前記手動運転中の運転特性と、前記学習結果の運転特性との間にある差が所定値以内の運転特性を有する学習結果が複数見つかった場合、
見つかった複数の前記学習結果に対応する複数の運転者のいずれかの選択を乗員に要求すること
を特徴とする走行支援方法。 - 請求項1~5のいずれか一項に記載の走行支援方法であって、
前記車両が走行するエリアの走行頻度が高いほど、前記運転者を特定する時の手動運転中の運転特性として優先して用いること
を特徴とする走行支援方法。 - 請求項1~6のいずれか一項に記載の走行支援方法であって、
手動運転中の減速タイミングを前記手動運転中の運転特性として用いること
を特徴とする走行支援方法。 - 請求項1~7のいずれか一項に記載の走行支援方法であって、
手動運転中の、前記車両の先行車との車間距離を前記手動運転中の運転特性として用いること
を特徴とする走行支援方法。 - 請求項1~8のいずれか一項に記載の走行支援方法であって、
手動運転中の、減速操作中の車速を前記手動運転中の運転特性として用いること
を特徴とする走行支援方法。 - 請求項1~9のいずれか一項に記載の走行支援方法であって、
登録済の学習結果が存在しない場合、もしくは、登録済の学習結果が1つである場合、前記学習結果に基づく前記運転者の特定を行わないこと
を特徴とする走行支援方法。 - 請求項1~10のいずれか一項に記載の走行支援方法であって、
前記車両の外部に備えた外部サーバによって、運転者ごとの運転特性を学習すること
を特徴とする走行支援方法。 - 運転者による手動運転と自動運転とを切り替え可能な車両において、運転者の手動運転中の走行データから運転者ごとの運転特性を学習し、この学習結果を自動運転の走行制御に適用する走行支援装置であって、
運転者の手動運転中の運転特性を用いて、前記運転者を特定する運転者特定回路と、
特定した前記運転者に対応した前記学習結果に基づいて前記走行制御を行う自動運転制御実行回路と、
を備えたことを特徴とする走行支援装置。
Priority Applications (9)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
BR112020005415-1A BR112020005415A2 (pt) | 2017-09-20 | 2017-09-20 | método de assistência de deslocamento e dispositivo de assistência de deslocamento |
US16/647,598 US20200278685A1 (en) | 2017-09-20 | 2017-09-20 | Travel Assistance Method and Travel Assistance Device |
CN201780095062.7A CN111108539A (zh) | 2017-09-20 | 2017-09-20 | 行驶支持方法以及行驶支持装置 |
MX2020002932A MX2020002932A (es) | 2017-09-20 | 2017-09-20 | Metodo de asistencia al desplazamiento y dispositivo de asistencia al desplazamiento. |
JP2019542871A JPWO2019058460A1 (ja) | 2017-09-20 | 2017-09-20 | 走行支援方法及び走行支援装置 |
PCT/JP2017/033920 WO2019058460A1 (ja) | 2017-09-20 | 2017-09-20 | 走行支援方法及び走行支援装置 |
EP17925860.3A EP3686862A4 (en) | 2017-09-20 | 2017-09-20 | DISPLACEMENT ASSISTANCE PROCESS AND DISPLACEMENT ASSISTANCE DEVICE |
RU2020113690A RU2743829C1 (ru) | 2017-09-20 | 2017-09-20 | Способ помощи при движении и устройство помощи при движении |
CA3076322A CA3076322A1 (en) | 2017-09-20 | 2017-09-20 | Travel assistance method and travel assistance device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2017/033920 WO2019058460A1 (ja) | 2017-09-20 | 2017-09-20 | 走行支援方法及び走行支援装置 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2019058460A1 true WO2019058460A1 (ja) | 2019-03-28 |
Family
ID=65811443
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2017/033920 WO2019058460A1 (ja) | 2017-09-20 | 2017-09-20 | 走行支援方法及び走行支援装置 |
Country Status (9)
Country | Link |
---|---|
US (1) | US20200278685A1 (ja) |
EP (1) | EP3686862A4 (ja) |
JP (1) | JPWO2019058460A1 (ja) |
CN (1) | CN111108539A (ja) |
BR (1) | BR112020005415A2 (ja) |
CA (1) | CA3076322A1 (ja) |
MX (1) | MX2020002932A (ja) |
RU (1) | RU2743829C1 (ja) |
