CN114771566A - Multi-mode stimulation adjusting method and system for automatic driving and manual taking over - Google Patents
Multi-mode stimulation adjusting method and system for automatic driving and manual taking over Download PDFInfo
- Publication number
- CN114771566A CN114771566A CN202210419353.XA CN202210419353A CN114771566A CN 114771566 A CN114771566 A CN 114771566A CN 202210419353 A CN202210419353 A CN 202210419353A CN 114771566 A CN114771566 A CN 114771566A
- Authority
- CN
- China
- Prior art keywords
- stimulation
- driver
- takeover
- quality
- over
- 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.)
- Pending
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
- B60W60/005—Handover processes
- B60W60/0053—Handover processes from vehicle to occupant
-
- 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
- B60W50/14—Means for informing the driver, warning the driver or prompting a driver intervention
-
- 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
- B60W50/14—Means for informing the driver, warning the driver or prompting a driver intervention
- B60W50/16—Tactile feedback to the driver, e.g. vibration or force feedback to the driver on the steering wheel or the accelerator pedal
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/23—Updating
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/25—Integrating or interfacing systems involving database management systems
- G06F16/252—Integrating or interfacing systems involving database management systems between a Database Management System and a front-end application
-
- 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
- B60W50/14—Means for informing the driver, warning the driver or prompting a driver intervention
- B60W2050/143—Alarm 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
- B60W50/08—Interaction between the driver and the control system
- B60W50/14—Means for informing the driver, warning the driver or prompting a driver intervention
- B60W2050/146—Display 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
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention provides a method and a system for adjusting multi-modal stimulation of automatic driving manual takeover, which are used for determining the takeover time of a sound prompt, the takeover time of a vibration prompt and the takeover time of a visual prompt when a driver automatically drives the takeover event each time, adding a sound action coefficient, a vibration action coefficient and a visual action coefficient which are related to the takeover quality of the three components, and pre-storing each stimulation and the takeover time corresponding to the stimulation in a cloud database, thereby facilitating the determination of a stimulation mode. And constructing an individual driver database to store historical driving data of individual drivers, namely updating the actual takeover quality, the expected takeover quality and the action coefficient of multi-modal stimulation received by the driver for each takeover event. The invention utilizes the simulated driving scene and the multi-mode stimulation to perform scene presentation and information provision, and can realize better user experience and takeover quality.
Description
Technical Field
The invention provides a multi-mode stimulation adjusting method and system for automatic driving manual takeover, and relates to the field of automatic driving technology and human factor engineering.
Background
According to the classification of Society of Automotive Engineers (SAE) for vehicle automation level standards, Automotive automatic driving is classified into six levels, ranging from level L0 to level L5. The automatic driving takeover behavior mainly occurs in automatic vehicles of class L2-L3, and when the automatic driving system cannot handle certain conditions, the driver must take over the control right of the vehicle in a safe time.
The whole process of taking over can be divided into three stages: wake-aware, take-over decisions, and behavioral decisions. Different takeover information providing modes, namely combination of multi-mode stimulation, such as visual stimulation, auditory stimulation, steering wheel vibration and other prompting modes, have great influence on the performance of the driver in the whole takeover process, and even directly determine whether the driver can well complete the takeover task. Thus, the multi-modal stimulus plays an important role in the quality of the driving take over and the safety of the vehicle driving.
At this stage, with the development of the automatic driving technology, the safety of automatic driving has become an increasingly focused focus. Along with the continuous maturity of the simulation driving simulation system, the driving simulation experiment platform is utilized, different modal stimuli are combined, the quality of the connection of the driver from the automatic connection to the manual connection is researched, and the method has important significance on the development and progress of the automatic driving vehicle.
In patent document CN113460074A, the pipe quality P is taken over0Parameters such as action coefficients, the advance time of taking over requests and taking over readiness degree are stored in a big data cloud database in advance, influence of multi-modal stimulation on behaviors of drivers is not mentioned, the patent aims are taking over request time adjustment of automatic driving, and adjustment targets not aiming at stimulation of different modal types are different.
