CN114323698A - Real vehicle experiment platform testing method for man-machine driving-together intelligent vehicle - Google Patents
Real vehicle experiment platform testing method for man-machine driving-together intelligent vehicle Download PDFInfo
- Publication number
- CN114323698A CN114323698A CN202210127398.XA CN202210127398A CN114323698A CN 114323698 A CN114323698 A CN 114323698A CN 202210127398 A CN202210127398 A CN 202210127398A CN 114323698 A CN114323698 A CN 114323698A
- Authority
- CN
- China
- Prior art keywords
- driving
- vehicle
- man
- machine
- driver
- 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.)
- Granted
Links
- 238000012360 testing method Methods 0.000 title claims abstract description 56
- 238000002474 experimental method Methods 0.000 title claims abstract description 36
- 238000000034 method Methods 0.000 claims abstract description 35
- 238000013461 design Methods 0.000 claims abstract description 4
- 238000011156 evaluation Methods 0.000 claims description 38
- 238000012545 processing Methods 0.000 claims description 16
- 230000001133 acceleration Effects 0.000 claims description 14
- 230000008859 change Effects 0.000 claims description 11
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000012937 correction Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 8
- 230000010365 information processing Effects 0.000 claims description 7
- 238000010998 test method Methods 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 claims description 5
- 230000004927 fusion Effects 0.000 claims description 5
- 230000004044 response Effects 0.000 claims description 4
- 230000006399 behavior Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000012886 linear function Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 206010039203 Road traffic accident Diseases 0.000 claims description 2
- 230000006870 function Effects 0.000 claims description 2
- 238000005070 sampling Methods 0.000 claims description 2
- 238000011160 research Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000010276 construction Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Images
Landscapes
- Steering Control In Accordance With Driving Conditions (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention relates to a human-computer co-driving oriented intelligent automobile real-vehicle experimental platform testing method which mainly comprises the following steps: the method comprises the following steps: on the basis of an E-HS3 real vehicle platform, a controllable motor and a torque/angle sensor are additionally arranged in a steering system to meet the requirement of a man-machine common driving interface, so that the platform has three modes of driving by a human driver, driving by an intelligent driving system and sharing driving by the human driver and the intelligent driving system; step two: deploying a millimeter wave radar, a camera, a GPS (global positioning system), an industrial personal computer and a bottom control system for the man-machine co-driving system on the basis of the step one to form a closed-loop system containing external information; step three: aiming at the characteristics of the man-machine driving-together real vehicle experiment, a test frame which accords with man-machine driving-together is designed. The invention designs an efficient and reliable man-machine driving-together experimental platform aiming at the experiment and test problems of a man-machine driving-together intelligent automobile, and designs a corresponding test control framework, and the platform can effectively verify the characteristics of man-machine driving-together in a real automobile environment.
Description
Technical Field
The invention relates to a test method for a human-computer driving-together intelligent automobile test platform, in particular to a driving experiment platform and a test method for a human-computer driving-together intelligent automobile under a real-vehicle environment.
Background
Autonomous vehicles have been rapidly developed over the past several years, but full unmanned driving at the level of L4 and L5 still has many safety problems and legal policy problems, so that advanced assisted driving systems (ADAS) based on shared control have been increasingly researched, and unlike conventional assisted driving, an intelligent controller in man-machine driving can continuously assist a driver in safe driving in a control field, thereby improving driving safety and reducing driving burden of the driver. In the research process of the human-computer co-driving research technology, the test and evaluation technology is widely researched in the industry, and particularly the establishment of the human-computer co-driving experiment platform and the establishment of the evaluation standard are carried out.
For the construction of a human-computer co-driving experiment platform, a hardware-in-the-loop experiment platform is widely developed in the industry at present, a human-computer co-driving hardware-in-the-loop experiment platform comprising a PC, a human-computer co-driving steering ECU, a driving simulator, a front-mounted torque/corner sensor, a rear-mounted torque/corner sensor, a CAN card and a data collector is developed in Jiangsu university Jianghou and the like, the platform has a human-computer driving mode and a machine driving mode, and CAN effectively reduce development cost, but the platform cannot consider the vehicle motion characteristics under the actual road environment (Chinese patent: CN, CN107727417A and 'a human-computer co-driving system hardware-in-the-loop simulation test platform').
The Jilin university Zhu Bing and the like disclose a driving test platform for man-machine co-driving of an intelligent automobile, which mainly introduces a mechanical construction principle built by the test platform and still lacks a test of a landing scene (Chinese patent: CN, CN109493681A and 'a driving test platform for man-machine co-driving of an intelligent automobile'). Therefore, the human-computer co-driving based experimental platform still needs further research in consideration of the actual road environment and the actual vehicle condition.
For the test of the man-machine co-driving experiment and the establishment of the evaluation standard, different evaluations are carried out from different objects in the industry at present, fault generation and control switching detection modules are constructed by Shishunming of Jilin university and the like, a set of man-machine co-driving reliability evaluation method is formed, but indexes such as driver burden, man-machine co-driving cooperative performance and the like are still lack of specific explanation (Chinese patent: CN, CN107871418A, an experiment platform for evaluating man-machine co-driving reliability). Therefore, the testing and evaluating method of the man-machine co-driving experiment still needs to be further improved, and the lane keeping performance, the operation load of the driver and the man-machine co-driving cooperation performance need to be evaluated more carefully.
Disclosure of Invention
In order to solve the problems, the invention aims to provide a real vehicle experiment platform testing method for a man-machine driving-together intelligent vehicle.
In order to achieve the purpose, the invention provides a real vehicle experiment platform testing method for a man-machine co-driving intelligent vehicle, which adopts the technical scheme that the method comprises the following steps: the method comprises the following steps: on the basis of an E-HS3 real vehicle platform, firstly, an EPS (electric power steering) power-assisted motor of an original vehicle needs to be shielded so as to counteract the influence of the power-assisted system of the original vehicle on a man-machine common driving system, a controllable motor and a torque/angle sensor are additionally arranged in a steering system so as to construct an interface meeting the man-machine common driving, and the platform has three modes of driving by a human driver, driving by an intelligent driving system and driving by the human driver and the intelligent driving system; step two: deploying a millimeter wave radar, a camera, a GPS (global positioning system), an industrial personal computer and a bottom control system for the man-machine co-driving system on the basis of the step one, so as to form a closed loop test system containing external information; step three: aiming at the characteristics of the man-machine driving-together real vehicle experiment, a test frame which accords with man-machine driving-together is designed. And evaluating the experimental result by a subjective and objective experimental evaluation scheme.
Further, (1) on the basis of an E-HS3 real vehicle platform, a steering system meeting a man-machine common driving interface is designed, and the method comprises the following steps:
firstly, because the torque and angle signals of the E-HS3 steering system of the original experimental vehicle cannot be obtained, the original torque and angle signals of the vehicle must be shielded, so that the influence of the signals on the analysis of the man-machine driving system after the modification is avoided, namely the power-assisted T of the EPS of the original vehicleepsIs approximately equal to 0 and is,
Teps≈0 (1)
secondly, a torque/corner reading sensor and a torque/angle motor are additionally arranged on a steering column, the sensor can read the torque and the angle of the vehicle steering, the motor can execute a control signal, and the control input of a driver is additionally arranged on the premise of outputting a torque/angle control signal (namely controller output) by the known industrial personal computer, so that the resultant torque/angle acting on the additionally arranged motor can be finally obtained, the scheme can reach the standard of touch type man-machine common driving, and when the output of the controller is shielded, the mode is the independent driving mode of a person; when the driver does not operate the steering wheel and the controller continuously outputs the control quantity, the controller is in the driving mode; when the driver continuously operates the steering wheel and the controller continuously outputs the control quantity, the man-machine driving mode is realized.
Human drivers drive alone:
Tsensor＝Td (2)
the intelligent driving system drives:
Tsensor＝Tc (3)
human drivers share driving with smart driving systems:
Tsensor＝Td+Tc (4)
wherein ,TsensorIs the torque value, T, read by a sensor additionally arranged on the steering columndIs the amount of torque, T, applied to the steering wheel by the drivercIs the amount of torque that the intelligent driving system exerts on the steering column.
Further, (2) a closed-loop man-machine co-driving test system containing external information is established, and the method mainly comprises the following steps:
the industrial personal computer is connected with the sensing system through 2 paths of CAN (controller area network) (one path is responsible for sending the yaw velocity and the speed of the vehicle to the camera, and the other path is responsible for acquiring information processed by the camera and the millimeter wave radar). The camera and the millimeter wave radar are connected through the 1-path CAN. The industrial personal computer is connected with a high-precision positioning system (used for obtaining information such as the position, the direction angle and the like of the vehicle) through 1 path of USB, and the GPS module is connected with the 4G module through one path of RS232 (used for solving the network problem of the positioning system). The bottom controller is connected with the industrial personal computer through the 1-channel CAN, and is required to send commands to the controller and receive steering wheel turning angle and torque information from the controller. Because the industrial personal computer only has 2 paths of CAN, the CAN which sends the yaw angular velocity and the vehicle speed of the vehicle to the camera is connected with the CAN of the bottom controller in parallel, and the CAN IDs cannot conflict with each other. The vehicle-mounted hardware is directly powered by a vehicle-mounted battery and provides 12V direct current.
Further, deploying a awareness system: the system is a set of fusion sensing device comprising a millimeter wave radar and a camera, and the speed V of a vehicle is inputegoAnd yaw rate γegoOn the premise of information, for obtaining the position (x) of the front obstacleobs,yobs) The direction angle psiobsVelocity VobsAnd size information size thereofobs(l, w, h). Wherein the position information of the obstacle output by the sensor is described by a track:
Trajobs＝{(xobs,yobs):f(xobs,yobs)＝0} (5)
if the lane line is the form of a binary linear function:
Trajobs＝{(xobs,yobs):Axobs+Byobs+C＝0} (6)
where A, B, C are the coefficients of the corresponding functions.
Further, deploying a high-precision positioning system: the system is a set of high-precision positioning systems based on a differential time kinematic (RTK) GPS and an Inertial Measurement Unit (IMU) and is used for acquiring the position (x) of a self-vehicleego,yego) The direction angle psiegoAngular velocity gammaegoAnd the like. The partial information can be directly analyzed and then input into an industrial personal computer for online processing. It should be noted that since the differential technology requires network support, another set of 4G modules needs to be deployed to meet the network requirements of the system. By knowing the position information, direction angle, speed and other information of the vehicle and the obstacle, the relative position d between the vehicle and the obstacle can be obtainedrelRelative direction angle psirelRelative yaw rate γrelAnd so on.
ψrel＝ψego-ψobs (8)
γrel＝γego-γobs (9)
Further, deploying an upper layer processing unit: the system uses a vehicle-scale industrial personal computer as a carrier and is used for carrying out information processing and real-time calculation of control commands. The system mainly receives vehicle-mounted CAN bus information, information such as position and attitude of a high-precision positioning system, road and obstacle information of a fusion sensing system, CAN output control commands of moment/corner and acceleration of a steering wheel for processing by a bottom actuator, and calculates the control commands mainly based on control signals calculated in real time by information processing, namely moment Tc，
δc＝C1drel+C2ψrel+C3γrel (10)
Tc＝Kδc (11)
wherein ,C1Is a coefficient relating to the relative position of the vehicle and the obstacle, C2Is a coefficient relating to the relative angle of the vehicle and the obstacle, C3Is a coefficient relating to the yaw rate of the vehicle relative to the obstacle. Output control torque TcAnd controlling the angle of rotation deltacThere is a conversion factor K in between.
Further, deploying a bottom-layer control system: a steering under-layer controller to receive steering wheel angle or torque commands, and a longitudinal control system to receive acceleration commands. Meanwhile, the bottom control system CAN also provide the upper processing unit with the state information of the CAN bus of the chassis such as the vehicle speed, the steering wheel angle, the torque and the like.
Further, (3) aiming at the characteristics of the human-computer co-driving real vehicle experiment, a test control method frame which accords with human-computer co-driving is designed, and the experimental result is evaluated by a subjective and objective experimental evaluation scheme, and the method mainly comprises the following steps:
the test framework mainly generates a reference track according to the position information and the external environment information of the high-precision positioning system, obtains a deviation value according to the position information and the posture information of the test framework, and finally obtains a moment regulator based on fuzzy PID and active disturbance rejection, thereby achieving the purpose of controlling the transverse motion of the vehicle; the method comprises the following steps: firstly, obtaining the angle needed by steering by a fuzzy PID method, and secondly, obtaining the tracking angle delta by an active disturbance rejection methodcMoment T ofc。
Further, the required steering angle is obtained by a fuzzy PID method:
in order to make the controller quickly stable, corresponding fuzzy rules are designed, so that the parameter k in the PID algorithm is updated in real timep,kI,kdRespectively obtain real-time updated parameters
Further obtain
The control angle of the final output is δc，
wherein ,δdThe target corner based on the reference track is used as a feedforward response to act on a subsequent active disturbance rejection controller, and the main purpose of the method is to obtain a quick and accurate corner response.
② obtaining tracking angle delta by active disturbance rejection methodcMoment T ofc：
Because a coefficient K exists between the control force rejection and the control corner, the invention calculates the control moment T by designing the active disturbance rejection algorithmcTo track the control angle delta as much as possiblec，
wherein ,
xii is 1,2 is system state quantity, r, h is adjustable parameter, T is sampling step length, ziWhere i is 1,2,3 is the expansion state quantity, betaiI is 1,2,3 is a tunable parameter, α, δ, b is a tunable parameter, eiI is 1,2 is the deviation of the input state from the developed state variable, and u is the adjusting torque acting on the steering column.
A coefficient K exists between the control force rejection and the control corner, and the control moment T is calculated by designing an active disturbance rejection algorithmcTo track the control angle deltacSee formula (16).
Further, for the evaluation of the experimental result and the subjective evaluation of the man-machine driving-sharing system, four indexes of driving safety, driving accuracy, driving comfort and overall driving experience in the man-machine driving-sharing process are considered for evaluation respectively. The driving safety includes whether the driving safety can be improved, whether the traffic accidents can be reduced and whether the wrong behaviors of the driver can be compensated; driving accuracy includes the accuracy and smoothness during driving that the driver subjectively understands; driving comfort includes subjective assessment of the physical and psychological loads of the driver; the overall evaluation comprises the trust degree of a driver on a human-computer co-driving system, and the evaluation items respectively cover gender (1), driving age (2), age (3), driving safety (4-5), driving accuracy (6-7), driving comfort (8-10) and overall evaluation (11-13). (ii) a Scores included scores of 1-5 (1-disagreement, 2-little agreement, 3-neutral, 4-little agreement, 5-very agreement);
(4) for objective evaluation of the man-machine driving-sharing system, lane keeping performance, driver operation load and man-machine driving-sharing coordination performance are respectively considered.
The lane keeping performance mainly considers lane departure degree, track tracking precision and average passing time; the operation of the driver conforms to the requirements of mainly considering the change of the moment of the driver, the change of the lateral acceleration and the change rate of the lateral acceleration; the man-machine cooperative control performance mainly considers the steering correction force and the steering correction frequency of a driver in the man-machine driving process.
Lane keeping performance index:
lane departure degree: including the relative positional deviation drelRelative angular deviation psirel；
And (3) track tracking precision: including deviations of the actual trajectory from the desired trajectory.
Trajerror＝{(xego-xobs,yego-yobs):AerrorΔx+BerrorΔy+Cerror＝0} (17)
wherein ,Aerror，Berror，CerrorIs the correlation coefficient.
Average transit time: under the condition of ensuring lane departure degree and track tracking error precision, the vehicle can pass through quickly
Where l is the test road distance, v (d)rel,ψrel,Trajpre) Is the longitudinal speed of the vehicle affected by the degree of lane departure and trajectory tracking errors, and t is the vehicle transit time. dpreIs a distance safety threshold, psipreIs a direction angle safety threshold, TrajpreIs a trajectory safety threshold.
Operation load index of driver:
driver torque: respectively acquiring driver torque when a driver drives alone and driver torque T under a man-machine driving moded,d,Td,cop。
Lateral acceleration and rate of change: respectively acquiring the moment of the driver when the driver drives alone and the lateral acceleration and the change rate a under the man-machine common driving modey,Δay。
And thirdly, man-machine co-driving cooperative performance indexes:
steering correction force: deviation T between controller moment and steering correcting momentcor＝Tc-Tal。
wherein ,Tal＝-Fyf(tm+tp) Is a steering return moment, FyfIs the tire lateral force, tmThe distance t between the ground and the tire tread of the extension line of the backward inclination of the king pinpIs the tire support distance, FyfCan be approximated by tm,tpUsual parameters may be taken.
Driver steering correction rate: the number of times the driver has corrected the steering wheel within a certain time. Compared with the existing man-machine co-driving experiment platform, the invention has the following advantages that:
1. the steering system modified based on the real vehicle E-HS3 can meet the requirement of man-machine common driving, forms a touch man-machine common driving mode under a real vehicle platform, and has three different switchable driving modes: human driver drives, intelligent driving system drives, human driver and intelligent driving system share and drive, compares other hardware and is in the ring platform, and this platform can effectively satisfy the real car experiment demand that man-machine system of driving was driven altogether. 2. According to the invention, a closed-loop man-machine co-driving real vehicle test system containing external information is constructed, and the movement characteristics of man-machine co-driving in a real environment can be more accurately verified through online processing of information such as external road and obstacle information and vehicle position and posture.
3. The invention designs a test control frame which accords with human-machine common driving aiming at the human-machine common driving characteristics, and evaluates the experimental result by a subjective and objective experimental evaluation scheme, so that the human-machine common driving real vehicle experimental platform can be effectively executed and evaluated.
Drawings
FIG. 1 is a schematic diagram of a steering system that satisfies a human-machine interface.
Fig. 2 is a hardware overall architecture of the man-machine co-driving experimental platform.
Fig. 3 is a test control structure of the man-machine driving-together experiment platform.
Fig. 4 is a subjective evaluation analysis of the man-machine co-driving experiment.
Fig. 5 is a longitudinal velocity tracking characteristic.
Fig. 6 shows the trajectory tracking changes of the driver during the single-drive and man-machine driving.
FIG. 7 is a driver torque variation for both driver-alone and man-machine co-driving.
FIG. 8 shows lateral deviation variation of a vehicle between driver-alone driving and man-machine driving.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it should be understood that the described embodiments are some, but not all embodiments of the present invention. The following examples are presented merely to further understand and practice the present invention and are not to be construed as further limiting the claims of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The following further describes the details of the present invention and its embodiments.
(1) Steering system modified to meet human-computer common driving interface
Considering the richness of the driving modes of the human-computer co-driving real vehicle experiment platform, the human-computer co-driving experiment platform has three modes of driving by a human driver, driving by an intelligent driving system and sharing driving by the human driver and the intelligent driving system, and the human-computer co-driving experiment platform needs to meet the following conditions:
when a human driver drives, the control signal of the intelligent system can be completely shielded.
And secondly, when the intelligent system is driven independently, the control signal of a person can be completely shielded.
When a human driver and the intelligent driving system share driving, the human driver and the intelligent driving system can jointly act on the steering system and can mutually sense.
In order to meet the above conditions, the steering system of the red-flag E-HS3 vehicle is improved, and the structure of the steering system is shown in FIG. 1, wherein a broken line frame is provided with a power-assisted motor (shield) of the original vehicle, a solid line frame is provided with an additional motor and a torque/angle sensor, the sensor can read the torque and the angle of the vehicle during steering, and the motor can execute a control signal. On the premise that the industrial personal computer outputs a control signal of torque/angle (namely controller output), the control input of a driver is added, and finally, the added torque/angle sensor can obtain the resultant torque/angle acting on the steering column. Because the original EPS (electric power steering) source signal cannot be obtained, the method only can shield the original EPS source signal, the final result is that the steering power of the vehicle is reduced, the motor outputs a smaller inertia moment to act on a steering column, and the result can be approximately ignored, so that the influence of the output of the original motor on a man-machine driving experiment is avoided, and the power-assisted T of the original motor isepsSmall enough so that it can be ignored, i.e. Teps≈0。
TABLE 1 transverse vehicle test data after steering System retrofit
When the human driver drives, the torque obtained by the sensor is the torque of the human driver applied to the steering wheel, as shown in equation (2).
When the intelligent system drives alone, the torque obtained by the sensor is the torque applied to the steering column by the intelligent system, as shown in equation (3).
When the human driver and the intelligent driving system share driving, the torque obtained by the sensor is the sum of the torques of the human driver and the intelligent driving system, as shown in formula (4).
Therefore, the structure can provide three driving modes for man-machine common driving real vehicle experiments: the method comprises the following steps of human driver driving, intelligent driving system driving and shared driving of a human driver and an intelligent driving system.
In order to further verify the effectiveness of the structure, the modified steering system is subjected to a transverse steering test, and the steering wheel is respectively subjected to left-turning and right-turning operations of different angles, so that the obtained results are shown in table 1, and the results in table 1 show that the zero drift of the steering system of the modified vehicle is almost within 0.4deg, the steady-state error of the turning angle is guaranteed to be within 0.5deg, and the maximum overshoot of the steering wheel is within 6.9deg, which are all within a reasonable range, namely the steering system meets the steering performance.
(2) Establishing closed-loop man-machine co-driving test system containing external information
The main contents of the part are that a perception system, a high-precision positioning system, an upper-layer processing unit and a bottom-layer control system are deployed for a vehicle, the hardware architecture of the part is shown in fig. 2, the hardware information is shown in table 2, and the part mainly comprises the following contents:
deploying a perception system: the system is a set of fusion sensing device comprising a millimeter wave radar and a camera, and the speed V of a vehicle is inputegoAnd yaw rate γegoOn the premise of information, forAcquiring the position (x) of the front obstacleobs,yobs) The direction angle psiobsVelocity vobsAnd size information size thereofobs(l, w, h). The position information of the obstacle output by the sensor is described by a track, as shown in formula (5), and is in a form of a binary linear function if the position information is a lane line, as shown in formula (6).
Deploying a high-precision positioning system: the system is a set of high-precision positioning systems based on a differential time kinematic (RTK) GPS and an Inertial Measurement Unit (IMU) and is used for acquiring the position (x) of a self-vehicleego,yego) The direction angle psiegoAngular velocity gammaegoAnd the like. The partial information can be directly analyzed and then input into an industrial personal computer for online processing. It should be noted that since the differential technology requires network support, another set of 4G modules needs to be deployed to meet the network requirements of the system. By knowing the position information, direction angle, speed and other information of the vehicle and the obstacle, the relative position d between the vehicle and the obstacle can be obtainedrelRelative direction angle psirelRelative yaw rate γrelEtc., as in formulas (7) - (9).
Deploying an upper layer processing unit: the system uses a vehicle-scale industrial personal computer as a carrier and is used for carrying out information processing and real-time calculation of control commands. The system mainly receives vehicle-mounted CAN bus information, information such as position and attitude of a high-precision positioning system, road and obstacle information of a fusion sensing system, CAN output control commands of moment/corner and acceleration of a steering wheel for processing by a bottom layer executor, and calculates the control commands mainly based on information processing to calculate control signals in real time, wherein the control signals comprise corner deltacSum torque TcAs shown in formulas (11) and (12).
Deploying a bottom control system: a steering under-layer controller to receive steering wheel angle or torque commands, and a longitudinal control system to receive acceleration commands. Meanwhile, the bottom control system CAN also provide the upper processing unit with the state information of the CAN bus of the chassis such as the vehicle speed, the steering wheel angle, the torque and the like.
In the aspect of hardware line connection, the industrial personal computer is connected with the sensing system through 2 paths of CAN (controller area network) (one path is responsible for sending the yaw velocity and the speed of the vehicle to the camera, and the other path is responsible for acquiring information processed by the camera and the millimeter wave radar). The camera and the millimeter wave radar are connected through the 1-path CAN. The industrial personal computer is connected with a high-precision positioning system (used for obtaining information such as the position, the direction angle and the like of the vehicle) through 1 path of USB, and the GPS module is connected with the 4G module through one path of RS232 (used for solving the network problem of the positioning system). The bottom controller is connected with the industrial personal computer through the 1-channel CAN, and is required to send commands to the controller and receive steering wheel turning angle and torque information from the controller. Because the industrial personal computer only has 2 paths of CAN, the CAN which sends the yaw angular velocity and the vehicle speed of the vehicle to the camera is connected with the CAN of the bottom controller in parallel, and the CAN IDs cannot conflict with each other. The vehicle-mounted hardware is directly powered by a vehicle-mounted battery and provides 12V direct current.
TABLE 2 Main hardware information
(3) Test control method framework designed to conform to man-machine common driving system
The test structure of the invention is shown in figure 3, wherein the longitudinal control is controlled by a PD algorithm, the accelerator pedal of the vehicle is continuously adjusted, the longitudinal speed of the vehicle can be kept at a stable constant, the transverse control mainly generates a reference track according to the position information and the external environment information of a high-precision positioning system, then obtains a transverse deviation amount according to the position information and the posture information of the transverse control, and finally adjusts the rotation angle or the moment of a steering motor by a rotation angle mode based on a fuzzy PID or a moment mode based on the fuzzy PID and the active disturbance rejection, thereby achieving the purpose of controlling the transverse movement of the vehicle.
Longitudinal control:
controlling the longitudinal speed of the vehicle in a PD method:
Verror＝Vego-Vd (19)
wherein ,VegoIs the actual longitudinal speed, V, of the vehicledIs the target longitudinal speed, V, of the vehicleerrorIs the longitudinal speed deviation of the vehicle, uVIs the adjustment amount of the accelerator pedal.
And (3) transverse control:
secondly, the required steering angle is obtained by a fuzzy PID method, and the result is shown in formulas (12) to (15).
Third, obtaining tracking angle delta by active disturbance rejection methodcMoment T ofcThe result is represented by the formula (16).
For subjective evaluation of the man-machine co-driving system, specific evaluation items are shown in a table 3, and the evaluation items respectively cover gender (1), driving age (2), age (3), driving safety (4-5), driving accuracy (6-7), driving comfort (8-10) and overall evaluation (11-13). (ii) a Scores included scores of 1-5 (1-disagreement, 2-little agreement, 3-neutral, 4-little agreement, 5-very agreement).
TABLE 3 subjective evaluation items
Finally, subjective evaluation results of different drivers are obtained, and the results can be averaged
Mean square error
Root mean square error
And (4) processing, so that subjective evaluation of different drivers on the man-machine common driving system is further analyzed.
(4) As shown in table 4, the average, mean square error, and root mean square error may be considered in analyzing the data.
Lane keeping performance index:
lane departure degree: including the relative positional deviation drelRelative angular deviation psirel(ii) a And (3) track tracking precision: including the deviation of the actual trajectory from the desired trajectory, as in equation (17); average transit time: and (3) under the condition of ensuring the lane departure degree and the track tracking error precision, enabling the vehicle to pass through quickly, as shown in the formula (18).
Operation load index of driver:
driver torque: respectively acquiring driver torque when a driver drives alone and driver torque T under a man-machine driving moded,d,Td,cop. Lateral acceleration and rate of change: respectively acquiring the moment of the driver when the driver drives alone and the lateral acceleration and the change rate a under the man-machine common driving modey,Δay。
And thirdly, man-machine co-driving cooperative performance indexes:
steering correction force: deviation T between controller moment and steering correcting momentcor＝Tc-Tal. wherein ,Tal＝-Fyf(tm+tp) Is a steering return moment, FyfIs the tire lateral force, tmThe distance t between the ground and the tire tread of the extension line of the backward inclination of the king pinpIs the tire support distance, FyfCan be approximated by tm,tpUsual parameters may be taken. Driver steering correction rate: the number of times the driver has corrected the steering wheel within a certain time.
TABLE 4 Objective evaluation items
On the basis of the three parts, the step one ensures a hardware interface for man-machine common driving, the step two ensures closed-loop testing including external information, and the step three ensures a man-machine common driving testing method and an evaluation scheme, so that the comprehensive testing effect of the man-machine common driving real vehicle experimental platform is further verified, and effective experimental verification is performed on the basis of a testing structure chart 3.
Firstly, an unmanned roundabout road condition is selected for the experimental road, and the double-line-shifting working condition is simulated approximately.
And secondly, planning the reference track according to positioning information (GPS), attitude heading Information (IMU) and environment information (millimeter wave radar + camera) to obtain the reference track.
And thirdly, in order to verify the effectiveness of the experimental platform, PD self-adaptive cruise control is adopted for longitudinal control, the vehicle speed is controlled at 15km/h, a fuzzy PID + active disturbance rejection control algorithm is adopted for transverse control, and a driver can also control a steering wheel in real time according to environmental information so as to control the vehicle.
Selecting drivers of different ages to carry out the real-vehicle man-machine driving test.
The statistics of the results of the evaluation of the subjective evaluation items by the drivers of different ages are shown in table 5, and the data analysis after the processing is shown in fig. 4.
The average value can be obtained by analyzing the average value, in the aspect of safety, a driver can improve conservative attitude of driving safety for the common driving system, but the common driving system can make up for the wrong behaviors of the driver when the situations of wrong operation, fatigue driving and the like occur to the driver; in the aspect of accuracy, a driver can recognize that the common driving system can enable the vehicle to be kept in the middle of the lane more easily and enable the vehicle to run more stably; in the aspect of comfort, a driver thinks that the co-driving system can reduce the physical burden of the driver and can be mutually adaptive to the co-driving system, but the co-driving system is not well accepted to reduce the psychological burden of the driver in driving, which is probably because the situation of inconsistent cooperation exists between human and machines, a running-in process between the driver and the intelligent controller is required, so that the rationality of the human-machine co-driving system is improved; finally, it can be seen that the driver as a whole can trust the co-drive system and consider it possible to consider equipping the co-drive system.
The variance and the mean value can be analyzed and analyzed, so that different drivers have great divergence in the problem that the driving safety of the co-driving system can be improved, and probably because a few drivers potentially feel to be confronted with the co-driving system psychologically, the controller feels to be confronted with the drivers, and the safety is influenced; however, in the overall evaluation, different drivers have use values for the common driving system, and it is considered that the provision of the common driving system has the smallest divergence, which shows that on the basis of the above experiments, drivers of different genders, driving ages and ages generally have positive and optimistic attitudes for the common driving system.
TABLE 4 subjective evaluation item statistics for man-machine co-driving
The objective evaluation of the experimental results is shown in fig. 5-8, and fig. 5 shows that the human-machine co-driving real vehicle experimental platform not only can realize transverse control, but also can research longitudinal control problems, and further can perform a series of transverse and longitudinal coupling test experiments. Fig. 6 shows that the human-computer co-driving real vehicle experimental platform can be used for analyzing the change characteristics of the trajectory tracking when a driver drives independently and drives together, and the situation that the trajectory tracking precision is higher than that when the driver drives independently under the condition that the human-computer co-driving is seen; FIG. 7 shows that the platform can be used for analyzing the moment operation load of a driver when the driver drives independently and drives with man and machine, so that the influence on the driver is analyzed, and the process that the driver and an intelligent system possibly resist in the process of driving with man and machine is seen; fig. 8 shows that the platform can be used for analyzing different lateral deviations between the independent driving and the man-machine driving of the driver, that is, the trajectory tracking deviations in different driving modes can be analyzed, it can be seen that a large deviation may suddenly appear when the driver drives alone, and the change of the lateral deviation in the man-machine driving process is relatively stable.
The platform only lists part of experiments and analyses with feasibility, and can meet the requirements of track tracking tests, driver load tests, anti-interference tests, characteristic analysis of different variable (transverse deviation, transverse acceleration, yaw rate and the like), model and algorithm verification and other experiments in three modes of independent driving of a driver, independent driving of an intelligent system and simultaneous driving of a man and a machine, and the like, and can also research the transverse and longitudinal coupling conditions of vehicle dynamics in different modes.
While embodiments of the invention have been disclosed above, it is not intended to be limited to the uses set forth in the specification and examples. It can be applied to all kinds of fields suitable for the present invention. Additional modifications will readily occur to those skilled in the art. It is therefore intended that the invention not be limited to the exact details and illustrations described and illustrated herein, but fall within the scope of the appended claims and equivalents thereof.
Claims (10)
1. A real vehicle experiment platform testing method for a man-machine driving-together intelligent vehicle comprises the following design steps:
the method comprises the following steps: on the basis of an E-HS3 real vehicle platform, an EPS (electric power steering) motor of an original vehicle is shielded, and a controllable motor and a torque/angle sensor are additionally arranged in a steering system, so that an interface meeting the requirement of man-machine shared driving is constructed, and the platform has three modes of driving by a human driver, driving by an intelligent driving system and shared driving by the human driver and the intelligent driving system;
step two: deploying a millimeter wave radar, a camera, a GPS (global positioning system), an industrial personal computer and a bottom layer control system for the man-machine co-driving system on the basis of the step one, so as to form a closed-loop man-machine co-driving test system containing external information;
step three: aiming at the characteristics of the man-machine driving-together real vehicle experiment, a test frame which accords with man-machine driving-together is designed.
2. The test method for the human-computer co-driving intelligent vehicle-oriented real vehicle experimental platform as claimed in claim 1, wherein in the step one, on the basis of the E-HS3 real vehicle platform, firstly, an EPS (electric power steering) motor of an original vehicle needs to be shielded so as to counteract the influence of the original vehicle power-assisted system on the human-computer co-driving system, namely, the power assistance of the EPS of the original vehicle is approximately equal to 0, then, a controllable motor and a torque/angle sensor are additionally arranged in a steering system so as to construct an interface meeting the human-computer co-driving requirement,
Teps≈0 (1)
and finally, three modes of driving by a human driver, driving by an intelligent driving system and sharing driving by the human driver and the intelligent driving system are formed:
driving by a human driver alone:
Tsensor＝Td (2)
driving by an intelligent driving system:
Tsensor＝Tc (3)
sharing driving by a human driver and the intelligent driving system:
Tsensor＝Td+Tc (4)
wherein ,TepsIs the EPS assistance of the original vehicle, TsensorIs the torque value, T, read by a sensor additionally arranged on the steering columndIs the amount of torque, T, applied to the steering wheel by the drivercIs the amount of torque that the intelligent driving system exerts on the steering column.
3. The real-vehicle experimental platform testing method for the man-machine co-driving intelligent vehicle as claimed in claim 1, wherein in the second step, the establishment of the closed-loop man-machine co-driving testing system containing external information comprises the following steps:
the industrial personal computer is connected with the sensing system through 2 paths of CAN, one path of the industrial personal computer is responsible for sending the yaw velocity and the vehicle speed of the vehicle to the camera, the other path of the industrial personal computer is responsible for acquiring information processed by the camera and the millimeter wave radar, the camera and the millimeter wave radar are connected through 1 path of CAN, the industrial personal computer is connected with the high-precision positioning system through 1 path of USB and used for acquiring information such as the position and the direction angle of the vehicle, and the GPS module is connected with the 4G module through one path of RS232 and used for solving the network problem of the positioning system; the bottom controller is connected with the industrial personal computer through the 1-channel CAN, and is required to send commands to the controller and receive steering wheel turning angle and torque information from the controller; because the industrial personal computer only has 2 paths of CAN, the CAN which sends the yaw angular velocity and the vehicle speed of the vehicle to the camera is connected with the CAN of the bottom controller in parallel, and the CAN IDs cannot conflict with each other; the vehicle-mounted hardware is directly powered by a vehicle-mounted battery to provide 12V direct current;
the closed-loop man-machine co-driving test system specifically comprises: the method comprises the steps of deploying a sensing system, deploying a high-precision positioning system, deploying an upper-layer processing unit and deploying a bottom-layer control system.
4. The real-vehicle experimental platform testing method for the man-machine co-driving intelligent vehicle is characterized in that the deployment sensing system comprises: the system is a set of fusion sensing device comprising a millimeter wave radar and a camera, and the speed V of a vehicle is inputegoAnd yaw rate γegoOn the premise of information, for obtaining a position (x) including a front obstacleobs,yobs) The direction angle psiobsVelocity VobsAnd size information size thereofobs(l, w, h), wherein the position information of the obstacle output by the sensor is described by a trajectory:
Trajobs＝{(xobs,yobs):f(xobs,yobs)＝0} (5)
if the lane line is the form of a binary linear function:
Trajobs＝{(xobs,yobs):Axobs+Byobs+C＝0} (6)
where A, B, C are the coefficients of the corresponding functions.
5. The real-vehicle experimental platform testing method for the man-machine co-driving intelligent vehicle as claimed in claim 3, wherein the deployment high-precision positioning system comprises: the system is a set of high-precision positioning systems based on a differential time kinematic (RTK) GPS and an Inertial Measurement Unit (IMU) and is used for acquiring the position (x) of a self-vehicleego,yego) The direction angle psiegoAngular velocity gammaegoWaiting for positioning information; the partThe sub information can be directly analyzed and then input into an industrial personal computer for online processing; because the differential technology needs network support, a set of 4G modules needs to be additionally deployed to meet the network requirement of the system; the relative position distance d between the vehicle and the obstacle is obtained by knowing the position information, the direction angle and the angular speed information of the vehicle and the obstaclerelRelative direction angle psirelRelative yaw rate γrelInformation;
ψrel＝ψego-ψobs (8)
γrel＝γego-γobs。 (9)
6. the real-vehicle experimental platform testing method for the man-machine co-driving intelligent vehicle as claimed in claim 3, wherein the deployment upper-layer processing unit: the system takes a vehicle-scale industrial personal computer as a carrier and is used for carrying out information processing and real-time calculation of control commands; the information processing comprises information input of a sensing system, high-precision positioning system input, vehicle-mounted CAN information input and control signal input; the control command is calculated mainly on the basis of the control signal calculated in real time by information processing, i.e. the torque Tc，
δc＝C1drel+C2ψrel+C3γrel (10)
Tc＝Kδc (11)
wherein ,C1Is a coefficient relating to the relative position of the vehicle and the obstacle, C2Is a coefficient relating to the relative angle of the vehicle and the obstacle, C3Is a coefficient of the relative yaw angular velocity of the vehicle and the obstacle, and outputs a control torque TcAnd controlling the angle of rotation deltacThere is a conversion factor K in between.
7. The real-vehicle experimental platform testing method for the man-machine co-driving intelligent vehicle as claimed in claim 3, wherein the deployment floor control system: the steering bottom layer controller receives a steering wheel corner or moment command and the longitudinal control system receives an acceleration command; meanwhile, the bottom control system CAN also provide the upper processing unit with the state information of the CAN bus of the chassis such as the vehicle speed, the steering wheel angle, the torque and the like.
8. The test method for the human-computer co-driving intelligent vehicle-oriented real vehicle experiment platform as claimed in claim 1, wherein a test control frame conforming to human-computer co-driving is designed aiming at the characteristics of the human-computer co-driving real vehicle experiment in the third step, and the experimental result is evaluated by a subjective and objective experimental evaluation scheme, and the test method comprises the following steps:
the test framework mainly generates a reference track according to the position information and the external environment information of the high-precision positioning system, obtains a deviation value according to the position information and the posture information of the test framework, and finally obtains a moment regulator based on fuzzy PID and active disturbance rejection, thereby achieving the purpose of controlling the transverse motion of the vehicle;
the method comprises the following steps: firstly, obtaining the angle needed by steering by a fuzzy PID method, and secondly, obtaining the tracking angle delta by an active disturbance rejection methodcMoment T ofc。
9. The real-vehicle experimental platform testing method for the man-machine co-driving intelligent vehicle as claimed in claim 8, wherein the steering required angle is obtained by a fuzzy PID method:
in order to make the controller quickly stable, corresponding fuzzy rules are designed, so that the parameter k in the PID algorithm is updated in real timep,kI,kdRespectively obtain real-time updated parameters
Further obtain
The control angle of the final output is δc，
wherein ,δdThe target corner based on the reference track is used as a feedforward response to act on a subsequent active disturbance rejection controller, and the main purpose is to obtain a quick and accurate corner response;
obtaining the tracking angle delta by an active disturbance rejection methodcMoment T ofc：
wherein ,
xii is 1,2 is system state quantity, r, h is adjustable parameter, T is sampling step length, ziWhere i is 1,2,3 is the expansion state quantity, betaiI is 1,2,3 is a tunable parameter, α, δ, b is a tunable parameter, eiI is 1,2 is the deviation of the input state from the spread state variable, u is the adjustment acting on the steering columnMoment of force;
a coefficient K exists between the control force rejection and the control corner, and the control moment T is calculated by designing an active disturbance rejection algorithmcTo track the control angle deltacSee formula (16).
10. The test method for the human-computer co-driving intelligent vehicle-oriented real vehicle experiment platform is characterized in that for the evaluation of the experiment result, the subjective evaluation of a human-computer co-driving intelligent vehicle-oriented experiment system respectively considers four indexes of driving safety, driving accuracy, driving comfort and overall driving experience in the human-computer co-driving process for evaluation; the driving safety includes whether the driving safety can be improved, whether the traffic accidents can be reduced and whether the wrong behaviors of the driver can be compensated; driving accuracy includes the accuracy and smoothness during driving that the driver subjectively understands; driving comfort includes subjective assessment of the physical and psychological loads of the driver; the overall evaluation comprises the trust degree of a driver on the man-machine co-driving system; the evaluation items respectively cover sex (1), driving age (2), age (3), driving safety (4-5), driving accuracy (6-7), driving comfort (8-10) and overall evaluation (11-13); scores included scores of 1-5 (1-disagreement, 2-little agreement, 3-neutral, 4-little agreement, 5-very agreement);
the objective evaluation mainly evaluates lane keeping performance, driver operation load and man-machine driving cooperation performance,
lane keeping performance index:
lane departure degree: including the relative positional deviation drelRelative angular deviation psirel；
And (3) track tracking precision: including deviations of the actual trajectory from the desired trajectory;
Trajerror＝{(xego-xobs,yego-yobs):AerrorΔx+BerrorΔy+Cerror＝0} (17)
wherein ,Aerror，Berror，CerrorIs the correlation coefficient;
average transit time: under the condition of ensuring the lane departure degree and the track tracking error precision, the vehicle can pass through quickly,
where l is the test road distance, v (d)rel,ψrel,Trajpre) Is the longitudinal speed of the vehicle influenced by the degree of lane departure and track following errors, t is the vehicle transit time, dpreIs a distance safety threshold, psipreIs a direction angle safety threshold, TrajpreIs a trajectory safety threshold;
operation load index of driver:
driver torque: respectively acquiring driver torque when a driver drives alone and driver torque T under a man-machine driving moded,d,Td,cop；
Lateral acceleration and rate of change: respectively acquiring the moment of the driver when the driver drives alone and the lateral acceleration and the change rate a under the man-machine common driving modey,Δay；
And thirdly, man-machine co-driving cooperative performance indexes:
steering correction force: deviation T between controller moment and steering correcting momentcor＝Tc-Tal, wherein ,Tal＝-Fyf(tm+tp) Is a steering return moment, FyfIs the tire lateral force, tmThe distance t between the ground and the tire tread of the extension line of the backward inclination of the king pinpIs the tire support distance, FyfCan be approximated by tm,tpCommon parameters can be taken;
driver steering correction rate: the number of times the driver has corrected the steering wheel within a certain time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210127398.XA CN114323698B (en) | 2022-02-11 | 2022-02-11 | Real vehicle experiment platform testing method for man-machine co-driving intelligent vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210127398.XA CN114323698B (en) | 2022-02-11 | 2022-02-11 | Real vehicle experiment platform testing method for man-machine co-driving intelligent vehicle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114323698A true CN114323698A (en) | 2022-04-12 |
| CN114323698B CN114323698B (en) | 2023-09-08 |
Family
ID=81031030
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210127398.XA Active CN114323698B (en) | 2022-02-11 | 2022-02-11 | Real vehicle experiment platform testing method for man-machine co-driving intelligent vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114323698B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116578103A (en) * | 2023-07-13 | 2023-08-11 | 清华大学 | Method for evaluating running risk of man-vehicle-road closed-loop system under limit working condition |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140123186A1 (en) * | 2002-05-10 | 2014-05-01 | Convergent Media Solutions Llc | Method and apparatus for browsing using alternative linkbases |
| CN106275061A (en) * | 2016-09-21 | 2017-01-04 | 江苏大学 | A kind of man-machine drive type electric boosting steering system and control method altogether based on mix theory |
| CN106347449A (en) * | 2016-09-21 | 2017-01-25 | 江苏大学 | Man and machine driven type electric power steering system and mode switching method |
| CN107727417A (en) * | 2017-09-11 | 2018-02-23 | 江苏大学 | One kind is man-machine to drive steering hardware-in-the-loop test platform altogether |
| CN108819951A (en) * | 2018-07-27 | 2018-11-16 | 重庆大学 | It is a kind of to consider that the man-machine of driver's driving efficiency drives transverse driving power distribution method altogether |
| CN109795486A (en) * | 2019-03-01 | 2019-05-24 | 大连理工大学 | The method of power distribution is driven in man-machine lane keeping system of driving altogether |
| CN111409695A (en) * | 2020-04-13 | 2020-07-14 | 安徽卡思普智能科技有限公司 | Steering-by-wire man-machine sharing control method for intelligent automobile and intelligent automobile |
| CN111766879A (en) * | 2020-06-24 | 2020-10-13 | 天津大学 | Intelligent vehicle formation system based on autonomous collaborative navigation |
| CN113219955A (en) * | 2021-05-13 | 2021-08-06 | 吉林大学 | Multi-driver in-the-loop driving test platform |
| CN113619563A (en) * | 2021-09-06 | 2021-11-09 | 厦门大学 | Intelligent electric vehicle transverse control system and method based on man-machine sharing |
| CN113650609A (en) * | 2021-09-28 | 2021-11-16 | 中国科学技术大学先进技术研究院 | Flexible transfer method and system for man-machine co-driving control power based on fuzzy rule |
| CN113978548A (en) * | 2021-11-12 | 2022-01-28 | 京东鲲鹏(江苏)科技有限公司 | Steering cooperative control method, device, equipment and medium applied to unmanned vehicle |
-
2022
- 2022-02-11 CN CN202210127398.XA patent/CN114323698B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140123186A1 (en) * | 2002-05-10 | 2014-05-01 | Convergent Media Solutions Llc | Method and apparatus for browsing using alternative linkbases |
| CN106275061A (en) * | 2016-09-21 | 2017-01-04 | 江苏大学 | A kind of man-machine drive type electric boosting steering system and control method altogether based on mix theory |
| CN106347449A (en) * | 2016-09-21 | 2017-01-25 | 江苏大学 | Man and machine driven type electric power steering system and mode switching method |
| CN107727417A (en) * | 2017-09-11 | 2018-02-23 | 江苏大学 | One kind is man-machine to drive steering hardware-in-the-loop test platform altogether |
| CN108819951A (en) * | 2018-07-27 | 2018-11-16 | 重庆大学 | It is a kind of to consider that the man-machine of driver's driving efficiency drives transverse driving power distribution method altogether |
| CN109795486A (en) * | 2019-03-01 | 2019-05-24 | 大连理工大学 | The method of power distribution is driven in man-machine lane keeping system of driving altogether |
| CN111409695A (en) * | 2020-04-13 | 2020-07-14 | 安徽卡思普智能科技有限公司 | Steering-by-wire man-machine sharing control method for intelligent automobile and intelligent automobile |
| CN111766879A (en) * | 2020-06-24 | 2020-10-13 | 天津大学 | Intelligent vehicle formation system based on autonomous collaborative navigation |
| CN113219955A (en) * | 2021-05-13 | 2021-08-06 | 吉林大学 | Multi-driver in-the-loop driving test platform |
| CN113619563A (en) * | 2021-09-06 | 2021-11-09 | 厦门大学 | Intelligent electric vehicle transverse control system and method based on man-machine sharing |
| CN113650609A (en) * | 2021-09-28 | 2021-11-16 | 中国科学技术大学先进技术研究院 | Flexible transfer method and system for man-machine co-driving control power based on fuzzy rule |
| CN113978548A (en) * | 2021-11-12 | 2022-01-28 | 京东鲲鹏(江苏)科技有限公司 | Steering cooperative control method, device, equipment and medium applied to unmanned vehicle |
Non-Patent Citations (2)
| Title |
|---|
| CHUNYANGFU: "Adaptive robust backstepping attitude control for a multi-rotor unmanned aerial vehicle with time-varying output constraints", 《AEROSPACE SCIENCE AND TECHNOLOGY》 * |
| 李寿涛: "一种基于模型预测复合控制的 车辆避碰控制方法", 《吉林大学学报》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116578103A (en) * | 2023-07-13 | 2023-08-11 | 清华大学 | Method for evaluating running risk of man-vehicle-road closed-loop system under limit working condition |
| CN116578103B (en) * | 2023-07-13 | 2023-10-03 | 清华大学 | Method for evaluating running risk of man-vehicle-road closed-loop system under limit working condition |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114323698B (en) | 2023-09-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | Automatic steering control strategy for unmanned vehicles based on robust backstepping sliding mode control theory | |
| CN105329238B (en) | A kind of autonomous driving vehicle lane-change control method based on monocular vision | |
| CN110187639B (en) | Trajectory planning control method based on parameter decision framework | |
| Gray et al. | A unified approach to threat assessment and control for automotive active safety | |
| Wu et al. | The heterogeneous systems integration design and implementation for lane keeping on a vehicle | |
| Guo et al. | Design of automatic steering controller for trajectory tracking of unmanned vehicles using genetic algorithms | |
| Chebly et al. | Coupled longitudinal/lateral controllers for autonomous vehicles navigation, with experimental validation | |
| Hima et al. | Trajectory tracking for highly automated passenger vehicles | |
| Zafeiropoulos et al. | Design of a lane-tracking driver steering assist system and its interaction with a two-point visual driver model | |
| Song et al. | Virtual-point-based fault-tolerant lateral and longitudinal control of 4W-steering vehicles | |
| CN111775949A (en) | Personalized driver steering behavior assisting method of man-machine driving-sharing control system | |
| CN112141101B (en) | Method and system for pre-aiming safety path based on CNN and LSTM | |
| CN110162046A (en) | Unmanned vehicle path following method based on event trigger type model predictive control | |
| CN113467470B (en) | Trajectory tracking control method of unmanned autonomous trolley | |
| Na et al. | Experimental evaluation of a game-theoretic human driver steering control model | |
| CN112644488A (en) | Adaptive cruise system | |
| CN114323698B (en) | Real vehicle experiment platform testing method for man-machine co-driving intelligent vehicle | |
| Chen et al. | Parallel distributed compensation/H∞ control of lane-keeping system based on the Takagi-Sugeno fuzzy model | |
| Rasib et al. | Are Self‐Driving Vehicles Ready to Launch? An Insight into Steering Control in Autonomous Self‐Driving Vehicles | |
| CN107856733B (en) | A kind of automobile towards man-machine harmony hides dynamic barrier control method | |
| Ahmadi | Design a Reliable Model Predictive Control for Path Following with Application to the Autonomous Vehicle and Considering Different Vehicle Models | |
| Sentouh et al. | The H 2-optimal preview controller for a shared lateral control | |
| Weir et al. | Review of control theory models for directional and speed control | |
| CN115447615A (en) | Trajectory optimization method based on vehicle kinematics model predictive control | |
| Miao et al. | Research on decoupling control for the longitudinal and lateral dynamics of a tractor considering steering delay |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |