CN113450570A - Autonomous intersection management system and method based on signal lamp-free intersection - Google Patents

Autonomous intersection management system and method based on signal lamp-free intersection Download PDF

Info

Publication number
CN113450570A
CN113450570A CN202110764024.4A CN202110764024A CN113450570A CN 113450570 A CN113450570 A CN 113450570A CN 202110764024 A CN202110764024 A CN 202110764024A CN 113450570 A CN113450570 A CN 113450570A
Authority
CN
China
Prior art keywords
vehicle
vehicles
driving
stage
intersection
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202110764024.4A
Other languages
Chinese (zh)
Other versions
CN113450570B (en
Inventor
李柏
钟翔
方勇
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.)
Hunan University
Original Assignee
Hunan University
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 Hunan University filed Critical Hunan University
Priority to CN202110764024.4A priority Critical patent/CN113450570B/en
Publication of CN113450570A publication Critical patent/CN113450570A/en
Application granted granted Critical
Publication of CN113450570B publication Critical patent/CN113450570B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • 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
    • G08G1/015—Detecting movement of traffic to be counted or controlled with provision for distinguishing between two or more types of vehicles, e.g. between motor-cars and cycles
    • 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
    • G08G1/052—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed
    • 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
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/16—Anti-collision systems

Abstract

The application provides an autonomous intersection management system and method based on a signal-lamp-free intersection, wherein sensing units arranged at roads in all directions of the signal-lamp-free intersection are utilized to form a driving takeover area, vehicles running into the driving takeover area are managed, and the driving control authority of the vehicles is completely taken over so as to plan driving tracks for the controlled vehicles, and then the driving tracks are issued to the controlled vehicles to be executed in a closed-loop tracking mode. The central processing equipment divides vehicles driving into a driving takeover area in batches, controls all vehicles in the same batch to keep moving ahead in a current lane in a straight line in a first stage, cooperatively drives through a signal lamp-free intersection in a second stage, and keeps running in a straight line at a constant speed in a third stage. By dividing the vehicles into batches so as to control the vehicles in each batch to cooperatively operate, the cooperative action of the vehicles in the same batch can be considered, and both the calculation speed and the traffic efficiency can be considered.

Description

Autonomous intersection management system and method based on signal lamp-free intersection
Technical Field
The application relates to the technical field of intelligent driving and control, in particular to an autonomous intersection management system and method based on a signal lamp-free intersection.
Background
For Autonomous Intersection Management (AIM), academic circles concern the software part of the management system, namely how to design a high-quality algorithm, so that vehicles about to enter an intersection can be distributed with high-quality driving tracks, even the vehicles can cooperate with each other, and the vehicles can quickly pass through the intersection at the minimum blocking and delay cost.
Existing AIM mainstream methods fall into two categories: subscription-based AIM methods and planning-based AIM methods.
The core idea of the former (an AIM method based on reservation) is to assign priorities to vehicles about to enter a crossing, assign higher priorities to vehicles arriving earlier according to a first-come-first-serve strategy, plan driving tracks one by one, and vehicles with low priority must avoid the tracks of vehicles with high priority (i.e., the vehicles with high priority are regarded as moving obstacles). The reservation-based approach is fast to compute because the multi-vehicle collaborative trajectory planning task is broken down into planning trajectories for only a single vehicle at a time. However, the solution quality of the method is low because the low-priority vehicle can only avoid the established track of the high-priority vehicle, the low-priority vehicle and the high-priority vehicle cannot cooperate with each other, only the low-priority vehicle gives way and caters to the established driving behavior of the high-priority vehicle, and the high-priority vehicle does not consider the low-priority vehicle at all when planning the track of the high-priority vehicle, so that the cooperation among multiple vehicles means weaker, the synergistic effect is poor, and finally the quality of the AIM scheme is low.
In the latter (AIM method based on planning), the coordinated motion tracks of all vehicles are simultaneously obtained at one time by constructing a centralized optimal control problem. The solving quality of the method is high, and the multiple vehicle tracks are calculated simultaneously, so that the method can realize the cooperative meaning among the multiple vehicle tracks. Meanwhile, the dimensionality of the centralized optimal control problem is high, so that the problem is very difficult to solve, thousands of seconds are generally needed for one calculation, the calculation task can be completed by means of a supercomputer, and practical popularization is difficult.
In summary, the AIM method based on reservation has a fast solving speed but poor solving quality, while the AIM method based on planning has a slow solving speed but high quality, so the effect of the current AIM method is unsatisfactory.
Disclosure of Invention
The embodiment of the application AIMs to provide an autonomous intersection management system and method based on a signal lamp-free intersection so as to ensure the running efficiency of an AIM method and ensure the management effect.
In order to achieve the above object, embodiments of the present application are implemented as follows:
in a first aspect, an embodiment of the present application provides an autonomous intersection management system based on a signal-lamp-free intersection, including: the system comprises a plurality of sensing units, a plurality of sensors and a controller, wherein each sensing unit is respectively arranged at the road of each direction of a no-signal lamp intersection according to a set distance range and is used for sensing vehicles which are driven to or leave the no-signal lamp intersection through the sensing unit, an area formed by taking the no-signal lamp intersection as a center and the sensing units of each direction as boundaries is a driving takeover area, cooperation is arranged between the sensing unit of each road direction and the no-signal lamp intersection, and an area formed by taking the no-signal lamp intersection as a center boundary line and the cooperation boundary lines of each direction as boundaries is a vehicle cooperation area; a central processing device which is respectively connected with each sensing unit in a communication mode and is used for taking over the driving control authority of the vehicle entering the driving takeover area and returning the driving control authority of the vehicle exiting the driving takeover area, wherein the vehicle taking over the driving control authority is a controlled vehicle, the vehicle returning the driving control authority is an automatic control vehicle, the process that the vehicle enters the driving takeover area and exits the driving takeover area comprises a first stage, a second stage and a third stage, the first stage represents that the vehicle travels to a cooperative boundary line from the sensing unit of the direction of the vehicle, the second stage represents that the vehicle travels to a cooperative boundary line from the cooperative boundary line of the direction of the vehicle after passing through the no-signal lamp intersection, the third stage represents that the vehicle travels to the sensing unit of the direction of the vehicle from the cooperative boundary line of the direction of the vehicle to the no-signal lamp intersection to indicate the direction of the road where the vehicle does not pass through the no-signal lamp intersection, the going direction represents the direction of a road where the vehicle passes through the non-signal lamp intersection; the central processing device is further configured to divide the vehicles driving into the driving connection area in batches, control each vehicle of the same batch to keep moving ahead in a straight line in the current lane in the first stage, cooperatively drive through the traffic signal-free intersection in the second stage, and keep moving in a straight line at a constant speed in the third stage, wherein a plurality of vehicles of the same batch in the same road direction keep fixed relative positions in the first stage.
In the embodiment of the application, the autonomous intersection management system based on the signal lamp-free intersection uses the sensing units arranged at the roads in all directions (for example, the intersection comprises four directions, and the intersection comprises three directions) of the signal lamp-free intersection to form a driving connection area, manages the vehicles (intelligent internet automobiles) driven into the driving connection area, completely takes over the driving control authority of the vehicles so as to plan the driving tracks for the controlled vehicles, and then sends the driving tracks to the controlled vehicles to perform closed-loop tracking. Cooperative boundary lines are arranged between the sensing units in each road direction and the signal-free intersections, and a vehicle cooperative area is formed by taking the signal-free intersections as centers and the cooperative boundary lines in all directions as boundaries. Taking the following as the basis for planning the driving track: the process from the vehicle entering the driving takeover area to the vehicle exiting the driving takeover area comprises a first stage (the cooperative boundary line of the direction from the vehicle-approaching sensing unit to the vehicle-approaching direction), a second stage (the cooperative boundary line of the direction from the vehicle-approaching direction is driven to the vehicle-approaching cooperative boundary line after the vehicle-approaching cooperative boundary line passes through the no-signal lamp crossing), and a third stage (the vehicle is driven from the vehicle-approaching cooperative boundary line to the vehicle-approaching sensing unit). Therefore, the central processing equipment divides vehicles driving into the driving takeover area in batches, controls each vehicle of the same batch to keep moving ahead in a current lane in a straight line in the first stage, cooperatively drives through a signal lamp-free intersection in the second stage, and keeps running in a straight line at a constant speed in the third stage. The vehicles are divided into batches, so that the vehicles in each batch are controlled to run cooperatively, the cooperative action of the vehicles in the same batch can be considered, and the traffic efficiency is improved. Moreover, the batch division of the vehicles can be set artificially (the number of the vehicles in the same batch is determined), the balance between the solving quality and the solving speed can be well considered, and the calculation speed (time consumption) and the traffic efficiency are considered. The vehicles keep moving ahead in a straight line in the current lane in the first stage, the vehicles in the same batch and positioned in the same road direction keep fixed relative positions in the first stage, so that the relative motion trend among the vehicles in the same batch and in the same road direction can be avoided, collision can be avoided, and the vehicles in the same batch keep moving in a straight line at a constant speed (running at a set speed) in the third stage, and collision can also be avoided.
With reference to the first aspect, in a first possible implementation manner of the first aspect, the central processing device is further configured to: receiving first perception information sent by any one perception unit, wherein the first perception information is generated when the perception unit perceives that a vehicle enters the driving takeover area, and the first perception information comprises a unique number of the perceived vehicle; according to the first sensing information, taking over the driving control authority of the vehicle corresponding to the unique number; when the number of the controlled vehicles which are not divided into batches currently reaches a set number, the controlled vehicles with the set number are divided into Nth batches, wherein N is a positive integer.
In this implementation manner, the central processing device may receive first sensing information (generated when the sensing unit senses that the vehicle enters the driving takeover area, where the sensing unit includes a unique number of the sensed vehicle) sent by any one sensing unit, and take over the driving control authority of the vehicle corresponding to the unique number; when the number of the controlled vehicles which are not divided into batches currently reaches a set number, the controlled vehicles with the set number are divided into Nth batches, wherein N is a positive integer. In this way, the vehicle batches can be divided according to the actual situation, namely, the controlled vehicles which are not divided into the batches and have the set number are subjected to batch division, so that the corresponding number can be set in consideration of the actual traffic condition of the road, and the balance between the traffic efficiency and the calculation speed is well balanced.
With reference to the first possible implementation manner of the first aspect, in a second possible implementation manner of the first aspect, after the central processing device takes over the driving control authority of the vehicle corresponding to the unique number, the central processing device is further configured to: and adjusting the speed of the controlled vehicle newly entering the driving takeover area to be consistent with the speed of the previous vehicle.
In the implementation mode, the speed of the controlled vehicles in the first stage can be kept consistent, so that the controlled vehicles are accelerated and decelerated synchronously, the speed control of the vehicles in the same batch is simply and reliably realized, the relative positions of the controlled vehicles in the same batch and the same road direction are kept consistent, the collision in the first stage can be avoided, the formation configuration of the controlled vehicles in the same batch can be predicted, and the planning of the vehicle track is facilitated.
With reference to the second possible implementation manner of the first aspect, in a third possible implementation manner of the first aspect, the central processing device is further configured to: obtaining the relative position relation of each vehicle of the Nth batch, and predicting each vehicle of the Nth batch at t based on the relative position relation0Formation configuration of time components, wherein t0The time is the time when the head car in the Nth batch reaches the starting point position of the second stage; each vehicle based on Nth batch at t0The formation configuration at the moment generates a coordinated driving track of each vehicle of the Nth batch in the second stage, wherein when each vehicle of the Nth batch reaches the end position of the second stage based on the coordinated driving track, the speed of each vehicle is a set speed, and the moment when the tail vehicle of the Nth batch reaches the end position of the second stage is t0+tstage2。
In the implementation mode, the collaborative driving track of each vehicle of the Nth batch in the second stage is planned in such a way, so that the reliability and the operability of the planned collaborative driving track can be ensured, the vehicle speeds of each vehicle of the Nth batch when the vehicle reaches the end position of the second stage are set speeds, the planning of the driving track of the third stage (uniform linear forward) is facilitated, and reasonable passing time (t) is reservedstage2) Ensuring that all vehicles of the Nth batch reach the end position of the second stage at the moment t0+tstage2I.e. the total passage time is tstage2The vehicle passing time of all vehicles in the Nth batch in the second stage is ensured, the passing efficiency can be effectively ensured, the basis of the time interval between batches can be used as, the collision of the vehicles in different batches is avoided, and the passing safety and the passing efficiency are ensured.
With reference to the third possible implementation manner of the first aspect, in a fourth possible implementation manner of the first aspect, the central processing device is further configured to: calling the driving track of the batch of vehicles (N-1, N-2, …, 1) which are still located in the driving takeover area and recorded in the database; and based on the trajectories of the vehicles of the Nth batch 1, N-2, …, 1 and the respective vehicles of the Nth batch at t0The formation configuration of the time, and the time t when the head vehicle of the Nth batch reaches the starting point position of the second stage is determined0(ii) a Based on the time t0N-1, N-2, …, the trajectory of the vehicle of batch 1, and the individual vehicles of batch N at t0And determining the driving track of each vehicle of the Nth batch in the first stage by the formation configuration at the moment, wherein the speed of each vehicle of the Nth batch is synchronously regulated in the first stage.
In this implementation, the trajectory of each vehicle of the nth lot in the first stage is planned in such a manner, and the trajectory of the vehicle of the nth lot still in the driving takeover area (N-1, N-2, …, 1) may be considered, where the smaller the data of the lot is (the smaller the value of N is), the higher the priority is, and therefore the nth lot needs to avoid the vehicle of the nth lot, N-2, …, 1, and avoid the collision of the vehicles between different lots.
With reference to the fourth possible implementation manner of the first aspect, in a fifth possible implementation manner of the first aspect, the central processing device is further configured to: and determining the driving track of each vehicle of the Nth batch in the third stage based on the set constant-speed straight-line driving rule and the time when each vehicle of the Nth batch reaches the end position of the second stage based on the running of the cooperative driving track.
In the implementation mode, the driving tracks of the vehicles of the Nth batch in the third phase are planned in such a way, so that the collision problem of the vehicles can be simply and reliably avoided, the calculation time can be greatly saved, and the requirement on central processing equipment is reduced.
With reference to the fifth possible implementation manner of the first aspect, in a sixth possible implementation manner of the first aspect, the central processing device is further configured to: sequentially integrating the driving tracks of the vehicles of the Nth batch in the first stage, the cooperative driving track of the second stage and the driving track of the third stage to obtain the controlled driving tracks of the vehicles of the Nth batch; the controlled trajectories of the vehicles of the nth lot are stored in a database.
In this implementation manner, the driving tracks of the vehicles of the nth batch in the first stage, the cooperative driving track of the second stage, and the driving track of the vehicles of the nth batch in the third stage are sequentially integrated to obtain the controlled driving tracks of the vehicles of the nth batch, which can be used as the driving basis of the vehicles of the nth batch in the driving interface area to control the operation of the vehicles of the nth batch. The method is stored in a database and can be used as an evasion reference of a subsequent batch, so that the collision between the vehicles of the subsequent batch and the vehicles of the Nth batch is avoided, and the vehicles of the Nth batch can pass according to a controlled driving track.
With reference to the first possible implementation manner of the first aspect, in a seventh possible implementation manner of the first aspect, the central processing device is further configured to: receiving second perception information sent by any one perception unit, wherein the second perception information is generated when the perception unit perceives that the vehicle exits from the driving takeover area, and the second perception information contains a unique number of the perceived vehicle; returning the driving control authority of the vehicle corresponding to the unique number according to the second perception information; judging whether a batch to be eliminated exists at present, wherein the batch to be eliminated represents that the driving control authority of each vehicle of the batch is returned; if so, eliminating the batch number of the to-be-eliminated batch, and reducing the numbers of all the current remaining batches by one respectively.
In this implementation manner, after the sensing unit senses that the vehicle exits from the driving takeover area, the driving control authority of the vehicle corresponding to the unique number may be returned, and after all vehicles of a certain batch exit from the driving takeover area, the central processing device may further eliminate the batch number of the batch to be eliminated (the driving control authority of each vehicle of the batch is returned), and reduce the numbers of all current remaining batches by one. In this way, the controlled trajectory of the batch of vehicles that has passed the driving take-over area can be cleared in time, and the amount of calculations can be reduced because the operation of other vehicles in the driving take-over area is no longer affected.
With reference to the third possible implementation manner of the first aspect, in an eighth possible implementation manner of the first aspect, the set number is 5 to 15, tstage2Is 10 to 20 seconds.
In the implementation mode, the set number is 5-15, the calculation speed can be effectively guaranteed, the performance requirement on central processing equipment is reduced, and meanwhile, multi-vehicle cooperation can be well considered, so that the passing efficiency of vehicles is guaranteed. And t isstage210-20 s, all vehicles in the same batch can be guaranteed to completely pass through the second stage within 10-20 s according to the set number.
In a second aspect, an embodiment of the present application provides an autonomous intersection management method based on a signal-free intersection, which is applied to a central processing device in the autonomous intersection management system based on a signal-free intersection described in any one of the first aspect or possible implementation manners of the first aspect, where the method includes: taking over the driving control authority of the vehicle entering the driving taking-over area, and returning the driving control authority of the vehicle exiting the driving taking-over area; and dividing the vehicles driving into the driving takeover area in batches, controlling each vehicle in the same batch to keep the vehicles going ahead straight in the current lane in the first stage, cooperatively driving through the signal lamp-free intersection in the second stage, and keeping constant-speed straight running in the third stage.
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and that those skilled in the art can also obtain other related drawings based on the drawings without inventive efforts.
Fig. 1 is a schematic diagram of an autonomous intersection management system based on a signal-lamp-free intersection according to an embodiment of the present application.
Fig. 2 is a schematic diagram of setting a cooperative boundary line near an intersection without a signal lamp.
FIG. 3 is a schematic illustration of controlled vehicle batching.
Fig. 4 is a schematic view of a plane crossroad scene without signal lamps.
Fig. 5 is a schematic diagram of passable areas of vehicles of a class a1, a2 and A3 in a traffic scene of the signal-light-free intersection.
Fig. 6 is a schematic diagram of an area where each vehicle stops in a traffic scene of the intersection without the signal lamp.
FIG. 7 is a schematic diagram of a two degree-of-freedom vehicle kinematics model.
Icon: 100-autonomous crossing management system based on no-signal lamp crossing; 110-a sensing unit; 120-central processing equipment.
Detailed Description
The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.
Referring to fig. 1, fig. 1 is a schematic diagram of an autonomous intersection management system 100 based on a signal-less intersection according to an embodiment of the present application.
In the present embodiment, the automated intersection management system 100 based on the signal-less intersection may include a central processing device 120 and a plurality of sensing units 110. Each sensing unit 110 can be respectively arranged at the road of each direction of the non-signal lamp intersection according to a set distance range (for example, 1000-1200 meters, 2500-3000, etc., the set distance range is determined according to actual needs). Since the actual no-signal intersection design difference and the roads in all directions may have some differences, resulting in different straight-line distances, the distances between the sensing units 110 arranged in all directions of the roads and the no-signal intersection may also have differences, which is suitable for the actual distance (or the average transit time), and is not limited herein. For convenience of understanding, in this scheme, taking an intersection as an example, each sensing unit 110 is disposed at a road in each direction of the intersection without signal lamps, and the distance between each sensing unit 110 and the intersection without signal lamps is the same.
Referring to fig. 2, fig. 2 is a schematic diagram of setting cooperative boundary lines near an intersection without a signal lamp. A cooperative boundary line (dotted line in fig. 2) is provided between the sensing unit 110 and the non-signal intersection in each road direction to divide a cooperative area in which vehicles in a smaller range cooperatively pass through the intersection. It should be noted that the cooperative boundary line may be set for the corresponding vehicle sensing unit 110 to sense, or may not be set, and is not limited herein, subject to actual needs.
For ease of understanding, some concepts to which the present solution will relate will be described herein first:
the driving takeover region is a region that is defined by (the sensing range of) the sensing unit 110 provided in each road direction with the intersection without the traffic signal as the center.
The vehicle cooperation area means an area formed by taking a non-signal intersection as a center and taking a cooperation boundary line of each road direction as a boundary.
The process from the vehicle entering the driving takeover area to the vehicle exiting the driving takeover area comprises a first stage, a second stage and a third stage:
the first stage represents the cooperative boundary line of the direction to which the vehicle is heading from the heading sensing unit 110.
And the second stage represents that the vehicle drives to the cooperative boundary line of the going direction after passing through the no-signal lamp crossing from the cooperative boundary line of the going direction.
And a third stage of representing that the vehicle drives from the cooperative boundary line of the forward direction to the forward direction sensing unit 110.
The direction of the road is the direction of the road where the vehicle does not pass through the intersection without the signal lamp.
The going direction represents the direction of the road where the vehicle passes through the intersection without the signal lamp.
In the present embodiment, the central processing device 120 is communicatively connected to each sensing unit 110. The central processing device 120 may be a terminal device (e.g., a personal computer) or a server (e.g., a cloud server, a server cluster, etc.) for taking over the driving control authority of the vehicle entering the driving take-over area and returning the driving control authority of the vehicle exiting the driving take-over area, wherein the vehicle taking over the driving control authority is a controlled vehicle (the operation of which is controlled by the central processing device 120), and the vehicle returning the driving control authority is an autonomous vehicle (the operation of which is not controlled by the central processing device 120 but is controlled by the system of the vehicle itself).
For a vehicle entering the driving takeover area, the central processing device 120 needs to fully take over the driving control authority of the vehicle and control the operation of the vehicle in the driving takeover area. The central processing device 120 manages the vehicles (intelligent networked automobiles) entering the central processing device, completely takes over the driving control authority of the vehicles, so as to plan the driving tracks for the controlled vehicles, and then issues the driving tracks to each controlled vehicle for closed-loop tracking execution.
In order to ensure the passing efficiency of the vehicles in the driving takeover area and reduce the calculation time required by the trajectory planning as much as possible, the central processing device 120 may divide the vehicles entering the driving takeover area into batches, and control each vehicle of the same batch to keep moving ahead in a straight line in the current lane in the first stage, and cooperatively drive through the intersection without the signal lamp in the second stage, and keep moving in a straight line at a constant speed in the third stage, wherein a plurality of vehicles of the same batch located in the same road direction keep fixed relative positions in the first stage. It should be noted that, here, the running speeds of the vehicles in the same batch are synchronized (and the acceleration/deceleration is adjusted synchronously), so that the running sequence is ensured to be unchanged, and the time required for reaching the starting position of the second stage is reduced synchronously.
The vehicles are divided into batches, so that the vehicles in each batch are controlled to run cooperatively, the cooperative action of the vehicles in the same batch can be considered, and the traffic efficiency is improved. Moreover, the batch division of the vehicles can be set artificially (the number of the vehicles in the same batch is determined), the balance between the solving quality and the solving speed can be well considered, and the calculation speed (time consumption) and the traffic efficiency are considered. The vehicles keep moving ahead in a straight line in the current lane in the first stage, the vehicles in the same batch and positioned in the same road direction keep fixed relative positions in the first stage, so that the relative motion trend among the vehicles in the same batch and in the same road direction can be avoided, collision can be avoided, and the vehicles in the same batch keep moving in a straight line at a constant speed (running at a set speed) in the third stage, and collision can also be avoided.
For example, when any sensing unit 110 senses that the vehicle enters the driving takeover area, corresponding first sensing information (including the unique number of the sensed vehicle) may be generated and sent to the central processing device 120.
And the central processing device 120 may receive the first sensing information sent by the sensing unit 110, and take over the driving control authority of the vehicle corresponding to the unique number according to the first sensing information.
Then, the central processing apparatus 120 may adjust the vehicle speed of the controlled vehicle that has newly entered the drive-over area to coincide with the vehicle speed of the preceding vehicle. Therefore, the speed of the controlled vehicles in the first stage can be kept consistent, so that the controlled vehicles are accelerated and decelerated synchronously, the speed control of the vehicles in the same batch is simply and reliably realized, the relative positions of the controlled vehicles in the same batch and the same road direction are kept consistent, the collision can be avoided in the first stage, the formation configuration of the controlled vehicles in the same batch can be predicted, and the planning of the vehicle track is facilitated.
Of course, in other possible cases, the buffer area may be specially set, so that the vehicle speed of the vehicle that wants to enter the driving takeover area is adjusted to a fixed value (the speed of each vehicle is the fixed value when entering the driving takeover area from the end of the buffer area), so that the speeds of the vehicles entering the driving takeover area are consistent, and the vehicle can be prevented from colliding in the first stage.
The number of the controlled vehicles which are not divided into batches at present reaches the set number NVThe central processing apparatus 120 may set this to the number NVIs divided into the Nth batch, and N is a positive integer. Here, the set number NVThe number of vehicles in a batch can be set according to actual needs. The number N is set based on the current conditions of the central processing apparatus 120VPreferably 5 to 15.
The batch dividing process here can be understood as follows: dividing all vehicles into a series of batches according to the distance from the central point of the intersection (namely the sequence of entering a driving takeover area). As shown in fig. 3, vehicles within the same ring belong to the same batch. It should be noted that vehicles of the same batch may be located on four roads (four-way roads), respectively, i.e., vehicles of the same batch are not necessarily all spatially closely spaced. The straight-line distances of the vehicles in the same batch from the intersection center point are generally not very different, so that the batch is exemplarily drawn as a ring in fig. 3, which is merely an exemplary concept and should not be construed as a limitation of the present application.
In this way, the vehicle batches can be divided according to the actual situation, namely, the controlled vehicles which are not divided into the batches and have the set number are subjected to batch division, so that the corresponding number can be set in consideration of the actual traffic condition of the road, and the balance between the traffic efficiency and the calculation speed is well balanced. And a set number NV5-15, can effectively guarantee the calculation speed, reduce the performance requirement to central processing equipment 120, simultaneously, also can consider the car cooperation of many cars well to guarantee the current efficiency of vehicle.
After dividing the batches of vehicles entering the driving takeover area, the central processing device 120 needs to plan the driving trajectories of the vehicles in the same batch so as to control the vehicles in the same batch to pass through the driving takeover area.
For convenience of explanation, the present embodiment will be described by taking a determination method of the trajectory of each vehicle of the nth lot as an example, but the present application is not limited thereto. In this embodiment, the planning of the driving trajectories of the vehicles in the nth batch may be divided into the first phase, the second phase and the third phase, but the planning sequence should be the second phase, the first phase, the third phase, or the second phase, the third phase, the first phase.
Planning the driving track of the second stage:
first, the central processing apparatus 120 may acquire the relative positional relationship of each vehicle of the nth lot, and predict each vehicle of the nth lot at t based on the relative positional relationship0Formation configuration composed of time instants (due to the fixed relative position between vehicles in the same road direction), wherein t0The time is the time when the head car in the nth batch reaches the start position of the second stage. Here, the relative positional relationship of the respective vehicles includes the relative positional relationship of the vehicles located in each road direction.
The central processing facility 120 may then determine the number of vehicles in the Nth lot at t0And (3) generating a coordinated driving track of each vehicle of the Nth batch in the second stage by the formation configuration at the moment (wherein, for the coordinated driving track of the vehicles in the second stage, each vehicle of the same batch reaches the end position of the second stage, the speed is set). Although the starting time of the second phase of each lot of vehicles is different from one another, it is not possible to determine at which determination time the current lot (nth lot) of vehicles starts the second phase. But since the second phase will last for a fixed period of time (assuming t is t)0+tstage2Time) and at the start time t of the second phase0(assume t as0) Where the formation configuration of the Nth lot of vehicles is known, that may utilize the agreementThe co-track planning technology directly plans the coordinated driving track of the vehicles of the current batch (Nth batch) in the second stage.
The method is used for planning the cooperative driving track of each vehicle of the Nth batch in the second stage, the reliability and the operability of the planned cooperative driving track can be ensured, the vehicle speeds of the vehicles of the Nth batch when the vehicles arrive at the end position of the second stage in operation are set speeds, the planning of the driving track of the third stage (uniform linear forward) is facilitated, and reasonable passing time (t) is reservedstage2) Ensuring that all vehicles of the Nth batch reach the end position of the second stage at the moment t0+tstage2I.e. the total passage time is tstage2The vehicle passing time of all vehicles in the Nth batch in the second stage is ensured, the passing efficiency can be effectively ensured, the basis of the time interval between batches can be used as, the collision of the vehicles in different batches is avoided, and the passing safety and the passing efficiency are ensured.
In the present embodiment, t is based on practical experiencestage210-20 s can be selected, so that all vehicles in the same batch can completely pass through the second stage within 10-20 s.
For ease of understanding, the following description will be made of a specific way of planning the coordinated driving trajectory of the current batch of vehicles in the second phase by using the coordinated trajectory planning technique:
for convenience of description, as shown in fig. 4, a plane coordinate system XOY is established, and the coordinate system is constructed by taking the central lines of two roads perpendicular to each other in the scene of the plane intersection as the X axis and the Y axis and taking the intersection point of the central lines as the origin O. Blocks (Block1, Block2, Block3 and Block4) around the crossroad are placed in four quadrants of a coordinate system to serve as rectangular obstacles, and basic scene arrangement (namely a traffic scene of the intersection without signal lamps) can be realized. Setting the unidirectional road width in the crossing scene as Lroad_widthThe length of the block is uniformly Lstreet_lengthTherefore, the position of each rectangular obstacle can be uniquely determined.
In the intersection scenario, each car does not have a chance to collide with all four blocks at the same time, because each car can further limit its passable area according to the direction of entering the intersection and the passing intention, and only one block rectangle is in its passable area at most. The concept of passable areas will be described in detail below.
As shown in fig. 4, vehicles can enter the intersection from 4 directions of south-east and north-west, and vehicles entering the intersection from each direction can exit the intersection in 3 ways of turning left, going straight and turning right, so all vehicles trying to pass through the intersection can be classified into 12 categories according to the above behavior characteristics, and the index sets containing the numbers of the vehicles in the corresponding categories can be sequentially defined as a1, a2, A3, B1, B2, B3, C1, C2, C3, D1, D2 and D3, obviously, any vehicle belongs to one of the 12 sets, the intersection of any two subsets is empty, and the union of all 12 subsets is { 1., N., n.V}。
First consider the case of driving from west to east into a non-signal intersection (i.e., a vehicle coordination area), which in fig. 4 correspond to vehicles of the a1, a2, A3 categories. Suppose that the time domain corresponding to the second stage is te [ t ∈ [ [ t ]0,t0+tstage2](wherein, t is0How to take the value is uncertain, but the time domain length of the second stage is tstage2I.e. t as described hereinbeforestage2Is a parameter that is explicitly known). The travelable regions of these three types of vehicles are shown in fig. 5.
Taking A3 as an example, it is first required that the automobile in this category always remains in the left area where the straight line y is 0 and the straight line x is 0, and since this area has a rectangular Block4, the vehicle of class A3 needs to avoid Block4 from running, and the passable area corresponding to the vehicle of class A3 is removed from the semi-closed area surrounded by two straight lines, which is the area occupied by Block 4. Vehicles belonging to class a2 need to remain constantly below and along line y-Lroad_widthTravel in the upper belt-like region. The passable area of the a1 type vehicle is arranged in a similar manner to that of A3, but the oncoming road space may be additionally used as a part of the a1 passable area, which is different from the existing traffic regulations. Allowing left-turning vehicles to utilize oncoming traffic is an important feature of the model built in this sectionThe purpose is to make left-turning vehicles more fully utilize the road space and improve the overall traffic efficiency. To summarize, the passable areas for vehicles of the a1, a2, A3 categories may be defined as:
Figure BDA0003150168180000151
Figure BDA0003150168180000152
Figure BDA0003150168180000153
wherein A isix(t),Bix(t),Cix(t),Dix(t) respectively referring to the abscissa of four vertexes of the rectangular outline of the vehicle at the moment t of the ith vehicle in the formation; similarly, Aiy(t),Biy(t),Ciy(t),Diy(t) respectively referring to the vertical coordinates of four vertexes of the rectangular outline of the ith vehicle at the moment t; VehicleOutOfPolygon gamma (γ, γ) refers to a collision avoidance constraint for describing that no collision occurs between the two convex polygons gamma and γ.
The passable areas of the remaining 9 types of vehicles (i.e., B1, B2, B3, C1, C2, C3, D1, D2, and D3) can be determined by the same method, and are not described herein again.
When all vehicles move in the corresponding passable area, all vehicle types overlapped in the passable area are required to be free of collision, and all vehicles in all the vehicle types are required to be free of collision. For simple writing, the collision avoidance constraint condition of the i car and the j car at the time t can be temporarily recorded as VehicleOutOfVehicle (i, j, t), and the complete collision avoidance constraint condition can be written as:
VehicleOutOfVehicle(i,j,t),i∈A1,
j∈A2∪A3∪B1∪B2∪B3∪C1∪C2∪C3∪D1∪D2∪D3；
VehicleOutOfVehicle(i,j,t),i∈A2,
j∈A3∪B1∪B2∪B3∪C1∪D1∪D2；
VehicleOutOfVehicle(i,j,t),i∈A3,j∈B1∪C1∪D1D2；
VehicleOutOfVehicle(i,j,t),i∈B1,
j∈B2∪B3∪C1∪C2∪C3∪D1∪D2∪D3；
VehicleOutOfVehicle(i,j,t),i∈B2,j∈B3∪C1∪C2∪C3∪D1；
VehicleOutOfVehicle(i,j,t),i∈B3,j∈C1∪D1；
VehicleOutOfVehicle(i,j,t),i∈C1,j∈C2∪C3∪D1∪D2∪D3；
VehicleOutOfVehicle(i,j,t),i∈C2,j∈C3∪D1∪D2∪D3；
VehicleOutOfVehicle(i,j,t),i∈C3,j∈D1；
VehicleOutOfVehicle(i,j,t),i∈D1,j∈D2∪D3；
VehicleOutOfVehicle(i,j,t),i∈D2,j∈D3； (4)
and the number of the first and second groups,
Figure BDA0003150168180000161
Figure BDA0003150168180000162
Figure BDA0003150168180000163
Figure BDA0003150168180000164
Figure BDA0003150168180000165
Figure BDA0003150168180000166
Figure BDA0003150168180000167
Figure BDA0003150168180000168
Figure BDA0003150168180000169
Figure BDA00031501681800001610
Figure BDA00031501681800001611
Figure BDA00031501681800001612
the above formula acts on the time domain t e [ t ] of the whole second stage0,t0+tstage2]Above. From the equation (4), it can be found that the passable areas of the left-turn vehicles (i.e., vehicles of the categories a1, B1, C1 and D1) all overlap with the passable areas of the non-left-turn vehicles, and therefore the left-turn vehicles are one of the important causes of difficulty in the co-planning problem. The specific meaning of vehicleotofvel (i, j, t) in formula (4) and formula (5) is:
VehicleOutOfPolygon(Ai(t)Bi(t)Ci(t)Di(t),Aj(t)Bj(t)Cj(t)Dj(t)).(6)
starting time t ═ t of crossing traffic dynamic process0The state of motion of each vehicle may be determined in combination with objective facts then obtained by the perception module. Can be used around the intersection in engineering practiceThe specific area is set as a buffer area, and each vehicle is required to complete the adjustment of the self motion state in the buffer area, and finally each vehicle is enabled to start at the starting time t equal to t0Travelling at a steady and uniform speed in the direction of the road section on which it is currently located, i.e. at the same speed
[xi(t0),yi(t0),vj(t0),aj(t0),φj(t0),ωj(t0)]＝[xi,yi,vstd,0,0,0],i∈{1,...,NV}； (7)
θi(t0)＝0,i∈A1∪A2∪A3； (8)
θi(t0)＝π/2,i∈B1∪B2∪B3； (9)
θi(t0)＝π,i∈C1∪C2∪C3； (10)
θi(t0)＝-π/2,i∈D1∪D2∪D3. (11)
Wherein v isstdThe speed is more than 0 and is a preset common speed standard value for each vehicle to run stably at a constant speed, (x)i,yi) Representing the starting position coordinates of the ith vehicle. At the end of the second phase0+tstage2Each vehicle should travel smoothly at a constant speed in the direction of the target road. The target road region of each type of vehicle marked in conjunction with fig. 6 can restrict the movement state of each vehicle at the termination time by the following conditions. For ease of description, t may be agreedf＝t0+tstage2。
[vi(tf),ai(tf),φi(tf),ωi(tf)]＝[vstd,0,0,0],i∈{1,...,NV}； (12)
Figure BDA0003150168180000171
Figure BDA0003150168180000172
Figure BDA0003150168180000173
Figure BDA0003150168180000174
θi(tf)＝θi(0)+π/2,i∈A1∪B1∪C1∪D1； (17)
θi(tf)＝θi(0),i∈A2∪B2∪C2∪D2； (18)
θi(tf)＝θi(0)-π/2,i∈A3∪B3∪C3∪D3. (19)
Where equation (12) reflects the requirement for "smooth uniform speed" travel, equations (13) to (16) reflect the position restrictions at the end time for each vehicle, and equations (17) to (19) are the end time angle restrictions.
Some constraints are also needed to describe the motion capability of the vehicle, which can be described using a classical bicycle model:
as shown in fig. 7, the 2-degree-of-freedom model combines two front wheels and two rear wheels of the vehicle in the longitudinal axis direction of the vehicle body into a virtual single wheel, and determines the rotation angular velocity of the virtual front wheel and the linear acceleration variable of the virtual rear wheel, thereby indirectly determining the rotation angle, the running speed, and the like of the front wheel of the vehicle and further realizing the vehicle motion. The presence of two virtual single wheels makes the vehicle morphologically similar to a bicycle, so the 2-degree-of-freedom model is also referred to as a bicycle model.
For vehicle i, the motion process of vehicle i in inertial coordinate system XOY is limited by the following system of differential equations according to the bicycle model:
Figure BDA0003150168180000181
wherein (x)i(t),yi(t)) represents the rear axle midpoint coordinates of vehicle i (fig. 7); v. ofi(t) and ai(t) represents the speed and acceleration in the longitudinal axis direction of the vehicle body, respectively, such that the direction in which the vehicle is advanced is the positive direction; phi is ai(t) is a vehicle front wheel deflection angle, and the left turning direction is a positive direction; omegai(t) front wheel yaw angular velocity; thetaiAnd (t) represents the attitude angle of the vehicle in the coordinate system, namely the rotation angle from the positive direction of the X axis of the coordinate system to the positive direction of the longitudinal axis of the vehicle body, and the counterclockwise turning is taken as the positive direction. In addition, four geometry-related parameters of the vehicle i are also defined in fig. 7: l iswRepresenting the front and rear wheel base, LfRepresents the front overhang distance of the vehicle, LrRepresents the rear overhang distance, LbRepresenting the vehicle width.
The optimal control problem includes a cost function for reflecting the optimal requirements for traffic efficiency, comfort performance and safety performance, in addition to the above-mentioned environmental restriction constraints, side value constraints and vehicle kinematics constraints. Wherein comfort performance index J(Comfort)The change amplitude and the speed of each state variable are required to be smaller, and the safety performance index J isSecureA proper distance between the vehicles is required. Passing efficiency JEfficiency of passageEach vehicle is required to travel as far as possible in the direction of its target lane, namely:
Figure BDA0003150168180000191
in order to enable each vehicle to finish the intersection passing task as soon as possible, J seems to be set intuitivelyEfficiency of passage＝tfHowever, the reason for selecting equation (21) in this embodiment is that JEfficiency of passage＝tfOnly the vehicle that is the slowest to achieve the end time constraint can be "incentivized" to complete the task as quickly as possible, but the vehicles that should achieve the end time constraint earlier cannot be effectively encouraged to continue to move. Use of JEfficiency of passage＝tfThe most direct effect of the optimization solution as a cost function is to result in a significant number of vehicle choices until t-tfThe time instants "willing" to fulfill the end-time constraint because they do not even if they are fulfilled earlierAt a cost function JEfficiency of passage＝tfThere is any reflection in. Therefore, the formula (21) can effectively stimulate all vehicles to travel far away as soon as possible, so that the traffic efficiency is really improved.
The weight coefficient can also be set as required to obtain:
J＝w1·Jefficiency of passage+w2·J(Comfort)+w3·JSecure, (22)
Wherein w1,w2,w3And the weight coefficients are more than 0.
Therefore, the constraint and the cost function can be combined to form a complete mathematical proposition for completely describing a task of planning the traffic collaborative track of a batch of vehicles at the traffic-signal-free crossroads, and obviously, the problem is an optimal control problem.
After describing the multi-vehicle collaborative trajectory planning task in the intersection scene as an optimal control problem, the optimal control problem can be solved numerically, because the analytic solving method (such as the Pontryagin extreme value principle and the like) cannot deal with the complicated problem. Therefore, the optimal control problem needs to be discretized into a nonlinear programming problem along independent variables (i.e. time dimension), and then the nonlinear programming problem is solved by adopting a gradient optimization algorithm, so that the trajectory programming task is completed.
Therefore, the driving track of each vehicle of the Nth batch in the second stage can be planned, and the coordinated driving track is obtained.
After obtaining the cooperative driving track of each vehicle of the Nth batch in the second stage, only the time t needs to be determined0The management work of the AIM on the vehicles in the current batch can be basically finished. That is, the central processing device 120 may further determine the driving paths of the vehicles of the nth lot in the first phase and the third phase. The specific way of determining the driving paths of the vehicles of the Nth batch in the first stage and the third stage is very simple and convenient, and the required calculation time is very small.
For example, the central processing device 120 may utilize the base for the determination of the driving paths of the vehicles of the Nth lot in the first stageAt the moment t when the reserved AIM method reserves the intersection as early as possible0This technique is well established and is briefly described here:
the central processing device 120 may call up the driving trace of the N-1, N-2, …, 1 th batch of vehicles still located in the driving takeover area recorded in the database; and based on the trajectories of the vehicles of the Nth batch 1, N-2, …, 1 and the respective vehicles of the Nth batch at t0The formation configuration of the time, and the time t when the head vehicle of the Nth batch reaches the starting point position of the second stage is determined0(ii) a Based on the time t0N-1, N-2, …, the trajectory of the vehicle of batch 1, and the individual vehicles of batch N at t0And (3) determining the driving track of each vehicle of the Nth batch in a first stage by the formation configuration at the moment, wherein the speed of each vehicle of the Nth batch is synchronously regulated in the first stage. For each vehicle of the Nth batch to keep driving in the forward direction of the current lane in the first stage, each vehicle accelerates/decelerates uniformly in pace to ensure that the head vehicle in the Nth batch at t0When the time reaches the cooperative boundary line, the vehicle can travel by using a mature ADAS (Advanced Driving Assistance System) technology.
By planning the driving paths of the vehicles of the Nth batch in the first stage in such a way, the driving paths of the vehicles of the Nth batch still in the driving takeover area can be considered, the smaller the data of the batches (the smaller the value of N) is, the higher the priority is, so the vehicles of the Nth batch need to be avoided from the N-1, N-2, … and 1 batches, and the collision of the vehicles among different batches can be avoided.
For the determination of the driving track of each vehicle in the nth batch in the third stage, the central processing device 120 may set that each vehicle in the nth batch is driven at a constant speed in a straight line in the third stage, and the driving speeds are all the set speeds vstd. Thus, the central processing device 120 can determine the track of each vehicle of the nth batch in the third stage based on the set uniform speed straight-line driving rule and the time when each vehicle of the nth batch reaches the end position of the second stage based on the operation of the coordinated driving trackAnd (4) tracing.
By planning the driving tracks of the vehicles of the Nth batch in the third phase in such a way, the collision problem of the vehicles can be simply and reliably avoided, and the calculation time can be greatly saved, so that the requirement on the central processing equipment 120 is reduced.
After determining the driving trajectories of the nth vehicle in the second, first and third stages, the central processing device 120 may integrate the driving trajectories of the nth vehicle in the first stage, the cooperative driving trajectories of the second stage and the driving trajectories of the third stage in order to obtain the controlled driving trajectories of the nth vehicle, and store the controlled driving trajectories of the nth vehicle in the database.
Therefore, the controlled driving tracks of the vehicles of the Nth batch can be used as the avoidance reference of the subsequent batch, the vehicles of the subsequent batch are prevented from colliding with the vehicles of the Nth batch, and the vehicles of the Nth batch can pass according to the controlled driving tracks.
For example, when any sensing unit 110 senses that the controlled vehicle exits from the driving takeover area, corresponding second sensing information (including the unique number of the sensed vehicle) may be generated and sent to the central processing device 120.
And the central processing device 120 may receive the second sensing information sent by the sensing unit 110, and return the driving control authority of the vehicle corresponding to the unique number according to the second sensing information.
And, the central processing device 120 may further determine whether there is a to-be-eliminated batch currently, wherein the to-be-eliminated batch indicates that the driving control authority of each vehicle of the batch is returned. If so, eliminating the batch number of the to-be-eliminated batch, and reducing the numbers of all the current remaining batches by one respectively. And reducing the number of all the current remaining batches by one respectively to represent that the priority of the remaining batches is increased.
In this way, the controlled trajectory of the batch of vehicles that has passed the driving take-over area can be cleared in time, and the amount of calculations can be reduced because the operation of other vehicles in the driving take-over area is no longer affected.
Based on the same inventive concept, the embodiment of the present application further provides an autonomous intersection management method based on the signal-lamp-free intersection, which is applied to the central processing device 120 in the autonomous intersection management system 100 based on the signal-lamp-free intersection in the embodiment, and takes over the driving control authority of the vehicle entering the driving takeover area and returns the driving control authority of the vehicle exiting the driving takeover area; and dividing the vehicles driving into the driving takeover area in batches, controlling each vehicle in the same batch to keep the current lane to move forward in a straight line in the first stage, cooperatively driving through the signal-free intersection in the second stage, and keeping constant-speed straight line running in the third stage.
Since the functions (operations to be performed) of the central processing apparatus 120 have been fully described in the foregoing, the method portion herein is also applied to the central processing apparatus 120, and reference is made to the foregoing, and details are not described herein, but should not be construed as limiting the present application.
In order to verify the effect of the autonomous intersection management system 100 based on the signal-free intersection, the inventor designs a corresponding simulation experiment:
at infinity, 2000 vehicles are given to drive into the non-signal intersection from all directions. The quality of the autonomous intersection management system 100 based on the signal-lamp-free intersection is evaluated by counting the passage efficiency index, and the instantaneity of the scheme is judged by the processing time consumption of the autonomous intersection management system 100 based on the signal-lamp-free intersection. The traffic efficiency mentioned here means the time t when the earliest of the 2000 vehicles enters the intersection1At the time t when the latest vehicle is out of the intersection2The difference between (and thus the dimension is time s, i.e. seconds).
Referring to Table 1, Table 1 shows the number of vehicles N per batchVComparison data of passage efficiency under the conditions and solution time (corresponding data are not shown in table 1 because the calculation time of the third stage is almost negligible), and the following results are obtained on a common home computer.
TABLE 1
Figure BDA0003150168180000231
As can be seen from the data in Table 1, NVWhen the effect is smaller, the effect of the scheme is similar to that of an AIM algorithm based on reservation, and the traffic efficiency is poor at this moment, because the synergistic effect among vehicles is almost not good (only 2 vehicles in a batch cooperate in a small scale at each time, and no synergy among batches means). In NVWhen the traffic quality is larger, the effect of the scheme is similar to that of an AIM method based on planning, so that the traffic quality is remarkably improved and approaches to 100%. Meanwhile, due to the large scale of vehicles in the batch, the calculation time consumed by the cooperative driving process of each vehicle in the second stage is correspondingly increased, but the increase of the calculation time consumption is a great breakthrough compared with thousands of seconds before (based on the planned AIM method).
Therefore, the solution quality and the solution time consumption are considered, and after the CPU of the computer is better and better in the future, the computer can process larger and larger batches, so that the solution quality can be continuously and stably improved on the premise that the calculation timeliness is guaranteed (in short, along with the better and better CPU, larger and larger N can be processed)VFurther improving the traffic efficiency).
To sum up, the embodiment of the present application provides an autonomous intersection management system 100 and method based on a signal-lamp-free intersection, which utilize sensing units 110 disposed at roads in various directions of the signal-lamp-free intersection to form a driving connection area, manage vehicles (intelligent internet automobiles) entering the driving connection area, and completely take over driving control authority of the vehicles, so as to plan driving tracks for the controlled vehicles, and then issue the driving tracks to the controlled vehicles for closed-loop tracking execution. A cooperative boundary line is arranged between the sensing unit 110 and the intersection without the signal lamp in each road direction, and a vehicle cooperative area is formed by taking the intersection without the signal lamp as the center and the cooperative boundary lines in all directions as the boundary. Taking the following as the basis for planning the driving track: the process from the vehicle entering the driving takeover area to the vehicle exiting the driving takeover area comprises a first stage (the cooperative boundary line of the direction from the vehicle-coming sensing unit 110 to the vehicle-coming direction), a second stage (the cooperative boundary line of the direction from the vehicle-coming direction is driven to the cooperative boundary line of the direction from the vehicle-coming direction after passing through the no-signal intersection) and a third stage (the vehicle is driven from the cooperative boundary line of the direction to the vehicle-going direction sensing unit 110). Therefore, the central processing device 120 divides the vehicles entering the driving takeover area into batches, and controls each vehicle of the same batch to keep moving ahead in the current lane in a straight line in the first stage, and to cooperatively drive through the intersection without the signal lamp in the second stage and keep moving in a straight line at a constant speed in the third stage. The vehicles are divided into batches, so that the vehicles in each batch are controlled to run cooperatively, the cooperative action of the vehicles in the same batch can be considered, and the traffic efficiency is improved. Moreover, the batch division of the vehicles can be set artificially (the number of the vehicles in the same batch is determined), the balance between the solving quality and the solving speed can be well considered, and the calculation speed (time consumption) and the traffic efficiency are considered. The vehicles keep moving ahead in a straight line in the current lane in the first stage, the vehicles in the same batch and positioned in the same road direction keep fixed relative positions in the first stage, so that the relative motion trend among the vehicles in the same batch and in the same road direction can be avoided, collision can be avoided, and the vehicles in the same batch keep moving in a straight line at a constant speed (running at a set speed) in the third stage, and collision can also be avoided.
In this document, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions.
The above description is only an example of the present application and is not intended to limit the scope of the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims (10)

1. An autonomous intersection management system based on a signal-lamp-free intersection, comprising:
the system comprises a plurality of sensing units, a plurality of sensors and a controller, wherein each sensing unit is respectively arranged at the road of each direction of a no-signal lamp intersection according to a set distance range and is used for sensing vehicles which are driven to or leave the no-signal lamp intersection through the sensing unit, an area formed by taking the no-signal lamp intersection as a center and the sensing units of each direction as boundaries is a driving takeover area, cooperation is arranged between the sensing unit of each road direction and the no-signal lamp intersection, and an area formed by taking the no-signal lamp intersection as a center boundary line and the cooperation boundary lines of each direction as boundaries is a vehicle cooperation area;
a central processing device which is respectively connected with each sensing unit in a communication mode and is used for taking over the driving control authority of the vehicle entering the driving takeover area and returning the driving control authority of the vehicle exiting the driving takeover area, wherein the vehicle taking over the driving control authority is a controlled vehicle, the vehicle returning the driving control authority is an automatic control vehicle, the process that the vehicle enters the driving takeover area and exits the driving takeover area comprises a first stage, a second stage and a third stage, the first stage represents that the vehicle travels to a cooperative boundary line from the sensing unit of the direction of the vehicle, the second stage represents that the vehicle travels to a cooperative boundary line from the cooperative boundary line of the direction of the vehicle after passing through the no-signal lamp intersection, the third stage represents that the vehicle travels to the sensing unit of the direction of the vehicle from the cooperative boundary line of the direction of the vehicle to the no-signal lamp intersection to indicate the direction of the road where the vehicle does not pass through the no-signal lamp intersection, the going direction represents the direction of a road where the vehicle passes through the non-signal lamp intersection;
the central processing device is further configured to divide the vehicles driving into the driving connection area in batches, control each vehicle of the same batch to keep moving ahead in a straight line in the current lane in the first stage, cooperatively drive through the traffic signal-free intersection in the second stage, and keep moving in a straight line at a constant speed in the third stage, wherein a plurality of vehicles of the same batch in the same road direction keep fixed relative positions in the first stage.
2. The automated intersection management system based on a signal-free intersection according to claim 1, wherein the central processing device is further configured to:
receiving first perception information sent by any one perception unit, wherein the first perception information is generated when the perception unit perceives that a vehicle enters the driving takeover area, and the first perception information comprises a unique number of the perceived vehicle;
according to the first sensing information, taking over the driving control authority of the vehicle corresponding to the unique number;
when the number of the controlled vehicles which are not divided into batches currently reaches a set number, the controlled vehicles with the set number are divided into Nth batches, wherein N is a positive integer.
3. The system of claim 2, wherein after the central processing device takes over the driving control right of the vehicle corresponding to the unique number, the system is further configured to:
and adjusting the speed of the controlled vehicle newly entering the driving takeover area to be consistent with the speed of the previous vehicle.
4. The automated intersection management system based on a signal-free intersection according to claim 3, wherein the central processing device is further configured to:
obtaining the relative position relation of each vehicle of the Nth batch, and predicting each vehicle of the Nth batch at t based on the relative position relation0Formation configuration of time components, wherein t0The time is the time when the head car in the Nth batch reaches the starting point position of the second stage;
each vehicle based on Nth batch at t0The formation configuration at the moment generates a coordinated driving track of each vehicle of the Nth batch in the second stage, wherein when each vehicle of the Nth batch reaches the end position of the second stage based on the coordinated driving track, each vehicleThe speed of the vehicles is set speed, and the time when the Nth batch of tail vehicles reaches the end position of the second stage is t0+tstage2。
5. The automated intersection management system based on a signal-free intersection according to claim 4, wherein the central processing device is further configured to:
calling the driving track of the batch of vehicles (N-1, N-2, …, 1) which are still located in the driving takeover area and recorded in the database;
and based on the trajectories of the vehicles of the Nth batch 1, N-2, …, 1 and the respective vehicles of the Nth batch at t0The formation configuration of the time, and the time t when the head vehicle of the Nth batch reaches the starting point position of the second stage is determined0；
Based on the time t0N-1, N-2, …, the trajectory of the vehicle of batch 1, and the individual vehicles of batch N at t0And determining the driving track of each vehicle of the Nth batch in the first stage by the formation configuration at the moment, wherein the speed of each vehicle of the Nth batch is synchronously regulated in the first stage.
6. The automated intersection management system based on a signal-free intersection according to claim 5, wherein the central processing device is further configured to:
and determining the driving track of each vehicle of the Nth batch in the third stage based on the set constant-speed straight-line driving rule and the time when each vehicle of the Nth batch reaches the end position of the second stage based on the running of the cooperative driving track.
7. The automated intersection management system based on a signal-free intersection according to claim 6, wherein the central processing device is further configured to:
sequentially integrating the driving tracks of the vehicles of the Nth batch in the first stage, the cooperative driving track of the second stage and the driving track of the third stage to obtain the controlled driving tracks of the vehicles of the Nth batch;
the controlled trajectories of the vehicles of the nth lot are stored in a database.
8. The automated intersection management system based on a signal-free intersection according to claim 2, wherein the central processing device is further configured to:
receiving second perception information sent by any one perception unit, wherein the second perception information is generated when the perception unit perceives that the vehicle exits from the driving takeover area, and the second perception information contains a unique number of the perceived vehicle;
returning the driving control authority of the vehicle corresponding to the unique number according to the second perception information;
judging whether a batch to be eliminated exists at present, wherein the batch to be eliminated represents that the driving control authority of each vehicle of the batch is returned;
if so, eliminating the batch number of the to-be-eliminated batch, and reducing the numbers of all the current remaining batches by one respectively.
9. The automatic intersection management system based on the signal-free intersection as claimed in claim 4, wherein the set number is 5-15, tstage2Is 10 to 20 seconds.
10. An autonomous intersection management method based on a signal-free intersection is applied to a central processing device in the autonomous intersection management system based on the signal-free intersection, which is described in any one of claims 1 to 9, and the method comprises the following steps:
taking over the driving control authority of the vehicle entering the driving taking-over area, and returning the driving control authority of the vehicle exiting the driving taking-over area;
and dividing the vehicles driving into the driving takeover area in batches, controlling each vehicle in the same batch to keep the vehicles going ahead straight in the current lane in the first stage, cooperatively driving through the signal lamp-free intersection in the second stage, and keeping constant-speed straight running in the third stage.
CN202110764024.4A 2021-07-06 2021-07-06 Autonomous intersection management system and method based on signal lamp-free intersection Active CN113450570B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110764024.4A CN113450570B (en) 2021-07-06 2021-07-06 Autonomous intersection management system and method based on signal lamp-free intersection

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110764024.4A CN113450570B (en) 2021-07-06 2021-07-06 Autonomous intersection management system and method based on signal lamp-free intersection

Publications (2)

Publication Number Publication Date
CN113450570A true CN113450570A (en) 2021-09-28
CN113450570B CN113450570B (en) 2022-04-12

Family

ID=77815617

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110764024.4A Active CN113450570B (en) 2021-07-06 2021-07-06 Autonomous intersection management system and method based on signal lamp-free intersection

Country Status (1)

Country Link
CN (1) CN113450570B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113870569A (en) * 2021-12-01 2021-12-31 华砺智行(武汉)科技有限公司 Intelligent networking vehicle no-signal intersection passing coordination method and system
CN115662157A (en) * 2022-10-28 2023-01-31 东风汽车集团股份有限公司 V2X-based intersection vehicle passing control method, device, equipment and medium
CN116519004A (en) * 2023-06-30 2023-08-01 福思(杭州)智能科技有限公司 Vehicle track planning method and device, storage medium and electronic equipment

Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
UA101064U (en) * 2015-03-02 2015-08-25 Харківський Національний Автомобільно-Дорожній Університет Method for the determination of traffic capacity of controlled road intersection
CN105139677A (en) * 2015-07-28 2015-12-09 苏州大学张家港工业技术研究院 Uncontrolled intersection vehicle passing guiding system based on cooperative vehicle infrastructure and guiding method thereof
CN106781435A (en) * 2016-12-15 2017-05-31 清华大学 A kind of Fei Xinkong intersections platooning passing method based on radio communication
CN106875710A (en) * 2017-01-24 2017-06-20 同济大学 A kind of intersection self-organization control method towards net connection automatic driving vehicle
CN107038863A (en) * 2017-05-17 2017-08-11 东南大学 A kind of urban road network broad sense right of way computational methods for considering comprehensive traffic management measure
CN107452218A (en) * 2017-09-22 2017-12-08 西北工业大学 A kind of intersection centralized scheduling method that more unmanned vehicles are formed into columns
CN111785062A (en) * 2020-04-01 2020-10-16 北京京东乾石科技有限公司 Method and device for realizing vehicle-road cooperation at signal lamp-free intersection
CN112185132A (en) * 2020-09-08 2021-01-05 大连理工大学 Coordination method for vehicle intersection without traffic light
CN112258875A (en) * 2020-10-26 2021-01-22 青岛理工大学 Intersection intelligent control method based on vehicle-road cooperation and automatic driving
CN112562371A (en) * 2020-11-02 2021-03-26 河海大学 Lightweight scheduling method based on automatic driving motorcade at signal lamp-free intersection
CN112967514A (en) * 2020-11-20 2021-06-15 安徽海博智能科技有限责任公司 Distributed control method and system for efficient running of intelligent vehicle at intersection without signal lamp
CN113012450A (en) * 2021-02-24 2021-06-22 清华大学 No-signal-lamp intersection intelligent vehicle passing decision method based on constraint tree

Patent Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
UA101064U (en) * 2015-03-02 2015-08-25 Харківський Національний Автомобільно-Дорожній Університет Method for the determination of traffic capacity of controlled road intersection
CN105139677A (en) * 2015-07-28 2015-12-09 苏州大学张家港工业技术研究院 Uncontrolled intersection vehicle passing guiding system based on cooperative vehicle infrastructure and guiding method thereof
CN106781435A (en) * 2016-12-15 2017-05-31 清华大学 A kind of Fei Xinkong intersections platooning passing method based on radio communication
CN106875710A (en) * 2017-01-24 2017-06-20 同济大学 A kind of intersection self-organization control method towards net connection automatic driving vehicle
CN107038863A (en) * 2017-05-17 2017-08-11 东南大学 A kind of urban road network broad sense right of way computational methods for considering comprehensive traffic management measure
CN107452218A (en) * 2017-09-22 2017-12-08 西北工业大学 A kind of intersection centralized scheduling method that more unmanned vehicles are formed into columns
CN111785062A (en) * 2020-04-01 2020-10-16 北京京东乾石科技有限公司 Method and device for realizing vehicle-road cooperation at signal lamp-free intersection
CN112185132A (en) * 2020-09-08 2021-01-05 大连理工大学 Coordination method for vehicle intersection without traffic light
CN112258875A (en) * 2020-10-26 2021-01-22 青岛理工大学 Intersection intelligent control method based on vehicle-road cooperation and automatic driving
CN112562371A (en) * 2020-11-02 2021-03-26 河海大学 Lightweight scheduling method based on automatic driving motorcade at signal lamp-free intersection
CN112967514A (en) * 2020-11-20 2021-06-15 安徽海博智能科技有限责任公司 Distributed control method and system for efficient running of intelligent vehicle at intersection without signal lamp
CN113012450A (en) * 2021-02-24 2021-06-22 清华大学 No-signal-lamp intersection intelligent vehicle passing decision method based on constraint tree

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
CHUNHUA HONG 等: "A Joint Design of Platoon Communication and Control Based on LTE-V2V", 《IEEE》 *
DIVYA DESIRAJU 等: "Minimizing the Disruption of Traffic Flow of Automated Vehicles During Lane Changes", 《IEEE》 *
刘天天 等: "智能网联环境下交叉口混行车队通行模型构建", 《交通运输研究》 *
吴官朴 等: "生态驾驶在智能网联汽车中的应用综述", 《汽车文摘》 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113870569A (en) * 2021-12-01 2021-12-31 华砺智行(武汉)科技有限公司 Intelligent networking vehicle no-signal intersection passing coordination method and system
CN115662157A (en) * 2022-10-28 2023-01-31 东风汽车集团股份有限公司 V2X-based intersection vehicle passing control method, device, equipment and medium
CN116519004A (en) * 2023-06-30 2023-08-01 福思(杭州)智能科技有限公司 Vehicle track planning method and device, storage medium and electronic equipment

Also Published As

Publication number Publication date
CN113450570B (en) 2022-04-12

Similar Documents

Publication Publication Date Title
CN113450570B (en) Autonomous intersection management system and method based on signal lamp-free intersection
CN110298122B (en) Unmanned vehicle urban intersection left-turn decision-making method based on conflict resolution
US10399564B2 (en) Vehicle roundabout management
JP2022523886A (en) Joint control of vehicles traveling on different crossroads
JP6308233B2 (en) Vehicle control apparatus and vehicle control method
Varaiya et al. Sketch of an IVHS systems architecture
Kumaravel et al. Optimal coordination of platoons of connected and automated vehicles at signal-free intersections
CN112193244B (en) Automatic driving vehicle motion planning method based on linear constraint
Raravi et al. Merge algorithms for intelligent vehicles
CN111325967B (en) Intelligent networking automobile formation control method and device based on cooperative assignment
CN109410619A (en) A kind of control method and system for automatic driving vehicle
CN113554886B (en) Traffic flow conflict resolution method for cooperative intersection of vehicle and road
CN111422191A (en) Automatic driving control system and method and electronic equipment
CN112046484A (en) Q learning-based vehicle lane-changing overtaking path planning method
Zhang et al. A trajectory optimization-based intersection coordination framework for cooperative autonomous vehicles
CN115050183B (en) Method for generating simulated traffic flow
Ding et al. Trajectory planning for automated lane-change on a curved road for collision avoidance
Zhang et al. Virtual traffic signals: Safe, rapid, efficient and autonomous driving without traffic control
US20220340177A1 (en) Systems and methods for cooperative driving of connected autonomous vehicles in smart cities using responsibility-sensitive safety rules
Khayatian et al. Cooperative driving of connected autonomous vehicles using responsibility-sensitive safety (RSS) rules
Zhang et al. Unified modeling and design of reservation-based cooperation mechanisms for intelligent vehicles
Ji et al. Tram-oriented traffic signal timing resynchronization
Yamamoto et al. Simulation Evaluation of Vehicle Movement Model Using Spatio-Temporal Grid Reservation for Automated Valet Parking
Wu et al. Cooperative U-turn merging behaviors and their impacts on road traffic in CVIS environment
Huang et al. Automated turning and merging for autonomous vehicles using a Nonlinear Model Predictive Control approach

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