Disclosure of Invention
The invention aims to provide a method and a system for dynamically adjusting three multi-modal stimuli of sound, vibration and vision by continuously adjusting the quality of a target connection pipe, continuously updating and optimizing in real time under the environment needing automatic driving and manual connection.
An automatic driving manual taking-over multi-modal stimulation adjusting method comprises the steps that auditory stimulation, vibration stimulation and visual stimulation are carried out; the method comprises the following specific steps:
step 1: constructing a driver cloud database through a driving simulator experiment and a real vehicle experiment based on a takeover scene; the driver cloud database comprises a target take-over quality P0Take-over time A due to Multi-modal stimulation and corresponding auditory stimulation0And the pipe connection time B caused by vibration stimulation0And the tube connection time C caused by visual stimulation0Coefficient of action a of the request for driver to take over by means of auditory stimulation0The effect coefficient b of taking over request sent by vibration stimulation to the taking over quality of the driver0The coefficient of action c of the request for taking over sent by visual stimulation to the quality of taking over of the driver0;
Step 2: constructing an individual driver database through real vehicle takeover data of a driven vehicle; the individual driver database comprises an action coefficient of an auditory stimulation request of a driven vehicle to the take-over quality of a driver, an action coefficient of a vibration stimulation request of the driven vehicle to the take-over quality of the driver, an action coefficient of a visual stimulation request of the driven vehicle to the take-over quality of the driver, a multi-mode stimulation mode of each take-over event, and corresponding target take-over quality and actual take-over quality;
and 3, step 3: judging whether the automatic driving exceeds the performance boundary of the automatic driving system, if the performance boundary is reached, not executing the method; if not, entering step 4;
and 4, step 4: calculating the taking-over time A caused by auditory stimulation expectation, the taking-over time B caused by vibration stimulation expectation and the taking-over time C caused by visual stimulation expectation according to the target taking-over quality P' of the current taking-over event, the action coefficient a of the auditory stimulation request of the driven vehicle on the taking-over quality of the driver, the action coefficient B of the vibration stimulation request of the driven vehicle on the taking-over quality of the driver and the action coefficient C of the visual stimulation request of the driven vehicle on the taking-over quality of the driver, and selecting a multi-mode stimulation mode meeting the requirements in a corresponding cloud driver database;
and 5: the individual driver finishes taking over, and the actual taking over quality P is calculated according to the taking over operation of the individual driver;
step 6: and uploading P', P, a, b and c corresponding to the current taking-over event to an individual driver database, and updating the individual driver database.
Further, in said step 1, P0=a0A0+b0B0+c0C0。
Further, the initial value of the coefficient of action of the auditory stimulus request of the driven vehicle on the driver's takeover quality is a0The initial value of the coefficient of action of the vibration stimulus request of the driven vehicle on the pipe mass is b0The initial value of the coefficient of action of the visual stimulus request of the driven vehicle on the driver's takeover quality is c0。
Further, the method for calculating the take-over time in step 4 is as follows:
X=max(0,P'/x)
Y=max(0,(P'-xX)/y)
Z=max(0,(P'-xX-yY)/z)
where x is max (a, b, c), z is min (a, b, c), y is the middle value of a, b, c, X, Y, Z is the take-over time corresponding to x, y, z, respectively.
Further, in step 5, the actual take-over quality P is TTBT-TOT, TTBT is the time distance between the driven vehicle and the boundary of the automatic driving system when taking over, and TOT is the reaction time of the driver.
In step 6, a, b, and c are updated by a multiple linear regression method according to the formula P ═ aA + bB + cC.