WO (1) | WO2019058460A1 (ja) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2021084502A (ja) * | 2019-11-27 | 2021-06-03 | 株式会社Subaru | 制御装置 |
WO2021202531A1 (en) * | 2020-03-30 | 2021-10-07 | Uatc, Llc | System and methods for controlling state transitions using a vehicle controller |
WO2022201345A1 (ja) * | 2021-03-24 | 2022-09-29 | 日本電気株式会社 | 運転者照合システム、運転者照合方法、記憶媒体 |
EP4074566A4 (en) * | 2019-12-28 | 2023-07-26 | Huawei Technologies Co., Ltd. | METHOD, DEVICE AND CONTROL SYSTEM OF A SMART CAR |
EP3990325A4 (en) * | 2019-06-28 | 2023-09-06 | Zoox, Inc. | SYSTEM AND METHOD FOR DETERMINING THE TARGET SPEED OF A VEHICLE |
JP7377042B2 (ja) | 2019-09-25 | 2023-11-09 | 株式会社Subaru | 車両システム |
WO2024080086A1 (ja) * | 2022-10-11 | 2024-04-18 | ソフトバンクグループ株式会社 | Autonomous Driving 10 finger |
JP7643305B2 (ja) | 2021-11-17 | 2025-03-11 | トヨタ自動車株式会社 | 運転者特定装置、運転者特定方法、及び運転者特定プログラム |
Families Citing this family (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11273836B2 (en) | 2017-12-18 | 2022-03-15 | Plusai, Inc. | Method and system for human-like driving lane planning in autonomous driving vehicles |
US11130497B2 (en) * | 2017-12-18 | 2021-09-28 | Plusai Limited | Method and system for ensemble vehicle control prediction in autonomous driving vehicles |
US20190185012A1 (en) | 2017-12-18 | 2019-06-20 | PlusAI Corp | Method and system for personalized motion planning in autonomous driving vehicles |
JP7210906B2 (ja) * | 2018-05-31 | 2023-01-24 | 株式会社デンソー | 車両の自動運転制御装置及びプログラム |
US11954736B1 (en) | 2019-08-28 | 2024-04-09 | State Farm Mutual Automobile Insurance Company | Systems and methods for generating mobility insurance products using ride-sharing telematics data |
DE112021007108T5 (de) * | 2021-02-18 | 2024-01-25 | Panasonic Intellectual Property Management Co., Ltd. | Anzeigesteuervorrichtung und Anzeigesteuerverfahren |
JP7578037B2 (ja) | 2021-03-25 | 2024-11-06 | トヨタ自動車株式会社 | 運転者特定装置及び運転者特定方法 |
US12036987B2 (en) | 2021-07-29 | 2024-07-16 | Toyota Motor Engineering & Manufacturing North America, Inc. | Student-T process personalized adaptive cruise control |
FR3140602A1 (fr) * | 2022-10-11 | 2024-04-12 | Renault S.A.S. | Procédé de gestion automatisée de la vitesse longitudinale d’un véhicule automobile. |
FR3143514A1 (fr) * | 2022-12-20 | 2024-06-21 | Renault S.A.S | Procédé de gestion automatisée de la vitesse longitudinale d’un véhicule automobile. |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2003080970A (ja) * | 2001-09-17 | 2003-03-19 | Mitsubishi Motors Corp | 車両速度制御装置 |
JP2008137639A (ja) * | 2006-11-06 | 2008-06-19 | Quality Kk | 車両制御装置および車両制御プログラム |
JP2008222167A (ja) * | 2007-03-15 | 2008-09-25 | Toyota Motor Corp | 乗員特定装置 |
JP2012069037A (ja) * | 2010-09-27 | 2012-04-05 | Toyota Motor Corp | 運転者特定装置 |
