CN116434524A - Unmanned system, method and vehicle for hybrid traffic flow down-road side perception cloud planning - Google Patents
Unmanned system, method and vehicle for hybrid traffic flow down-road side perception cloud planning Download PDFInfo
- Publication number
- CN116434524A CN116434524A CN202211528633.0A CN202211528633A CN116434524A CN 116434524 A CN116434524 A CN 116434524A CN 202211528633 A CN202211528633 A CN 202211528633A CN 116434524 A CN116434524 A CN 116434524A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- road
- planning
- decision
- unmanned
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 230000008447 perception Effects 0.000 title claims abstract description 26
- 238000004891 communication Methods 0.000 claims abstract description 109
- 230000004927 fusion Effects 0.000 claims abstract description 11
- 230000007246 mechanism Effects 0.000 claims abstract description 10
- 238000004364 calculation method Methods 0.000 claims abstract description 7
- 230000010365 information processing Effects 0.000 claims abstract description 5
- 230000003993 interaction Effects 0.000 claims description 14
- 230000008569 process Effects 0.000 claims description 14
- 238000007499 fusion processing Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 238000013178 mathematical model Methods 0.000 claims description 3
- 230000002618 waking effect Effects 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 4
- 206010039203 Road traffic accident Diseases 0.000 description 3
- 238000005265 energy consumption Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000002910 structure generation Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/02—Ensuring safety in case of control system failures, e.g. by diagnosing, circumventing or fixing failures
- B60W50/035—Bringing the control units into a predefined state, e.g. giving priority to particular actuators
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/02—Ensuring safety in case of control system failures, e.g. by diagnosing, circumventing or fixing failures
- B60W50/029—Adapting to failures or work around with other constraints, e.g. circumvention by avoiding use of failed parts
-
- 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
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/0967—Systems involving transmission of highway information, e.g. weather, speed limits
- G08G1/096708—Systems involving transmission of highway information, e.g. weather, speed limits where the received information might be used to generate an automatic action on the vehicle control
- G08G1/096725—Systems involving transmission of highway information, e.g. weather, speed limits where the received information might be used to generate an automatic action on the vehicle control where the received information generates an automatic action on the vehicle control
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/02—Ensuring safety in case of control system failures, e.g. by diagnosing, circumventing or fixing failures
- B60W50/029—Adapting to failures or work around with other constraints, e.g. circumvention by avoiding use of failed parts
- B60W2050/0292—Fail-safe or redundant systems, e.g. limp-home or backup systems
Abstract
The invention discloses an unmanned system for hybrid traffic flow roadside perception cloud planning, which comprises unmanned vehicles, roadside intelligent infrastructure and a decision planning cloud platform; the unmanned vehicle comprises a positioning module, a vehicle-mounted network communication terminal and a drive-by-wire chassis; the road side intelligent infrastructure comprises a radar, a camera, a road traffic sign, a traffic signal lamp, an environment information fusion calculation module and a road side communication module; the decision planning cloud platform comprises an information storage module, an information processing module and a cloud communication module; the perception system is planned to the road section in a unified way, and the decision planning system is arranged at the cloud end, so that the sharing of the perception sensor and the computing unit is realized, and the cost of the unmanned automobile is reduced; the communication safety redundancy mechanism, the network connection switching method and the signal interruption avoiding mechanism are provided; the reliability and the safety of the unmanned system are effectively improved.
Description
Technical Field
The invention belongs to the field of unmanned vehicles, and particularly relates to an unmanned system and method for hybrid traffic flow road side perception cloud planning.
Background
Along with the continuous increase of the automobile usage amount, traffic congestion often occurs to reduce the travel efficiency of users, so that drivers often encounter the situation of mutually robbing the road in the driving process to further cause serious traffic accidents. The vehicle-road cooperation and cloud computing technology realizes vehicle-vehicle, vehicle-road, vehicle cloud and road cloud dynamic real-time information interaction in an omnibearing manner, and develops vehicle active safety control and road cooperation management on the basis of full-time empty dynamic traffic information acquisition and fusion, so that effective cooperation of people and vehicles and roads is fully realized, traffic safety is ensured, traffic efficiency is improved, and a safer, efficient and environment-friendly active safety system is formed.
An unmanned vehicle is a vehicle that can dynamically and autonomously avoid a series of obstacles in the environment during driving without relying on conscious decisions of humans. The vehicle relies on the vehicle-mounted sensor to finish sensing detection of surrounding environment, generate map data, vehicle position and obstacle information, realize autonomous control according to information integration, plan an optimal driving path, and meanwhile make identification sensing to various traffic identifications by means of artificial intelligence, so that an optimal driving decision is selected, driving tasks of the vehicle are finished in a highly intelligent mode, accident occurrence rate is reduced, and driving efficiency is improved. However, the high cost of the sensors and the computing units seriously hinders the popularization of the unmanned vehicle, and how to reduce the hardware cost of the unmanned bicycle becomes the most needed problem in the current unmanned industry.
Disclosure of Invention
In order to solve the problems, the invention provides an unmanned system and a method for hybrid traffic flow down-road side perception cloud planning.
Aiming at the defects or improvement demands of the prior art, the invention relates to an unmanned system for mixed traffic flow down-road side perception cloud planning, which comprises an unmanned vehicle, a road side intelligent infrastructure arranged on a road section and a decision-making planning cloud platform arranged on the cloud;
the unmanned vehicle comprises a positioning module for acquiring positioning and attitude information, a vehicle-mounted network communication terminal for data interaction and control of the drive-by-wire chassis and the drive-by-wire chassis;
the road side intelligent infrastructure comprises an information sensing module for sensing road traffic environment information, an environment information fusion calculation module for fusion processing the sensing information and a data interaction road side communication module for carrying out data interaction with vehicles in a communication range and a decision planning cloud platform;
the decision planning cloud platform comprises an information storage module for storing road traffic environment information and vehicle state information, a processing module for planning path information and updating the road traffic environment information, and a data interaction cloud communication module for a road side intelligent infrastructure and an unmanned vehicle;
the system comprises a drive-by-wire chassis, a vehicle-mounted network communication terminal, a positioning module, a decision-making planning cloud platform, a road side intelligent foundation facility and a vehicle-mounted network communication terminal, wherein the drive-by-wire chassis is connected with the vehicle-mounted network communication terminal, one output end of the drive-by-wire chassis is connected with one input end of the positioning module, one output end of the positioning module is connected with one input end of the vehicle-mounted network communication terminal, the decision-making planning cloud platform is connected with the vehicle-mounted network communication terminal through 5G communication, and the road side intelligent foundation facility is connected with the vehicle-mounted network communication terminal through PC5 communication; and the decision planning cloud platform is connected with the vehicle-mounted network communication terminal through a hard wire or 5G communication.
Further, the positioning module acquires the position information and the driving gesture information of the vehicle and sends the information to the vehicle-mounted network communication terminal, and the vehicle-mounted network communication terminal is used for carrying out data interaction on unmanned vehicles, other vehicles, road side intelligent infrastructures and decision planning cloud platforms and CAN control the drive-by-wire chassis through the CAN bus.
Further, the information sensing module senses road traffic environment information within the intelligent infrastructure range of the road side and sends the sensed information to the environment information fusion calculation module for fusion processing; the environment information fusion calculation module is used for processing the road traffic environment information perceived by the radar and the camera and sending the road traffic environment information to the road side communication module.
Further, the information storage module records and stores road traffic environment information uploaded by the intelligent road side infrastructure and state information uploaded by the vehicle; the information processing module plans a global driving path and a local driving path of the unmanned vehicle under the mixed traffic flow, and builds a mathematical model to dynamically update road traffic environment information recorded in the information storage module.
As another aspect of the present invention, an unmanned method for hybrid traffic flow roadside awareness cloud planning is further related, comprising the following steps:
step one: starting a vehicle unmanned mode, and connecting the vehicle-mounted network communication terminal with the decision-making planning cloud platform to match user information; meanwhile, sending a signal of successful access to the vehicle-mounted network connection terminal and the road side intelligent infrastructure;
step two: after the connection is successful, the vehicle enters a self-checking mode, and whether all systems of the vehicle work normally or not is checked, and whether the connection between the network communication terminal and the decision planning cloud platform is stable or not is checked;
step three: after the self-checking mode is finished, reminding a user of inputting a destination address, and after the user inputs the address and confirms, transmitting basic state information and running state information of the vehicle to a decision planning cloud platform by a vehicle-mounted network communication terminal;
step four: after the intelligent infrastructure on the road side is built, connection is established with a decision-making planning cloud platform, and the decision-making planning cloud platform plans the global path of the vehicle according to the position information and the destination address of the unmanned vehicle at the current moment according to whether the condition of the path fully covered by the intelligent infrastructure on the road side exists;
step five: the decision-making planning cloud platform takes a 5G communication mode as a main priority, and transmits a control signal to a vehicle-mounted network communication terminal to control an unmanned vehicle in a mode of forwarding the control signal to a secondary priority through a road side intelligent infrastructure;
step six: in the running process of the vehicle, the control signal is prevented from being lost in a short time through the cooperation of the decision-making cloud platform and a plurality of road side intelligent infrastructures to be experienced by the running path of the vehicle;
step seven: in the running process of the vehicle, safety is ensured through a safety redundant braking mechanism, namely, if a special accident occurs, the vehicle-mounted network terminal controls the drive-by-wire chassis to stop by-edge; otherwise, executing the rest driving tasks.
Further, the specific method of the fourth step is as follows: the decision-making planning cloud platform finds out all possible paths between the position information of the unmanned vehicle at the current moment and the destination address as a path information total set B (x), and screens all road side intelligent infrastructures covered by the information set paths in the B (x) and wakes up the intelligent infrastructures, and the road side intelligent infrastructures upload real-time traffic environment information in the perception range of the intelligent infrastructures; and then selecting a path information set which is fully covered by the intelligent infrastructure at the road side: b (B) 1 (x) = {1, 2, …, n }, if there is no path fully covered by the intelligent infrastructure on the road side, the decision cloud platform controls the vehicle to travel to the intelligent infrastructure on the road side by remote driving and then resumes to the unmanned mode to execute the subsequent travel task, or reminds the passenger to drive the vehicle to travel to the infrastructure coverage and then resume to the unmanned mode to execute the subsequent travel task; then the cloud platform is planned by decision at B 1 (x) And remotely controlling the unmanned vehicle to execute the running task according to the optimal global path.
Further, the method for determining the optimal global path comprises the following steps: the decision planning cloud platform segments all planned global paths according to the user demands and calculates the time cost f required to be paid by passing through the nth road in the paths n (n), i.e. the total time cost of the nth travel path is D (n) =f n (1)+f n (2)+…+f n (n), the path with the smallest D (n) value is the optimal global path.
Further, in a road through which no unmanned vehicle passes, the intelligent infrastructure on the road is in a dormant state, and when the unmanned vehicle passes through the road, the intelligent infrastructure on the road section is awakened.
Further, the calculated nth road of the nth driving path requires a time to payValence f n And (n) calculating according to the predicted road environment information when the vehicle runs to the road, wherein the predicted road traffic environment information is obtained by collecting the traffic flow of the road and the traffic environment information in real time by the decision planning cloud platform.
Further, the method in the fifth step specifically comprises the following steps: the control signal of the decision cloud platform can also be forwarded to the vehicle-mounted network communication terminal through the road side intelligent infrastructure; and after the route planning is completed to select an optimal driving route, the decision-making cloud platform numbers the IP address or other unique marks of the intelligent road-side infrastructure of the route according to the passing sequence of vehicles, then forms a set of intelligent road-side infrastructure information D (x) to be sent to the communication terminal of the vehicle-mounted network, when 5G communication is normal, the received control signal of the decision-making cloud platform is executed, and when the control signal of the decision-making cloud platform is not received within a preset time delta T, the control signal sent by the intelligent road-side infrastructure is executed.
Further, in the sixth step, the method for avoiding the loss of the control signal in a short time by matching the decision-making cloud platform with a plurality of intelligent infrastructures on the road side to be experienced by the vehicle driving path comprises the following steps: because the communication distance of the intelligent infrastructure on the road side is limited, the vehicle can drive away from the coverage area of the intelligent infrastructure on the road side in the running process of the vehicle, in order to avoid the loss of control signals in a short time caused by the frequency conversion switching of the intelligent infrastructure on the road side connected with the communication terminal on the vehicle, the decision cloud platform can send the control signals to a plurality of intelligent infrastructures on the road side, which are about to be experienced, of the running path of the vehicle, the intelligent infrastructures on the road side continuously broadcast the control signals sent by the decision cloud platform, in the whole running process, the communication terminal on the vehicle can receive the control signals sent by the decision cloud platform, when the vehicle runs away from the intelligent infrastructures on the road side, the decision planning cloud platform recognizes according to the position of the vehicle, then controls the intelligent infrastructures on the road side to stop sending the control signals, and if no other unmanned vehicle passes through the intelligent infrastructures on the road side, the decision cloud platform is sent with sleep signals so as to reduce the energy consumption of the system and improve the service life of the system.
Further, the safety redundant braking mechanism in the step seven is as follows: when a special accident occurs, the vehicle-mounted network connection terminal controls the drive-by-wire chassis to stop by side, the vehicle-mounted network connection terminal acquires the transverse distance between the vehicle and the roadside at the moment, the information road side intelligent infrastructure monitors the transverse distance signal in real time through a sensor carried by the vehicle-mounted network connection terminal, and then the information road side intelligent infrastructure broadcasts the transverse distance signal to the vehicle-mounted network connection communication terminal along with a control signal of a forwarding decision planning cloud platform.
As another aspect of the present invention, a vehicle includes the unmanned system for hybrid traffic flow roadside awareness cloud planning described above.
In general, the above technical solutions conceived by the present invention, compared with the prior art, enable the following beneficial effects to be obtained:
(1) According to the unmanned system and the unmanned method for the mixed traffic flow road side perception cloud planning, the 5G communication, the vehicle-road cooperation and the cloud computing technology are utilized to uniformly plan the perception system to the road section, the decision planning system is arranged on the cloud, so that the perception sensor and the computing unit are shared, and the problem that the popularization of unmanned vehicles is seriously hindered due to high sensor and computing unit cost is solved;
(2) According to the unmanned system and the unmanned method for the mixed traffic flow road side perception cloud planning, two communication modes of 5G wireless communication and PC5 wireless communication are adopted to send control signals, a communication safety redundancy mechanism which takes the 5G communication mode as a main priority and forwards the communication safety redundancy mechanism as a secondary priority through a road side intelligent infrastructure is added, and a corresponding network switching method is provided; the unmanned vehicle traffic accident caused by the network communication quality is effectively avoided;
(3) According to the unmanned system and the unmanned method for the hybrid traffic flow road side perception cloud planning, the control signals are prevented from being interrupted due to the fact that the coverage distance of the road side intelligent infrastructure is limited through the cooperation of the decision cloud platform and the plurality of road side intelligent infrastructures to be experienced by the vehicle driving path, and the reliability of the system is improved;
(4) According to the unmanned system and the unmanned method for the hybrid traffic flow road side perception cloud planning, safety of an unmanned vehicle is guaranteed through a safety redundant braking mechanism.
Drawings
FIG. 1 is a schematic diagram of an unmanned system architecture for hybrid traffic flow roadside awareness cloud planning in accordance with a preferred embodiment of the present invention;
FIG. 2 is a schematic illustration of unmanned vehicle-decision-making cloud platform communication according to a preferred embodiment of the present invention;
FIG. 3 is a schematic diagram illustrating the management of a road side intelligent infrastructure (RSU) by a decision-making cloud platform according to a preferred embodiment of the present invention;
fig. 4 is a schematic diagram of a tree structure generation process of an RRT algorithm according to a preferred embodiment of the present invention;
fig. 5 is a schematic diagram illustrating connection between a vehicle-mounted network communication terminal and a roadside intelligent infrastructure according to a preferred embodiment of the present invention;
fig. 6 is a schematic diagram of a decision-making cloud platform for managing communication terminals of a vehicle-mounted network and intelligent infrastructure on a road side according to a preferred embodiment of the present invention;
FIG. 7 is a schematic illustration of a temporary side parking of a vehicle under a safety redundancy scheme in accordance with a preferred embodiment of the present invention;
fig. 8 is a logic flow diagram of the whole driving logic of an unmanned vehicle with a hybrid traffic flow roadside awareness cloud planning according to a preferred embodiment of the present invention;
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention. In addition, the technical features of the embodiments of the present invention described below may be combined with each other as long as they do not collide with each other.
Example 1:
please refer to fig. 1. The embodiment relates to an unmanned system for hybrid traffic flow Road Side perception cloud planning, which comprises three parts, namely an unmanned vehicle, a Road Side intelligent infrastructure (RSU) and a decision planning cloud platform (Central Service Unit, CSU, also called a central service Unit).
The unmanned vehicle comprises a positioning module, an On Board Unit (OBU) and a drive-by-wire chassis, wherein the positioning module is used for acquiring the position information and the driving gesture information of the vehicle and sending the information to the On Board Unit, the On Board Unit is used for carrying out data interaction On unmanned vehicles, other vehicles, road side intelligent infrastructures and decision planning cloud platforms, the drive-by-wire chassis CAN be controlled through a CAN bus, the drive-by-wire chassis CAN control driving, gear, braking, steering, parking and necessary indicator lights of the vehicle, and the vehicle CAN give correct and timely state feedback. The road side intelligent infrastructure comprises an information sensing module (such as a radar and a camera), an environment information fusion computing module and a communication module, wherein the radar and the camera are used for sensing road traffic environment information within a certain range of the road side intelligent infrastructure and sending the sensed information to the environment information fusion computing module for fusion processing, the environment information fusion computing module is used for processing the road traffic environment information sensed by the radar and the camera and sending the road traffic environment information to the communication module, and the communication module is used for carrying out data interaction with vehicles within a communication range and a decision planning cloud platform. The road side intelligent infrastructure can also comprise road traffic signs, the road traffic signs refer to speed limit or early warning signs, the road traffic signs are used for reminding drivers of driving the non-network-connected functional vehicles under the mixed traffic flow, the traffic signal lamps are used for reminding drivers of driving the non-network-connected functional vehicles under the mixed traffic flow,
the decision-making planning cloud platform comprises an information storage module, an information processing module and a communication module, wherein the information storage module is used for recording and storing road traffic environment information uploaded by the intelligent infrastructure of the road side and state information uploaded by the vehicle, the information processing module is used for planning a global driving path and a local driving path of the unmanned vehicle under mixed traffic and constructing a mathematical model to dynamically update the road traffic environment information recorded in the information storage module, and the communication module is used for carrying out data interaction with the intelligent infrastructure of the road side and the unmanned vehicle.
The system comprises a drive-by-wire chassis, a vehicle-mounted network communication terminal, a positioning module, a decision-making cloud platform, a road side intelligent foundation facility and a PC5 communication connection, wherein the drive-by-wire chassis is connected with the vehicle-mounted network communication terminal (for example, through a CAN interface), one output end of the drive-by-wire chassis is connected with one input end of the positioning module, one output end of the positioning module is connected with one input end of the vehicle-mounted network communication terminal, the decision-making cloud platform is connected with the vehicle-mounted network communication terminal through 5G communication, and the road side intelligent foundation facility is connected with the vehicle-mounted network communication terminal through the PC5 communication connection; and the decision planning cloud platform is connected with the vehicle-mounted network communication terminal through a hard wire or 5G communication.
Based on the system, the embodiment also relates to an unmanned method for hybrid traffic flow roadside perception cloud planning, which specifically comprises the following five stages.
Referring to fig. 2, a vehicle unmanned mode is started in a first stage, an on-board network communication terminal OBU applies for establishing connection with a decision-making cloud platform, sends a user unique identity ID/password to the decision-making cloud platform CSU, the decision-making cloud platform CSU performs database matching on received user information, the decision-making cloud platform creates session information (session) of the user after the matching is successful, simultaneously sends a signal of successful access to the on-board network communication terminal, the vehicle enters a self-checking mode after the connection is successful, checks whether each system of the vehicle works normally, whether the connection between the network communication terminal and the decision-making cloud platform is stable (whether communication quality is good), reminds the user of inputting a destination address after the self-checking is finished, and the on-board network communication terminal sends basic state information and running state information of the vehicle to the decision-making cloud platform after the user inputs the address and confirms.
Referring to fig. 3, the second stage decision-making cloud platform finds all possible paths between the location information of the unmanned vehicle at the current moment and the destination address as a path information aggregate B (x), screens all the intelligent infrastructures of the road side covered by the information aggregate paths in B (x) and wakes up the intelligent infrastructures, and after the intelligent infrastructures of the road side are built, the connection is established with the decision-making cloud platform in such a way that firstly, a unique identity ID/password of a user is sent to the decision-making cloud platform, the decision-making cloud platform performs database matching on the received RSU information, and after the matching is successful, the decision-making cloud platform creates session information of the intelligent infrastructures of the road side and sends a signal of successful access to the intelligent infrastructures of the road side.
In order to reduce the energy consumption of the system and increase the service life of the system, the intelligent infrastructure of the road section is usually in a dormant state when no unmanned vehicle passes through the road section, and the intelligent infrastructure of the road section is awakened when the unmanned vehicle passes through the road section,
the intelligent infrastructure at the road side uploads the real-time traffic environment information within the perception range. Selecting a path information set B fully covered by a road side intelligent infrastructure 1 (x) If no path fully covered by the intelligent infrastructure on the road side exists, the decision cloud platform controls the vehicle to travel to the intelligent infrastructure on the road side through a remote driving mode and then resumes to the unmanned mode to execute the subsequent travel task, or reminds the passenger to drive the vehicle to travel to the infrastructure coverage and then resume to the unmanned mode to execute the subsequent travel task. The decision planning cloud platform segments all planned global paths according to the user demands and calculates the time cost f required to be paid by each section of road in the paths n (n) the time cost f required to be paid by the nth road of the nth travel path calculated by the scheme n (n) not based on the road environment information at the time of system planning but based on the predicted road environment information when the vehicle is driving to the road, the predicted road traffic environment information is summarized by the decision-making cloud platform collecting the traffic flow of the road and traffic environment information in real time, and some objective factors affecting the traffic environment (including but not limited to weatherFactors such as whether to get on or off duty, season, whether traffic accidents exist, holidays and the like) are considered, so that the prediction accuracy is further ensured, namely the total time cost of the nth driving path is D (n) =f n (1)+f n (2)+…+f n And (n), the path with the minimum D (n) value is the optimal global path, and then the decision-making cloud platform remotely controls the unmanned vehicle to execute the running task according to the path.
Referring to fig. 4, as a preferred scheme: the above-mentioned finding out all possible paths between the location information and the destination address of the current moment of the unmanned vehicle and finding out the optimal global path can all adopt a fast-expansion random tree algorithm, the fast-expansion random tree (RRT) algorithm continuously builds a tree search structure to unexplored blank areas in a multidimensional space according to a random increment mode, the vertex of each tree structure is a state node, and a line segment between two adjacent nodes represents the connection process between the current state node and the last state node.
FIG. 4 is a tree structure generation process of RRT algorithm, which first defines a global path planning task space
n represents the spatial dimension. The task space can be divided into a space where an obstacle exists +.>
Blank area
Let the initial status point of the environment be +.>
The target point is->
There are obstacles in the environment (black areas in fig. 4).
Let P be start Algorithm for root node of whole tree structureGenerating a random point P at random position in unexplored region rand In P rand In the center, performing traversal search on all nodes on the tree structure, and calculating the nodes and P rand The Euclidean distances among the nodes are ordered, and the node P with the smallest distance is selected near As the nearest node.
Let the slave P near Point to P rand The direction of the point is the growth direction of the tree structure, and the search tree is led to be in the P direction by setting the growth step length (marked as l) of the algorithm near The points grow a certain distance along the growth direction (the value of l is required to be selected through a test), the algorithm can 'cross over' an obstacle with smaller cross section due to the overlarge growth step length, the traversal searching capability of the algorithm is weakened due to the fact that the step length is too short, the algorithm planning efficiency is reduced), and the next node on the tree structure is obtained and is marked as P 1 . Judging P 1 If the random point sampling search is within the range of the obstacle, eliminating the node if the random point sampling search collides with the obstacle; if no collision occurs, P is 1 Points are added to the tree. The algorithm is iterated until the newly generated node reaches the target position or the distance between the newly generated node and the target point is smaller than a unit of growth step length l, which indicates that the searching process is finished, and the algorithm sequentially backtracks a series of father nodes from the target point to obtain a final path.
Referring to fig. 5, in the third stage, the decision-making cloud platform CSU sends the control signal to the vehicle-mounted network communication terminal OBU to perform unmanned vehicle control, so as to avoid the problem that the unmanned vehicle collides out of control due to delay or loss of the control signal caused by fluctuation of the 5G signal, and the control signal of the decision-making cloud platform can also be forwarded to the vehicle-mounted network communication terminal through the intelligent infrastructure at the road side. In order to ensure the communication safety of the whole communication link, the link between the vehicle-mounted network communication terminal and the road side intelligent infrastructure is controlled by a decision cloud platform in an overall mode, after the optimal driving path is selected by path planning, the decision cloud platform numbers the IP address or other unique marks of the road side intelligent infrastructure of the path according to the passing sequence of vehicles, then a road side intelligent infrastructure information set D (x) is formed and sent to the vehicle-mounted network communication terminal, when 5G communication is normal, a received decision cloud platform control signal is executed, and when a control signal of the decision cloud platform is not received at a certain time delta T, a control signal sent by the road side intelligent infrastructure is executed.
Referring to fig. 6, in the fourth stage, when a vehicle is executing a control signal sent by a road side intelligent infrastructure, because the communication distance of the road side intelligent infrastructure RSU is furthest limited (generally not more than 1000 meters), during the running process of the vehicle, an on-board network communication terminal OBU quickly drives away from the coverage area of a certain road side intelligent infrastructure, so as to avoid the loss of the control signal in a short time caused by the frequency switching of the road side intelligent infrastructure connected with the on-board network communication terminal.
Referring to fig. 7, in the fifth stage, in order to further ensure the driving safety of the unmanned vehicle, the vehicle joins in a safety redundant braking mechanism, and when a special accident occurs, the vehicle-mounted network connection terminal can control the drive-by-wire chassis to stop by side, so that the vehicle-mounted network connection terminal needs to acquire the lateral distance from the vehicle to the roadside at the moment, therefore, the information road side intelligent infrastructure can monitor in real time through the sensors carried by the information road side intelligent infrastructure, and then broadcast the control signals of the forwarding decision planning cloud platform to the vehicle-mounted network communication terminal together, when the communication terminal or other uncontrollable faults occur, the vehicle-mounted network communication terminal plans a driving path for the vehicle to the roadside, controls the vehicle to stop by side, and firstly turns on a dangerous alarm lamp and broadcasts outside before executing the stop by side task, so as to avoid collision with the vehicle which is about to pass through the road.
Example 2:
the embodiment 2 of the invention provides a vehicle, which comprises the unmanned system for the hybrid traffic flow roadside awareness cloud planning provided in the embodiment 1.
According to the technical scheme, technologies such as 5G communication, vehicle-road cooperation and cloud computing technology are fully utilized, a perception system is planned to a road section in a unified mode, a decision planning system is arranged on a cloud end, so that the perception sensor and a computing unit are shared, and the problem that the popularization of unmanned vehicles is seriously hindered due to high sensor and computing unit cost is solved.
It will be readily appreciated by those skilled in the art that the foregoing description is merely a preferred embodiment of the invention and is not intended to limit the invention, but any modifications, equivalents, improvements or alternatives falling within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (13)
1. The unmanned system for the hybrid traffic flow road side perception cloud planning is characterized by comprising an unmanned vehicle, a road side intelligent infrastructure arranged on a road section and a decision-making planning cloud platform arranged on the cloud;
the unmanned vehicle comprises a positioning module for acquiring positioning and attitude information, a vehicle-mounted network communication terminal for data interaction and control of the drive-by-wire chassis and the drive-by-wire chassis;
the road side intelligent infrastructure comprises an information sensing module for sensing road traffic environment information, an environment information fusion calculation module for fusion processing the sensing information and a data interaction road side communication module for carrying out data interaction with vehicles in a communication range and a decision planning cloud platform;
the decision planning cloud platform comprises an information storage module for storing road traffic environment information and vehicle state information, a processing module for planning path information and updating the road traffic environment information, and a data interaction cloud communication module for a road side intelligent infrastructure and an unmanned vehicle;
the system comprises a drive-by-wire chassis, a vehicle-mounted network communication terminal, a positioning module, a decision-making planning cloud platform, a road side intelligent foundation facility and a vehicle-mounted network communication terminal, wherein the drive-by-wire chassis is connected with the vehicle-mounted network communication terminal, one output end of the drive-by-wire chassis is connected with one input end of the positioning module, one output end of the positioning module is connected with one input end of the vehicle-mounted network communication terminal, the decision-making planning cloud platform is connected with the vehicle-mounted network communication terminal through 5G communication, and the road side intelligent foundation facility is connected with the vehicle-mounted network communication terminal through PC5 communication; and the decision planning cloud platform is connected with the vehicle-mounted network communication terminal through a hard wire or 5G communication.
2. The unmanned system for hybrid traffic flow roadside aware cloud planning according to claim 1, wherein the positioning module obtains own vehicle position information and driving posture information and sends the information to a vehicle-mounted network communication terminal, and the vehicle-mounted network communication terminal is used for data interaction of unmanned vehicles, other vehicles, roadside intelligent infrastructure and decision planning cloud platform, and controls a drive-by-wire chassis.
3. The unmanned system of the hybrid traffic flow roadside perception cloud planning of claim 1, wherein the information perception module perceives road traffic environment information within the roadside intelligent infrastructure range and sends the perceived information to the environment information fusion calculation module for fusion processing; the environment information fusion calculation module is used for processing the road traffic environment information perceived by the radar and the camera and sending the road traffic environment information to the road side communication module.
4. The unmanned system of hybrid traffic flow roadside aware cloud planning of claim 1, wherein the information storage module records and stores road traffic environment information uploaded by a roadside intelligent infrastructure and status information uploaded by a vehicle; the information processing module plans a global driving path and a local driving path of the unmanned vehicle under the mixed traffic flow, and builds a mathematical model to dynamically update road traffic environment information recorded in the information storage module.
5. An unmanned method for hybrid traffic flow roadside perception cloud planning is characterized by comprising the following steps:
step one: starting a vehicle unmanned mode, and connecting the vehicle-mounted network communication terminal with the decision-making planning cloud platform to match user information; meanwhile, sending a signal of successful access to the vehicle-mounted network connection terminal and the road side intelligent infrastructure;
step two: after the connection is successful, the vehicle enters a self-checking mode, and whether all systems of the vehicle work normally or not is checked, and whether the connection between the network communication terminal and the decision planning cloud platform is stable or not is checked;
step three: after the self-checking mode is finished, reminding a user of inputting a destination address, and after the user inputs the address and confirms, transmitting basic state information and running state information of the vehicle to a decision planning cloud platform by a vehicle-mounted network communication terminal;
step four: after the intelligent infrastructure on the road side is built, connection is established with a decision-making planning cloud platform, and the decision-making planning cloud platform plans the global path of the vehicle according to the position information and the destination address of the unmanned vehicle at the current moment according to whether the condition of the path fully covered by the intelligent infrastructure on the road side exists;
step five: the decision-making planning cloud platform takes a 5G communication mode as a main priority, and transmits a control signal to a vehicle-mounted network communication terminal to control an unmanned vehicle in a mode of forwarding the control signal to a secondary priority through a road side intelligent infrastructure;
step six: in the running process of the vehicle, the control signal is prevented from being lost in a short time through the cooperation of the decision-making cloud platform and a plurality of road side intelligent infrastructures to be experienced by the running path of the vehicle;
step seven: in the running process of the vehicle, safety is ensured through a safety redundant braking mechanism, namely, if a special accident occurs, the vehicle-mounted network terminal controls the drive-by-wire chassis to stop by-edge; otherwise, executing the rest driving tasks.
6. The unmanned method of hybrid traffic flow roadside aware cloud planning of claim 5, wherein: the fourth stepThe specific method comprises the following steps: the decision-making planning cloud platform finds out all possible paths between the position information of the unmanned vehicle at the current moment and the destination address as a path information total set B (x), and screens all road side intelligent infrastructures covered by the information set paths in the B (x) and wakes up the intelligent infrastructures, and the road side intelligent infrastructures upload real-time traffic environment information in the perception range of the intelligent infrastructures; and then selecting a path information set which is fully covered by the intelligent infrastructure at the road side: b (B) 1 (x) = {1, 2, …, n }, if there is no path fully covered by the intelligent infrastructure on the road side, the decision cloud platform controls the vehicle to travel to the intelligent infrastructure on the road side by remote driving and then resumes to the unmanned mode to execute the subsequent travel task, or reminds the passenger to drive the vehicle to travel to the infrastructure coverage and then resume to the unmanned mode to execute the subsequent travel task; then the cloud platform is planned by decision at B 1 (x) And remotely controlling the unmanned vehicle to execute the running task according to the optimal global path.
7. The unmanned method for hybrid traffic flow roadside awareness cloud planning for extended range vehicles according to claim 6, wherein the unmanned method comprises the steps of: the method for determining the optimal global path comprises the following steps: the decision planning cloud platform segments all planned global paths according to the user demands and calculates the time cost f required to be paid by passing through the nth road in the paths n (n), i.e. the total time cost of the nth travel path is D (n) =f n (1)+f n (2)+…+f n (n), the path with the smallest D (n) value is the optimal global path.
8. The unmanned method for hybrid traffic flow roadside awareness cloud planning for extended range vehicles according to claim 6, wherein the unmanned method comprises the steps of: and when the unmanned vehicle passes through the road, waking up the intelligent road side infrastructure of the road section.
9. The extended program of claim 7The unmanned method for the hybrid traffic flow roadside perception cloud planning of the automobile is characterized by comprising the following steps of: the calculated time cost f of the nth road of the nth driving path n And (n) calculating according to the predicted road environment information when the vehicle runs to the road, wherein the predicted road traffic environment information is obtained by collecting the traffic flow of the road and the traffic environment information in real time by the decision planning cloud platform.
10. The unmanned method of hybrid traffic flow roadside aware cloud planning of claim 5, wherein: the method in the fifth step comprises the following steps: the control signal of the decision cloud platform can also be forwarded to the vehicle-mounted network communication terminal through the road side intelligent infrastructure; and after the route planning is completed to select an optimal driving route, the decision-making cloud platform numbers the IP address or other unique marks of the intelligent road-side infrastructure of the route according to the passing sequence of vehicles, then forms a set of intelligent road-side infrastructure information D (x) to be sent to the communication terminal of the vehicle-mounted network, when 5G communication is normal, the received control signal of the decision-making cloud platform is executed, and when the control signal of the decision-making cloud platform is not received within a preset time delta T, the control signal sent by the intelligent road-side infrastructure is executed.
11. The unmanned method for hybrid traffic flow roadside aware cloud planning according to claim 5, wherein the specific method in the step six is as follows: in the running process of the vehicle, the vehicle-mounted network communication terminal can drive away from the coverage area of a certain road side intelligent infrastructure, the decision cloud platform can issue control signals to a plurality of road side intelligent infrastructures to be experienced by the running path of the vehicle, the road side intelligent infrastructures continuously broadcast the control signals issued by the decision cloud platform, in the whole running process, the vehicle-mounted network communication terminal can receive the control signals issued by the decision cloud platform, when the vehicle drives away from the road side intelligent infrastructures, the decision planning cloud platform recognizes according to the position of the vehicle, then the road side intelligent infrastructures are controlled to stop transmitting the control signals, and if no other unmanned vehicle passes through the road side intelligent infrastructures, sleep signals are transmitted to the road side intelligent infrastructures.
12. The unmanned method for hybrid traffic flow roadside aware cloud planning according to claim 5, wherein the safety redundant braking mechanism of the step seven is: when a special accident occurs, the vehicle-mounted network connection terminal controls the drive-by-wire chassis to stop by side, the vehicle-mounted network connection terminal acquires the transverse distance between the vehicle and the roadside at the moment, the intelligent infrastructure at the information road side monitors the transverse distance signal in real time through the carried sensor, and then the transverse distance signal is broadcast to the vehicle-mounted network communication terminal along with the control signal of the forwarding decision planning cloud platform, when the communication terminal or other uncontrollable faults occur, the vehicle-mounted network communication terminal plans a running path for the vehicle to run to the roadside, the vehicle is controlled to stop by side, and before the vehicle stops by side, the dangerous alarm lamp is firstly turned on and is broadcast outside.
13. A vehicle comprising the unmanned system of hybrid traffic flow roadside aware cloud planning of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211528633.0A CN116434524A (en) | 2022-11-30 | 2022-11-30 | Unmanned system, method and vehicle for hybrid traffic flow down-road side perception cloud planning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211528633.0A CN116434524A (en) | 2022-11-30 | 2022-11-30 | Unmanned system, method and vehicle for hybrid traffic flow down-road side perception cloud planning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116434524A true CN116434524A (en) | 2023-07-14 |
Family
ID=87087817
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211528633.0A Pending CN116434524A (en) | 2022-11-30 | 2022-11-30 | Unmanned system, method and vehicle for hybrid traffic flow down-road side perception cloud planning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116434524A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117395292A (en) * | 2023-12-12 | 2024-01-12 | 中科慧拓(北京)科技有限公司 | Cloud monitoring system and method for digital parallel vehicle |
-
2022
- 2022-11-30 CN CN202211528633.0A patent/CN116434524A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117395292A (en) * | 2023-12-12 | 2024-01-12 | 中科慧拓(北京)科技有限公司 | Cloud monitoring system and method for digital parallel vehicle |
| CN117395292B (en) * | 2023-12-12 | 2024-02-20 | 中科慧拓(北京)科技有限公司 | Cloud monitoring system and method for digital parallel vehicle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113811929B (en) | System and method for controlling vehicles in combination | |
| WO2022063331A1 (en) | V2x-based formation driving networked intelligent passenger vehicle | |
| CN101859494B (en) | Autonomous vehicle management | |
| WO2020258277A1 (en) | Way-giving method and apparatus for intelligent driving vehicle, and vehicle-mounted device | |
| WO2020164238A1 (en) | Method, apparatus and device for driving control, and medium and system | |
| CN112543958B (en) | Vehicle control device, vehicle control method, computer-readable storage medium, and formation travel system | |
| WO2021147748A1 (en) | Self-driving method and related device | |
| WO2021102957A1 (en) | Lane keeping method, vehicle-mounted device, and storage medium | |
| CN113496602B (en) | Intelligent roadside tool box | |
| JP5056613B2 (en) | Driving support system | |
| CN113012448B (en) | Intelligent driving system for vehicle distribution formation for solving intersection traffic jam | |
| CN112562409A (en) | Autonomous parking system and method based on multi-access edge calculation | |
| CN115004275A (en) | Adaptive control of vehicular traffic | |
| CN110568847B (en) | Intelligent control system and method for vehicle, vehicle-mounted equipment and storage medium | |
| CN114363862A (en) | Intelligent information conversion system and method for serving cooperative automatic driving of vehicle and road | |
| Baskar et al. | Hierarchical traffic control and management with intelligent vehicles | |
| WO2020258276A1 (en) | Yielding method and apparatus for intelligent driving vehicle, and vehicle-mounted device | |
| CN114501385A (en) | Collaborative automatic driving system applied to intelligent network connection traffic system | |
| CN116434524A (en) | Unmanned system, method and vehicle for hybrid traffic flow down-road side perception cloud planning | |
| CN113844465B (en) | Automatic driving method and system | |
| US20220032934A1 (en) | Method, apparatus, device and system for controlling driving | |
| CN109656242A (en) | A kind of automatic Pilot planning driving path planning system | |
| CN108592930B (en) | Intelligent auxiliary driving method for new energy automobile based on large system optimization and Internet of vehicles | |
| CN113971883A (en) | Vehicle-road cooperative automatic driving method and efficient transportation system | |
| CN115092159A (en) | Lane line autonomous intelligent mapping system and method |
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 |