An autopilot manual takeover multi-modal stimulation adjustment system, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the following steps of the autopilot manual takeover multi-modal stimulation adjustment method when executing the computer program:
step 1: real vehicle based on taking over scene through driving simulator experimentPerforming an experiment, and constructing a driver cloud database; the driver cloud database comprises a target take-over quality P0Take-over time A due to multi-modal stimulation and corresponding auditory stimulation0And tube connection time B caused by vibration stimulation0And the time of taking over the tube caused by visual stimulation0Coefficient of action a of the request for driver to take over by means of auditory stimulation0The action coefficient b of taking over request sent by vibration stimulation to the taking over quality of the driver0The effect coefficient c of taking over request sent by visual stimulation to the taking over quality of the driver0;
Step 2: constructing an individual driver database through real vehicle takeover data of a driven vehicle; the individual driver database comprises an action coefficient of the auditory stimulation request of the driven vehicle to the take-over quality of the driver, an action coefficient of the vibration stimulation request of the driven vehicle to the take-over quality of the driver, an action coefficient of the visual stimulation request of the driven vehicle to the take-over quality of the driver, a multi-mode stimulation mode of each take-over event, and corresponding target take-over quality and actual take-over quality;
and step 3: judging whether the automatic driving exceeds the performance boundary of the automatic driving system, if so, not executing the method; if not, entering step 4;
and 4, step 4: calculating the taking-over time A caused by auditory stimulation expectation, the taking-over time B caused by vibration stimulation expectation and the taking-over time C caused by visual stimulation expectation according to the target taking-over quality P' of the current taking-over event, the action coefficient a of the auditory stimulation request of the driven vehicle on the taking-over quality of the driver, the action coefficient B of the vibration stimulation request of the driven vehicle on the taking-over quality of the driver and the action coefficient C of the visual stimulation request of the driven vehicle on the taking-over quality of the driver, and selecting a multi-mode stimulation mode meeting the requirements in a corresponding cloud driver database;
and 5: the individual driver finishes taking over, and the actual taking over quality P is calculated according to the taking over operation of the individual driver;
step 6: and uploading P', P, a, b and c corresponding to the current taking-over event to an individual driver database, and updating the individual driver database.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of an autopilot manual takeover multi-modal stimulation conditioning method of:
step 1: constructing a driver cloud database through a driving simulator experiment and a real vehicle experiment based on a takeover scene; the driver cloud database comprises a target take-over quality P0Take-over time A due to multi-modal stimulation and corresponding auditory stimulation0And the pipe connection time B caused by vibration stimulation0And the tube connection time C caused by visual stimulation0The coefficient of action a of the request for connection to the driver by means of an auditory stimulus0The effect coefficient b of taking over request sent by vibration stimulation to the taking over quality of the driver0The coefficient of action c of the request for taking over sent by visual stimulation to the quality of taking over of the driver0;
Step 2: constructing an individual driver database through real vehicle takeover data of a driven vehicle; the individual driver database comprises an action coefficient of the auditory stimulation request of the driven vehicle to the take-over quality of the driver, an action coefficient of the vibration stimulation request of the driven vehicle to the take-over quality of the driver, an action coefficient of the visual stimulation request of the driven vehicle to the take-over quality of the driver, a multi-mode stimulation mode of each take-over event, and corresponding target take-over quality and actual take-over quality;
and step 3: judging whether the automatic driving exceeds the performance boundary of the automatic driving system, if the performance boundary is reached, not executing the method; if not, entering step 4;
and 4, step 4: calculating the takeover time A caused by auditory stimulation expectation, the takeover time B caused by vibration stimulation expectation and the takeover time C caused by visual stimulation expectation according to the target takeover quality P' of the current takeover event, the action coefficient a of the auditory stimulation request of the driven vehicle on the takeover quality of the driver, the action coefficient B of the vibration stimulation request of the driven vehicle on the takeover quality of the driver and the action coefficient C of the visual stimulation request of the driven vehicle on the takeover quality of the driver, and selecting a multi-mode stimulation mode meeting the requirements from a corresponding cloud driver database;
and 5: the individual driver finishes taking over, and the actual taking over quality P is calculated according to the taking over operation of the individual driver;
and 6: and uploading P', P, a, b and c corresponding to the current taking-over event to an individual driver database, and updating the individual driver database.