JP2015510622A (ja) * | 2011-12-19 | 2015-04-09 | マイクロソフト コーポレーション | アクションを開始および実行するための写真の使用 |
JP2016216021A (ja) | 2015-04-21 | 2016-12-22 | パナソニックIpマネジメント株式会社 | 運転支援方法およびそれを利用した運転支援装置、自動運転制御装置、車両、プログラム |
JP2016215658A (ja) * | 2015-05-14 | 2016-12-22 | アルパイン株式会社 | 自動運転装置および自動運転システム |
WO2017057060A1 (ja) * | 2015-09-30 | 2017-04-06 | ソニー株式会社 | 運転制御装置、および運転制御方法、並びにプログラム |
Family Cites Families (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5521823A (en) * | 1991-09-03 | 1996-05-28 | Mazda Motor Corporation | Learning control vehicle |
DE4215406A1 (de) * | 1992-05-11 | 1993-11-18 | Zahnradfabrik Friedrichshafen | Steuersystem zum Schalten eines automatischen Getriebes |
JP3622744B2 (ja) * | 2001-11-15 | 2005-02-23 | 株式会社デンソー | 車両の走行制御装置 |
JP3846494B2 (ja) * | 2004-07-13 | 2006-11-15 | 日産自動車株式会社 | 移動障害物検出装置 |
WO2007069568A1 (ja) * | 2005-12-14 | 2007-06-21 | Matsushita Electric Industrial Co., Ltd. | 危険運転予測装置 |
JP4375420B2 (ja) * | 2007-03-26 | 2009-12-02 | 株式会社デンソー | 眠気警報装置、及びプログラム |
JP5664533B2 (ja) * | 2011-12-09 | 2015-02-04 | トヨタ自動車株式会社 | 車両ドライバ特定用学習装置及び車両ドライバ特定用学習方法、並びに車両ドライバ特定装置及び車両ドライバ特定方法 |
US10518782B2 (en) * | 2012-06-05 | 2019-12-31 | Toyota Jidosha Kabushiki Kaisha | Driving characteristics estimating device and drive assisting system |
US9766625B2 (en) * | 2014-07-25 | 2017-09-19 | Here Global B.V. | Personalized driving of autonomously driven vehicles |
JP6201927B2 (ja) * | 2014-08-01 | 2017-09-27 | トヨタ自動車株式会社 | 車両制御装置 |
US10449957B2 (en) * | 2014-12-29 | 2019-10-22 | Robert Bosch Gmbh | Systems and methods for operating autonomous vehicles using personalized driving profiles |
JP6237685B2 (ja) * | 2015-04-01 | 2017-11-29 | トヨタ自動車株式会社 | 車両制御装置 |
US10627813B2 (en) * | 2015-04-21 | 2020-04-21 | Panasonic Intellectual Property Management Co., Ltd. | Information processing system, information processing method, and program |
US10759446B2 (en) * | 2015-04-21 | 2020-09-01 | Panasonic Intellectual Property Management Co., Ltd. | Information processing system, information processing method, and program |
CN106652515B (zh) * | 2015-11-03 | 2020-03-20 | 中国电信股份有限公司 | 车辆自动控制方法、装置和系统 |
CN106828503B (zh) * | 2017-02-15 | 2018-11-30 | 武汉理工大学 | 一种驾驶员制动行为及状态实时辨识方法 |
-
2017
- 2017-09-20 RU RU2020113690A patent/RU2743829C1/ru active
- 2017-09-20 MX MX2020002932A patent/MX2020002932A/es unknown
- 2017-09-20 CA CA3076322A patent/CA3076322A1/en not_active Abandoned
- 2017-09-20 WO PCT/JP2017/033920 patent/WO2019058460A1/ja unknown
- 2017-09-20 CN CN201780095062.7A patent/CN111108539A/zh active Pending
- 2017-09-20 US US16/647,598 patent/US20200278685A1/en not_active Abandoned
