CN114446053B - Uncontrolled intersection safety evaluation method for intelligent networked vehicle track error - Google Patents
Uncontrolled intersection safety evaluation method for intelligent networked vehicle track error Download PDFInfo
- Publication number
- CN114446053B CN114446053B CN202210072956.7A CN202210072956A CN114446053B CN 114446053 B CN114446053 B CN 114446053B CN 202210072956 A CN202210072956 A CN 202210072956A CN 114446053 B CN114446053 B CN 114446053B
- Authority
- CN
- China
- Prior art keywords
- track
- conflict
- vehicle
- intersection
- pet
- 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
Images
Classifications
-
- 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
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/07—Controlling traffic signals
- G08G1/08—Controlling traffic signals according to detected number or speed of vehicles
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a non-control intersection safety evaluation method aiming at intelligent networked vehicle track errors. The invention fully considers the decision driving mode of the intelligent internet vehicle from the acquisition and evaluation mode, considers the traffic conflict distribution condition based on Post-invasion time (PET) indexes under two conditions of a design track and an actual track aiming at the problem of unavoidable track error of the intelligent internet vehicle, provides an effective safety evaluation method of the intelligent internet uncontrolled intersection under the condition that the track error exists, and provides effective data support for market application popularization and policy making of the intelligent internet vehicle.
Description
Technical Field
The invention relates to a non-control intersection safety evaluation method aiming at intelligent networked vehicle track errors, and belongs to the field of road safety analysis.
Background
In recent years, with the proposal of related strategies for developing national intelligent networked vehicles, the large-scale application of the intelligent networked vehicles has great influence on road traffic flow, and is considered as an important way for effectively improving the traffic capacity of road facilities and reducing traffic pollution and energy consumption. Due to different vehicle behavior characteristics and formed heterogeneous traffic flow characteristics of the intelligent networked vehicles and the manually driven vehicles, road traffic safety evaluation indexes and technologies suitable for the environment of the intelligent networked vehicles are needed, and safety benefits of the intelligent networked vehicles on road traffic are effectively evaluated.
The development of the intelligent networking technology brings a brand-new opportunity and challenge to the intersection management. Under the complete intelligent networking environment, when intelligent networking vehicle permeability reached 100%, intelligent networking vehicle was dodged with peripheral vehicle safety and is passed in coordination through car communication (V2V) at the intersection of no control or was carried out the coordinated dispatch vehicle by the roadside control unit through vehicle road communication (V2I) and pass through in coordination, avoided vehicle conflict and accident, space gap resource when the while make full use of intersection promotes the current efficiency of intersection and vehicle fuel economy.
In the intelligent networked vehicle cooperative control, vehicle safety is contained in the underlying control logic, namely, vehicle collision is avoided by controlling the real-time speed and position of the vehicle. When a control strategy and a vehicle driving track are established, the surrounding vehicle information respectively comes from the driving state and intention of the surrounding vehicle obtained by vehicle-to-vehicle communication and vehicle-to-road communication, and the state of the surrounding vehicle detected by a vehicle sensor and the prediction of the driving intention of the surrounding vehicle. Theoretically, the speed and the position track of the intelligent networked vehicle at the intersection for executing the optimal design can avoid collision. In practice, deviations of the actual trajectory from the designed trajectory are inevitable due to uncertainties in the trajectory of the vehicle's position (e.g., different turning radii and turning patterns in the turning path) and uncertainties in the effects of the control algorithm (e.g., speed control errors). In order to verify the influence of the intelligent networking vehicle on road safety, the safety level of the intersection needs to be effectively evaluated aiming at the vehicle track error, and the result has very important significance for the popularization of the intelligent networking technology and the acceptance of social public.
In the aspect of the evaluation of the safety of vehicle Collision at an intersection, commonly used traffic Collision indexes include Time-To-Collision (TTC) or Post-intrusion Time (PET), and the like. From the perspective of PET, the smaller the PET value is, the closer the two vehicles are at the data acquisition time is, and the higher the possibility of collision is; from the perspective of TTC, a smaller TTC value indicates that the two vehicles are closer at the data acquisition time and the rear vehicle speed is higher than that of the front vehicle, and the possibility of collision is higher. Compared with a human-driven vehicle, the intelligent networked vehicle has communication and calculation capabilities and higher controllability, so that the intelligent networked vehicle can actively reduce the inter-vehicle distance and controllably accelerate according to the track optimization design, and the TTC or PET value can be reduced at the moment, but the TTC or PET value does not necessarily represent the reduction of safety. Therefore, a safety evaluation method for the intelligent networked vehicle at the uncontrolled intersection needs to be developed.
Disclosure of Invention
The invention aims to provide an intelligent network connection mixed traffic flow signal intersection vehicle arrival prediction correction method to solve the problems in the prior art.
In order to achieve the purpose, the invention provides the following technical scheme:
a traffic conflict technology is adopted to analyze a target track and an actual track of a vehicle at an uncontrolled intersection, and later invasion time (PET) is taken as a quantitative index of conflict severity and conflict classification is carried out, so that the intersection safety evaluation aiming at the track error of the intelligent internet vehicle is carried out, and the method is characterized in that:
step A, defining the conflict type of a target intersection region, determining a corresponding conflict region and defining PET;
b, determining an intelligent internet vehicle target driving path of the uncontrolled intersection based on the actual intersection channelized design and the geometric parameters, and determining a vehicle design speed track based on a vehicle cooperative control algorithm;
step C, identifying and collecting the actual tracks of the intelligent networked vehicles from the video of the area of the uncontrolled intersection, wherein the actual tracks comprise geometric paths and speed tracks;
step D, collecting and counting PET values of the conflict data of the target intersection region;
and E, grading the severity of the conflict, and evaluating the influence of the track error of the intelligent networked vehicles on the running safety of the intersection.
Further, the method for defining the conflict type and the PET of the target intersection region in the step A comprises the following steps:
step A1: defining the following conflict types according to the intersection form and canalization design:
shunting conflict: vehicles which are driven into the intersection by the same entrance lane and have different driving directions collide with each other due to the speed change or the steering of the front vehicle;
confluent collision: collisions that occur when vehicles in different driving directions drive into the same exit lane;
right angle collision: conflicts between vehicles traveling vertically straight and between straight and counter-turning left-turning vehicles;
collision in rear-end collision: collision between the front and rear vehicles in the same travel track direction.
Step A2: definition of PET:
PET is the difference in time between the intrusion line after the rear car head reaches the collision zone and the intrusion line after the front car tail leaves the collision zone. The intelligent networked vehicle track path is represented by a rectangular model, namely the vehicle path is a rectangular or annular belt which has the same width as the vehicle and the center line of which is coincident with the particle track of the vehicle. The collision area refers to an overlapping area of the designed trajectory path or the actual trajectory path. The rear intrusion line refers to a virtual straight line which is parallel to the tail of the front vehicle, perpendicular to the central line of the track path of the front vehicle and passes through the vertex of the overlapping area, and a virtual straight line which is parallel to the head of the rear vehicle, perpendicular to the central line of the track path of the rear vehicle and passes through the vertex of the overlapping area.
Further, the step D of collecting and counting the PET value of the conflict data of the target intersection region comprises the following steps:
step D1: the PET values generated by the design trajectory may be calculated from the PET definition using the design velocity trajectory and the path.
Step D2: for an actual track, when extracting PET values of two vehicles driving in a collision direction and successively passing through a collision area, processing a running video of an intersection by using video recognition software, determining an approximate position and a collision type of the collision area according to the collision type determined in the step A1, and capturing a frame of an intrusion line after a tail of a front vehicle leaves and a frame of an intrusion line after a head of a rear vehicle leaves according to a potential conflict point and a collision type of a target intersection, wherein if the frames are shown in fig. 1, PET = t 2 –t 1 。
Further, the step E of grading the severity of the conflict and determining the safety of the intersection without control includes the following steps:
step E1: drawing a frequency and cumulative percentage distribution situation graph according to the PET value obtained by calculating the design track, and determining the following threshold values:
maximum critical value of PET: if the threshold value is larger than the threshold value, the event is regarded as a non-conflict event, and no statistical analysis is carried out;
critical point of severe conflict: the PET value at the first inflection point of the percentage curve is accumulated and a conflict below this value is defined as a severe conflict. The critical point value generally depends on the constraint condition of the vehicle distance when the intelligent networked vehicle track is designed, the design track generally should not have serious conflict, but the serious conflict may also occur due to the limitation of calculation optimization accuracy.
General collision critical point: the remaining data after removing the severe conflict is divided into two layers on average, the corresponding critical point is used as the general conflict and potential conflict PET critical value, below which is the general conflict, and above which is the potential conflict.
And E2: and respectively counting various collision frequencies in the designed track and the actual track according to the threshold values.
Step E3: and respectively comparing various collision frequencies of the designed track and the actual track.
When serious conflict exists in the design track, calculating the proportion R of the number of the serious conflict under the actual track to the number of the serious conflict under the design track s When R is s >When the vehicle speed is 1.5 hours, the track error of the intelligent networked vehicle is considered to have great negative influence on the running safety of the intersection; when no serious conflict exists in the designed track, when the number of serious conflicts under the actual track accounts for more than 1% of the total conflict events, the track error of the intelligent networked vehicle is considered to have great negative influence on the operation safety of the intersection.
Calculating the proportion R of the general conflict number under the actual track to the general conflict under the designed track n When R is n >1.1, the track error of the intelligent networked vehicles is considered to have great negative influence on the running safety of the intersection, the running of the intersection is unsafe under the current track design and control method, and the geometric design optimization of the vehicle running path is required to be further carried out.
And if the two judgment conditions are satisfied, the situation that the track error of the intelligent networked vehicle has a great negative influence on the operation safety of the intersection can be judged.
Compared with the prior art, the uncontrolled intersection safety evaluation method aiming at the track error of the intelligent networked vehicle adopts the technical scheme that the data acquisition and evaluation mode fully considers the decision-making driving mode of the intelligent networked vehicle, and provides an effective uncontrolled intersection safety evaluation method under the intelligent networked environment aiming at the problem of inevitable track error of the intelligent networked vehicle, so that effective data support is provided for market application popularization and policy making of the intelligent networked vehicle.
Drawings
FIG. 1 is a PET-defined acquisition diagram of the actual trajectory of a vehicle according to the present disclosure, wherein (a) is t 1 Time (b) is t 2 Time of day;
FIG. 2 is a schematic illustration of an uncontrolled intersection geometric canalization design and conflict distribution in accordance with an exemplary embodiment of the present invention;
FIG. 3 is a traffic conflict PET distribution for an exemplary embodiment of the present invention;
fig. 4 is a flow chart of an exemplary embodiment of the present invention.
Detailed Description
In order to better understand the technical content of the present invention, specific embodiments are described below with reference to the accompanying drawings.
Aspects of the invention are described herein with reference to the accompanying drawings, in which a number of illustrative embodiments are shown. Embodiments of the invention are not limited to those shown in the drawings. It is to be understood that the invention is capable of implementation in any of the numerous concepts and embodiments described above and described in detail below, since the disclosed concepts and embodiments are not limited to any particular implementation. Additionally, some aspects of the present disclosure may be used alone, or in any suitable combination with other aspects of the present disclosure.
The method for evaluating the safety of the uncontrolled intersection aiming at the track error of the intelligent networked vehicle, as shown in fig. 4, comprises the following steps:
step a, the conflict type and the approximate position distribution of the conflict area of the uncontrolled intersection of the embodiment are shown in fig. 2.
B, determining a vehicle driving path based on the actual intersection channelized design and the geometric parameters; according to the designed path and the condition that the vehicle enters the intersection influence area, a central cooperative control method is adopted to establish a mixed integer programming problem and solve the problem to obtain the vehicle passing speed and the passing time; and on the basis, the optimal control method and the intelligent driver model are combined to solve to obtain the real-time speed track of the vehicle.
Step C, identifying and collecting the actual tracks of the intelligent networked vehicles from the video of the area of the uncontrolled intersection, wherein the actual tracks comprise geometric paths and speed tracks;
and D, collecting and counting PET values of the regional conflict data of the target intersection. Calculating the time of the front vehicle leaving the conflict area and the time of the rear vehicle arriving at the conflict area according to the path length of the designed track and the designed speed, thereby obtaining the PET T (ii) a Capturing a frame of the intrusion line after the tail part of the front vehicle leaves and a frame of the intrusion line after the head part of the rear vehicle leaves according to the intersection video, and obtaining the PET (positron emission tomography) as shown in figure 1 A ＝t 2 –t 1 。
And E, the distribution of the traffic conflict PET under the designed track is shown in figure 3. Taking 5 seconds as the maximum critical value of PET; the minimum PET in the constraint condition in the track design is 0.8 second, and the minimum PET is basically consistent with the PET value corresponding to the first inflection point of the cumulative percentage curve, so the critical point of serious conflict is 0.8 second; according to the statistical data, the residual data after removing the serious conflict is averagely divided into two layers, the corresponding critical point is 1.2 seconds, and the value is the PET critical value of the general conflict and the potential conflict.
According to the above division, the key conflict parameter conditions under the design trajectory and the actual trajectory are shown in table 1.
TABLE 1 Key conflict parameter statistics
As shown in Table 1, although the general conflict index R n Does not reach 1.1, but has a severe conflict index R s If the track error exceeds 1.5, the track error of the intelligent internet vehicle has great negative influence on the running safety of the intersection, and the intersection runs insecurely under the current track design and control method, so that the geometric design optimization of a vehicle track path is required.
The embodiment of the invention provides a non-control intersection safety evaluation device aiming at intelligent networked vehicle track errors, which comprises: a processor and a memory, the number of which may be one or more.
The memory is used as a computer readable storage medium and can be used for storing software programs, computer executable programs and modules, such as program instructions/modules corresponding to the method for evaluating the safety of the uncontrolled intersection for the trajectory error of the intelligent networked vehicle according to any embodiment of the application. Further, the memory may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, the memory may further include memory located remotely from the processor 60, which may be connected to the device over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The processor executes various functional applications and data processing of the device by running software programs, instructions and modules stored in the memory, namely, the method for evaluating the safety of the uncontrolled intersection aiming at the intelligent networked vehicle track error is realized.
The embodiment of the invention also provides a computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the method for evaluating the safety of the uncontrolled intersection aiming at the intelligent networked vehicle track error is realized.
Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a Read-Only Memory (ROM), an erasable Programmable Read-Only Memory (EPROM or flash Memory), an optical fiber, a portable Compact Disc Read-Only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, smalltalk, C + +, or the like, as well as conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
Although the present invention has been described with reference to the preferred embodiments, it is not intended to be limited thereto. Those skilled in the art can make various changes and modifications without departing from the spirit and scope of the invention. Therefore, the protection scope of the present invention should be defined by the appended claims.
Claims (3)
1. A non-control intersection safety evaluation method for intelligent networked vehicle track errors is characterized by comprising the following steps:
step A, defining conflict types of a target intersection region, determining a corresponding conflict region and defining post-invasion time PET;
b, determining a target running path of the intelligent internet vehicle at the target intersection based on the actual intersection channelized design and the geometric parameters, and determining a vehicle design speed track based on a vehicle cooperative control algorithm;
step C, identifying and collecting an actual track of the intelligent internet vehicle from the video of the target intersection region, wherein the actual track comprises a geometric path and a speed track;
step D, collecting and counting PET of the regional conflict data of the target intersection;
e, grading the severity of the conflict, and evaluating the influence of the track error of the intelligent networked vehicle on the operation safety of the target intersection;
the step A comprises the following steps:
step A1: according to the form and canalization design of the target intersection, defining the following conflict types:
shunting conflict: vehicles which are driven into the same entrance lane and have different driving directions enter the target intersection, and conflict is caused by the speed change or steering of the front vehicle;
confluent collision: collisions that occur when vehicles in different driving directions drive into the same exit lane;
right angle collision: conflicts between vehicles traveling vertically straight and between straight and counter-turning left-turning vehicles;
collision in rear-end collision: conflict between front and rear vehicles in the same driving track direction;
step A2: the conflict area refers to an overlapping area of a designed track path or an actual track path;
step A3: PET is the time difference between the time when the head of the rear vehicle enters the conflict region and the time when the tail of the front vehicle leaves the conflict region; the rear intrusion line refers to a virtual straight line which is parallel to the tail of the front vehicle, perpendicular to the central line of the track path of the front vehicle and passes through the vertex of the overlapping area, and a virtual straight line which is parallel to the head of the rear vehicle, perpendicular to the central line of the track path of the rear vehicle and passes through the vertex of the overlapping area;
the step E comprises the following steps:
step E1: according to the PET calculated by the design track, drawing the collision event frequency with different PET values and a cumulative percentage distribution situation graph of the frequency, and determining the following threshold values:
maximum critical value of PET: if the threshold value is larger than the threshold value, the event is determined as a non-conflict event, and no statistical analysis is carried out;
critical point of severe collision: accumulating the first inflection value of the percentage curve, and defining the conflict below the inflection value as serious conflict;
general collision critical point: the residual data after removing the serious conflict is averagely divided into two layers, the corresponding demarcation point is used as a PET critical value of general conflict and potential conflict, general conflict is determined when the corresponding demarcation point is lower than the PET critical value, and potential conflict is determined when the corresponding demarcation point is higher than the PET critical value;
step E2: respectively counting various collision frequencies in the designed track and the actual track according to the threshold;
step E3: comparing various collision frequencies of the design track and the actual track respectively:
when there is a serious conflict in the design trajectory, the meterCalculating the proportion R of the number of serious conflicts under the actual track to the number of serious conflicts under the designed track s When R is s >When the vehicle speed is 1.5 hours, the track error of the intelligent networked vehicle is considered to have great negative influence on the running safety of the intersection; when no serious conflict exists in the designed track, when the number of serious conflicts under the actual track accounts for more than 1% of the total conflict events, the track error of the intelligent internet vehicle is considered to have great negative influence on the running safety of the intersection;
calculating the proportion R of the general conflict number under the actual track to the general conflict number under the designed track n When R is n >1.1, considering that the track error of the intelligent network vehicle has great negative influence on the traffic safety;
when the track error of the intelligent networked vehicle has great negative influence on the operation safety of the intersection, the intersection is considered to be unsafe to operate under the current track design and control method, and the geometric design optimization of the vehicle running path is required to be further carried out.
2. An uncontrolled intersection safety evaluation device for intelligent networked vehicle trajectory errors, the device comprising: a memory and one or more processors; a memory for storing one or more programs; when executed by the one or more processors, cause the one or more processors to implement the method of claim 1 for uncontrolled intersection safety assessment of intelligent networked vehicle trajectory error.
3. A computer-readable storage medium having stored thereon a computer program, wherein the program, when executed by a processor, implements the method for uncontrolled intersection safety assessment for intelligent networked vehicle trajectory error of claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210072956.7A CN114446053B (en) | 2022-01-21 | 2022-01-21 | Uncontrolled intersection safety evaluation method for intelligent networked vehicle track error |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210072956.7A CN114446053B (en) | 2022-01-21 | 2022-01-21 | Uncontrolled intersection safety evaluation method for intelligent networked vehicle track error |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114446053A CN114446053A (en) | 2022-05-06 |
| CN114446053B true CN114446053B (en) | 2023-02-14 |
Family
ID=81366974
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210072956.7A Active CN114446053B (en) | 2022-01-21 | 2022-01-21 | Uncontrolled intersection safety evaluation method for intelligent networked vehicle track error |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114446053B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102778802A (en) * | 2011-05-10 | 2012-11-14 | 立志凯株式会社 | Light quantity adjustment apparatus, lens unit and optical apparatus provided with the same |
| CN107085428A (en) * | 2017-05-18 | 2017-08-22 | 广州视源电子科技股份有限公司 | Intelligent moving method, device, robot and storage medium |
| CN107564336A (en) * | 2017-09-11 | 2018-01-09 | 哈尔滨工业大学 | A kind of signalized intersections left-hand rotation conflict early warning system and method for early warning |
| CN109859478A (en) * | 2019-04-03 | 2019-06-07 | 苏州易通交通科技有限公司 | Signalized crossing Driving Decision-making event recognition method based on track of vehicle |
| CN113689692A (en) * | 2021-07-14 | 2021-11-23 | 东南大学 | Intelligent network connection mixed traffic flow signal intersection vehicle arrival prediction correction method |
-
2022
- 2022-01-21 CN CN202210072956.7A patent/CN114446053B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102778802A (en) * | 2011-05-10 | 2012-11-14 | 立志凯株式会社 | Light quantity adjustment apparatus, lens unit and optical apparatus provided with the same |
| CN107085428A (en) * | 2017-05-18 | 2017-08-22 | 广州视源电子科技股份有限公司 | Intelligent moving method, device, robot and storage medium |
| CN107564336A (en) * | 2017-09-11 | 2018-01-09 | 哈尔滨工业大学 | A kind of signalized intersections left-hand rotation conflict early warning system and method for early warning |
| CN109859478A (en) * | 2019-04-03 | 2019-06-07 | 苏州易通交通科技有限公司 | Signalized crossing Driving Decision-making event recognition method based on track of vehicle |
| CN113689692A (en) * | 2021-07-14 | 2021-11-23 | 东南大学 | Intelligent network connection mixed traffic flow signal intersection vehicle arrival prediction correction method |
Non-Patent Citations (1)
| Title |
|---|
| 基于轨迹数据的高速公路分流区冲突替代指标研究;姜雪娇等;《交通信息与安全》;20160428(第02期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114446053A (en) | 2022-05-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Murphey et al. | Driver's style classification using jerk analysis | |
| CN110027553B (en) | Anti-collision control method based on deep reinforcement learning | |
| CN109598950B (en) | Ramp cooperative convergence control method and system for intelligent networked vehicles | |
| CN114664078B (en) | Road confluence area cooperation convergence control method based on automatic driving vehicle queue | |
| CN102568206B (en) | Video monitoring-based method for detecting cars parking against regulations | |
| Weng et al. | Rear‐end crash potential estimation in the work zone merging areas | |
| CN110077398B (en) | Risk handling method for intelligent driving | |
| CN110843789A (en) | Vehicle lane change intention prediction method based on time sequence convolution network | |
| CN108986488A (en) | Ring road imports collaboration track and determines method and apparatus under a kind of truck traffic environment | |
| Qi et al. | Connected cooperative ecodriving system considering human driver error | |
| CN108694841A (en) | A kind of intelligent vehicle passage crossroads traffic light method based on V2X technologies | |
| CN113370996A (en) | Automatic driving lane changing and following decision method and system and automatic driving vehicle | |
| CN110619340B (en) | Method for generating lane change rule of automatic driving automobile | |
| Zhou et al. | Long-tail prediction uncertainty aware trajectory planning for self-driving vehicles | |
| Choi et al. | Framework for connected and automated bus rapid transit with sectionalized speed guidance based on deep reinforcement learning: Field test in Sejong city | |
| CN114446053B (en) | Uncontrolled intersection safety evaluation method for intelligent networked vehicle track error | |
| CN116740944B (en) | Driving safety early warning method, device and storage medium in road tunnel | |
| CN112068542B (en) | Automatic driving behavior planning method based on fuzzy control | |
| Yu et al. | Online legal driving behavior monitoring for self-driving vehicles | |
| Ding et al. | Research on safety lane change warning method based on potential angle collision point | |
| KR20160071164A (en) | Apparatus and Method for Drive Controlling of Vehicle Considering Cut in | |
| Tian et al. | Examining the safety, mobility and environmental sustainability co-benefits and tradeoffs of intelligent transportation systems | |
| CN116777062A (en) | Extreme difficult-case-oriented self-adaptive fusion learning automatic driving safety decision-making method | |
| CN113353087A (en) | Driving assistance method, device and system | |
| CN117456737B (en) | Intelligent traffic big data processing method and system based on 3D visual intelligence |
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 |