CN116957345B - Data processing method for unmanned system - Google Patents

Data processing method for unmanned system Download PDF

Info

Publication number
CN116957345B
CN116957345B CN202311220629.2A CN202311220629A CN116957345B CN 116957345 B CN116957345 B CN 116957345B CN 202311220629 A CN202311220629 A CN 202311220629A CN 116957345 B CN116957345 B CN 116957345B
Authority
CN
China
Prior art keywords
vehicle
unmanned
comprehensive
vehicles
distance
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
Application number
CN202311220629.2A
Other languages
Chinese (zh)
Other versions
CN116957345A (en
Inventor
杨扬
胡心怡
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Boonray Intelligent Technology Co Ltd
Original Assignee
Shanghai Boonray Intelligent Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shanghai Boonray Intelligent Technology Co Ltd filed Critical Shanghai Boonray Intelligent Technology Co Ltd
Priority to CN202311220629.2A priority Critical patent/CN116957345B/en
Publication of CN116957345A publication Critical patent/CN116957345A/en
Application granted granted Critical
Publication of CN116957345B publication Critical patent/CN116957345B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0635—Risk analysis of enterprise or organisation activities
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
    • B60W40/04—Traffic conditions
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W50/0097—Predicting future conditions
    • G—PHYSICS
    • 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
    • G08G1/16—Anti-collision systems
    • G08G1/166—Anti-collision systems for active traffic, e.g. moving vehicles, pedestrians, bikes
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W2050/0001—Details of the control system
    • B60W2050/0019—Control system elements or transfer functions
    • B60W2050/0028—Mathematical models, e.g. for simulation
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W2050/0001—Details of the control system
    • B60W2050/0043—Signal treatments, identification of variables or parameters, parameter estimation or state estimation
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/40—Dynamic objects, e.g. animals, windblown objects
    • B60W2554/404—Characteristics
    • B60W2554/4041—Position
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/40—Dynamic objects, e.g. animals, windblown objects
    • B60W2554/404—Characteristics
    • B60W2554/4042—Longitudinal speed
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/40—Dynamic objects, e.g. animals, windblown objects
    • B60W2554/404—Characteristics
    • B60W2554/4043—Lateral speed
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/80—Spatial relation or speed relative to objects
    • B60W2554/801—Lateral distance
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/80—Spatial relation or speed relative to objects
    • B60W2554/802—Longitudinal distance

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Mechanical Engineering (AREA)
  • Economics (AREA)
  • Transportation (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Automation & Control Theory (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • Mathematical Physics (AREA)
  • Operations Research (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Theoretical Computer Science (AREA)
  • Game Theory and Decision Science (AREA)
  • Quality & Reliability (AREA)
  • Educational Administration (AREA)
  • Development Economics (AREA)
  • Human Computer Interaction (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Traffic Control Systems (AREA)

Abstract

The application relates to the technical field of data processing, in particular to a data processing method used in an unmanned system, which is used for collecting the total number of road vehicles, inter-vehicle distance, running speed of each vehicle and illuminance data detected by the unmanned system vehicle and obtaining the comprehensive hidden danger index of the vehicle distance of the unmanned vehicle according to the inter-vehicle distance; obtaining a comprehensive speed safety index of the unmanned vehicle according to the running speed data of each vehicle; obtaining a comprehensive risk assessment coefficient of the unmanned system according to the vehicle distance comprehensive hidden danger index, the vehicle speed comprehensive safety index and the illumination data of the unmanned vehicle; and predicting the comprehensive risk assessment coefficient of the unmanned system at the future moment according to the comprehensive risk assessment coefficient of the unmanned system at each moment and the autoregressive moving average model. Therefore, data processing in the unmanned system is realized, the risk assessment accuracy of the unmanned system is improved, the vehicle safety of the unmanned system is improved, and the real-time performance of risk detection is higher.

Description

Data processing method for unmanned system
Technical Field
The application relates to the technical field of data processing, in particular to a data processing method used in an unmanned system.
Background
With the continuous development of the current social economy and urban process, the vehicle is used as a convenient and rapid transportation tool, and as the development direction and trend of the vehicle industry, the unmanned system can continuously collect traffic information through the technologies of vision, positioning, mapping and the like, not only can liberate hands of a driver, but also can reduce accidents caused by personal overspeed, fatigue, drunk driving and the like of the driver, improve the driving safety, and is in particular to the industry. The risk prediction is a part of the unmanned system, helps the unmanned system to better cope with emergency, improves driving safety, and can provide key information for the unmanned system to perform optimal safe driving strategy so that the unmanned system can make more intelligent decisions under different road traffic and weather conditions.
The unmanned system has the advantages that the real-time performance is high, the data scale is large, the actual road traffic condition is complex and changeable, the traditional prediction algorithm, such as a gray prediction model, is sensitive to small changes of data, and if the data change is large, the prediction result error is large; if the EMA algorithm is used to predict it, the nonlinear relationship may exist due to factors affecting the risk of the unmanned system, and the EMA algorithm essentially performs a linear weighted average, which may be difficult to capture.
In summary, the data processing method for the unmanned system is provided by the application, the comprehensive risk assessment coefficient of the unmanned system at each moment is obtained by collecting the road vehicle data detected by the unmanned system vehicle, and the comprehensive risk assessment coefficient at the future moment is predicted by combining the autoregressive moving average model, so that the vehicle safety of the unmanned system is improved.
Disclosure of Invention
In order to solve the technical problems, the application provides a data processing method for an unmanned system, so as to solve the existing problems.
The data processing method for the unmanned system adopts the following technical scheme:
one embodiment of the present application provides a data processing method for use in an unmanned system, the method comprising the steps of:
collecting the total number of road vehicles, inter-vehicle distance, running speed and illumination of each vehicle detected by the unmanned system vehicle; marking the unmanned system vehicle as an unmanned vehicle;
obtaining the position weight of each vehicle according to the position of each vehicle relative to the unmanned vehicle; obtaining potential vehicle distance factors of unmanned vehicles according to the position distances among vehicles and the position weights of the vehicles; acquiring a vehicle distance hidden danger factor of each vehicle; obtaining a comprehensive potential risk factor of the road distance according to the potential risk factors of the distance between vehicles; obtaining a vehicle distance comprehensive hidden danger index of the unmanned vehicle according to the road vehicle distance comprehensive hidden danger factor; obtaining the number of hidden vehicles of the vehicle speed according to the running speed data of each vehicle; obtaining the comprehensive speed safety index of the unmanned vehicle according to the number of the hidden vehicles; obtaining a traffic comprehensive hidden danger index of the unmanned vehicle according to the vehicle distance comprehensive hidden danger index and the vehicle speed comprehensive safety index of the unmanned vehicle; obtaining a visual risk evaluation index of the unmanned vehicle according to the illuminance; obtaining a comprehensive risk assessment coefficient of the unmanned system according to the traffic comprehensive hidden danger index and the visual risk assessment index of the unmanned vehicle;
acquiring comprehensive risk assessment coefficients of the unmanned system at each moment; and predicting the comprehensive risk assessment coefficient of the unmanned system at the future moment according to the comprehensive risk assessment coefficient of the unmanned system at each moment and the autoregressive moving average model.
Preferably, the obtaining the position weight of each vehicle according to the position of each vehicle relative to the unmanned vehicle specifically includes:
setting the distance weight of each vehicle to 2 when each vehicle is in the same lane as the unmanned vehicle; when each vehicle is in a different lane from the unmanned vehicle, the distance weight of each vehicle is set to 1.
Preferably, the obtaining the vehicle distance hidden danger factor of the unmanned vehicle according to the vehicle-to-vehicle position distance and the position weight of each vehicle specifically includes:
for a plurality of vehicles adjacent to the unmanned vehicle, obtaining the distance between each vehicle and the unmanned vehicle; calculating the product of the reciprocal of the distance weight of each vehicle and the distance; calculating the sum of all the products; and taking the reciprocal of the sum value as a vehicle distance hidden danger factor of the unmanned vehicle.
Preferably, the comprehensive potential risk factor of the road distance is obtained according to the potential risk factors of the distance between vehicles. The method specifically comprises the following steps:
calculating the product of the distance weight of each vehicle and the vehicle distance hidden danger factor; calculating the average value of the products; and taking the average value as a comprehensive hidden danger factor of the road distance.
Preferably, the obtaining the comprehensive hidden danger index of the vehicle distance of the unmanned vehicle according to the comprehensive hidden danger factor of the road vehicle distance specifically includes: and taking the sum of the normalized vehicle distance hidden danger factor of the unmanned vehicle and the road vehicle distance comprehensive hidden danger factor as the vehicle distance comprehensive hidden danger index of the unmanned vehicle.
Preferably, the number of hidden vehicles of the vehicle speed is obtained according to the running speed data of each vehicle, and the expression is:
is the firstThe number of potential vehicles at the moment;the number of potential vehicles is the initial vehicle speed;is the firstVehicle with unmanned system at momentIs a vehicle speed of (2);is the firstThe maximum speeds in all vehicles are detected at the moment,is the firstThe minimum speed in all vehicles is detected at the moment,is the firstThe total number of all vehicles detected at the moment,representing an upward rounding.
Preferably, the obtaining the comprehensive speed safety index of the unmanned vehicle according to the number of hidden vehicles of the speed specifically includes:
acquiring a plurality of vehicles close to the unmanned vehicle as close-neighbor vehicles, wherein the number of the close-neighbor vehicles is the same as the number of the vehicles with hidden speed hazards; taking the average value of the speeds of the neighboring vehicles as a hidden speed factor of the unmanned vehicle; calculating the absolute value of the difference between the speed of the unmanned vehicle and the potential vehicle speed factor; calculating the sum of all the absolute values of the differences; obtaining a calculation result of an exponential function taking a natural constant as a base number and a vehicle speed hidden danger factor opposite number as an index; and taking the ratio of the calculated result to the sum value as a comprehensive speed safety index of the unmanned vehicle.
Preferably, the traffic comprehensive hidden danger index of the unmanned vehicle specifically comprises: and taking the ratio of the comprehensive potential hazard index of the vehicle distance and the comprehensive safety index of the vehicle speed of the unmanned vehicle as the comprehensive potential hazard index of the traffic of the unmanned vehicle.
Preferably, the obtaining the visual risk evaluation index of the unmanned vehicle according to the illuminance specifically includes:
presetting an illuminance threshold; presetting a visual risk evaluation index of the unmanned vehicle with illuminance smaller than an illuminance threshold value to be 0; and for the unmanned vehicle with the illuminance larger than the illuminance threshold, calculating the difference value between the illuminance of the unmanned vehicle and the illuminance threshold, and taking the ratio of the difference value to the illuminance threshold as a visual risk evaluation index of the unmanned vehicle.
Preferably, the comprehensive risk assessment coefficient of the unmanned system is specifically: and taking the product of the traffic comprehensive hidden danger index and the visual risk evaluation index of the unmanned vehicle as a comprehensive risk evaluation coefficient of the unmanned system.
The application has at least the following beneficial effects:
according to the application, the comprehensive risk assessment coefficient of the unmanned system at the future moment is predicted by combining the road vehicle movement characteristics, so that the problem that the risk prediction of the unmanned system is inaccurate due to the large data scale of the road traffic condition is solved, the problem that the risk of the unmanned system is difficult to predict due to the nonlinear relation between the complex road traffic condition and the traffic risk is avoided, the influence of the whole information and the weather condition of the road vehicle on the road safety risk is considered, the accuracy of the unmanned system on the road safety risk detection is improved, and the real-time performance of the risk detection is higher;
the application provides a data processing method for an unmanned system, which is used for collecting road vehicle position, vehicle speed and external illuminance data detected by an unmanned system vehicle, and constructing a vehicle distance comprehensive hidden danger index according to the influence of adjacent vehicles and vehicles on the unmanned system vehicle and the relationship of vehicle distances among vehicles; constructing a vehicle speed comprehensive safety index according to the vehicle speed and the relative speed between vehicles; the comprehensive risk assessment coefficient of the unmanned system at each moment is obtained according to the comprehensive hidden danger index of the vehicle distance, the comprehensive safety index of the vehicle speed and the external illuminance, and is input into an autoregressive moving average model (ARIMA), so that the risk at the next moment is accurately and comprehensively assessed, the risk assessment accuracy of the unmanned system is improved, and the vehicle safety of the unmanned system is improved.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the application, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a data processing method for use in an unmanned system provided by the present application.
Detailed Description
In order to further describe the technical means and effects of the present application for achieving the predetermined objects, the following detailed description refers to the specific embodiments, structures, features and effects of the data processing method for use in the unmanned system according to the present application with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
The following specifically describes a specific scheme of the data processing method for the unmanned system provided by the application with reference to the accompanying drawings.
One embodiment of the application provides a data processing method for an unmanned system.
Specifically, the following data processing method for use in an unmanned system is provided, referring to fig. 1, the method includes the following steps:
step S001, collecting road vehicle total number, inter-vehicle distance, running speed of each vehicle and illumination data.
Based on the analysis, considering the factors that traffic conditions and weather conditions possibly influence the safety of the unmanned vehicle, the application adopts the steps that the vehicle-mounted laser radar is arranged on the unmanned vehicle, and the total number of vehicles in the own lane and two adjacent lanes at each moment, the relative position between each vehicle and the unmanned vehicle and the corresponding speed of each vehicle are collected by using the laser radar; an illuminance sensor is installed to obtain illuminance of external environment at each moment, and an implementer can select the specific model of the data acquisition equipment according to actual conditions.
Because of the specificity of the scene, the unmanned system vehicle needs to sense the data in the dynamic environment in real time, so that data acquisition is carried out once at each moment, a time node with a smaller time interval with the current moment is selected as a time period, the length of the time period of specific acquisition is defined by an implementer, and the method is set as followsIs common in the time periodAt various moments, i.e. atAcquisition within a time periodData of various moments, the application is provided with。
The sequence of the data acquired at all moments is recorded as a first sequence，Represent the firstAll data collected by the vehicle (host vehicle) of the unmanned system at the moment, wherein，Represent the firstThe total number of vehicles (including the own vehicle) on the road detected at the moment;represent the firstDetecting the position distance between each vehicle and the own vehicle at the moment, whereinWhileRepresent the firstTime host vehicle and detected firstA positional distance between the vehicles;represent the firstAt the moment of time, the speed of travel of the respective vehicle, whereWhileRepresent the firstTime of day detected vehicleSpeed of the vehicle;represent the firstExternal illuminance of the unmanned system vehicle (host vehicle) at the moment.
Meanwhile, as the data may have the condition of value missing and the like in the transmission process, the influence on the subsequent analysis and processing is prevented.
Step S002, obtaining the comprehensive hidden danger index of the unmanned system vehicle according to the relative position and the speed of the vehicle, and constructing the comprehensive risk assessment coefficient of the unmanned system at each moment by combining the illuminance.
During road traffic, the vehicles should pay attention to keeping a safe distance from other vehicles, the faster the speed, the lower the visibility, the larger the vehicle distance, and the smaller the risk coefficient between the vehicles. When the road section where the unmanned system vehicles run at a certain moment is provided with more vehicles and has larger traffic flow, the road is blocked, the distance between each two vehicles is shorter, at the moment, due to limited visual field and slower reaction, the vehicles run with inertia and can not be stopped directly, the emergency avoidance is difficult, the rear-end collision risk is caused, the vehicles are easy to collide, and for the unmanned system, the class has larger potential distance hazards, accidents are likely to happen with larger probability, and the personnel and the vehicles are damaged.
In actual road traffic, the hidden danger of the vehicle distance is often caused by vehicles which are close to the unmanned system vehicle or belong to the same lane with the vehicle, and the vehicles can have larger influence on the unmanned system vehicle when the vehicles change lanes, accelerate, decelerate, overtake and the like on the road traffic, the hidden danger of the vehicle distance is caused between the vehicles, and the hidden danger of the vehicle distance is caused when other vehicles are close to the vehicle in running.
Based on the analysis, the unmanned system vehicle is marked as an unmanned vehicleThe position distance between vehicles at each moment is analyzed and processed as follows to obtain the following pointTime of day dataFor example, calculate the vehicle at each momentIs a vehicle distance hidden danger factor:
in the method, in the process of the application,is the firstTime vehicleIs a vehicle distance hidden danger factor;indicating distance from vehicleAdjacent toOther vehicles, the vehicles being to the vehicleThe influence is large, and it should be noted that,the value of the embodiment can be selected by the user, and the embodiment willSet to 5;is the firstTime of dayIn the next nearest neighbor vehicleIndividual vehicle and vehicleA positional distance therebetween;is distance weight and represents and is connected with the vehicleWhether or not the vehicle is in the same lane;、respectively preset weights, wherein，、Can be set by the value implementation of the (B) in the embodimentIs set to 2,Set to 1;is thatIn the next nearest neighbor vehicleThe number of vehicles to be used in a single vehicle,is in combination with a vehicleA collection of vehicles on the same lane,representation ofIn the next nearest neighbor vehicleIndividual vehicle and vehicleAt this time belonging to the same lane,representing the vehicleWith vehiclesAt this time, the vehicle does not belong to the same lane.
For approaching vehiclesIs a vehicle of (2)In the sense that the number of the cells,as a weight, if the vehicleAnd a vehicleBelongs to the same lane, and the change of the distance between two vehicles is to the vehiclesThe potential distance hazard of (2) has larger influence, namely weightThe larger;smaller, describe the vehicleWith vehiclesThe closer the European distance is, the closer the actual running distance is, the more the two vehicles possibly have the conditions of avoiding failure and collision, the vehiclesIs a factor of hidden danger of vehicle distanceThe larger.
Thus, the vehicle at each moment is acquiredIs a factor of hidden danger of vehicle distanceHowever, when analyzing the potential vehicle distance of a vehicle, there may be a situation that the road vehicle is in a green light, the vehicles are in a start accelerating state, a few vehicles are gathered together, but the road has more idle positions, and the potential vehicle distance factor is the potential vehicle distance factor for a single vehicleAlthough large, the traffic flow on the road is small at this time, the maximum bearing capacity of the road is not reached yet, the vehicle has sufficient avoidance space, and the comprehensive potential hazard of the vehicle distance should be small at this time. In order to obtain the comprehensive hidden danger of the vehicle distance more accurately, the vehicle distance among all detected vehicles is considered to obtain the comprehensive hidden danger factor of the road vehicle distance of the road condition at the moment, and the hidden danger factor of the vehicle distance of the unmanned driving system vehicle is obtainedAnd (5) performing correction. Therefore, the position distance of each vehicle relative to other vehicles is obtained, and the vehicle distance hidden danger factors of other vehicles detected by the unmanned system vehicle at each moment are calculated through the mode. Based on the analysis, calculating the comprehensive vehicle distance hidden danger index of the unmanned system vehicle at each moment:
in the method, in the process of the application,is the firstVehicle at momentIs a vehicle distance comprehensive hidden danger index;represent the firstTime vehicleIs a vehicle distance hidden danger factor;is a weight factor, vehicleIs a factor of hidden danger of vehicle distanceCompared with comprehensive hidden danger factor of road distanceShould have a higher weight and thereforeTaking an empirical value of 0.7;represent the firstThe comprehensive hidden danger factors of the road distance at the moment,represent the firstTime of dayThe distance risk factor of the individual vehicle,for distance weight, representing vehicleWhether or not to be matched with a vehicleIs positioned on the same lane of the vehicle,for vehiclesWith vehiclesA positional distance therebetween;is the firstThe number of vehicles detected at a single moment in time,is a normalization function.
The larger the potential factor of the vehicle distance of a single vehicle is, the more vehicles in the situation are, the smaller the vehicle distance among all vehicles on the road is, the larger the traffic flow of the road is, the more likely the vehicles collide, and the comprehensive potential factor of the vehicle distance of the road isThe larger and largerAs a weight, when the vehicleWith vehiclesWhen belonging to the same lane, the larger the influence is, the larger weight should be given to the road and the vehicle distance comprehensive hidden trouble factorThe larger. For the unmanned system vehicle, the larger the vehicle distance hidden danger factor obtained from the vehicle distance of the adjacent vehicle is, the smaller the vehicle distance between the vehicle and the adjacent vehicle is, and meanwhile, the larger the road vehicle distance comprehensive hidden danger factor is, the larger the vehicle flow is, the smaller the vehicle distance between all vehicles is, and the linkage accident is more likely to happen, and the vehicle distance comprehensive hidden danger index of the unmanned system vehicle is higherThe larger.
So far, each moment has a comprehensive risk index RF of the vehicle distance of the unmanned system vehicle. However, only the direct position and the distance between vehicles are used, and whether the vehicles have great hidden danger and risk on road traffic at the moment cannot be accurately judged. Because in actual road traffic, not every moment, every vehicle is in motion state, for example, when the red light of the road is on, all vehicles are in a state of being stationary and waiting for green light, at this time, in order to improve traffic efficiency, the vehicle distance between all vehicles is smaller, the vehicle distance hidden danger index RF of the unmanned system vehicle is larger, but in reality, the vehicles are in a stationary state, and the vehicles have a high probability of being safe. Therefore, not only the position and the distance of the vehicle have influence on the hidden danger and the risk of the road of the unmanned system vehicle, but also the speed of the vehicle has influence on the hidden danger, the faster the vehicle has longer braking time, the more likely to influence more vehicles, and the faster the vehicle has the potential for hidden danger in general, meanwhile, the speed difference between the vehicles is larger, so that the speed between the vehicles is unstable, and the potential for hidden danger in speed is more likely to exist at the moment.
Based on the analysis, for the first sequenceSpeed at each time of (a)All have the following same analysis and treatment, byFor example, the following processing is performed on the data of the time:
in the method, in the process of the application,is the firstThe vehicle speed comprehensive safety index at the moment,is the firstThe potential factor of the vehicle speed at the moment,is the firstVehicle with unmanned system at momentIs a vehicle speed of (2);is the firstThe number of vehicles hidden by speed at moment, i.e. distance from the vehicleAdjacent toA vehicle;is the first vehicle of hidden dangerThe speed of the individual vehicle, i.e. distance from the vehicleAdjacent toSpeed of the vehicle;for the number of potential vehicles of the initial vehicle speed, taking a checked value of 5, namely the initial selected distance vehicleThe number of vehicles in the vicinity is 5, and it is noted that,the value of (2) can be set by the user himself, and the embodiment is not particularly limited;is the firstThe maximum speeds in all vehicles are detected at the moment,is the firstThe minimum speed in all vehicles is detected at the moment,is the firstTotal number of all vehicles detected at the moment, whereTo subtract the vehicle，Representing an upward rounding.
The larger the representation of the firstThe faster the speed of the unmanned system is, the more time is needed for complete standstill, more vehicles are more easily influenced, and the number of vehicles with hidden speed is increasedThe larger the speed of the vehicle in the number of vehicles with hidden danger of the speedThe faster the speed of the vehicleThe faster the overall speed of the vehicle on the road is, the more possible accidents are caused by the vehicle speed, the greater the hidden danger is, so the hidden danger factor of the vehicle speed isThe larger;the smaller the speed of the vehicles is, the more the speeds of the vehicles are the same, the vehicles are more stable, the more dangerous events such as rear-end collision are not easy to happen at the moment, and meanwhile, the potential factor of the vehicle speed is the sameThe smaller the vehicle speed is, the lower the possibility of accident is, the smaller the hidden trouble is, so the vehicle speed comprehensive safety index at the moment isThe larger.
So far, each moment has a comprehensive speed safety index VS of the unmanned system vehicle.
The traffic comprehensive hidden danger index F can be obtained by the vehicle distance comprehensive hidden danger index RF and the vehicle speed comprehensive safety index VS according to the firstBy taking time as an example, the comprehensive hidden danger index of traffic can be obtained：
In the method, in the process of the application,is the firstTime vehicleIs characterized by that the traffic comprehensive hidden danger index is set,is the firstTime vehicleIs a comprehensive hidden danger index of the vehicle distance,is the firstTime vehicleIs characterized by that the vehicle speed comprehensive safety index of said vehicle is,is a normalization function. Index of comprehensive hidden danger of vehicle distanceThe larger the vehicle distance is, the smaller the vehicle distance between all vehicles is, and all vehicles are opposite to each otherThe greater the potential hazard of the vehicle distance, the comprehensive safety index of the vehicle speedThe smaller the vehicle speed of the unmanned system is, the more other vehicles are affected, the speed of the affected vehicle is also higher, the relative speed between the affected vehicle and the vehicle is unstable, and at the moment, the more likely traffic accidents are caused for the unmanned system vehicle, the greater the traffic hidden danger is, and the traffic comprehensive hidden danger index isThe larger.
In road traffic, weather and meteorological conditions are also important factors influencing road traffic risks, and if the road traffic has severe weather phenomena such as haze, heavy rain, heavy fog and the like, the light is insufficient and the external illuminance is highThe smaller values of (2) may cause the sensors, equipment of the unmanned system to be affected, resulting in accuracyThe accuracy of unmanned system risk assessment is lowered, the unmanned system risk assessment is affected, the unmanned system is not only the vehicle in the road, other vehicles are not generally provided with the unmanned system at present, the visibility of drivers of other vehicles is lowered due to bad weather, hidden danger of accident occurrence is caused, traffic chain accidents are likely to occur, the vehicle is affected, and risk assessment of the unmanned system is also affected.
Based on the analysis, for the first sequenceExternal illuminance at each time of (a)All have the following same analysis and treatment, byFor example, the time data is processed as follows to obtain the comprehensive risk assessment coefficient:
in the method, in the process of the application,is the firstThe comprehensive risk assessment coefficient of the unmanned system at the moment;is the firstTime vehicleIs a traffic comprehensive hidden danger index;is the firstA visual risk assessment index for time of day;is the firstTime vehicleThe larger the illuminance, the more sufficient the light is, the higher the visibility is;for the illumination threshold, it should be noted that,can be set by the value-taking implementer, and the embodiment willSet to 100.
When (when)At this time, the external illuminance is lower than the minimum limit and the visibility is lowThe larger the value is, the lower the external illuminance is, the more severe weather phenomena such as haze, heavy rain, heavy fog and the like are likely to exist on the road, the smaller the visible range of the vehicle on the road is, the more accidents are likely to occur due to the smaller visibility, and the visual risk evaluation index is higher at the momentThe larger, whenAt the moment, the road external illuminance is higher, the weather state is good, and the visible range is widerThe influence of visibility factors on traffic accidents is extremely small, so that the visual risk evaluation index is highIs 0;the larger the vehicle distance comprehensive hidden danger index is, the smaller the vehicle speed comprehensive safety index is, the larger the visual risk evaluation index is, the smaller the vehicle distance at the moment is, the faster the vehicle speed is, the lower the visibility is, the accident is easy to occur, the road risk is larger, and the comprehensive risk evaluation coefficient of the unmanned system is largerThe larger.
To this end, each moment has an integrated risk assessment coefficient of the unmanned system。
And step S003, predicting the comprehensive risk assessment coefficient of the unmanned system at the future moment according to the comprehensive risk assessment coefficient of the unmanned system at each moment and the autoregressive moving average model.
For the comprehensive risk assessment coefficient of the unmanned system at each moment, the comprehensive risk assessment coefficient is formed into a risk sequence in time ascending orderInputting the sequence into an autoregressive moving average model (ARIMA), and evaluating the coefficient of comprehensive risk of the unmanned system at the future momentAnd carrying out more accurate prediction. According to its predicted valueRegulating and controlling the unmanned system vehicle in advance, and predicting the comprehensive risk assessment coefficient of the unmanned system at the next momentThe speed of the unmanned system vehicle is properly adjusted to ensure a safe vehicle distance with other vehicles, so that the unmanned system vehicle cannot avoid in time when the accident is prevented. The autoregressive moving average model is constructed as the prior art, and the specific construction method is not described in detail in this embodiment.
In summary, the embodiment of the application predicts the comprehensive risk assessment coefficient of the unmanned system at the future moment by combining the motion characteristics of the road vehicle, solves the problem of inaccurate risk prediction of the unmanned system caused by larger data scale of the road traffic condition, avoids the problem of difficult risk prediction of the unmanned system caused by nonlinear relation between the complex road traffic condition and traffic risk, considers the influence of the whole information and weather condition of the road vehicle on the road safety risk, improves the accuracy of the road safety risk prediction result, and has higher risk detection instantaneity;
the embodiment provides a data processing method for an unmanned system, which is used for collecting road vehicle position, vehicle speed and external illuminance data detected by the unmanned system vehicle, and constructing a vehicle distance comprehensive hidden danger index according to the influence of adjacent vehicles and vehicles in the same lane on the unmanned system vehicle and the relationship of vehicle distances between vehicles; constructing a vehicle speed comprehensive safety index according to the vehicle speed and the relative speed between vehicles; the comprehensive risk assessment coefficient of the unmanned system at each moment is obtained according to the comprehensive hidden danger index of the vehicle distance, the comprehensive safety index of the vehicle speed and the external illuminance, and is input into an ARIMA model to carry out more accurate and comprehensive assessment on the risk at the next moment, so that the risk assessment accuracy of the unmanned system is improved, and the vehicle safety of the unmanned system is improved.
It should be noted that: the sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. And the foregoing description has been directed to specific embodiments of this specification. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and the same or similar parts of each embodiment are referred to each other, and each embodiment mainly describes differences from other embodiments.
The above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; the technical solutions described in the foregoing embodiments are modified or some of the technical features are replaced equivalently, so that the essence of the corresponding technical solutions does not deviate from the scope of the technical solutions of the embodiments of the present application, and all the technical solutions are included in the protection scope of the present application.

Claims (1)

1. A data processing method for use in an unmanned system, the method comprising the steps of:
collecting the total number of road vehicles, inter-vehicle distance, running speed of each vehicle and illuminance data detected by the unmanned system vehicle; marking the unmanned system vehicle as an unmanned vehicle;
obtaining the position weight of each vehicle according to the position of each vehicle relative to the unmanned vehicle; obtaining potential vehicle distance factors of unmanned vehicles according to the position distances among vehicles and the position weights of the vehicles; acquiring a vehicle distance hidden danger factor of each vehicle; obtaining a comprehensive potential risk factor of the road distance according to the potential risk factors of the distance between vehicles; obtaining a vehicle distance comprehensive hidden danger index of the unmanned vehicle according to the road vehicle distance comprehensive hidden danger factor; obtaining the number of hidden vehicles of the vehicle speed according to the running speed data of each vehicle; obtaining the comprehensive speed safety index of the unmanned vehicle according to the number of the hidden vehicles; obtaining a traffic comprehensive hidden danger index of the unmanned vehicle according to the vehicle distance comprehensive hidden danger index and the vehicle speed comprehensive safety index of the unmanned vehicle; obtaining a visual risk evaluation index of the unmanned vehicle according to the illuminance; obtaining a comprehensive risk assessment coefficient of the unmanned system according to the traffic comprehensive hidden danger index and the visual risk assessment index of the unmanned vehicle;
acquiring comprehensive risk assessment coefficients of the unmanned system at each moment; predicting the comprehensive risk assessment coefficient of the unmanned system at the future moment according to the comprehensive risk assessment coefficient of the unmanned system at each moment and an autoregressive moving average model;
the position weight of each vehicle is obtained according to the position of each vehicle relative to the unmanned vehicle, specifically: when each vehicle is in the same lane as the unmanned vehicle, the distance weight of each vehicle is set toThe method comprises the steps of carrying out a first treatment on the surface of the When each vehicle is in a different lane from the unmanned vehicle, the distance weight of each vehicle is set to +.>； />、/>Respectively preset weights, wherein ∈>；
The method for obtaining the potential vehicle distance factor of the unmanned vehicle according to the position distance between vehicles and the position weight of each vehicle specifically comprises the following steps: for a plurality of vehicles adjacent to the unmanned vehicle, obtaining the distance between each vehicle and the unmanned vehicle; calculating the product of the reciprocal of the distance weight of each vehicle and the distance; calculating the sum of all the products; taking the reciprocal of the sum value as a vehicle distance hidden danger factor of the unmanned vehicle;
the method for obtaining the comprehensive potential risk factors of the road distance according to the potential risk factors of the distance between vehicles specifically comprises the following steps: calculating the product of the distance weight of each vehicle and the vehicle distance hidden danger factor; calculating the average value of the products; taking the average value as a comprehensive hidden danger factor of the road distance;
the method for obtaining the comprehensive hidden danger index of the vehicle distance of the unmanned vehicle according to the comprehensive hidden danger factor of the road vehicle distance comprises the following steps: taking the sum of the normalized vehicle distance hidden danger factors of the unmanned vehicles and the road vehicle distance comprehensive hidden danger factors as the vehicle distance comprehensive hidden danger index of the unmanned vehicles;
the number of hidden vehicles at the vehicle speed is obtained according to the running speed data of each vehicle, and the expression is as follows:
;
is->The number of potential vehicles at the moment; />The number of potential vehicles is the initial vehicle speed; />Is->Vehicle with unmanned system at moment ∈>Is a vehicle speed of (2); />Is->Maximum speed in all vehicles detected at the moment, +.>Is->Detecting the minimum speed in all vehicles at the moment, < >>Is->Total number of all vehicles detected at the moment, +.>Representing an upward rounding;
the method for obtaining the comprehensive speed safety index of the unmanned vehicle according to the number of the hidden vehicles of the speed specifically comprises the following steps: acquiring a plurality of vehicles close to the unmanned vehicle as close-neighbor vehicles, wherein the number of the close-neighbor vehicles is the same as the number of the vehicles with hidden speed hazards; taking the average value of the speeds of the neighboring vehicles as a hidden speed factor of the unmanned vehicle; calculating the absolute value of the difference between the speed of the unmanned vehicle and the speed of each neighboring vehicle; calculating the sum of all the absolute values of the differences; obtaining a calculation result of an exponential function taking a natural constant as a base number and a vehicle speed hidden danger factor opposite number as an index; taking the ratio of the calculated result to the sum value as a comprehensive speed safety index of the unmanned vehicle;
the traffic comprehensive hidden danger index of the unmanned vehicle comprises: taking the ratio of the comprehensive potential hazard index of the vehicle distance and the comprehensive safety index of the vehicle speed of the unmanned vehicle as the comprehensive potential hazard index of the traffic of the unmanned vehicle;
the method for obtaining the visual risk evaluation index of the unmanned vehicle according to the illuminance specifically comprises the following steps: presetting an illuminance threshold; presetting a visual risk evaluation index of the unmanned vehicle with illuminance smaller than an illuminance threshold value to be 0; for the unmanned vehicle with the illuminance larger than the illuminance threshold, calculating the difference value between the illuminance of the unmanned vehicle and the illuminance threshold, and taking the ratio of the difference value to the illuminance threshold as a visual risk evaluation index of the unmanned vehicle;
the comprehensive risk assessment coefficient of the unmanned system specifically comprises the following steps: and taking the product of the traffic comprehensive hidden danger index and the visual risk evaluation index of the unmanned vehicle as a comprehensive risk evaluation coefficient of the unmanned system.
CN202311220629.2A 2023-09-21 2023-09-21 Data processing method for unmanned system Active CN116957345B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311220629.2A CN116957345B (en) 2023-09-21 2023-09-21 Data processing method for unmanned system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311220629.2A CN116957345B (en) 2023-09-21 2023-09-21 Data processing method for unmanned system

Publications (2)

Publication Number Publication Date
CN116957345A CN116957345A (en) 2023-10-27
CN116957345B true CN116957345B (en) 2023-12-08

Family

ID=88449681

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311220629.2A Active CN116957345B (en) 2023-09-21 2023-09-21 Data processing method for unmanned system

Country Status (1)

Country Link
CN (1) CN116957345B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117208021B (en) * 2023-11-09 2024-01-19 上海伯镭智能科技有限公司 Unmanned vehicle control method for complex road conditions
CN117251818B (en) * 2023-11-17 2024-01-26 上海伯镭智能科技有限公司 Data management method for safe operation of unmanned mine car

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2018147111A (en) * 2017-03-02 2018-09-20 パナソニックＩｐマネジメント株式会社 Driving support method, driving support device utilizing the same, automatic driving control device, vehicle, program, and driving support system
CN110782125A (en) * 2019-09-23 2020-02-11 同济大学 Road safety risk degree evaluation method for automatically driving automobile
KR20200058947A (en) * 2018-11-20 2020-05-28 서울대학교산학협력단 Method and apparatus of prediction for unmanned aerial vehicle traffic management
CN112242059A (en) * 2020-09-30 2021-01-19 南京航空航天大学 Intelligent decision-making method for unmanned vehicle based on motivation and risk assessment
CN112508392A (en) * 2020-12-02 2021-03-16 云南省交通规划设计研究院有限公司 Dynamic evaluation method for traffic conflict risk of hidden danger road section of mountain area double-lane highway
CN114898042A (en) * 2022-05-20 2022-08-12 南京理工大学 Time-space urgency-based human-vehicle collision danger situation prediction method
CN115620530A (en) * 2022-09-19 2023-01-17 哈尔滨工业大学 Automatic driving takeover risk assessment model considering driving risk field and construction method thereof
WO2023116344A1 (en) * 2021-12-23 2023-06-29 清华大学 Driverless driving test method, driverless driving test system, and computer device

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2018147111A (en) * 2017-03-02 2018-09-20 パナソニックＩｐマネジメント株式会社 Driving support method, driving support device utilizing the same, automatic driving control device, vehicle, program, and driving support system
KR20200058947A (en) * 2018-11-20 2020-05-28 서울대학교산학협력단 Method and apparatus of prediction for unmanned aerial vehicle traffic management
CN110782125A (en) * 2019-09-23 2020-02-11 同济大学 Road safety risk degree evaluation method for automatically driving automobile
CN112242059A (en) * 2020-09-30 2021-01-19 南京航空航天大学 Intelligent decision-making method for unmanned vehicle based on motivation and risk assessment
CN112508392A (en) * 2020-12-02 2021-03-16 云南省交通规划设计研究院有限公司 Dynamic evaluation method for traffic conflict risk of hidden danger road section of mountain area double-lane highway
WO2023116344A1 (en) * 2021-12-23 2023-06-29 清华大学 Driverless driving test method, driverless driving test system, and computer device
CN114898042A (en) * 2022-05-20 2022-08-12 南京理工大学 Time-space urgency-based human-vehicle collision danger situation prediction method
CN115620530A (en) * 2022-09-19 2023-01-17 哈尔滨工业大学 Automatic driving takeover risk assessment model considering driving risk field and construction method thereof

Also Published As

Publication number Publication date
CN116957345A (en) 2023-10-27

Similar Documents

Publication Publication Date Title
CN116957345B (en) Data processing method for unmanned system
CN110488802B (en) Decision-making method for dynamic behaviors of automatic driving vehicle in internet environment
CN113190921B (en) Automatic evaluation method and system for intelligent automobile driving performance test
CN107742193A (en) A kind of driving Risk Forecast Method based on time-varying state transition probability Markov chain
CN107316010A (en) A kind of method for recognizing preceding vehicle tail lights and judging its state
CN103914688A (en) Urban road obstacle recognition system
CN110837800A (en) Port severe weather-oriented target detection and identification method
CN111563555A (en) Driver driving behavior analysis method and system
CN115782905B (en) Automatic driving safety degree quantification system for driving vehicle
CN115329865A (en) Driving condition identification method based on multi-core learning support vector machine
CN116186884A (en) Intelligent network-connected automobile function safety and expected function safety linkage verification method
CN116434523A (en) Vehicle active safety control method and device based on constraint degree in information perception scene
CN116631187B (en) Intelligent acquisition and analysis system for case on-site investigation information
Yang et al. Dynamic safety estimation of airport pick-up area based on video trajectory data
CN112633055A (en) General automatic driving navigation system based on pavement disease detection
CN111477002B (en) Highway confluence district traffic conflict early warning system based on danger degree is differentiateed
CN110610611B (en) Driving safety evaluation method for intelligent network-connected vehicle in mixed-driving traffic flow
CN111027365B (en) Positioning method based on human face object position analysis
CN116946089B (en) Intelligent brake auxiliary system
CN116386365B (en) Traffic path induction method and system for improving harbor road safety
Ito et al. Risk map generation system for intelligent vehicles on community roads via data-driven approach
Dang et al. Comprehensive Evaluation of Regional Road Transport Safety Service Level
CN118470977B (en) Traffic safety early warning system and traffic safety early warning method in man-machine mixed driving environment
CN117184124B (en) Pedestrian crosswalk automatic driving passing method based on responsibility sensitive safety model
CN117429419B (en) Automatic driving method applied to port and driving vehicle

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