- 2017-09-20 EP EP17925860.3A patent/EP3686862A4/en not_active Withdrawn
- 2017-09-20 BR BR112020005415-1A patent/BR112020005415A2/pt not_active IP Right Cessation
- 2017-09-20 JP JP2019542871A patent/JPWO2019058460A1/ja active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2003080970A (ja) * | 2001-09-17 | 2003-03-19 | Mitsubishi Motors Corp | 車両速度制御装置 |
JP2008137639A (ja) * | 2006-11-06 | 2008-06-19 | Quality Kk | 車両制御装置および車両制御プログラム |
JP2008222167A (ja) * | 2007-03-15 | 2008-09-25 | Toyota Motor Corp | 乗員特定装置 |
JP2012069037A (ja) * | 2010-09-27 | 2012-04-05 | Toyota Motor Corp | 運転者特定装置 |
JP2015510622A (ja) * | 2011-12-19 | 2015-04-09 | マイクロソフト コーポレーション | アクションを開始および実行するための写真の使用 |
JP2016216021A (ja) | 2015-04-21 | 2016-12-22 | パナソニックIpマネジメント株式会社 | 運転支援方法およびそれを利用した運転支援装置、自動運転制御装置、車両、プログラム |
JP2016215658A (ja) * | 2015-05-14 | 2016-12-22 | アルパイン株式会社 | 自動運転装置および自動運転システム |
WO2017057060A1 (ja) * | 2015-09-30 | 2017-04-06 | ソニー株式会社 | 運転制御装置、および運転制御方法、並びにプログラム |
Non-Patent Citations (1)
Title |
---|
See also references of EP3686862A4 |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP3990325A4 (en) * | 2019-06-28 | 2023-09-06 | Zoox, Inc. | SYSTEM AND METHOD FOR DETERMINING THE TARGET SPEED OF A VEHICLE |
JP7377042B2 (ja) | 2019-09-25 | 2023-11-09 | 株式会社Subaru | 車両システム |
JP7414490B2 (ja) | 2019-11-27 | 2024-01-16 | 株式会社Subaru | 制御装置 |
JP2021084502A (ja) * | 2019-11-27 | 2021-06-03 | 株式会社Subaru | 制御装置 |
EP4074566A4 (en) * | 2019-12-28 | 2023-07-26 | Huawei Technologies Co., Ltd. | METHOD, DEVICE AND CONTROL SYSTEM OF A SMART CAR |
US11513517B2 (en) | 2020-03-30 | 2022-11-29 | Uatc, Llc | System and methods for controlling state transitions using a vehicle controller |
CN115427279A (zh) * | 2020-03-30 | 2022-12-02 | Uatc有限责任公司 | 使用车辆控制器控制状态转变的系统和方法 |
US11768490B2 (en) | 2020-03-30 | 2023-09-26 | Uatc, Llc | System and methods for controlling state transitions using a vehicle controller |
WO2021202531A1 (en) * | 2020-03-30 | 2021-10-07 | Uatc, Llc | System and methods for controlling state transitions using a vehicle controller |
CN115427279B (zh) * | 2020-03-30 | 2024-06-07 | 欧若拉运营公司 | 使用车辆控制器控制状态转变的系统和方法 |
WO2022201345A1 (ja) * | 2021-03-24 | 2022-09-29 | 日本電気株式会社 | 運転者照合システム、運転者照合方法、記憶媒体 |
JP7578184B2 (ja) | 2021-03-24 | 2024-11-06 | 日本電気株式会社 | 運転者照合システム、運転者照合方法、及び、プログラム |
JP7643305B2 (ja) | 2021-11-17 | 2025-03-11 | トヨタ自動車株式会社 | 運転者特定装置、運転者特定方法、及び運転者特定プログラム |
WO2024080086A1 (ja) * | 2022-10-11 | 2024-04-18 | ソフトバンクグループ株式会社 | Autonomous Driving 10 finger |
Also Published As
Publication number | Publication date |
---|---|
BR112020005415A2 (pt) | 2020-09-29 |
EP3686862A4 (en) | 2020-11-04 |
RU2743829C1 (ru) | 2021-02-26 |
MX2020002932A (es) | 2020-07-24 |
US20200278685A1 (en) | 2020-09-03 |
CN111108539A (zh) | 2020-05-05 |
EP3686862A1 (en) | 2020-07-29 |
CA3076322A1 (en) | 2019-03-28 |
JPWO2019058460A1 (ja) | 2020-10-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2019058460A1 (ja) | 走行支援方法及び走行支援装置 | |
WO2017163667A1 (ja) | 運転支援方法およびそれを利用した運転支援装置、自動運転制御装置、車両、運転支援システム、プログラム | |
US10518783B2 (en) | Automatic driving control device | |
US11079758B2 (en) | Systems and methods for incentivizing user-aided improvement of autonomous vehicle control systems and methods of operating a vehicle using the same | |
CN111524346B (zh) | 服务器以及信息提供装置 | |
CN109383523B (zh) | 用于车辆的辅助驾驶方法和系统 | |
US9771054B2 (en) | Travel resistance arithmetic device | |
JP2019043495A (ja) | 自動運転調整装置、自動運転調整システム、及び自動運転調整方法 | |
CN112699721B (zh) | 离开道路扫视时间的情境相关调整 | |
JPWO2014045355A1 (ja) | 車両運転行動予測装置 | |
US20210163015A1 (en) | Method for Learning Travel Characteristics and Travel Assistance Device | |
WO2019030916A1 (ja) | 車線情報管理方法、走行制御方法及び車線情報管理装置 | |
JPWO2019003280A1 (ja) | 車両の走行支援方法及び走行支援装置 | |
US11221228B2 (en) | Vehicle, and method of controlling the same | |
JP2018173816A (ja) | 運転支援方法およびそれを利用した運転支援装置、自動運転制御装置、車両、プログラム、運転支援システム | |
CN111240314A (zh) | 用于l2自动驾驶的基于预定校准表的车辆油门/制动辅助系统 | |
WO2023029469A1 (zh) | 车辆行驶预警方法及装置 | |
JP2006160032A (ja) | 運転状態判定装置及び運転状態判定方法 | |
US20200130691A1 (en) | Information processing device, non-transitory storage medium in which program is recorded, and information processing method | |
US20220222946A1 (en) | Traffic environment recognition device and vehicle control device | |
US20250103971A1 (en) | Method and System for Providing a Function Recommendation in a Vehicle | |
JP7615938B2 (ja) | 情報処理サーバ、情報処理サーバの処理方法、プログラム | |
JP2024015574A (ja) | 車両の運転支援システム | |
WO2023156036A1 (en) | A computer-implemented method for providing a function recommendation in a vehicle, a vehicle and a system for implementing the method | |
CN119611408A (zh) | 车辆控制方法、装置、车载终端及车辆 |
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: 17925860 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2019542871 Country of ref document: JP Kind code of ref document: A |
|
ENP | Entry into the national phase |
Ref document number: 3076322 Country of ref document: CA |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
ENP | Entry into the national phase |
Ref document number: 2017925860 Country of ref document: EP Effective date: 20200420 |
|
REG | Reference to national code |
Ref country code: BR Ref legal event code: B01A Ref document number: 112020005415 Country of ref document: BR |
|
ENP | Entry into the national phase |
Ref document number: 112020005415 Country of ref document: BR Kind code of ref document: A2 Effective date: 20200318 |