The invention has the beneficial effects that: according to the multi-modal stimulation adjustment method and system for the automatic driving manual takeover request, when a takeover event is triggered each time, the sound action coefficient a, the vibration action coefficient B and the visual action coefficient C which are related to the takeover quality P are added when the takeover time A of the sound prompt, the takeover time B of the vibration prompt and the takeover time C of the visual prompt during the automatic driving takeover are determined for a driver, and each stimulation and the corresponding takeover time are stored in the cloud database in advance, so that the stimulation mode can be determined conveniently. And constructing an individual driver database to store historical driving data of individual drivers, namely updating the actual takeover quality P and the expected takeover quality P' of each takeover event and the action coefficients a, b and c of multi-modal stimulation received by the drivers. Through such steps, the action coefficients a, b and c reflecting the operation habits of the individual drivers can be updated in time by learning the historical driving data of the individual drivers, so that the values according with the current driving habits and attention of each driver can be obtained when different prompting modes are selected in the face of different driving takeover events. A high user experience and take-over quality can be achieved.
Drawings
Fig. 1 is a flowchart illustrating a control method of an automatic driving system according to the present invention.
Detailed Description
The embodiment of the invention discloses a multi-modal stimulation adjustment method for an automatic driving takeover request, which selects a multi-modal stimulation scheme meeting the current takeover quality requirement and the driver state on the basis of continuously collecting and updating a real-time signal receiving coefficient of a driver, and realizes that the overall flow is as shown in figure 1. The method comprises the following steps:
step 1: step of constructing driver cloud database
The method comprises the steps that a driver big data cloud database is built through a driving simulator experiment and a real vehicle experiment based on a take-over scene, and parameters stored in the database comprise P0、A0、B0、C0、a0、b0、c0Each parameter satisfies the formula: p0=a0A0+b0B0+c0C0。
Wherein P is0The method is based on the target takeover quality of experimental big data, and can take 6 to 12 seconds based on experimental data and different takeover scenes to ensure the takeover quality of the safe takeover of a driver; a is a0The action coefficient of taking over request sent by auditory information obtained by simulation driving experiment to the taking over quality of the driver, b0The action coefficient of the take-over request sent by the vibration information obtained by the simulation driving experiment to the take-over quality of the driver, c0The action coefficient of taking over quality of the driver is obtained by simulating a driving experiment and sending out a taking over request by using visual information. a is a0、b0And c0The data pairs obtained by the driving simulation experiment are subjected to multiple linear regression analysis; a. the0、B0、C0The method is the general take-over time caused by various kinds of auditory information, vibration information and take-over information which are pre-stored in a database, namely the take-over time corresponding to various types of modal stimulation schemes based on the statistics and analysis of driving simulation experiment data.
And 2, step: step of constructing an individual driver database
An individual driver database is constructed through actual vehicle takeover data of a driven vehicle (hereinafter referred to as the ' own vehicle '), obviously, the individual driver databases of different vehicles are different, one-time takeover of the driver is marked as a takeover event, and parameters stored in the database comprise a, b and c, expected takeover quality P ' of data corresponding to each takeover event and actual takeover quality P.
a is the action coefficient of the auditory stimulation request of the vehicle to the take-over quality of the driver, and the initial value is a0B is the action coefficient of the vibration stimulation request of the vehicle on the quality of the pipe, and the initial value b is taken0C is the action coefficient of the vision stimulation request of the vehicle to the take-over quality of the driver, and the initial value is c0. In data P 'and P corresponding to each takeover event, P' is target takeover quality, and P in a driver big data cloud database is taken as an initial value0And P is the actual takeover mass, and the units of the two are seconds.
And 3, step 3: determining performance boundaries of an autopilot system
Whether the automatic driving exceeds the performance boundary of the automatic driving system (namely, the working conditions which cannot be processed when the automatic driving systems of the L3 and L4 levels are in the automatic driving mode) is judged. If the performance boundary is not reached, go to step 4. If the performance boundary is exceeded, the method is exited.
And 4, step 4: taking over request prompting step
And calculating corresponding required takeover time A, B, C according to the expected takeover quality P' required by the current driving takeover scene and the receiving coefficients a, b and c of the influence of the driver on the multi-modal stimulation currently, and further selecting a multi-modal stimulation mode meeting the requirement from the resource library. In the takeover request prompt module, the relationship among the action coefficients a, b and c of the auditory sense, the vibration and the vision stored in the storage module on the driver is taken as a standard, and the action coefficients are ranked according to the calculated priority, so that the takeover time caused by the corresponding stimulation is calculated in sequence.
In one embodiment, taking an auditory coefficient > vibration coefficient > visual coefficient as an example, at this time a > b > c, the stimulation priority given to the driver in the database is sequentially auditory > vibration > visual, and the taking time of a specific stimulation is calculated according to the following formula:
A=max(0,P'/a)
B=max(0,(P'-aA)/b)
C=max(0,(P'-aA-bB)/c)
when the magnitude relation of the three coefficients in the database changes, the magnitude relation of the corresponding a, b and c and the calculation priority order also change.
And 5: step of evaluating quality of connecting pipe
And the driver completes the current takeover according to the current takeover request. And then calculating the current actual takeover quality P according to the current takeover operation data of the driver. There are various kinds of indexes for taking over the quality, such as statistical value of input data of a steering wheel of a driver, statistical value of input data of an accelerator pedal of the driver, statistical value of input data of a decelerator pedal of the driver, reaction time of the driver and the like.
In one embodiment, the difference between the time distance TTBT from the vehicle to the autopilot system boundary and the reaction time TOT of the driver when a more general take-over is used is the take-over quality, namely:
P=TTBT-TOT。
in particular, when the take-over fails, i.e., a collision or the like occurs, P takes 0
And 6: step of recording takeover data
A database updating step of updating the action coefficients a, b and C in the individual driver database according to the take-over quality P of the driver recorded in the data group of the individual driver database and the take-over times A, B and C corresponding to the given stimulus signal, so as to be used as a calculation reference of the stimulus given in the next take-over event.
According to the above embodiment, the following advantageous effects can be obtained.
(1) In the method and the system for adjusting the automatic driving manual takeover request time, when selecting which multi-modal stimulation, such as auditory stimulation, vibration stimulation and visual stimulation, an auditory action coefficient a related to takeover quality P and an action coefficient c related to vibration action coefficient b and visual action are added, and historical driving data of an individual driver, namely the takeover quality P and the action coefficients a, b and c of each takeover event, of the individual driver database are established. Through such a procedure, the action coefficients a, b and c reflecting the multi-modal stimulation of the individual driver can be updated in time by learning the historical driving data of the individual driver, so that a value according with the driving habit of each driver can be obtained when calculating which multi-modal stimulation is adopted. A high user experience and take-over quality can be achieved.
(2) The data recorded in the individual driver database can be uploaded to the driver big data cloud database, and the parameter P which is stored in the driver big data cloud database and is used as the initial value of the parameters P', a, b and c in the individual driver database is updated according to the uploaded data periodically0、a0、b0、c0Therefore, the initial value of the cloud database can be updated based on more takeover data performed by more drivers, and a better initial value is provided for vehicles produced later.
(3) In the individual driver database updating step, the action coefficients a, b and c are updated by a formula by using a multiple linear regression method, and P ═ aA + bB + cC, so that data capable of accurately reflecting the driving habits and states of the individual drivers can be simply obtained, and a suitable multi-modal stimulation mode can be calculated.
