CN113335293B - Highway road surface detection system of drive-by-wire chassis - Google Patents
Highway road surface detection system of drive-by-wire chassis Download PDFInfo
- Publication number
- CN113335293B CN113335293B CN202110694166.8A CN202110694166A CN113335293B CN 113335293 B CN113335293 B CN 113335293B CN 202110694166 A CN202110694166 A CN 202110694166A CN 113335293 B CN113335293 B CN 113335293B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- road
- information
- road surface
- neural network
- 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.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 84
- 238000000034 method Methods 0.000 claims abstract description 33
- 230000008569 process Effects 0.000 claims abstract description 15
- 238000013528 artificial neural network Methods 0.000 claims description 146
- 206010039203 Road traffic accident Diseases 0.000 claims description 113
- 238000007726 management method Methods 0.000 claims description 68
- 230000004927 fusion Effects 0.000 claims description 60
- 230000001133 acceleration Effects 0.000 claims description 34
- 238000004364 calculation method Methods 0.000 claims description 30
- 238000004891 communication Methods 0.000 claims description 27
- 238000013461 design Methods 0.000 claims description 21
- 238000012549 training Methods 0.000 claims description 20
- 239000000725 suspension Substances 0.000 claims description 19
- 238000011156 evaluation Methods 0.000 claims description 18
- 239000000523 sample Substances 0.000 claims description 16
- 238000005259 measurement Methods 0.000 claims description 9
- 238000013500 data storage Methods 0.000 claims description 8
- 230000036541 health Effects 0.000 claims description 8
- 230000006870 function Effects 0.000 claims description 7
- 230000006378 damage Effects 0.000 claims description 6
- 201000010099 disease Diseases 0.000 claims description 6
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 6
- 238000007790 scraping Methods 0.000 claims description 6
- 238000011088 calibration curve Methods 0.000 claims description 5
- 230000007613 environmental effect Effects 0.000 claims description 5
- 230000003993 interaction Effects 0.000 claims description 5
- 230000006996 mental state Effects 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 3
- 206010019233 Headaches Diseases 0.000 claims description 2
- 208000002193 Pain Diseases 0.000 claims description 2
- 206010037660 Pyrexia Diseases 0.000 claims description 2
- 208000027418 Wounds and injury Diseases 0.000 claims description 2
- 238000013459 approach Methods 0.000 claims description 2
- 230000003750 conditioning effect Effects 0.000 claims description 2
- 239000000284 extract Substances 0.000 claims description 2
- 231100000869 headache Toxicity 0.000 claims description 2
- 208000014674 injury Diseases 0.000 claims description 2
- 208000024891 symptom Diseases 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 4
- 206010041349 Somnolence Diseases 0.000 description 2
- 230000036626 alertness Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 208000032140 Sleepiness Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000007789 sealing Methods 0.000 description 1
- 230000037321 sleepiness Effects 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
- B60W40/06—Road conditions
- B60W40/064—Degree of grip
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
- B60W40/06—Road conditions
- B60W40/072—Curvature of the road
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
- B60W40/06—Road conditions
- B60W40/076—Slope angle of the road
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
-
- 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
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64C—AEROPLANES; HELICOPTERS
- B64C39/00—Aircraft not otherwise provided for
- B64C39/02—Aircraft not otherwise provided for characterised by special use
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
- G08G1/0112—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from the vehicle, e.g. floating car data [FCD]
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/0967—Systems involving transmission of highway information, e.g. weather, speed limits
- G08G1/096766—Systems involving transmission of highway information, e.g. weather, speed limits where the system is characterised by the origin of the information transmission
- G08G1/096775—Systems involving transmission of highway information, e.g. weather, speed limits where the system is characterised by the origin of the information transmission where the origin of the information is a central station
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/40—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]
- H04W4/44—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P] for communication between vehicles and infrastructures, e.g. vehicle-to-cloud [V2C] or vehicle-to-home [V2H]
-
- 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
- B60W2420/00—Indexing codes relating to the type of sensors based on the principle of their operation
- B60W2420/40—Photo, light or radio wave sensitive means, e.g. infrared sensors
- B60W2420/408—Radar; Laser, e.g. lidar
-
- 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
- B60W2510/00—Input parameters relating to a particular sub-units
- B60W2510/30—Auxiliary equipments
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2520/00—Input parameters relating to overall vehicle dynamics
- B60W2520/10—Longitudinal speed
- B60W2520/105—Longitudinal acceleration
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2520/00—Input parameters relating to overall vehicle dynamics
- B60W2520/28—Wheel speed
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2530/00—Input parameters relating to vehicle conditions or values, not covered by groups B60W2510/00 or B60W2520/00
- B60W2530/20—Tyre 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
- B60W2540/00—Input parameters relating to occupants
- B60W2540/221—Physiology, e.g. weight, heartbeat, health or special needs
-
- 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
- B60W2555/00—Input parameters relating to exterior conditions, not covered by groups B60W2552/00, B60W2554/00
- B60W2555/20—Ambient conditions, e.g. wind or rain
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Mathematical Physics (AREA)
- General Physics & Mathematics (AREA)
- Analytical Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Aviation & Aerospace Engineering (AREA)
- Human Computer Interaction (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Atmospheric Sciences (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses an expressway pavement detection system with a drive-by-wire chassis, which is used for automatically detecting pavement parameters through an unmanned aerial vehicle and a detection vehicle equipped with the drive-by-wire chassis under the condition of closed expressways, aiming at the problems that vehicles are inconvenient and dangerous to pass and the road unsealing time is difficult to determine under the condition of closed expressways. The method of managing vehicles is to predict road passability by integrating the conditions of vehicles and drivers, and further determine whether to release vehicles and plan a driving plan. In addition, the vehicle detects the road surface parameters of the current road in the driving process, predicts the passability of the road in real time, corrects the driving scheme, guides the driver to drive in a voice mode, improves the safe driving capacity of the driver, ensures that the vehicle can safely pass through, quickly recovers the traffic, and reduces the inconvenience in passing caused by road closure.
Description
The technical field is as follows:
the invention relates to the field of traffic accident prevention, in particular to a highway pavement detection system with a drive-by-wire chassis and a vehicle management method, which are used for actively detecting pavement conditions under the condition of closed highway, predicting road trafficability by integrating the conditions of vehicles and drivers, further determining whether to release the vehicles and planning a driving scheme, detecting pavement parameters of the current road by the vehicles in the driving process, predicting road trafficability in real time and correcting the driving scheme, guiding the drivers to drive in a voice mode, improving the driver alertness and preventing traffic accidents.
Background art:
under the condition that the highway is blocked due to the conditions of snow, fog, rain and the like, the highway is not smooth to pass and is easy to block, a large number of vehicles are detained for waiting, the passing time is always fuzzy, the vehicles to be passed cannot be evacuated in time, and the traffic convenience is greatly influenced.
In the current measures about the driving safety of the expressway or reducing traffic accidents, an intelligent driving assistance system is mostly adopted to improve the driving safety, and the intelligent driving assistance system needs more sensor information to identify the environment, so that the processing is complex and time-consuming; at present, the mature auxiliary driving technology mainly relates to the aspects of longitudinal control, such as lane keeping, self-adaptive cruise and the like, is few in applicable traffic scenes, incomplete in function, incapable of coping with complex traffic environments temporarily and limited in effect of improving driving safety. If the traffic accident occurrence rate can be predicted, namely the road safety is evaluated, corresponding measures can be taken to remind a driver so that the driver can take the safety measures in time, the traffic accident can be avoided to a certain extent, the method is convenient to apply to various traffic scenes, but the measures for predicting and preventing the traffic accident occurrence rate on the overall road level are rarely reported. In addition, for the road sealing condition caused by poor highway adhesion condition, the existing solution is generally to wait until the severe weather is completely dissipated, the waiting time is long and unreasonable, and after the vehicle is unsealed, the vehicle runs according to the road regulation under the normal adhesion condition, and the special condition of the road surface and the special condition of part of the vehicle are not considered. The invention is thus proposed. The invention detects road parameters on a closed expressway by sending out an unmanned aerial vehicle and a detection motorcade carrying a drive-by-wire chassis, comprehensively predicts road trafficability according to road conditions and states of vehicles and drivers, plans a route for the vehicles which are allowed to pass, and broadcasts the route in real time in the driving process so as to improve the safe trafficability rate and accelerate the dredging of the vehicles; and the trafficability of the road is predicted in real time aiming at the current road in the driving process of the vehicle, and corresponding warning information is sent to remind a driver, so that the driver alertness is improved, the driving safety is guaranteed, and the traffic accident rate is further reduced.
The invention content is as follows:
the invention aims to overcome the problems in the prior art, a detection fleet provided with an aerial unmanned aerial vehicle and a wired control chassis is dispatched to detect the whole-line surface parameters of a highway under the condition of road closure of the highway caused by poor road attachment conditions, the road surface parameter data is returned to a vehicle management intelligent platform, a whole-line surface condition distribution library is generated by the vehicle management intelligent platform, and the safety passing grade of the vehicle is judged by integrating driver information and vehicle information so as to determine whether to pass and establish a safe running route scheme allowing the vehicle to pass, so that the safety passing efficiency of the highway is improved, and the vehicle is dredged safely and quickly.
In order to achieve the purpose, the invention is realized according to the following technical scheme:
a highway pavement detection system of a drive-by-wire chassis comprises a pavement parameter detection module, a wireless communication module, a vehicle management intelligent platform, a vehicle information storage module, a voice prompt module, a driver information input module and a vehicle-mounted prediction module; the vehicle-mounted prediction module comprises a vehicle-mounted road surface detection submodule and a passability prediction submodule; the wireless communication module comprises a vehicle-mounted wireless receiving and transmitting unit and an intelligent platform wireless receiving and transmitting unit; the road surface parameter detection module is responsible for collecting road surface parameter information and sending the road surface parameter information to the intelligent vehicle management platform; the vehicle management system comprises a driver information input module, a vehicle information storage module, a wireless communication module and a vehicle management intelligent platform, wherein the driver information input module acquires driver information, the vehicle information storage module collects vehicle information, and the wireless communication module sends the driver information and the vehicle information to the vehicle management intelligent platform; the vehicle management intelligent platform judges whether the vehicle can be released according to the information, formulates a safe driving scheme for the vehicle which is allowed to be released, and sends the safe driving scheme to a voice prompt module of the vehicle through the wireless communication module; the voice guidance module plays related voice to guide the running route and speed of the vehicle in the whole course; in the vehicle running process, a vehicle-mounted detection submodule in a vehicle-mounted prediction module is responsible for detecting road surface parameters in real time, a driver information input module and a vehicle information storage module respectively input driver information and vehicle information into a passability prediction submodule, a vehicle management intelligent platform sends the road surface parameters and safety region prediction information to the vehicle-mounted prediction module through a wireless communication module, the passability prediction submodule judges whether the safety level of a current running safety region is reduced or not in real time according to the input information so as to judge whether the safety region can pass or not, the information about whether the safety region passes or not is stored in a data storage submodule, and the information is sent to the vehicle management platform at an exit of a highway.
The technical scheme is that the pavement parameter detection module comprises a detection vehicle and an aerial unmanned aerial vehicle; the detection vehicle is an unmanned intelligent vehicle based on a wire control chassis, the wheel base, the wheel track and the vehicle body height can be changed within a certain range, an area with the worst front road surface adhesion condition is identified and judged by shooting images through an aerial unmanned aerial vehicle in the detection process, the wheel base and the vehicle track are correspondingly adjusted to adapt to the area with the worst road surface condition, and the worst adhesion coefficient is detected; the tires are classified into two types of probe vehicles using passenger tires and commercial tires, each equipped with 8 wheels, four types of tires, two tires each on the front, rear, left, and right sides, arranged in parallel, and the tire pressure can be dynamically adjusted so as to equip the tires of the probe vehicles and adjust the tire pressure according to the type of the vehicle tires to be passed through and the load. The tire type has longitudinal pattern radial tires with two flat rates and longitudinal pattern common bias tires, the flat rate can be selected from 70%, 65%, 60%, 55% and 50%, the flat rate of the tire is selected from two names of the flat rate statistics of vehicle tires at the entrance of the expressway, and if no vehicle is waiting for the next time, the tire with the flat rate of 65% and 55% is used by default; commercial tires include longitudinal pattern radial tires, transverse pattern radial tires, and mixed pattern radial tires;
the detection scheme is that each lane of a passenger vehicle type detection vehicle and a commercial vehicle type detection vehicle is respectively provided with one vehicle, the vehicles run according to the specified speed of the lane, and the detection vehicles are respectively sent out from the starting points of two running directions of a highway at the same time during the first detection, namely two groups of detection vehicles run in opposite directions; the road surface adhesion coefficient that two teams of detection cars will detect uploads vehicle management wisdom platform, is compared the adhesion condition in two direction lanes by vehicle management wisdom platform, if similar, when then dispatching the detection car of a direction the second time, only need send the detection car of a direction carry out road surface parameter acquisition can.
The method for acquiring the road surface parameters by the detection vehicle in the road surface parameter detection module is characterized in that the detection vehicle is provided with an information acquisition unit, a road curvature calculation unit, a road adhesion coefficient calculation unit and a road gradient calculation unit; the system comprises an information acquisition unit, a detection vehicle, a vehicle acceleration sensor, a vehicle wheel angular velocity sensor, a vehicle speed sensor, a global positioning system receiver and an electronic navigation map, wherein the information acquisition unit respectively acquires signals and electronic navigation maps of the suspension height sensor, the aerial unmanned aerial vehicle speed sensor shoots road speed sensor, shoots road speed sensor 500 meters ahead the aerial unmanned aerial vehicle estimates the vehicle, estimates the road speed sensor shoots road speed sensor, estimates the road speed sensor shoots road grade and the road speed sensor and the vehicle and the road speed sensor, and the vehicle speed sensor, and the vehicle and the information respectively, and the information respectively sends the information to the information, and the information to the information, wherein the information to the information, and the information to the information, and the information of the aerial vehicle, and the information of the aerial vehicle, and the aerial vehicle height sensor of the aerial vehicle, and the aerial vehicle, and the aerial vehicle, and the aerial; the information acquired by the information acquisition unit is used by a road curvature calculation unit, a road adhesion coefficient calculation unit and a road gradient calculation unit; the road adhesion coefficient calculation unit calculates the road adhesion rate according to the vertical load of the tire and the tire stress condition acquired by the tire force sensor, estimates the slip rate according to the vehicle acceleration and the wheel angular velocity, finally obtains a road adhesion coefficient estimation value ac according to a road adhesion rate-slip rate calibration curve, and calculates an adhesion coefficient estimation value ac every 5 meters; the global positioning system receiver acquires the position of a probe vehicle, and the road curvature calculation unit extracts the line shape of the current road position from the electronic navigation map so as to calculate a road curvature value C2; searching a road curvature design value of a corresponding road position in the road design data according to the position of the probe vehicle to obtain a road curvature design value C3 corresponding to the current position; weighting and fusing a road curvature design value C3, a road curvature estimation value C1 estimated by an aerial unmanned aerial vehicle and a road curvature estimation value C2 to obtain a final road curvature value C, wherein the fusion weight is set according to the weather condition: under severe weather conditions such as rain, snow, fog and hail, the weight of the road curvature value C1 estimated by the aerial unmanned aerial vehicle is 0.2, and the weight of the road curvature design value C3 is 0.5; under other meteorological conditions, the weight of the road curvature value C1 estimated by the aerial unmanned aerial vehicle is 0.3, the weight of the road curvature value C2 is 0.3, and the weight of the road curvature value C3 is 0.4; when the positioning information cannot be normally acquired, the weight of the road curvature value C1 estimated by the aerial unmanned aerial vehicle is 1, the weight of the road curvature value C2 is 0, and the weight of the road curvature value C3 is 0; the information acquisition unit inputs acceleration, wheel torque and rotating speed signals and point cloud data generated by a laser radar into a slope degree computing subunit, and the slope degree computing subunit separates road longitudinal slope information from an original acceleration sensor signal by adopting a least square method so as to obtain a road longitudinal slope angle XA 1; estimating the roll angle of the vehicle body relative to the chassis through the information of the suspension height sensor, and finally estimating a road lateral slope angle YA 1; establishing an interval grid map under a Cartesian coordinate system by using point cloud data, performing plane fitting in intervals to obtain a normal vector of the road surface, and calculating a longitudinal slope angle XA2 and a lateral slope angle YA2 of the road surface by using the normal vector; meanwhile, a vehicle longitudinal state observer based on a vehicle longitudinal dynamic model in a slope degree subunit estimates a longitudinal slope angle XA3 according to vehicle torque, rotating speed and acceleration; the vehicle lateral state observer based on the two-degree-of-freedom vehicle kinematic model estimates a road lateral slope angle YA3 according to a front wheel corner, a vehicle body yaw angular velocity and a vehicle body lateral acceleration; acquiring the position of a probe vehicle by a global positioning system receiver, and searching a slope angle design value in road design data according to the position of the probe vehicle to obtain a longitudinal slope angle XA4 and a lateral slope angle YA 4; weighting and fusing the 5 types of longitudinal gradient angles XA0, XA1, XA2, XA3 and XA4 to obtain a final longitudinal gradient angle XA; the fusion weight of various longitudinal slope angles is fixed, the fusion weight of the longitudinal slope angle XA1 is 0.05, the fusion weight of the longitudinal slope angle XA1 estimated according to signals of the acceleration sensor is 0.1, the fusion weight of the longitudinal slope angle XA3 estimated by a longitudinal observer is 0.2, the fusion weight of the slope angle XA2 estimated according to a laser radar is 0.3, and the fusion weight of the longitudinal slope angle XA4 is 0.5; weighting and fusing the four lateral slope angles YA1, YA2, YA3 and YA4 to obtain a final lateral slope angle YA; when entering and leaving a side slope, the fusion weight of the side slope angle YA1 calculated based on the information of the suspension height sensor is 0.35, the fusion weight of the side slope angle YA3 estimated by the side state observer is 0.15, the fusion weight of the side slope angle YA3 estimated by the side state observer is 0.35 when on the slope, the fusion weight of the side slope angle YA1 calculated based on the information of the suspension height sensor is 0.15, the fusion weight of the side slope angle YA0 is always 0.05, the fusion weight of the side slope angle YA2 estimated according to the laser radar is always 0.2, and the fusion weight of the side slope angle YA4 is always 0.25.
The driver information input module comprises a human-computer interaction interface and a data storage device, and basic information of a driver, basic information of passengers in the same row and accident characteristics of a traffic accident which once occurs to the driver are input by the driver in a questionnaire form through the human-computer interaction interface; wherein the basic information of the driver comprises age, gender, identification number, driving age, daily average driving time, physical health condition, mental state and occupation; the driving age takes natural numbers of 0, 1 and 2 … … as input, and the unit is year; the daily average driving time allows the input of an integer between 0 and 24, and the unit is hour; there are three options for physical health: health, sub-health, disease state, under the option given corresponding comments for the driver to understand, "disease state" means having one of the symptoms of cold, headache, fever, "sub-health state" is painful or feels uncomfortable in other parts of the body but difficult to describe, "health state" means normal, no disease and no pain; mental states provide three options: good, poor and poor, corresponding comments are given below the options to facilitate the understanding of the driver, the 'poor' means feeling sleepy and hard to concentrate on, the 'good' means no sleepiness and capable of concentrating on, the description has strong subjectivity and is input by the driver after self-evaluation; professional options offer two broad categories: professional and non-professional drivers; the accident characteristics comprise accident frequency, accident forms, accident severity, accident reasons, hit-and-run vehicle types and accident time, wherein the accident forms comprise rear-end collision, scraping and fixed objects, the accident severity is divided into casualty accidents, personal injury accidents and death accidents, the accident reasons comprise that the same lane is driven and does not keep safe distance with a front vehicle according to regulations, the operation is improper, the light is not used according to the regulations under the condition of low visibility or the vehicle speed is not driven according to the regulations, the lane is illegally changed, traffic signals are violated, fatigue driving is carried out, illegal road driving is carried out, the hit-and-run vehicle types comprise heavy trucks, medium trucks, light trucks, mini trucks, large buses, medium buses, light buses, small buses and passenger vehicles, and the accident time is particularly up to the time of the month and the day; the data storage device stores the above information.
The vehicle information storage module stores vehicle type parameters, tire information, braking system information, driving system information, steering system information, the service life of the vehicle, the driving mileage and accident characteristics of historical traffic accidents of the vehicle, wherein the vehicle type parameters comprise vehicle type, vehicle length, width, height, size, minimum turning radius, vehicle conditioning quality, maximum driving force, total vehicle mass, wheel distance, mass center height, distance from the mass center to a rear axle, windward area, wheel distance, minimum ground clearance, approach angle, departure angle, maximum vehicle speed, maximum output torque, wheel number, driving wheel number and automatic driving level; the tire information indicates the tire type and the tire radius; the brake system information comprises brake type and size parameters; the driving system information comprises a power type and related size parameters; the steering system information comprises a steering system type and related size parameters; the types of vehicles are divided into commercial vehicles and passenger vehicles, and the commercial vehicles are divided into heavy trucks, medium trucks, light trucks, mini trucks, large buses, medium buses, light buses and small buses; the used age of the vehicle is obtained from the automobile data recorder, and the time from the time recorded by the automobile data recorder for the first time to the current time is taken as the used age of the vehicle; the accident characteristics of the historical traffic accident of the vehicle comprise accident frequency, accident form, damage condition and accident time, the accident form comprises rear-end collision, scraping and impact on a fixed object, the damage condition comprises a scraping part, a damaged part and a repaired or replaced part, and the accident time records year, month and day.
The intelligent vehicle management platform comprises an environmental information acquisition module, a historical traffic accident information storage module and a vehicle management core module; the environment information acquisition module acquires visibility, road surface parameters, time and meteorological information, wherein the meteorological information comprises rain, snow, fog, temperature and humidity; the historical traffic accident information storage module stores the related characteristic information of traffic accidents, including the distribution characteristic of hit-and-run vehicle types, the distribution characteristic of traffic accident time, the distribution characteristic of traffic accident visibility, the meteorological characteristic of traffic accidents, the distribution characteristic of traffic accident positions, the density characteristic of traffic accidents, the road surface characteristic of traffic accidents and the characteristic of hit-and-run drivers; the road surface characteristics of the traffic accident refer to a road surface adhesion coefficient, a road curvature and a slope, and the characteristics of the hit-cause driver comprise the age, the sex, the driving age and the occupation of the hit-cause driver;
the vehicle management core module comprises a traffic flow distribution subunit, a safety passing grade evaluation subunit and a safety driving scheme planning subunit; the number of vehicles, the motorcycle type of vehicle are released in traffic flow distribution subunit decision, utilize neural network to estimate the number of the vehicle of allowing under current environment, the road surface condition, motorcycle type, and neural network includes input layer, hides layer and output layer, and the input layer has 4 units: time, visibility, meteorological vector and road surface parameter, the hidden layer is divided into two layers, the first layer hidden layer is composed of 4 units, the second layer hidden layer is composed of 2 units, the output layer is provided with 2 units, the neural network is trained by using the distribution characteristic of hit-and-run vehicle types, the distribution characteristic of traffic accident time, the distribution characteristic of traffic accident positions, the distribution characteristic of traffic accident visibility, the meteorological characteristic of traffic accident and the density characteristic of traffic accident vehicles in the historical traffic accident information storage module in advance, the time, visibility, meteorological vector and road surface parameter information are input into the neural network, and the neural network outputs the maximum value of the number of vehicles allowed to pass and the vehicle types allowed to pass;
the safety passing grade evaluation subunit respectively evaluates the passing performance of the vehicle on the specific road surface and the driving reliability of the driver on the specific road surface, and evaluates the safety passing grade by integrating the results of the two aspects; the trafficability assessment of the vehicle on the specific road surface is calculated by establishing a vehicle dynamic model and a road model, wherein the dynamic model comprises a tire model, a driving system model, a braking system model, a vehicle body model and an air resistance model, the vehicle dynamic model is established according to vehicle type parameters, tire information, braking system information, driving system information and steering system information stored in a vehicle information storage module, and the road model comprises 4 parameters: the road surface adhesion coefficient, the curvature radius of a curve, the longitudinal gradient and the transverse gradient, and data come from a road surface parameter detection module; the road type comprises straight roads, curved roads, ramps and combinations thereof with different road adhesion coefficients, and the trafficability, the passable vehicle speed and the transmission gear of the vehicle under various roads are respectively calculated to obtain the position of the road where the vehicle can run;
the driving reliability of a driver on a specific road surface uses a fuzzy neural network to predict the probability of the driver driving on a drivable road surface, the structure of the fuzzy neural network is a preposed neural network and the fuzzy neural network, the preposed neural network is divided into 3 sub-neural networks which are respectively a neural network 1, a neural network 2 and a neural network 3, and the structure of each sub-neural network is 3 layers: the input layer, hide layer, output layer, fuzzy neural network structure divide into 5 layers altogether: the fuzzy neural network comprises an input layer, a fuzzy rule layer, a fuzzy decision layer and an output layer, wherein the output layer of the 3 subneural networks is one part of the input layer of the fuzzy neural network; training a neural network 1 by using hit-and-run driver characteristic data, inputting basic information of a driver, basic information of passengers in the same row and accident characteristics of a traffic accident which once occurs to the driver into the neural network 1, and evaluating hit-and-run probability of the driver, wherein the accident characteristics of the traffic accident which once occurs to the driver influence the weight of each layer of the neural network, and the neural network 1 finally outputs a value between 0 and 100 percent; training a neural network 2 by using hit vehicle type distribution data, inputting vehicle type parameters of the vehicle into the neural network 2, evaluating the safety level of the vehicle, and outputting the probability of the vehicle having a traffic accident, wherein the probability value is between 0 and 100 percent; training a neural network 3 by using traffic accident road surface characteristic data, sequentially inputting road surface parameters of a vehicle travelable road surface into the neural network 3, predicting the probability of causing traffic accidents on the road surfaces by the neural network 3, wherein the probability value is between 0 and 100 percent; the input layer of the fuzzy neural network comprises 4 units: the hit-and-miss probability of the driver, the probability of the traffic accident of the vehicle, the probability of the traffic accident caused by the vehicle on the road surface where the vehicle can run, the highest vehicle speed of the lane limit is input for multiple times, the highest vehicle speed of one lane limit is input at one time, the membership function of the fuzzy layer is generated by the neural network according to the historical traffic accident data, the fuzzy rule of the fuzzy rule layer is extracted from the knowledge base by the neural network, the neural network adjusts the knowledge base in real time according to the update of the traffic accident information, the parameters of the fuzzy rule are automatically optimized on line, and the fuzzy language values are 4: { LPL, MPL, HPL, SPL }, meaning: { the safety pass level is low, the safety pass level is medium, the safety pass level is high, and the safety pass level is high }, and the output layer outputs the safety pass level with the highest degree of membership of the road surface;
the safe driving scheme planning subunit utilizes the safe passing grade of the road surface where the vehicle can drive output by the safe passing grade evaluation subunit, and preferentially connects the positions of the road surface with high safe passing grade according to the safe passing grade to form a driving path with the highest comprehensive safe passing grade; the proportion of the road surface with the lower safe passing grade to all the road surfaces of the whole running path is not more than 5%, the proportion of the road surface with the middle safe passing grade to all the road surfaces of the whole running path is less than 10%, the vehicle is considered as an effective safe path and allowed to pass through and enter a waiting area, otherwise, the vehicle is considered as an ineffective safe path and not allowed to pass through and enter the waiting area; the method comprises the steps of grading vehicles capable of forming an effective safe path according to comprehensive safe passing grades, wherein the grading rule is that 25, 50, 75 and 100 grades are respectively obtained for roads with lower safe passing grades, medium safe passing grades, higher safe passing grades and high safe passing grades, the sum of the scores of all the roads in the driving path is accumulated, the vehicles are sorted according to the sum, a corresponding number of vehicles ranked in the front are released according to traffic flow allowable values, and safe path data are sent to the vehicles through wireless communication.
The vehicle-mounted prediction module comprises a vehicle-mounted prediction module and a passability prediction module, wherein the vehicle-mounted prediction module comprises a vehicle-mounted road surface detection submodule and a passability prediction submodule, the vehicle-mounted road surface detection submodule detects current road surface parameters in the driving process, and the passability prediction submodule refers to the safety level of platform evaluation according to the detected road surface parameter conditions and carries out passability evaluation on the current road surface again; the vehicle-mounted road surface detection submodule comprises an information acquisition subunit, a road surface adhesion coefficient calculation subunit and a road slope calculation subunit; the system comprises an information acquisition unit, a road slope measurement unit, a road surface adhesion coefficient calculation subunit and a road slope measurement subunit, wherein the information acquisition unit respectively acquires signals of a suspension height sensor, an inertia measurement unit, a laser radar, a tire force sensor, a vehicle acceleration sensor and a wheel angular velocity sensor, and the signals are used by the road surface adhesion coefficient calculation subunit and the road slope measurement subunit;
the road adhesion coefficient calculation unit calculates the road adhesion rate according to the vertical load of the tire and the tire stress condition acquired by the tire force sensor, estimates the slip rate according to the vehicle acceleration and the wheel angular velocity, and finally obtains a road adhesion coefficient estimation value ac' according to a road adhesion rate-slip rate calibration curve;
the information acquisition subunit inputs the acceleration, the wheel torque and rotating speed signals and point cloud data generated by the laser radar into a slope degree calculation subunit, and the slope degree calculation subunit separates road longitudinal slope information from an original acceleration sensor signal by adopting a least square method so as to obtain a road longitudinal slope angle XA 1'; estimating the roll angle of the vehicle body relative to the chassis through the information of the suspension height sensor, and finally estimating a road side slope angle YA 1'; establishing an interval grid map under a Cartesian coordinate system by using point cloud data, performing plane fitting in intervals to obtain a road surface normal vector, and calculating a longitudinal slope angle XA2 'and a lateral slope angle YA 2' of the road surface by using the normal vector; meanwhile, a longitudinal slope angle XA 3' is estimated by a vehicle longitudinal state observer based on a vehicle longitudinal dynamic model in a slope degree subunit according to vehicle torque, rotating speed and acceleration; the vehicle lateral state observer based on the two-degree-of-freedom vehicle kinematic model estimates a road lateral slope angle YA 3' according to a front wheel corner, a vehicle body yaw angular velocity and a vehicle body lateral acceleration; weighting and fusing the three longitudinal gradient angles XA1 ', XA 2' and XA3 'to obtain a final longitudinal gradient angle XA'; the fusion weight of various longitudinal slope angles is fixed, the fusion weight of the slope angle XA1 ' estimated according to the signals of the acceleration sensor is 0.2, the fusion weight of the longitudinal slope angle XA3 ' estimated by a longitudinal observer is 0.3, and the fusion weight of the slope angle XA2 ' estimated according to the laser radar is always 0.5; weighting and fusing the three lateral slope angles YA1 ', YA 2' and YA3 'to obtain a final lateral slope angle YA'; when entering and leaving a side slope, the fusion weight of the side slope angle YA1 ' calculated based on the information of the suspension height sensor is 0.35, the fusion weight of the side slope angle YA3 ' estimated by the side state observer is 0.15, the fusion weight of the side slope angle YA3 ' estimated by the side state observer is 0.35 when on the slope, the fusion weight of the side slope angle calculated based on the information of the suspension height sensor is 0.15, and the fusion weight of the side slope angle YA2 estimated according to the laser radar is 0.5;
if the ratio of the road gradient and the road adhesion coefficient calculated by the vehicle-mounted road surface detection submodule to the difference value of the corresponding parameter value measured by the detection vehicle to the corresponding parameter value measured by the detection vehicle exceeds 10%, the passability prediction submodule is started to carry out passability evaluation on the current road again; the passability prediction submodule predicts the road passability of a model by using a fuzzy neural network, the fuzzy neural network prediction model structure is a preposed neural network and the fuzzy neural network, the preposed neural network is divided into 3 sub-neural networks which are respectively a neural network 1, a neural network 2 and a neural network 3, and the structure of each sub-neural network is 3 layers: the input layer, hide layer, output layer, fuzzy neural network structure divide into 5 layers altogether: the fuzzy neural network comprises an input layer, a fuzzy rule layer, a fuzzy decision layer and an output layer, wherein the output layer of the 3 subneural networks is one part of the input layer of the fuzzy neural network; training a neural network 1 by using hit-and-run driver characteristic data, inputting basic information of a driver and accident characteristics of a traffic accident which the driver has happened into the neural network 1, evaluating hit-and-run probability of the driver, and finally outputting a value between 0 and 100 percent; training a neural network 2 by using hit-and-accident vehicle type distribution data, inputting vehicle type parameters of the vehicle into the neural network 2, evaluating the safety level of the vehicle, and outputting the probability of traffic accidents of the vehicle, wherein the probability value is between 0 and 100 percent; training a neural network 3 by using traffic accident road surface characteristic data, inputting the acquired road surface parameters into the neural network 3, and predicting the probability of causing a traffic accident on a certain road surface, wherein the probability value is between 0 and 100 percent; the input layer of the fuzzy neural network comprises 5 units: the probability of causing a traffic accident of a driver, the probability of the traffic accident of a vehicle, the probability of the traffic accident caused by a road surface, the probability of the traffic accident caused by the environment and the vehicle speed, wherein a membership function of a fuzzy layer is generated by a neural network according to historical traffic accident data, fuzzy rules of a fuzzy rule layer are extracted from a knowledge base by the neural network, the neural network adjusts the knowledge base in real time according to the update of traffic accident information, the parameters of the fuzzy rules are automatically optimized on line, and 4 fuzzy language values are provided: { LPL, MPL, HPL, SPL }, meaning: { the safety passing grade is low, the safety passing grade is medium, the safety passing grade is high, and the safety passing grade is high }, the output layer outputs the safety passing grade with the highest road surface membership degree, and sends the safety passing grade to the voice prompt module.
The voice prompt module comprises a voice playing unit and a decision unit; in the driving process, if the passability prediction submodule is not started or the output probability value is less than 60%, the voice playing unit plays the driving scheme of the intelligent vehicle management platform, and plays prompt information of a corresponding road surface position according to vehicle positioning, wherein the prompt information comprises a reasonable vehicle speed and a driving lane; otherwise, the decision unit improves the driving scheme according to the intelligent vehicle management platform, redefines the driving speed and sends the corrected driving scheme to the voice playing unit for real-time playing; when the vehicle reaches an exit of a highway or the vehicle cannot pass in the midway, the wireless communication module returns successful passing information or unsafe passing information, the platform records the safe passing times and the unsafe passing times of all roads on the vehicle running path, and the data are used as a training data set for training a neural network and a fuzzy neural network of a vehicle management core module in the vehicle management intelligent platform, so that the prediction accuracy is improved.
Particularly, under certain conditions, the mobile phone can be used as a human-computer interaction interface to collect driver information, and used as a vehicle-mounted wireless communication device to communicate with a vehicle management intelligent platform, send the driver and vehicle information, receive a driving scheme, and serve as a voice playing unit to broadcast route information and a reasonable speed value in the driving process.
Compared with the prior art, the invention has the beneficial effects that:
1. at present, means for preventing traffic accidents mainly aim at strengthening safety education, and safety driving consciousness of drivers is expected to be improved through safety education, but the method is poor in real-time performance, driving capabilities of different drivers are different, driving experience cannot be improved through safety education, and traffic accidents cannot be avoided.
2. Although the conventional driving assisting system for improving driving safety can guarantee driving safety to a certain extent, most of the driving assisting systems passively assist driving and mainly play a role in correcting and rarely actively preventing traffic accidents.
3. The conventional driving assistance system for improving driving safety has single function, cannot be used in complex traffic environments for a while, and has no report, but the road trafficability prediction method is not influenced by complex driving scenes, and is suitable for various environments.
4. The road surface detection system with the wire-control chassis can detect the road surface condition in time, further judge whether the vehicle is released and plan a safe driving route, so that the vehicle can be dredged quickly and efficiently, the safety is ensured, and the vehicle management is more convenient.
Description of the drawings:
the invention will be further described with reference to the accompanying drawings and examples, in which:
FIG. 1 is a block diagram of the system components of the present invention;
FIG. 2 is a schematic diagram of a road adhesion coefficient estimation method according to the present invention;
FIG. 3 is a schematic diagram of a road curvature estimation method according to the present invention;
FIG. 4 is a schematic illustration of a road grade estimation method of the present invention;
FIG. 5 is a schematic diagram of a vehicle management method of the present invention.
The specific implementation mode is as follows:
in order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, the highway pavement detection system with the drive-by-wire chassis comprises a pavement parameter detection module, a vehicle-mounted correlation module, a wireless communication module, a vehicle management intelligent platform and a voice prompt module; wherein, there are four modules in total on the vehicle: the vehicle-mounted prediction system comprises a vehicle information storage module, a voice prompt module, a driver information input module and a vehicle-mounted prediction module. The vehicle-mounted prediction module comprises a vehicle-mounted road surface detection submodule, a passability prediction submodule and a data storage submodule. The vehicle-mounted prediction module is respectively connected with the vehicle information storage module, the voice prompt module and the driver information input module, and the four modules on the vehicle are respectively communicated with the intelligent vehicle management platform through the wireless communication module. The intelligent platform for vehicle management comprises three modules: the system comprises a vehicle management core module and a historical traffic accident information storage module; the road surface parameter acquisition module composed of a detection motorcade and an unmanned aerial vehicle is connected with an environmental information acquisition module in the vehicle management intelligent platform.
The road surface parameter detection module is responsible for collecting road surface parameter information, sending the road surface parameter information to the intelligent vehicle management platform and receiving the information by the environment information acquisition module; the vehicle management system comprises a driver information input module, a vehicle information storage module, a wireless communication module, a vehicle management core module, a vehicle management intelligent platform and a vehicle management module, wherein the driver information input module acquires driver information, the vehicle information storage module collects vehicle information, and the wireless communication module sends the driver information and the vehicle information to the vehicle management core module of the vehicle management intelligent platform; the intelligent vehicle management platform judges whether the vehicle can safely pass according to the information and the information of the historical traffic accident information storage module, establishes a safe driving route scheme for the vehicle which is allowed to pass, and sends the safe driving scheme to the voice prompt module of the vehicle through the wireless communication module; the voice guidance module plays relevant voice to guide the running route and the speed of the vehicle in the whole course. In the vehicle running process, a vehicle-mounted detection submodule in a vehicle-mounted prediction module is responsible for detecting road surface parameters in real time, a driver information input module and a vehicle information storage module respectively input driver information and vehicle information into a passability prediction submodule, a vehicle management intelligent platform sends the road surface parameters and safety region prediction information to the vehicle-mounted prediction module through a wireless communication module, the passability prediction submodule judges whether the safety level of a current running safety region is reduced or not in real time according to the input information so as to judge whether the safety region can pass or not, the information about whether the safety region passes or not is stored in a data storage submodule, and the information is sent to the vehicle management platform at an exit of a highway.
Referring to fig. 2, the road adhesion coefficient estimation method of the present invention calculates a road adhesion rate according to a tire vertical load and a tire stress condition acquired by a tire force sensor, estimates a slip rate from a vehicle acceleration and a wheel angular velocity, and finally obtains a road adhesion coefficient estimation value ac according to a road adhesion rate-slip rate calibration curve.
Referring to fig. 3, the method for estimating the road curvature of the invention includes that the aerial unmanned aerial vehicle shoots a road image, estimates the road curvature through image recognition, communicates with the wireless communication module of the probe vehicle, and sends the curvature estimation value C1 to the probe vehicle. Acquiring the position of a probe vehicle by a global positioning system receiver, extracting the line shape of the current road position from an electronic navigation map, and further calculating to obtain a road curvature value C2; searching a road curvature design value of a corresponding road position in the road design data according to the position of the probe vehicle to obtain a road curvature design value C3 corresponding to the current position; weighting and fusing a road curvature design value C3, a road curvature estimation value C1 estimated by an aerial unmanned aerial vehicle and a road curvature estimation value C2 to obtain a final road curvature value C, wherein the fusion weight is set according to the weather condition: under severe weather conditions such as rain, snow, fog and hail, the weight of the road curvature value C1 estimated by the aerial unmanned aerial vehicle is 0.2, and the weight of the road curvature design value C3 is 0.5; under other meteorological conditions, the weight of the road curvature value C1 estimated by the aerial unmanned aerial vehicle is 0.3, the weight of the road curvature value C2 is 0.3, and the weight of the road curvature value C3 is 0.4; when the positioning information cannot be normally acquired, the weight of the road curvature value C1 estimated by the aerial unmanned aerial vehicle is 1, the weight of the road curvature value C2 is 0, and the weight of the road curvature value C3 is 0;
referring to fig. 4, the method for estimating the road gradient of the invention includes that an aerial unmanned aerial vehicle shoots a road image, and the road gradient is estimated through image recognition to obtain a longitudinal gradient estimated value XA0 and a transverse gradient estimated value YA0 of the road; separating the longitudinal gradient information of the road from the original acceleration sensor signal by adopting a least square method so as to obtain a longitudinal gradient angle XA1 of the road; estimating the roll angle of the vehicle body relative to the chassis through the information of the suspension height sensor, and finally estimating a road lateral slope angle YA 1; establishing an interval grid map under a Cartesian coordinate system by using point cloud data, performing plane fitting in intervals to obtain a normal vector of the road surface, and calculating a longitudinal slope angle XA2 and a lateral slope angle YA2 of the road surface by using the normal vector; a vehicle longitudinal state observer based on a vehicle longitudinal dynamic model estimates a longitudinal slope angle XA3 according to vehicle torque, rotation speed and acceleration; the vehicle lateral state observer based on the two-degree-of-freedom vehicle kinematic model estimates a road lateral slope angle YA3 according to a front wheel corner, a vehicle body yaw angular velocity and a vehicle body lateral acceleration; acquiring the position of a probe vehicle by a global positioning system receiver, and searching a slope angle design value in road design data according to the position of the probe vehicle to obtain a longitudinal slope angle XA4 and a lateral slope angle YA 4; weighting and fusing the 5 types of longitudinal gradient angles XA0, XA1, XA2, XA3 and XA4 to obtain a final longitudinal gradient angle XA; the fusion weight of various longitudinal slope angles is fixed, the fusion weight of the longitudinal slope angle XA1 is 0.05, the fusion weight of the longitudinal slope angle XA1 estimated according to the signal of the acceleration sensor is 0.1, the fusion weight of the longitudinal slope angle XA3 estimated by a longitudinal observer is 0.2, the fusion weight of the slope angle XA2 estimated according to a laser radar is 0.3, and the fusion weight of the longitudinal slope angle XA4 is 0.5; weighting and fusing the four lateral slope angles YA1, YA2, YA3 and YA4 to obtain a final lateral slope angle YA; when entering and leaving a side slope, the fusion weight of the side slope angle YA1 calculated based on the information of the suspension height sensor is 0.35, the fusion weight of the side slope angle YA3 estimated by the side state observer is 0.15, the fusion weight of the side slope angle YA3 estimated by the side state observer is 0.35 when on the slope, the fusion weight of the side slope angle YA1 calculated based on the information of the suspension height sensor is 0.15, the fusion weight of the side slope angle YA0 is always 0.05, the fusion weight of the side slope angle YA2 estimated according to the laser radar is always 0.2, and the fusion weight of the side slope angle YA4 is always 0.25.
Referring to fig. 5, the vehicle management method of the present invention is that the vehicle management intelligent platform determines whether the vehicle can safely pass through, and makes a safe driving scheme for the vehicle; and correcting the safe driving scheme by the vehicle-mounted prediction module according to the change condition of the road surface parameters in the driving process of the vehicle. The intelligent vehicle management platform comprises an environmental information acquisition module, a historical traffic accident information storage module and a vehicle management core module. The environment information acquisition module acquires visibility, road surface parameters, time and meteorological information, wherein the meteorological information comprises rain, snow, fog, temperature and humidity. The historical traffic accident information storage module stores the related characteristic information of traffic accidents, including the distribution characteristic of hit-and-run vehicle types, the distribution characteristic of traffic accident time, the distribution characteristic of traffic accident visibility, the meteorological characteristic of traffic accidents, the distribution characteristic of traffic accident positions, the density characteristic of traffic accidents, the road surface characteristic of traffic accidents and the characteristic of hit-and-run drivers. The road surface characteristics of the traffic accident refer to the road surface adhesion coefficient, the road curvature and the gradient, and the characteristics of the troublemaker comprise the age, the sex, the driving age and the occupation of the troublemaker.
The vehicle management core module comprises a traffic flow distribution subunit, a safety passing grade evaluation subunit and a safety driving scheme planning subunit. The traffic flow distribution subunit estimates the models and the quantity of vehicles allowed to pass under the current environment and road conditions by utilizing a neural network, the neural network comprises an input layer, a hidden layer and an output layer, and the input layer comprises 4 units: time, visibility, meteorological vector, road surface parameter, hidden layer are total two-layerly, and the first layer hidden layer comprises 4 units, and the second layer hidden layer comprises 2 units, and the output layer has 2 units: the number and types of vehicles allowed to pass. The neural network is trained by using the distribution characteristics of hit-and-run vehicle types, the distribution characteristics of traffic accident time, the distribution characteristics of traffic accident positions, the visibility distribution characteristics of traffic accidents, the weather characteristics of traffic accidents and the density characteristics of traffic accidents in the historical traffic accident information storage module in advance, time, visibility, weather and road surface parameter information is input into the neural network, the maximum value of the number of vehicles allowed to pass and the types of vehicles allowed to pass are output by the neural network, and vehicles meeting conditions are selected by the vehicle intelligent platform to communicate with the neural network according to the information.
The safety passing grade evaluation subunit establishes a vehicle dynamic model according to the vehicle type parameters, the tire parameters, the braking system parameters, the driving system parameters and the steering system parameters stored in the vehicle information storage module, wherein the vehicle dynamic model comprises a tire model, a driving system model, a braking system model, a vehicle body model and an air resistance model. The environmental information acquisition module stores road surface parameters from the road surface parameter detection module: road adhesion coefficient, curve curvature radius, longitudinal gradient and transverse gradient, and establishing a road model according to the road parameters, wherein the road type comprises straight roads, curves, ramps and combinations thereof with different road adhesion coefficients. The trafficability, the passable vehicle speed and the transmission gear of the vehicle under various roads are respectively calculated to obtain the position of the road surface where the vehicle can run, and the position is input to a fuzzy neural network for predicting the reliability of a driver.
The structure of the fuzzy neural network is a preposed neural network and a fuzzy neural network, the preposed neural network is divided into 3 sub-neural networks which are respectively a neural network 1, a neural network 2 and a neural network 3, and the structure of each sub-neural network is 3 layers: the input layer, hide layer, output layer, fuzzy neural network structure divide into 5 layers altogether: the fuzzy neural network comprises an input layer, a fuzzy rule layer, a fuzzy decision layer and an output layer, wherein the output layer of the 3 subneural networks is one part of the input layer of the fuzzy neural network; training a neural network 1 by using hit-and-run driver characteristic data, inputting basic information of a driver, basic information of passengers on the same-row and accident characteristics of a traffic accident which once occurs to the driver into the neural network 1, and evaluating hit-and-run probability of the driver, wherein the accident characteristics of the traffic accident which once occurs to the driver influence weight values of all layers of the neural network, and the neural network 1 finally outputs a value between 0 and 100 percent; training a neural network 2 by using hit vehicle type distribution data, inputting vehicle type parameters of the vehicle into the neural network 2, evaluating the safety level of the vehicle, and outputting the probability of the vehicle having a traffic accident, wherein the probability value is between 0 and 100 percent; training a neural network 3 by using traffic accident road surface characteristic data, sequentially inputting road surface parameters of a vehicle travelable road surface into the neural network 3, predicting the probability of causing traffic accidents on the road surfaces by the neural network 3, wherein the probability value is between 0 and 100 percent; the input layer of the fuzzy neural network comprises 4 units: the hit probability of the driver, the probability of traffic accident of the vehicle, the probability of traffic accident caused by the vehicle on the road surface, the maximum speed of the traffic lane, the maximum speed of one traffic lane, the membership function of the fuzzy layer is generated by the neural network according to the historical traffic accident data, the fuzzy rule of the fuzzy rule layer is extracted from the knowledge base by the neural network, the neural network adjusts the knowledge base in real time according to the update of the traffic accident information, the parameters of the fuzzy rule are automatically optimized on line, and the fuzzy language values are 4: { LPL, MPL, HPL, SPL }, meaning: { the safety passing grade is low, the safety passing grade is medium, the safety passing grade is high, and the safety passing grade is high }, and the output layer outputs the safety passing grade with the highest road surface membership degree and inputs the safety passing grade to the safe driving scheme planning subunit.
The safe driving scheme planning subunit utilizes the safe passing grade of the road surface which can be driven by the vehicle and is output by the safe passing grade evaluation subunit, and preferentially connects the positions of the road surface with high safe passing grade according to the high and low safe passing grade to form a driving path with the highest comprehensive safe passing grade; the proportion of the road surface with the lower safe passing grade to all the road surfaces of the whole running path is not more than 5%, the proportion of the road surface with the middle safe passing grade to all the road surfaces of the whole running path is less than 10%, the vehicle is considered as an effective safe path and allowed to pass through and enter a waiting area, otherwise, the vehicle is considered as an ineffective safe path and not allowed to pass through and enter the waiting area; the vehicles capable of forming the effective safe path are graded according to the comprehensive safe passing grade, the grading rule is that the road surfaces with lower safe passing grade, medium safe passing grade, higher safe passing grade and high safe passing grade are respectively graded by 25 points, 50 points, 75 points and 100 points, the sum of the scores of all the road surfaces in the driving path is accumulated, the vehicles with corresponding number ranked in the front are released according to the traffic flow allowable value, and the safe path data and the specified vehicle speed are sent to the vehicles through wireless communication. Vehicles receiving the information can start in order.
In the running process of the vehicle, if the ratio of the difference value of the road gradient and the road adhesion coefficient calculated by the vehicle-mounted road surface detection submodule to the corresponding parameter value measured by the detection vehicle exceeds 10%, the road gradient and the road adhesion coefficient are sent to the vehicle management intelligent platform, and the environment information acquisition module updates the road surface parameters. And the passability prediction submodule is started to carry out passability evaluation on the current road again. If the passability prediction submodule is not started or the output safe passage grade is not lower than the safe passage grade predicted by the intelligent vehicle management platform, the voice playing unit plays the driving scheme of the intelligent vehicle management platform and plays prompt information of the corresponding road surface position according to vehicle positioning, wherein the prompt information comprises reasonable vehicle speed and driving lanes; otherwise, the decision unit improves the driving scheme according to the intelligent vehicle management platform, re-specifies the driving speed, and sends the corrected driving scheme to the voice playing unit for real-time playing; when the vehicle reaches an exit of a highway or the vehicle cannot pass in the midway, the wireless communication module returns successful passing information or unsafe passing information, the platform records the safe passing times and the unsafe passing times of all roads on the vehicle running path, and the data are used for training the neural network and the fuzzy neural network of the vehicle management core module in the intelligent vehicle management platform.
The foregoing discussion is that of the preferred embodiments of the present invention only, and is intended to be illustrative and explanatory only and not limiting of the invention itself. It is intended that the invention not be limited to the particular embodiments disclosed herein, but that it be defined by the claims that follow. Furthermore, references made in the foregoing description to specific embodiments are not intended to be interpreted as limitations on the scope of the invention or on the definition of terms used in the claims. Various other embodiments and various modifications to the disclosed embodiments will be apparent to those skilled in the art. All such embodiments, changes and modifications that do not depart from the basic inventive concepts are intended to be included within the scope of the appended claims.
Claims (8)
1. The utility model provides a highway road surface detection system of drive-by-wire chassis which characterized in that: the system comprises a road surface parameter detection module, a wireless communication module, a vehicle management intelligent platform, a vehicle information storage module, a voice prompt module, a driver information input module and a vehicle-mounted prediction module; the vehicle-mounted prediction module comprises a vehicle-mounted road surface detection submodule and a passability prediction submodule; the wireless communication module comprises a vehicle-mounted wireless receiving and transmitting unit and an intelligent platform wireless receiving and transmitting unit; the intelligent vehicle management platform comprises an environmental information acquisition module, a historical traffic accident information storage module and a vehicle management core module; the road surface parameter detection module is responsible for collecting road surface parameter information and sending the road surface parameter information to the intelligent vehicle management platform; the vehicle management system comprises a driver information input module, a vehicle information storage module, a wireless communication module and a vehicle management intelligent platform, wherein the driver information input module acquires driver information, the vehicle information storage module collects vehicle information, and the wireless communication module sends the driver information and the vehicle information to the vehicle management intelligent platform; the vehicle management core module of the intelligent vehicle management platform judges whether the vehicle can be released or not according to the information, establishes a safe driving scheme for the vehicle allowed to be released, and sends the safe driving scheme to the voice prompt module of the vehicle through the wireless communication module; the voice guidance module plays related voice to guide the running route and speed of the vehicle in the whole course; in the running process of a vehicle, a vehicle-mounted road surface detection submodule in a vehicle-mounted prediction module is responsible for detecting road surface parameters in real time, a driver information input module and a vehicle information storage module respectively input driver information and vehicle information into a passability prediction submodule, a vehicle management intelligent platform sends the road surface parameters and safety region prediction information to the vehicle-mounted prediction module through a wireless communication module, the passability prediction submodule judges whether the safety level of a safety region which runs currently is reduced or not in real time according to the input information so as to judge whether the safety region can pass or not, the passing success or failure information is stored in a data storage submodule, and the information is sent to the vehicle management intelligent platform at an exit of a highway.
2. The drive-by-wire chassis highway pavement detection system according to claim 1, wherein: the pavement parameter detection module comprises a detection vehicle and an aerial unmanned aerial vehicle; the detection vehicle is an unmanned intelligent vehicle based on a wire control chassis, the wheel base, the wheel track and the vehicle body height can be changed within a certain range, an area with the worst front road surface adhesion condition is identified and judged by shooting images through an aerial unmanned aerial vehicle in the detection process, the wheel base and the vehicle track are correspondingly adjusted to adapt to the area with the worst road surface condition, and the worst road surface adhesion coefficient is detected; the tires are divided into two types of detection vehicles using passenger tires and commercial tires, each vehicle is provided with 8 wheels and four types of tires, and the front tires, the rear tires, the left tires and the right tires are arranged in parallel, and the tire pressure can be dynamically adjusted, so that the tires of the detection vehicles can be arranged and the tire pressure can be adjusted according to the type and the load of the vehicle tires to be passed; the detection scheme is that each lane of a passenger vehicle type detection vehicle and a commercial vehicle type detection vehicle is respectively provided with one vehicle, the vehicles run according to the specified speed of the lane, and the detection vehicles are respectively sent out from the starting points of two running directions of a highway at the same time during the first detection, namely two groups of detection vehicles run in opposite directions; the two groups of detection vehicles upload the detected road surface adhesion coefficient to the vehicle management intelligent platform, the vehicle management intelligent platform compares the adhesion conditions of the lanes in two directions, and if the road surface adhesion coefficients at the same position are similar, the detection vehicles in one direction only need to be dispatched to acquire road surface parameters when the detection vehicles are dispatched for the second time.
3. The drive-by-wire chassis highway pavement detection system according to claim 1, wherein: the method for acquiring the road surface parameters by the detection vehicle in the road surface parameter detection module is that the detection vehicle is provided with an information acquisition unit, a road curvature calculation unit, a road adhesion coefficient calculation unit and a road gradient calculation unit; the system comprises an information acquisition unit, a detection vehicle, a vehicle longitudinal gradient estimation unit, an information acquisition unit, a vehicle acceleration sensor, a vehicle wheel angular velocity sensor, a laser radar, a tire force sensor, a vehicle wheel angular velocity sensor, a global positioning system receiver and an electronic navigation map, wherein the information acquisition unit is used for respectively acquiring signals of a suspension height sensor, an inertia measurement unit, a laser radar, a tire force sensor, a vehicle acceleration sensor, a vehicle wheel angular velocity sensor and a global positioning system receiver, an aviation unmanned aerial vehicle is used for shooting road images 500 m in front of the vehicle, estimating the road gradient and the curvature through image recognition, communicating with a wireless communication module of the detection vehicle, and sending a road longitudinal gradient estimation value XA0, a road transverse gradient estimation value YA0 and a curvature estimation value C1 to the detection vehicle; the information acquired by the information acquisition unit is used by a road curvature calculation unit, a road adhesion coefficient calculation unit and a road gradient calculation unit; the road adhesion coefficient calculation unit calculates the road adhesion rate according to the vertical load of the tire and the tire stress condition acquired by the tire force sensor, estimates the slip rate according to the vehicle acceleration and the wheel angular velocity, finally obtains a road adhesion coefficient estimation value ac according to a road adhesion rate-slip rate calibration curve, and calculates an adhesion coefficient estimation value ac every 5 meters; the global positioning system receiver acquires the position of a probe vehicle, and the road curvature calculation unit extracts the line shape of the current road position from the electronic navigation map so as to calculate a road curvature value C2; searching a road curvature design value of a corresponding road position in the road design data according to the position of the probe vehicle to obtain a road curvature design value C3 corresponding to the current position; weighting and fusing a road curvature design value C3, a road curvature estimation value C1 estimated by an aerial unmanned aerial vehicle and a road curvature estimation value C2 to obtain a final road curvature value C, wherein the fusion weight is set according to the weather condition: under severe weather conditions such as rain, snow, fog and hail, the weight of the road curvature value C1 estimated by the aerial unmanned aerial vehicle is 0.2, and the weight of the road curvature design value C3 is 0.5; under other meteorological conditions, the weight of the road curvature value C1 estimated by the aviation unmanned aerial vehicle is 0.3, the weight of the road curvature value C2 is 0.3, and the weight of the road curvature value C3 is 0.4; when the positioning information cannot be normally acquired, the weight of the road curvature value C1 estimated by the aerial unmanned aerial vehicle is 1, the weight of the road curvature value C2 is 0, and the weight of the road curvature value C3 is 0; the information acquisition unit inputs acceleration, wheel torque and rotating speed signals and point cloud data generated by a laser radar into a slope degree computing subunit, and the slope degree computing subunit separates road longitudinal slope information from an original acceleration sensor signal by adopting a least square method so as to obtain a road longitudinal slope angle XA 1; estimating the roll angle of the vehicle body relative to the chassis through the information of the suspension height sensor, and finally estimating a road lateral slope angle YA 1; establishing an interval grid map under a Cartesian coordinate system by using point cloud data, performing plane fitting in intervals to obtain a normal vector of the road surface, and calculating a longitudinal slope angle XA2 and a lateral slope angle YA2 of the road surface by using the normal vector; meanwhile, a vehicle longitudinal state observer based on a vehicle longitudinal dynamic model in a slope degree subunit estimates a longitudinal slope angle XA3 according to vehicle torque, rotating speed and acceleration; the vehicle lateral state observer based on the two-degree-of-freedom vehicle kinematic model estimates a road lateral slope angle YA3 according to a front wheel corner, a vehicle body yaw angular velocity and a vehicle body lateral acceleration; acquiring the position of a probe vehicle by a global positioning system receiver, and searching a slope angle design value in road design data according to the position of the probe vehicle to obtain a longitudinal slope angle XA4 and a lateral slope angle YA 4; weighting and fusing the 5 types of longitudinal gradient angles XA0, XA1, XA2, XA3 and XA4 to obtain a final longitudinal gradient angle XA; the fusion weight of various longitudinal slope angles is fixed, the fusion weight of the longitudinal slope angle XA1 is 0.05, the fusion weight of the longitudinal slope angle XA1 estimated according to signals of the acceleration sensor is 0.1, the fusion weight of the longitudinal slope angle XA3 estimated by a longitudinal observer is 0.2, the fusion weight of the slope angle XA2 estimated according to a laser radar is 0.3, and the fusion weight of the longitudinal slope angle XA4 is 0.5; weighting and fusing the four lateral slope angles YA1, YA2, YA3 and YA4 to obtain a final lateral slope angle YA; when entering and leaving a side slope, the fusion weight of the side slope angle YA1 calculated based on the information of the suspension height sensor is 0.35, the fusion weight of the side slope angle YA3 estimated by the side state observer is 0.15, the fusion weight of the side slope angle YA3 estimated by the side state observer is 0.35 when on the slope, the fusion weight of the side slope angle YA1 calculated based on the information of the suspension height sensor is 0.15, the fusion weight of the side slope angle YA0 is always 0.05, the fusion weight of the side slope angle YA2 estimated according to the laser radar is always 0.2, and the fusion weight of the side slope angle YA4 is always 0.25.
4. The drive-by-wire chassis highway pavement detection system according to claim 1, wherein: the driver information input module comprises a man-machine interaction interface and a data storage device, and basic driver information, basic co-passenger information and accident characteristics of a traffic accident which once occurs to the driver are input by the driver in a questionnaire form through the man-machine interaction interface; wherein the basic information of the driver comprises age, gender, identification number, driving age, daily average driving time, physical health condition, mental state and occupation; the driving age takes natural numbers of 0, 1 and 2 … … as input, and the unit is year; the daily average driving time allows the input of an integer between 0 and 24, and the unit is hour; there are three options for physical health: health, sub-health, disease state, under the option given corresponding comments for the driver to understand, "disease state" means having one of the symptoms of cold, headache, fever, "sub-health state" is painful or feels uncomfortable in other parts of the body but difficult to describe, "health state" means normal, no disease and no pain; mental states provide three options: good, bad and bad, and corresponding comments are given below the options for the driver to understand, wherein the bad means feeling drowsy and hardly focusing attention, the good means not focusing attention, and the good is input after self-evaluation by the driver; professional options offer two broad categories: professional and non-professional drivers; the accident characteristics comprise accident frequency, accident form, accident severity, accident reasons, hit-and-run vehicle types and accident time, wherein the accident form comprises rear-end collision, scraping and collision fixtures, the accident severity is divided into casualty accidents, personal injury accidents and death accidents, the accident causes comprise that the same lane runs without keeping a safe distance with a front vehicle according to regulations, the operation is improper, the lane runs with low visibility are not performed with lamplight according to the regulations or the vehicle speed is not performed according to the regulations, the lane is illegally changed, traffic signals are violated, fatigue driving is performed, illegal road driving is performed, the hit-and-run vehicle types comprise heavy trucks, medium trucks, light trucks, mini-trucks, large buses, medium buses, light buses, small buses and passenger cars, and the accident time is specifically to the time of the day of the month; the data storage device stores the above information.
5. The drive-by-wire chassis highway pavement detection system according to claim 1, wherein: the vehicle information storage module stores vehicle type parameters, tire information, braking system information, driving system information, steering system information, the service life of the vehicle, the driving mileage and accident characteristics of historical traffic accidents of the vehicle, wherein the vehicle type parameters comprise vehicle type, vehicle length, width, height, minimum turning radius, vehicle conditioning quality, maximum driving force, total vehicle mass, wheelbase, high centroid, centroid-to-rear axle distance, windward area, wheelbase, minimum ground clearance, approach angle, departure angle, maximum vehicle speed, maximum output torque, the number of wheels, the number of driving wheels and automatic driving level; the tire information indicates the tire type and the tire radius; the brake system information comprises brake type and size parameters; the driving system information comprises a power type and related size parameters; the steering system information comprises a steering system type and related dimension parameters; the types of vehicles are divided into commercial vehicles and passenger vehicles, and the commercial vehicles are divided into heavy trucks, medium trucks, light trucks, mini trucks, large buses, medium buses, light buses and small buses; the service life of the vehicle is acquired from the automobile data recorder, and the time from the first time the automobile data recorder starts to record to the current moment is taken as the service life of the vehicle; the accident characteristics of the historical traffic accident of the vehicle comprise accident frequency, accident form, damage condition and accident time, the accident form comprises rear-end collision, scraping and impact on a fixed object, the damage condition comprises a scraping part, a damaged part and a repaired or replaced part, and the accident time records year, month and day.
6. The system for detecting the highway pavement with the drive-by-wire chassis as set forth in claim 1, wherein: the environment information acquisition module acquires visibility, road surface parameters, time and meteorological information, wherein the meteorological information comprises rain, snow, fog, temperature and humidity; the historical traffic accident information storage module stores the related characteristic information of traffic accidents, including the distribution characteristic of hit-and-run vehicle types, the distribution characteristic of traffic accident time, the distribution characteristic of traffic accident visibility, the meteorological characteristic of traffic accidents, the distribution characteristic of traffic accident positions, the density characteristic of traffic accidents, the road surface characteristic of traffic accidents and the characteristic of hit-and-run drivers; the road surface characteristics of the traffic accident refer to the road surface adhesion coefficient, the road curvature and the gradient, and the characteristics of the troublemaker comprise the age, the sex, the driving age and the occupation of the troublemaker;
the vehicle management core module comprises a traffic flow distribution subunit, a safety passing grade evaluation subunit and a safety driving scheme planning subunit; the traffic flow distribution subunit determines the number and the type of released vehicles, estimates the types and the number of allowed released vehicles under the current environment and the road surface condition by utilizing a neural network, wherein the neural network comprises an input layer, a hidden layer and an output layer, and the input layer comprises 4 units: time, visibility, meteorological vector, road surface parameter, hidden layer are total two-layerly, and the first layer hidden layer comprises 4 units, and the second layer hidden layer comprises 2 units, and the output layer has 2 units: the number and the types of vehicles allowed to pass are used for training the neural network in advance by using the distribution characteristics of vehicle types causing accidents, the distribution characteristics of traffic accident time, the distribution characteristics of traffic accident positions, the visibility distribution characteristics of traffic accidents, the meteorological characteristics of traffic accidents and the density characteristics of vehicles caused by traffic accidents in the historical traffic accident information storage module, the time, visibility, weather and road surface parameter information is input into the neural network, and the neural network outputs the maximum value of the number of the vehicles allowed to pass and the vehicle types allowed to pass;
the safety passing grade evaluation subunit respectively evaluates the passing property of the vehicle on the specific road surface and the driving reliability of the driver on the specific road surface, and evaluates the safety passing grade by combining the results of the two aspects; the trafficability assessment of the vehicle on the specific road surface is calculated by establishing a vehicle dynamic model and a road model, wherein the dynamic model comprises a tire model, a driving system model, a braking system model, a vehicle body model and an air resistance model, the vehicle dynamic model is established according to vehicle type parameters, tire parameters, braking system parameters, driving system parameters and steering system parameters stored in a vehicle information storage module, and the road model comprises 4 parameters: the road surface adhesion coefficient, the curvature radius of a curve, the longitudinal gradient and the transverse gradient, and the data come from a road surface parameter detection module; the road type comprises straight roads, curved roads, ramps and combinations thereof with different road adhesion coefficients, and the trafficability, the passable vehicle speed and the transmission gear of the vehicle under various roads are respectively calculated to obtain the position of the road where the vehicle can run;
the driving reliability of a driver on a specific road surface uses a fuzzy neural network to predict the probability of the driver driving on a drivable road surface, the structure of the fuzzy neural network is a preposed neural network and the fuzzy neural network, the preposed neural network is divided into 3 sub-neural networks which are respectively a neural network 1, a neural network 2 and a neural network 3, and the structure of each sub-neural network is 3 layers: the input layer, hide layer, output layer, fuzzy neural network structure divide into 5 layers altogether: the fuzzy neural network comprises an input layer, a fuzzy rule layer, a fuzzy decision layer and an output layer, wherein the output layer of the 3 subneural networks is one part of the input layer of the fuzzy neural network; training a neural network 1 by using hit-and-run driver characteristic data, inputting basic information of a driver, basic information of passengers in the same row and accident characteristics of a traffic accident which once occurs to the driver into the neural network 1, and evaluating hit-and-run probability of the driver, wherein the accident characteristics of the traffic accident which once occurs to the driver influence the weight of each layer of the neural network, and the neural network 1 finally outputs a value between 0 and 100 percent; training a neural network 2 by using hit vehicle type distribution data, inputting vehicle type parameters of the vehicle into the neural network 2, evaluating the safety level of the vehicle, and outputting the probability of the vehicle having a traffic accident, wherein the probability value is between 0 and 100 percent; training a neural network 3 by using traffic accident road surface characteristic data, sequentially inputting road surface parameters of a vehicle travelable road surface into the neural network 3, predicting the probability of causing traffic accidents on the road surfaces by the neural network 3, wherein the probability value is between 0 and 100 percent; the input layer of the fuzzy neural network comprises 4 units: the hit-and-miss probability of the driver, the probability of the traffic accident of the vehicle, the probability of the traffic accident caused by the vehicle on the road surface where the vehicle can run, the highest vehicle speed of the lane limit is input for multiple times, the highest vehicle speed of one lane limit is input at one time, the membership function of the fuzzy layer is generated by the neural network according to the historical traffic accident data, the fuzzy rule of the fuzzy rule layer is extracted from the knowledge base by the neural network, the neural network adjusts the knowledge base in real time according to the update of the traffic accident information, the parameters of the fuzzy rule are automatically optimized on line, and the fuzzy language values are 4: { LPL, MPL, HPL, SPL }, meaning: { the safety pass level is low, the safety pass level is medium, the safety pass level is high, and the safety pass level is high }, and the output layer outputs the safety pass level with the highest degree of membership of the road surface;
the safe driving scheme planning subunit utilizes the safe passing grade of the road surface where the vehicle can drive output by the safe passing grade evaluation subunit, and preferentially connects the positions of the road surface with high safe passing grade according to the safe passing grade to form a driving path with the highest comprehensive safe passing grade; the proportion of the road surface with the lower safe passing grade to all the road surfaces of the whole running path is not more than 5%, the proportion of the road surface with the middle safe passing grade to all the road surfaces of the whole running path is less than 10%, the road surface is regarded as an effective safe path, the vehicle is allowed to pass through and enters a waiting area, otherwise, the road surface is regarded as an ineffective safe path, the vehicle is not allowed to pass through and enters the waiting area; the vehicles capable of forming the effective safe path are graded according to the comprehensive safe passing grade, the grading rule is that the road surfaces with lower safe passing grade, medium safe passing grade, higher safe passing grade and high safe passing grade are respectively graded by 25 points, 50 points, 75 points and 100 points, the sum of the scores of all the road surfaces in the driving path is accumulated, the vehicles with corresponding number ranked in the front are released according to the traffic flow allowable value, and the safe path data and the specified vehicle speed are sent to the vehicles through wireless communication.
7. The drive-by-wire chassis highway pavement detection system according to claim 1, wherein: the vehicle-mounted road surface detection submodule detects the current road surface parameters, and the passability prediction submodule refers to the safety level of the platform evaluation according to the detected road surface parameter conditions and carries out passability evaluation on the current road surface again; the vehicle-mounted road surface detection submodule comprises an information acquisition subunit, a road surface adhesion coefficient calculation subunit and a road slope calculation subunit; the system comprises an information acquisition unit, a road slope measurement unit, a road surface adhesion coefficient calculation subunit and a road slope measurement subunit, wherein the information acquisition unit respectively acquires signals of a suspension height sensor, an inertia measurement unit, a laser radar, a tire force sensor, a vehicle acceleration sensor and a wheel angular velocity sensor, and the signals are used by the road surface adhesion coefficient calculation subunit and the road slope measurement subunit;
the road adhesion coefficient calculation unit calculates the road adhesion rate according to the vertical load of the tire and the tire stress condition acquired by the tire force sensor, estimates the slip rate according to the vehicle acceleration and the wheel angular velocity, and finally obtains a road adhesion coefficient estimation value ac' according to a road adhesion rate-slip rate calibration curve;
the information acquisition subunit inputs the acceleration, the wheel torque and rotating speed signals and point cloud data generated by the laser radar into a slope degree calculation subunit, and the slope degree calculation subunit separates road longitudinal slope information from an original acceleration sensor signal by adopting a least square method so as to obtain a road longitudinal slope angle XA 1'; estimating the roll angle of the vehicle body relative to the chassis through the information of the suspension height sensor, and finally estimating a road side slope angle YA 1'; establishing an interval grid map under a Cartesian coordinate system by using point cloud data, performing plane fitting in intervals to obtain a road surface normal vector, and calculating a longitudinal slope angle XA2 'and a lateral slope angle YA 2' of the road surface by using the normal vector; meanwhile, a longitudinal slope angle XA 3' is estimated by a vehicle longitudinal state observer based on a vehicle longitudinal dynamic model in a slope degree subunit according to vehicle torque, rotating speed and acceleration; a vehicle lateral state observer based on a two-degree-of-freedom vehicle kinematic model estimates a road lateral slope angle YA 3' according to a front wheel corner, a vehicle body yaw angular velocity and a vehicle body lateral acceleration; weighting and fusing the three longitudinal gradient angles XA1 ', XA 2' and XA3 'to obtain a final longitudinal gradient angle XA'; the fusion weight of various longitudinal slope angles is fixed, the fusion weight of the slope angle XA1 ' estimated according to the signals of the acceleration sensor is 0.2, the fusion weight of the longitudinal slope angle XA3 ' estimated by a longitudinal observer is 0.3, and the fusion weight of the slope angle XA2 ' estimated according to the laser radar is always 0.5; weighting and fusing the three lateral slope angles YA1 ', YA 2' and YA3 'to obtain a final lateral slope angle YA'; when entering and leaving a side slope, the fusion weight of the side slope angle YA1 ' calculated based on the information of the suspension height sensor is 0.35, the fusion weight of the side slope angle YA3 ' estimated by the side state observer is 0.15, the fusion weight of the side slope angle YA3 ' estimated by the side state observer is 0.35 when on the slope, the fusion weight of the side slope angle calculated based on the information of the suspension height sensor is 0.15, and the fusion weight of the side slope angle YA2 estimated according to the laser radar is 0.5;
if the ratio of the road gradient and the road adhesion coefficient calculated by the vehicle-mounted road surface detection submodule to the difference value of the corresponding parameter value measured by the detection vehicle to the corresponding parameter value measured by the detection vehicle exceeds 10%, the passability prediction submodule is started to carry out passability evaluation on the current road again; the passability prediction submodule predicts the passability of a model road by using a fuzzy neural network, the structure of the fuzzy neural network prediction model is a preposed neural network and the fuzzy neural network, the preposed neural network is divided into 3 sub-neural networks which are respectively a neural network 1, a neural network 2 and a neural network 3, and the structure of each sub-neural network is 3 layers: the input layer, hide layer, output layer, fuzzy neural network structure divide into 5 layers altogether: the fuzzy neural network comprises an input layer, a fuzzy rule layer, a fuzzy decision layer and an output layer, wherein the output layer of the 3 subneural networks is one part of the input layer of the fuzzy neural network; training a neural network 1 by using hit-and-miss driver characteristic data, inputting basic information of a driver and accident characteristics of a traffic accident which the driver has happened into the neural network 1, evaluating hit-and-miss probability of the driver, and finally outputting a value between 0 and 100 percent; training a neural network 2 by using hit-and-accident vehicle type distribution data, inputting vehicle type parameters of the vehicle into the neural network 2, evaluating the safety level of the vehicle, and outputting the probability of traffic accidents of the vehicle, wherein the probability value is between 0 and 100 percent; training a neural network 3 by using traffic accident road surface characteristic data, inputting the acquired road surface parameters into the neural network 3, and predicting the probability of causing a traffic accident on a certain road surface, wherein the probability value is between 0 and 100 percent; the input layer of the fuzzy neural network comprises 5 units: the probability of causing a traffic accident of a driver, the probability of the traffic accident of a vehicle, the probability of the traffic accident caused by a road surface, the probability of the traffic accident caused by the environment and the vehicle speed, wherein a membership function of a fuzzy layer is generated by a neural network according to historical traffic accident data, fuzzy rules of a fuzzy rule layer are extracted from a knowledge base by the neural network, the neural network adjusts the knowledge base in real time according to the update of traffic accident information, the parameters of the fuzzy rules are automatically optimized on line, and 4 fuzzy language values are provided: { LPL, MPL, HPL, SPL }, meaning: { the safety passing grade is low, the safety passing grade is medium, the safety passing grade is high, and the safety passing grade is high }, and the output layer outputs the safety passing grade with the highest road surface membership degree.
8. The drive-by-wire chassis highway pavement detection system according to claim 1, wherein: the voice prompt module comprises a voice playing unit and a decision unit; in the driving process, if the passability prediction submodule is not started or the output safe passing grade is not lower than the safe passing grade predicted by the intelligent vehicle management platform, the voice playing unit plays the driving scheme of the intelligent vehicle management platform and plays prompt information of a corresponding road surface position according to vehicle positioning, wherein the prompt information comprises a reasonable vehicle speed and a driving lane; otherwise, the decision unit improves the driving scheme according to the intelligent vehicle management platform, re-specifies the driving speed, and sends the corrected driving scheme to the voice playing unit for real-time playing; when the vehicle reaches an exit of a highway or the vehicle cannot pass in the midway, the wireless communication module returns successful passing information or unsafe passing information, the platform records the safe passing times and the unsafe passing times of all roads on the vehicle running path, and the data are used for training the neural network and the fuzzy neural network of the vehicle management core module in the intelligent vehicle management platform.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110694166.8A CN113335293B (en) | 2021-06-22 | 2021-06-22 | Highway road surface detection system of drive-by-wire chassis |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110694166.8A CN113335293B (en) | 2021-06-22 | 2021-06-22 | Highway road surface detection system of drive-by-wire chassis |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113335293A CN113335293A (en) | 2021-09-03 |
CN113335293B true CN113335293B (en) | 2022-09-02 |
Family
ID=77477859
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110694166.8A Active CN113335293B (en) | 2021-06-22 | 2021-06-22 | Highway road surface detection system of drive-by-wire chassis |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113335293B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115195890B (en) * | 2022-07-19 | 2024-01-19 | 岚图汽车科技有限公司 | Vehicle running control method and related equipment |
CN115497296B (en) * | 2022-09-27 | 2023-11-17 | 吉林大学 | Intersection vehicle passing management system suitable for automatic driving automobile |
Citations (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2002056493A (en) * | 2000-08-07 | 2002-02-22 | Hitachi Ltd | Vehicle specifying device |
CN105654757A (en) * | 2016-03-14 | 2016-06-08 | 奇瑞汽车股份有限公司 | Road surface information acquiring method and system |
CN106128140A (en) * | 2016-08-11 | 2016-11-16 | 江苏大学 | Car networked environment down train service active perception system and method |
CN206171449U (en) * | 2016-10-14 | 2017-05-17 | 武汉理工大学 | Vehicle velocity early warning system based on vehicle status road surface condition |
CN107564296A (en) * | 2017-09-11 | 2018-01-09 | 安徽实运信息科技有限责任公司 | A kind of car speed early warning system based on condition of road surface |
CN108230718A (en) * | 2018-01-26 | 2018-06-29 | 山东省交通规划设计院 | A kind of traffic flow dynamic bootstrap technique based on region unit |
KR20180117776A (en) * | 2017-04-20 | 2018-10-30 | 주식회사 대솔오시스 | System for preventing wrong way vehicle on entry ramp |
CN108944740A (en) * | 2018-07-10 | 2018-12-07 | 青岛千钧投资企业(有限合伙) | Control method for vehicle and system |
CN109808615A (en) * | 2019-03-22 | 2019-05-28 | 北京经纬恒润科技有限公司 | A kind of automatic Pilot method and device |
CN109872554A (en) * | 2019-03-22 | 2019-06-11 | 山西省交通科学研究院有限公司 | A kind of expressway fog zone promotes the bus or train route early warning system of traffic safety |
CN109979219A (en) * | 2017-12-28 | 2019-07-05 | 丰田自动车株式会社 | Vehicle operation management system and vehicle operation management method |
CN109993988A (en) * | 2019-04-12 | 2019-07-09 | 吉林大学 | Variable speed-limit control system and method under a kind of highway ice and snow weather |
US10434935B1 (en) * | 2018-06-29 | 2019-10-08 | Nissan North America, Inc. | Interactive external vehicle-user communication |
CN110503823A (en) * | 2019-07-11 | 2019-11-26 | 江苏大学 | A kind of automatic driving vehicle dedicated Lanes control system and method |
CN110503824A (en) * | 2019-07-31 | 2019-11-26 | 贵州省交通规划勘察设计研究院股份有限公司 | A kind of traffic safety auxiliary driving method and system |
CN112037351A (en) * | 2020-09-30 | 2020-12-04 | 吉林大学 | Toll station ETC (electronic toll Collection) gate delayed opening control method for risk prevention and control |
WO2021096935A2 (en) * | 2019-11-11 | 2021-05-20 | Mobileye Vision Technologies Ltd. | Systems and methods for determining road safety |
CN112874502A (en) * | 2021-03-01 | 2021-06-01 | 南京航空航天大学 | Wire control chassis information physical system in intelligent traffic environment and control method |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10922969B2 (en) * | 2018-06-04 | 2021-02-16 | GM Global Technology Operations LLC | Systems, methods and apparatuses for detecting elevated freeways to prevent engaging cruise features |
JP2020154623A (en) * | 2019-03-19 | 2020-09-24 | 株式会社Subaru | Traffic control system |
-
2021
- 2021-06-22 CN CN202110694166.8A patent/CN113335293B/en active Active
Patent Citations (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2002056493A (en) * | 2000-08-07 | 2002-02-22 | Hitachi Ltd | Vehicle specifying device |
CN105654757A (en) * | 2016-03-14 | 2016-06-08 | 奇瑞汽车股份有限公司 | Road surface information acquiring method and system |
CN106128140A (en) * | 2016-08-11 | 2016-11-16 | 江苏大学 | Car networked environment down train service active perception system and method |
CN206171449U (en) * | 2016-10-14 | 2017-05-17 | 武汉理工大学 | Vehicle velocity early warning system based on vehicle status road surface condition |
KR20180117776A (en) * | 2017-04-20 | 2018-10-30 | 주식회사 대솔오시스 | System for preventing wrong way vehicle on entry ramp |
CN107564296A (en) * | 2017-09-11 | 2018-01-09 | 安徽实运信息科技有限责任公司 | A kind of car speed early warning system based on condition of road surface |
CN109979219A (en) * | 2017-12-28 | 2019-07-05 | 丰田自动车株式会社 | Vehicle operation management system and vehicle operation management method |
CN108230718A (en) * | 2018-01-26 | 2018-06-29 | 山东省交通规划设计院 | A kind of traffic flow dynamic bootstrap technique based on region unit |
US10434935B1 (en) * | 2018-06-29 | 2019-10-08 | Nissan North America, Inc. | Interactive external vehicle-user communication |
CN108944740A (en) * | 2018-07-10 | 2018-12-07 | 青岛千钧投资企业(有限合伙) | Control method for vehicle and system |
CN109872554A (en) * | 2019-03-22 | 2019-06-11 | 山西省交通科学研究院有限公司 | A kind of expressway fog zone promotes the bus or train route early warning system of traffic safety |
CN109808615A (en) * | 2019-03-22 | 2019-05-28 | 北京经纬恒润科技有限公司 | A kind of automatic Pilot method and device |
CN109993988A (en) * | 2019-04-12 | 2019-07-09 | 吉林大学 | Variable speed-limit control system and method under a kind of highway ice and snow weather |
CN110503823A (en) * | 2019-07-11 | 2019-11-26 | 江苏大学 | A kind of automatic driving vehicle dedicated Lanes control system and method |
CN110503824A (en) * | 2019-07-31 | 2019-11-26 | 贵州省交通规划勘察设计研究院股份有限公司 | A kind of traffic safety auxiliary driving method and system |
WO2021096935A2 (en) * | 2019-11-11 | 2021-05-20 | Mobileye Vision Technologies Ltd. | Systems and methods for determining road safety |
CN112037351A (en) * | 2020-09-30 | 2020-12-04 | 吉林大学 | Toll station ETC (electronic toll Collection) gate delayed opening control method for risk prevention and control |
CN112874502A (en) * | 2021-03-01 | 2021-06-01 | 南京航空航天大学 | Wire control chassis information physical system in intelligent traffic environment and control method |
Non-Patent Citations (4)
Title |
---|
Path-following control of autonomous ground vehicles using triple-step model predictive control;Yulei WANG等;《SCIENCE CHINA》;20200327;全文 * |
基于车路协同的动态车辆安全状态评价模型;田晶晶等;《哈尔滨工业大学学报》;20120430(第04期);全文 * |
基于风险状态预估的弯道防侧滑超速预警系统;张德兆等;《公路交通科技》;20091215;全文 * |
线控汽车底盘控制技术研究进展及展望;宗长富等;《中国公路学报》;20130315;全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN113335293A (en) | 2021-09-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11908328B2 (en) | Determining changes in a driving environment based on vehicle behavior | |
CN107993453B (en) | Method for calculating safe speed of curve based on vehicle-road cooperation | |
US11100801B2 (en) | Utilizing sensors to detect hazard from other vehicle while driving | |
US9604648B2 (en) | Driver performance determination based on geolocation | |
CN109885040B (en) | Vehicle driving control right distribution system in man-machine driving | |
EP3473510B1 (en) | Maneuevering autonomous vehicles | |
CN111583693B (en) | Intelligent traffic cooperative operation system for urban road and intelligent vehicle control method | |
CN110155046A (en) | Automatic emergency brake hierarchical control method and system | |
US8478499B2 (en) | System and method for vehicle speed monitoring using historical speed data | |
WO2021243710A1 (en) | Intelligent transportation system-based automatic driving method and device, and intelligent transportation system | |
CN107618512A (en) | Driving behavior safe evaluation method based on people's car environment multi-data source | |
CN113335293B (en) | Highway road surface detection system of drive-by-wire chassis | |
CN110316198A (en) | A kind of safe-guard system and operation method for highway speed-raising | |
CN107054375B (en) | Management and evaluation device and method for driving behavior safety of motorcade drivers | |
CN113723699B (en) | Method and system for warning correction handle control of expressway safety vehicle speed in severe weather | |
CN112950811B (en) | New energy automobile region operation risk assessment and early warning system integrating whole automobile safety | |
CN116206440A (en) | Intelligent high-speed traffic flow acquisition, prediction, control and informatization pushing system and method | |
CN111311947B (en) | Driving risk assessment method and device considering driver intention in internet environment | |
CN112991685A (en) | Traffic system risk assessment and early warning method considering fatigue state influence of driver | |
CN114056346B (en) | Automatic driving control method and device | |
CN115892063A (en) | Road condition monitoring and coping method for unmanned commercial vehicle | |
CN109895766B (en) | Active obstacle avoidance system of electric automobile | |
Torbic et al. | Design guidance for freeway main-line ramp terminals | |
CN111243291B (en) | Method for early warning vehicles behind traffic abnormal points on sharp-curved highway sections | |
CN116935641A (en) | Road condition risk early warning method, device and control equipment |
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 |