In one embodiment, a system for adjusting multi-modal stimulation by automatic driving and manual taking over is further provided, which includes a memory and a processor, where the memory stores a computer program, and the processor implements the steps of the method for adjusting multi-modal stimulation by automatic driving and manual taking over when executing the computer program.
In one embodiment, a computer-readable storage medium is also provided, having stored thereon a computer program, which when executed by a processor, performs the steps of the above-described automated driver manual takeover multi-modal stimulation conditioning method.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above may be implemented by hardware instructions of a computer program, which may be stored in a non-volatile computer-readable storage medium, and when executed, may include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The above embodiments are only for illustrating the technical idea of the present invention, and the protection scope of the present invention is not limited thereby, and any modifications made on the basis of the technical scheme according to the technical idea of the present invention fall within the protection scope of the present invention.
Claims (8)
1. A multi-modal stimulation adjusting method for automatic driving and manual taking over is characterized in that the multi-modal stimulation comprises auditory stimulation, vibration stimulation and visual stimulation; the method comprises the following specific steps:
step 1: constructing a driver cloud database through a driving simulator experiment and a real vehicle experiment based on a takeover scene; the driver cloud database comprises a target take-over quality P0Take-over time A due to Multi-modal stimulation and corresponding auditory stimulation0And tube connection time B caused by vibration stimulation0And the time of taking over the tube caused by visual stimulation0The coefficient of action a of the request for connection to the driver by means of an auditory stimulus0The effect coefficient b of taking over request sent by vibration stimulation to the taking over quality of the driver0The coefficient of action c of the request for taking over sent by visual stimulation to the quality of taking over of the driver0;
And 2, step: constructing an individual driver database through real vehicle takeover data of a driven vehicle; the individual driver database comprises an action coefficient of the auditory stimulation request of the driven vehicle to the take-over quality of the driver, an action coefficient of the vibration stimulation request of the driven vehicle to the take-over quality of the driver, an action coefficient of the visual stimulation request of the driven vehicle to the take-over quality of the driver, a multi-mode stimulation mode of each take-over event, and corresponding target take-over quality and actual take-over quality;
and 3, step 3: judging whether the automatic driving exceeds the performance boundary of the automatic driving system, if so, not executing the method; if not, entering step 4;
and 4, step 4: calculating the takeover time A caused by auditory stimulation expectation, the takeover time B caused by vibration stimulation expectation and the takeover time C caused by visual stimulation expectation according to the target takeover quality P' of the current takeover event, the action coefficient a of the auditory stimulation request of the driven vehicle on the takeover quality of the driver, the action coefficient B of the vibration stimulation request of the driven vehicle on the takeover quality of the driver and the action coefficient C of the visual stimulation request of the driven vehicle on the takeover quality of the driver, and selecting a multi-mode stimulation mode meeting the requirements from a corresponding cloud driver database;
and 5: the individual driver finishes taking over, and the actual taking over quality P is calculated according to the taking over operation of the individual driver;
and 6: and uploading P', P, a, b and c corresponding to the current taking-over event to an individual driver database, and updating the individual driver database.
2. The automated manual takeover multi-modal stimulation adjustment method of claim 1, wherein in step 1, P is0=a0A0+b0B0+c0C0。
3. The method for adjusting multi-modal stimulation through automatic driving and manual taking over according to claim 1, wherein the driven vehicle is drivenThe initial value of the coefficient of action of the auditory stimulus request of the vehicle on the driver's quality of take-over is a0The initial value of the coefficient of action of the vibration stimulus request of the driven vehicle on the pipe mass is b0The initial value of the coefficient of action of the visual stimulus request of the driven vehicle on the driver's take-over quality is c0。
4. The adjustment method for taking over the multi-modal stimulation by the automatic driver and the manual driver according to claim 1, wherein the taking over time in the step 4 is calculated as follows:
X=max(0,P'/x)
Y=max(0,(P'-xX)/y)
Z=max(0,(P'-xX-yY)/z)
where x is max (a, b, c), z is min (a, b, c), y is the middle value of a, b, c, X, Y, Z is the pipe connection time corresponding to x, y, z.
5. The method as claimed in claim 1, wherein the actual takeover quality P in step 5 is TTBT-TOT, TTBT is the time distance between the driven vehicle and the boundary of the automatic driving system when taking over, and TOT is the reaction time of the driver.
6. The method as claimed in claim 1, wherein in step 6, a, b and c are updated by a multiple linear regression method and a formula P ═ aA + bB + cC.
7. An autopilot manual takeover multi-modal stimulation conditioning system comprising a memory and a processor, the memory having stored thereon a computer program, wherein the processor, when executing the computer program, performs the steps of the autopilot manual takeover multi-modal stimulation conditioning method of any one of claims 1 to 6.
8. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the autopilot manual takeover multi-modal stimulation adaptation method of one of claims 1 to 6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210419353.XA CN114771566A (en) | 2022-04-20 | 2022-04-20 | Multi-mode stimulation adjusting method and system for automatic driving and manual taking over |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210419353.XA CN114771566A (en) | 2022-04-20 | 2022-04-20 | Multi-mode stimulation adjusting method and system for automatic driving and manual taking over |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114771566A true CN114771566A (en) | 2022-07-22 |
Family
ID=82430557
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210419353.XA Pending CN114771566A (en) | 2022-04-20 | 2022-04-20 | Multi-mode stimulation adjusting method and system for automatic driving and manual taking over |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114771566A (en) |
-
2022
- 2022-04-20 CN CN202210419353.XA patent/CN114771566A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10816978B1 (en) | Automated vehicle artificial intelligence training based on simulations | |
US20220363259A1 (en) | Method for generating lane changing decision-making model, method for lane changing decision-making of unmanned vehicle and electronic device | |
WO2021129156A1 (en) | Control method, device and system of intelligent car | |
AT521832B1 (en) | Test terminal to support an executing person | |
CN113561986B (en) | Automatic driving automobile decision making method and device | |
CN110869858B (en) | Method and device for setting at least one parameter of an actuator control system, actuator control system and data set | |
CN113665593B (en) | Longitudinal control method and system for intelligent driving of vehicle and storage medium | |
US20200192307A1 (en) | Control customization system, control customization method, and control customization program | |
CN113366509A (en) | Arithmetic device | |
DE102019134053A1 (en) | Process for the continuous validation of automated driving functions applied in driving tests | |
CN112382165A (en) | Driving strategy generation method, device, medium, equipment and simulation system | |
CN109976153B (en) | Method and device for controlling unmanned equipment and model training and electronic equipment | |
US20230236088A1 (en) | Computer-aided method and device for predicting speeds for vehicles on the basis of probability | |
CN116348355A (en) | Method and system for testing a driver assistance system of a vehicle | |
CN114987511A (en) | Method for simulating human driving behavior to train neural network-based motion controller | |
CN114771566A (en) | Multi-mode stimulation adjusting method and system for automatic driving and manual taking over | |
CN110826695A (en) | Data processing method, device and computer readable storage medium | |
CN116262507A (en) | Human data driven interpretable artificial intelligence system and method | |
US20220138575A1 (en) | Computer implemented method and test unit for approximating test results and a method for providing a trained, artificial neural network | |
Guo et al. | Modeling, learning and prediction of longitudinal behaviors of human-driven vehicles by incorporating internal human DecisionMaking process using inverse model predictive control | |
US20100333070A1 (en) | Multiple ECU Software-In-The-Loop Simulation Environment | |
US20230192118A1 (en) | Automated driving system with desired level of driving aggressiveness | |
CN114021307A (en) | Vehicle controller debugging method and device, computer equipment and storage medium | |
CN106716422B (en) | Method for modeling a motor vehicle using time dispersion | |
CN111077769A (en) | Method for controlling or regulating a technical system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |