CN112562409B - Autonomous parking system and method based on multi-access edge calculation - Google Patents
Autonomous parking system and method based on multi-access edge calculation Download PDFInfo
- Publication number
- CN112562409B CN112562409B CN202011402894.9A CN202011402894A CN112562409B CN 112562409 B CN112562409 B CN 112562409B CN 202011402894 A CN202011402894 A CN 202011402894A CN 112562409 B CN112562409 B CN 112562409B
- Authority
- CN
- China
- Prior art keywords
- module
- vehicle
- parking
- service
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/166—Anti-collision systems for active traffic, e.g. moving vehicles, pedestrians, bikes
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
- B60W30/06—Automatic manoeuvring for parking
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/168—Driving aids for parking, e.g. acoustic or visual feedback on parking space
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/40—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]
- H04W4/44—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P] for communication between vehicles and infrastructures, e.g. vehicle-to-cloud [V2C] or vehicle-to-home [V2H]
Abstract
The invention relates to an autonomous parking system and method based on multi-access edge computing, the system uses the sunk service processing mode and the edge computing node as the core, including: the system comprises an environment sensing module, a vehicle positioning module, a high-precision map module, a planning and strategy module, a data fusion and calculation module, an information interaction module, a parking path guiding module and an operation and maintenance management module; and the system is carried on the road side sensing equipment, the network communication equipment, the information issuing equipment and the cloud control platform. The invention can process large-scale vehicle parking service requirements in a low-delay and non-blocking way, dynamically updates the vehicle parking requirements, has high-precision sensing capability of the surrounding environment, can provide safe, accurate and efficient parking guide path service, does not need the vehicle to have automatic driving capability, and is convenient, efficient, safe and rapid.
Description
Technical Field
The invention relates to the field of automobile control systems, in particular to an autonomous parking system and method based on multi-access edge calculation.
Background
At present, the rapid development of the intelligent network vehicle-connecting industry provides a practical demand for high-precision map information service. By 2020, vehicles with level L1-L2 driving assistance functions have begun to be commercially mass produced in a large scale, and vehicles with level L3 or higher and with partial or highly automated driving functions have entered the stage of mass measurement.
At present, compared with an automatic driving application scene of an L4/L5 level under an open city and a high-speed working condition, the low-speed autonomous parking application is easier to enter the visual field of the public, and the implementation of the autonomous parking function at the present stage mainly depends on two technical routes, namely the enhancement of the self sensing capability of a vehicle end and the enhancement of the communication capability of a field end, but the two modes have the defects of difficulty in landing a commercial vehicle, redundant equipment deployment, high cost and the like.
The automatic parking system mainly measures the relative distance, speed and angle between the vehicle and the surrounding objects by using sensors distributed in the vehicle and the surrounding environment, then calculates an operation process through a vehicle-mounted computing platform or a cloud computing platform, and controls the steering and acceleration and deceleration of the vehicle so as to realize the functions of automatic parking, parking and partial driving.
On the aspect of a vehicle end sensor, an autonomous parking system carries a camera, an ultrasonic radar and a laser radar to realize links such as environment sensing, parking space detection and identification, parking path planning, parking path following control and simulation display, and the method has high requirements on vehicle intellectualization and is only suitable for part of vehicle types;
and field end scheme: the method comprises the steps that a laser radar or a binocular camera is arranged in a parking lot to monitor the state of a vehicle and the surrounding environment, all sensor data are collected and analyzed in the center through detection of a pre-embedded parking lot sensor, and matching is completed according to stored meta information. Although the requirements of the vehicle are reduced, only a controllable chassis execution system is needed, 25 laser radars are required to be distributed in every 3 parking spaces, the cost is greatly increased, and the application range of autonomous parking is limited.
To date, these systems have relied on expensive sensors, and the cost of full coverage for parking lot construction, smart devices, lidar and internet of things, etc. is high.
Chinese patent 2018115005190 discloses an autonomous parking lot system and a method for controlling autonomous parking of vehicles in the parking lot, which comprises a field terminal device, which is installed in a parking lot and transmits data information required by the vehicles to perform autonomous parking; and the autonomous parking control device is arranged on the vehicle, receives the data information from the field terminal device in a wireless communication mode, and generates a vehicle execution instruction according to the data information to control the vehicle to execute a corresponding function so as to realize the autonomous parking of the vehicle. This patent has realized accurately controlling the vehicle, realizes automatic parking, but need install automatic parking controlling means additional on the vehicle, but circulated utilization, but operation and management are comparatively troublesome, and through camera device monitoring environment in the place, do not relate to real-time dynamic update high accuracy map, and the inside environmental data of place probably has great error, can't provide safe accurate efficient guide path that parks.
Therefore, it is a urgent need for those skilled in the art to implement an autonomous parking service with all weather, full scene, low cost, low delay, high performance, and fast data processing capability by using a "vehicle-side-field" software and hardware integrated solution.
Disclosure of Invention
In view of the above, an object of the present application is to provide an autonomous parking system and method based on multi-access edge calculation, which can handle large-scale vehicle parking service requirements with low delay and no blocking, provide safe, accurate, and efficient parking guidance path service, perform real-time information interaction with a target vehicle in real time, and dynamically update vehicle parking requirements.
In order to achieve the above object, the present application provides the following technical solutions.
An autonomous parking system based on multiple access edge computing, comprising: the system comprises an environment sensing module, a vehicle positioning module, a high-precision map module, a planning and strategy module, a data fusion and calculation module, an information interaction module, a parking path guiding module and an operation and maintenance management module;
the environment sensing module is arranged on the road end sensing equipment and used for processing the internal environment data of the parking lot station sensed by the road end sensing equipment;
the information interaction module is arranged on the internet communication equipment and the information publishing equipment and used for information interaction between the vehicle and the edge computing node;
the high-precision map module, the data fusion and calculation module, the parking path guide module and the vehicle positioning module are arranged on the edge calculation node;
the high-precision map module is used for constructing a high-precision map of a station, semi-dynamic parking space occupation information and dynamic position information of vehicles, pedestrians and obstacles and constructing a dynamic map scene;
the data fusion and calculation module is used for further processing the data processed by the environment perception module and unifying a space-time coordinate system;
the vehicle positioning module is used for positioning a target vehicle sending a parking service request, associating the target vehicle with a high-precision dynamic map based on an ultrafast zone service, and providing a high-precision positioning service for the vehicle in a ground library environment;
the parking path guiding module is used for planning a specific parking path according to the current positioning of a target vehicle and a high-precision map in a station, and guiding the vehicle to avoid a dynamic and static barrier to successfully reach an allocated parking space;
the planning and strategy module is arranged on the cloud control platform and used for evaluating the service level and the capability of the current station, predicting the traffic flow and the parking space occupation condition within a period of time, adopting a strategy with the optimal overall service level, decomposing the overall strategy into specific parking service tasks according to the coverage range of each edge computing node and sending the parking service tasks to the corresponding edge computing nodes;
the operation and maintenance management module is arranged on the cloud control platform and the edge computing node and used for maintaining normal and stable operation of other modules, monitoring the operation state and fault information of each module and monitoring whether the hardware equipment in the system has a power failure and disconnection phenomenon.
Preferably, the road end sensing equipment comprises a microwave radar, a video monitor, a geomagnetic coil, an ultra wide band, a gate control and radio frequency identification;
the microwave radar is used for sensing vehicle and traffic event data;
the video monitor is used for sensing pedestrian and vehicle data;
the geomagnetic coil is used for sensing parking space occupation data;
the ultra-wideband is used for providing high-precision positioning service for vehicles.
Preferably, the edge computing node comprises a CPU computing unit, a GPU computing unit, an external interface, an external hard disk, an exchanger, and a heat sink, and is configured to provide the parking service request, the vehicle positioning, and the high-precision dynamic map information of the current scene to the cloud control platform.
Preferably, the internet communication equipment comprises a road side and a vehicle-mounted communication terminal, and the road test and the vehicle-mounted communication terminal comprise an LTE-V2X technology and a 5G technology.
Preferably, the cloud control platform comprises a central machine room server and a trillion switch, and the trillion switch is communicated with the edge computing nodes; the cloud control platform is used for issuing the overall plan and tasks of the parking service to the edge computing nodes in different areas through the planning and strategy module based on the total traffic flow and the parking space occupation condition of the parking lot, and receiving the unsolvable fault information reported by the maintenance and operation management module.
Preferably, the information distribution device comprises an LED display screen, an electronic sign and a broadcasting facility, and the information distribution device provides guidance for the target vehicle to complete the autonomous parking service.
Preferably, when the data fusion and calculation module further processes the data processed by the environment sensing module, the timestamp of the sensing device on the same road segment is the same, the target detection results in different coordinate systems are unified to the same coordinate system, and the same object detected by the sensing devices on different road ends is unified to the same ID by using the corresponding target association algorithm.
Preferably, the precision of the high-precision map module component is centimeter level, the high-precision map comprises static parking lot internal roads, marked lines, parking spaces and charging pile map information, semi-dynamic parking space occupation information and dynamic vehicle, pedestrian and obstacle position information.
Preferably, the method of operation is as follows:
s1, an intelligent internet vehicle sends an automatic parking request, and internet communication equipment receives a parking service request instruction sent by the vehicle and motion position information of the vehicle;
s2, the road end sensing equipment and the vehicle sensing equipment operate to sense the internal environment data of the parking lot;
s3, the environment sensing module processes the environment sensing data, inputs video frames or radar point cloud data of a camera and outputs structured target and obstacle monitoring data;
s4, the information interaction module carries out information interaction between the vehicle and the edge computing node; inputting a parking service request instruction sent by a vehicle and motion position information of the vehicle, and outputting high-precision map information and parking service path guide information in a station;
s5, the data fusion and calculation module further processes the environmental perception data and unifies a space-time coordinate system; inputting structured target detection data provided by an environment sensing module, and outputting holographic sensing data under a unified space-time coordinate system;
s6, constructing a high-precision map of the station with the precision reaching centimeter level by a high-precision map module, and providing high-precision maps of different levels for users; the station environment perception data processed by the data fusion and calculation module is input, and a high-precision three-dimensional dynamic map for decision making and planning is output to the edge calculation node and the cloud control platform in combination with the target vehicle position data provided by the information interaction module;
s7, the vehicle positioning module operates to position a target vehicle sending out a parking service request, and according to the position of the vehicle provided by the information interaction module, the target vehicle is checked with vehicle data detected by the environment sensing module to establish the association between the target vehicle and a lane or a parking space in the high-precision map;
s8, a planning and strategy module operates, according to vehicle parking service requests reported by each edge computing node and total vehicle operation and parking space occupation information of the current station, a high-precision dynamic and static map is combined to evaluate the service level and the capacity of the current station, and the traffic flow and the parking space occupation condition in a period of time are predicted, so that a strategy with the optimal total service level is adopted, according to the coverage range of each edge computing node, the total strategy is disassembled into specific parking service tasks and issued to the corresponding edge computing nodes; inputting a vehicle service request reported by an edge computing node, a scene high-precision dynamic and static map, and outputting an unoccupied parking space allocation service instruction;
s9, the parking path guiding module operates, follows a parking task issued by the planning and strategy module, plans a specific parking path according to the current positioning of the target vehicle and in combination with a high-precision map in the station, predicts the movement tracks of other vehicles and pedestrians, identifies the collision risk, and guides the vehicle to avoid a dynamic and static barrier to successfully reach the distributed parking space; inputting a parking task instruction, target vehicle positioning and a high-precision map issued by a planning and strategy module, and outputting a path guide suggestion for a parking service;
s10, the information interaction module provides various parking service guiding means including C-V2X communication for the vehicle, sends a V2X message set to the Internet-connected vehicle, provides voice and picture guidance for the non-Internet-connected vehicle through the information publishing device, meanwhile keeps feedback contact with the parking service of the vehicle, and repeats S2-S9 according to the updated parking service request until the vehicle successfully completes parking; inputting a path guidance suggestion for a parking service, and outputting a target vehicle-oriented map and a path guidance message set;
the set of V2X messages includes a site map, a guidance path, a suggested speed, and an effective time.
Preferably, the operation and maintenance management module continuously operates in the system operation process, maintains the normal stable operation of other modules, monitors the operation states and fault information of other modules, monitors whether the hardware equipment in the system has a power failure and disconnection phenomenon, processes the normal fault of trip in the system operation process in real time, reports the fault possibly influencing the current parking guidance service to the cloud control platform, and provides backup service by coordinating other edge computing nodes through the cloud control platform.
The invention has the following beneficial technical effects:
1) The system of the invention realizes the sinking processing of the parking guidance service based on the edge computing node, and avoids the information congestion and delay caused by the large-scale convergence of the service request of the traditional central parking guidance system.
2) The system of the invention converges the traffic target and traffic event detection data provided by the sensor based on the edge computing node, dynamically updates the high-precision map based on the real-time dynamic detection data, and avoids the data error caused by the intelligent provision of a static map by the traditional parking guidance system;
3) The system has the internet communication function, can communicate with a target vehicle in real time, update parking requirements in time, and dynamically plan a parking path, so that the problem that the traditional parking guide system cannot know the position of the vehicle and the parking requirements in time to cause untimely ground service is avoided;
4) The system realizes intelligent control based on the edge computing node, has high-precision sensing capability of surrounding environment and autonomous decision-making path planning capability, and reduces the technical level of the vehicle and the requirement on equipment cost; the system can realize safe and reliable AVP function depending on information interaction with the system without the vehicle having automatic driving capability of L2 or above.
The foregoing description is only an overview of the technical solutions of the present application, so that the technical means of the present application can be more clearly understood and the present application can be implemented according to the content of the description, and in order to make the above and other objects, features and advantages of the present application more clearly understood, the following detailed description is made with reference to the preferred embodiments of the present application and the accompanying drawings.
The above and other objects, advantages and features of the present application will become more apparent to those skilled in the art from the following detailed description of specific embodiments thereof, taken in conjunction with the accompanying drawings.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following descriptions are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative efforts. Throughout the drawings, like elements or portions are generally identified by like reference numerals. In the drawings, elements or portions are not necessarily drawn to scale.
FIG. 1 is a diagram of the software and hardware components of the present invention;
fig. 2 is a flow chart of the operation of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. In the following description, specific details such as specific configurations and components are provided only to help the embodiments of the present application be fully understood. Accordingly, it will be apparent to those skilled in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present application. In addition, descriptions of well-known functions and constructions are omitted in the embodiments for clarity and conciseness.
It should be appreciated that reference throughout this specification to "one embodiment" or "the embodiment" means that a particular feature, structure or characteristic described in connection with the embodiment is included in at least one embodiment of the present application. Thus, the appearances of the phrase "one embodiment" or "the present embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
Further, the present application may repeat reference numerals and/or letters in the various examples. This repetition is for the purpose of simplicity and clarity and does not in itself dictate a relationship between the various embodiments and/or configurations discussed.
The term "and/or" herein is merely an association relationship describing an associated object, and means that there may be three relationships, for example, a and/or B, which may mean: a exists alone, B exists alone, and A and B exist at the same time, and the term "/and" is used herein to describe another association object relationship, which means that two relationships may exist, for example, A/and B, may mean: a alone, and both a and B alone, and further, the character "/" in this document generally means that the former and latter associated objects are in an "or" relationship.
The term "at least one" herein is merely an association relationship describing an associated object, and means that there may be three relationships, for example, at least one of a and B, may mean: a exists alone, A and B exist simultaneously, and B exists alone.
It is further noted that, herein, 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. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion.
Example 1
As shown in fig. 1, an autonomous parking system based on multiple access edge calculation includes: the system comprises an environment sensing module, a vehicle positioning module, a high-precision map module, a planning and strategy module, a data fusion and calculation module, an information interaction module, a parking path guiding module and an operation and maintenance management module;
the environment sensing module is arranged on the road end sensing equipment and is used for processing the internal environment data of the parking lot station sensed by the road end sensing equipment;
the information interaction module is arranged on the internet communication equipment and the information publishing equipment and is used for information interaction between the vehicle and the edge computing node;
the high-precision map module, the data fusion and calculation module, the parking path guide module and the vehicle positioning module are arranged on the edge calculation node;
the high-precision map module is used for constructing a high-precision map of a station, semi-dynamic parking space occupation information and dynamic position information of vehicles, pedestrians and obstacles and constructing a dynamic map scene;
the data fusion and calculation module is used for further processing the data processed by the environment perception module and unifying a space-time coordinate system;
the vehicle positioning module is used for positioning a target vehicle sending a parking service request, associating the target vehicle with a high-precision dynamic map based on an ultrafast zone service, and providing a high-precision positioning service for the vehicle in a ground library environment;
the parking path guiding module is used for planning a specific parking path according to the current positioning of a target vehicle and in combination with a high-precision map in a station, and guiding the vehicle to avoid a dynamic and static barrier to successfully reach an allocated parking space;
the planning and strategy module is arranged on the cloud control platform and used for evaluating the service level and the capability of the current station, predicting the traffic flow and the parking space occupation condition within a period of time, adopting a strategy with the optimal overall service level, decomposing the overall strategy into specific parking service tasks according to the coverage range of each edge computing node and sending the parking service tasks to the corresponding edge computing nodes;
the operation and maintenance management module is arranged on the cloud control platform and the edge computing node and used for maintaining normal and stable operation of other modules, monitoring the operation state and fault information of each module and monitoring whether the hardware equipment in the system has a power failure and disconnection phenomenon.
Further, the road end sensing equipment comprises a microwave radar, a video monitor, a geomagnetic coil, an ultra wide band, a gate control and radio frequency identification;
the microwave radar is used for sensing vehicle and traffic event data;
the video monitor is used for sensing pedestrian and vehicle data;
the geomagnetic coil is used for sensing parking space occupation data;
the ultra-wideband is used for providing high-precision positioning service for vehicles.
Furthermore, the edge computing node comprises a CPU computing unit, a GPU computing unit, an external interface, an external hard disk, a switch and a radiating fin, and is used for providing parking service requests, vehicle positioning and current scene high-precision dynamic map information to the cloud control platform.
Furthermore, the networking communication equipment comprises a road side and a vehicle-mounted communication terminal, and the road test and the vehicle-mounted communication terminal comprise an LTE-V2X technology and a 5G technology.
Further, the cloud control platform comprises a central machine room server and a ten-gigabit switch, and the ten-gigabit switch is communicated with the edge computing nodes; the cloud control platform is used for issuing the overall plan and tasks of the parking service to the edge computing nodes in different areas through the planning and strategy module based on the total traffic flow and the parking space occupation condition of the parking lot, and receiving the unsolvable fault information reported by the maintenance and operation management module.
Further, the information issuing equipment comprises an LED display screen, an electronic sign and a broadcasting facility, and the information issuing equipment provides guidance for the target vehicle to complete the autonomous parking service.
Furthermore, when the data fusion and calculation module further processes the data processed by the environment sensing module, the timestamp of the sensing equipment on the same road section is the same, the target detection results in different coordinate systems are unified to the same coordinate system, and the same object detected by the sensing equipment on different road ends is unified to the same ID by using the corresponding target association algorithm.
Further, the accuracy of the high accuracy map module component is centimeter level, the high accuracy map includes static inside road in parking area, marking, parking stall and fills electric pile map information, semi-dynamic parking stall occupation information and dynamic vehicle, pedestrian, obstacle positional information.
The beneficial technical effects obtained by the embodiment are as follows:
1) The embodiment realizes the sinking processing of the parking guidance service based on the edge computing node, and avoids information congestion and delay caused by large-scale convergence of service requests of the traditional central parking guidance system.
2) The embodiment converges the traffic target and traffic event detection data provided by the sensor based on the edge computing node, dynamically updates the high-precision map based on the real-time dynamic detection data, and avoids data errors caused by the intelligent provision of a static map by the traditional parking guidance system;
3) The system has the internet communication function, can communicate with a target vehicle in real time, timely updates parking requirements, dynamically plans a parking path, and avoids untimely ground service caused by the fact that a traditional parking guide system cannot timely know the position of the vehicle and the parking requirements;
4) The intelligent control is realized based on the edge computing nodes, the intelligent control has the high-precision sensing capability of the surrounding environment and the autonomous decision-making path planning capability, and the technical level and equipment cost requirements of the vehicle are reduced; the system can realize safe and reliable AVP function depending on information interaction with the system without the vehicle having automatic driving capability of L2 or above.
Example 2
This embodiment is explained based on the above embodiment 1, and the same parts as those of the above embodiment 1 are not repeated.
The present embodiment mainly describes a method for using an autonomous parking system based on multi-access edge calculation.
As shown in fig. 2, the method for using the autonomous parking system based on multi-access edge calculation includes the following steps:
s1, an intelligent internet vehicle sends an automatic parking request, and internet communication equipment receives a parking service request instruction sent by the vehicle and motion position information of the vehicle;
s2, the road end sensing equipment and the vehicle sensing equipment operate to sense the internal environment data of the parking lot;
s3, the environment sensing module processes environment sensing data, inputs video frames or radar point cloud data of the camera and outputs structured target and obstacle monitoring data;
s4, the information interaction module carries out information interaction between the vehicle and the edge computing node; inputting a parking service request instruction sent by a vehicle and motion position information of the vehicle, and outputting high-precision map information and parking service path guide information in a station;
s5, the data fusion and calculation module further processes the environmental perception data and unifies a space-time coordinate system; inputting structured target detection data provided by an environment sensing module, and outputting holographic sensing data under a unified space-time coordinate system;
s6, constructing a high-precision map of the station with the precision reaching centimeter level by a high-precision map module, and providing high-precision maps of different levels for users; the station environment perception data processed by the data fusion and calculation module is input, and a high-precision three-dimensional dynamic map for decision making and planning is output to the edge calculation node and the cloud control platform in combination with the target vehicle position data provided by the information interaction module;
s7, the vehicle positioning module operates to position a target vehicle sending out a parking service request, and according to the position of the vehicle provided by the information interaction module, the target vehicle is checked with vehicle data detected by the environment sensing module to establish the association between the target vehicle and a lane or a parking space in the high-precision map;
s8, a planning and strategy module operates, according to vehicle parking service requests reported by each edge computing node and total vehicle operation and parking space occupation information of the current station, a high-precision dynamic and static map is combined to evaluate the service level and the capacity of the current station, and the traffic flow and the parking space occupation condition in a period of time are predicted, so that a strategy with the optimal total service level is adopted, according to the coverage range of each edge computing node, the total strategy is disassembled into specific parking service tasks and issued to the corresponding edge computing nodes; inputting a vehicle service request reported by an edge computing node, a scene high-precision dynamic and static map, and outputting an unoccupied parking space allocation service instruction;
s9, the parking path guiding module operates, plans a specific parking path according to the current positioning of the target vehicle and a high-precision map in the station according to the parking task issued by the planning and strategy module, predicts the movement tracks of other vehicles and pedestrians, identifies the collision risk, and guides the vehicle to avoid a dynamic and static barrier to successfully reach the distributed parking space; inputting a parking task instruction, target vehicle positioning and a high-precision map issued by a planning and strategy module, and outputting a path guide suggestion for a parking service;
s10, the information interaction module provides various parking service guiding means including C-V2X communication for the vehicle, sends a V2X message set to the networked vehicle, provides voice and picture guidance for the non-networked vehicle through the information issuing equipment, meanwhile keeps the feedback connection with the parking service of the vehicle, and repeats S2-S9 according to the updated parking service request until the vehicle successfully completes parking; inputting a path guidance suggestion for a parking service, and outputting a target vehicle-oriented map and a path guidance message set;
the set of V2X messages includes a site map, a guidance path, a suggested speed, and an effective time.
Furthermore, the operation and maintenance management module continuously operates in the system operation process, maintains the normal stable operation of other modules, monitors the operation state and fault information of other modules, monitors whether the hardware equipment in the system has the outage and disconnection phenomenon, processes the normal fault going out in the system operation process in real time, reports the fault possibly influencing the current parking guidance service to the cloud control platform, and provides backup service by coordinating other edge computing nodes through the cloud control platform.
The embodiment can independently position the vehicle position and state through the service request of the vehicle autonomous parking of dynamic update, and environmental data in the real-time monitoring field forms the high accuracy map, and the autonomous decision-making path planning and guide vehicle park need not that the vehicle possesses the autopilot ability, convenient and fast, and data is accurate, and the availability factor is high.
The above description is only a preferred embodiment of the present invention, and it is not intended to limit the scope of the present invention, and it is obvious to those skilled in the art that various modifications and variations can be made in the present invention. Variations, modifications, substitutions, integrations and parameter changes of the embodiments may be made by the conventional substitutes or the same functions may be performed within the spirit and principle of the invention without departing from the principle and spirit of the invention.
Claims (2)
1. An autonomous parking system based on multiple access edge calculation, comprising: environmental perception module, vehicle orientation module, high accuracy map module, planning and strategy module, data fusion and calculation module, information interaction module, route guide module, fortune dimension management module park, its characterized in that:
the environment sensing module is arranged on the road end sensing equipment and is used for processing the internal environment data of the parking lot station sensed by the road end sensing equipment;
the information interaction module is arranged on the internet communication equipment and the information publishing equipment and used for information interaction between the vehicle and the edge computing node;
the high-precision map module, the data fusion and calculation module, the parking path guide module and the vehicle positioning module are arranged on the edge calculation node;
the high-precision map module is used for constructing a high-precision map of a station, semi-dynamic parking space occupation information and dynamic position information of vehicles, pedestrians and obstacles and constructing a dynamic map scene;
the data fusion and calculation module is used for further processing the data processed by the environment perception module and unifying a space-time coordinate system;
the vehicle positioning module is used for positioning a target vehicle sending a parking service request, associating the target vehicle with a high-precision dynamic map based on an ultrafast zone service, and providing a high-precision positioning service for the vehicle in a ground library environment;
the parking path guiding module is used for planning a specific parking path according to the current positioning of a target vehicle and a high-precision map in a station, and guiding the vehicle to avoid a dynamic and static barrier to successfully reach an allocated parking space;
the planning and strategy module is arranged on the cloud control platform and used for evaluating and predicting a strategy with the optimal overall service level, resolving the overall strategy into a specific parking service task according to the coverage range of each edge computing node and issuing the parking service task to the corresponding edge computing node;
the operation and maintenance management module is arranged on the cloud control platform and the edge computing node and used for maintaining normal and stable operation of other modules and monitoring the operation state and fault information of each module;
the road end sensing equipment comprises a microwave radar, a video monitor, a geomagnetic coil, an ultra wide band, a gate control and radio frequency identification;
the microwave radar is used for sensing vehicle and traffic event data;
the video monitor is used for sensing pedestrian and vehicle data;
the geomagnetic coil is used for sensing parking space occupation data;
the ultra wide band is used for providing high-precision positioning service for the vehicle;
the edge computing node comprises a CPU computing unit, a GPU computing unit, an external interface, an external hard disk, a switch and a heat radiating fin, and is used for providing parking service requests, vehicle positioning and current scene high-precision dynamic map information to the cloud control platform;
the network communication equipment comprises a road side and a vehicle-mounted communication terminal, wherein the road side and the vehicle-mounted communication terminal comprise an LTE-V2X technology and a 5G technology;
the cloud control platform comprises a central machine room server and a trillion switch, and the trillion switch is communicated with the edge computing node; the cloud control platform is used for issuing the overall plan and tasks of the parking service to edge computing nodes in different areas through a planning and strategy module based on the total traffic flow and the parking space occupation condition of the parking lot, and receiving the unsolvable fault information reported by the maintenance management module;
the information issuing equipment comprises an LED display screen, an electronic label and a broadcasting facility, and provides guidance for a target vehicle to finish autonomous parking service;
when the data fusion and calculation module further processes the data processed by the environment sensing module, the data fusion and calculation module shares the timestamps of sensing equipment on different road sections, and simultaneously unifies the target detection results under different coordinate systems into the same coordinate system, and utilizes the corresponding target association algorithm to unify the same object detected by the sensing equipment on different road ends into the same ID;
the accuracy of the high-precision map module component is centimeter level, the high-precision map comprises static parking lot internal roads, marked lines, parking spaces and charging pile map information, semi-dynamic parking space occupation information and dynamic vehicle, pedestrian and obstacle position information.
2. An operation method of an autonomous parking system based on multi-access edge calculation, which is used for operating the system of claim 1, characterized in that the operation method comprises the following steps:
s1, an intelligent internet vehicle sends an automatic parking request, and internet communication equipment receives a parking service request instruction sent by the vehicle and motion position information of the vehicle;
s2, the road end sensing equipment and the vehicle sensing equipment operate to sense the internal environment data of the parking lot;
s3, the environment sensing module processes environment sensing data;
s4, the information interaction module carries out information interaction between the vehicle and the edge computing node;
s5, the data fusion and calculation module further processes the environmental perception data and unifies a space-time coordinate system;
s6, constructing a high-precision map of the station with the precision reaching centimeter level by a high-precision map module, and providing high-precision maps of different levels for users;
s7, the vehicle positioning module positions a target vehicle which sends out a parking service request, and checks vehicle data detected by the environment sensing module according to the position of the vehicle provided by the information interaction module to establish the association between the target vehicle and a lane or a parking space in the high-precision map;
s8, operating a planning and strategy module, and evaluating and predicting a strategy with the optimal overall service level; the overall strategy is disassembled into specific parking service tasks and is issued to corresponding edge computing nodes;
s9, the parking path guiding module plans a specific parking path according to the parking task issued by the planning and strategy module and the current positioning of the target vehicle by combining a high-precision map in the station, and guides the vehicle to avoid the dynamic and static barriers and successfully reach the distributed parking spaces;
s10, the information interaction module provides various parking service guiding means including C-V2X communication for the vehicle and sends a V2X message set to the networked vehicle; repeating S2-S9 according to the updated parking service request until the vehicle successfully completes parking;
the information issuing equipment provides voice and picture guidance for the non-networked vehicle, and meanwhile maintains a parking service feedback connection with the vehicle;
the operation and maintenance management module continuously operates in the system operation process, maintains the normal stable operation of other modules, monitors the operation state and fault information of other modules, monitors whether hardware equipment in the system has a power failure and loss of connection phenomenon, processes normal faults going out in the system operation process in real time, reports faults possibly influencing the current parking guidance service to the cloud control platform, and provides backup service by coordinating other edge computing nodes through the cloud control platform.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011402894.9A CN112562409B (en) | 2020-12-04 | 2020-12-04 | Autonomous parking system and method based on multi-access edge calculation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011402894.9A CN112562409B (en) | 2020-12-04 | 2020-12-04 | Autonomous parking system and method based on multi-access edge calculation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112562409A CN112562409A (en) | 2021-03-26 |
| CN112562409B true CN112562409B (en) | 2022-11-15 |
Family
ID=75048247
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011402894.9A Active CN112562409B (en) | 2020-12-04 | 2020-12-04 | Autonomous parking system and method based on multi-access edge calculation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112562409B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113085842B (en) * | 2021-04-30 | 2023-06-06 | 北京百度网讯科技有限公司 | Vehicle control method and device and vehicle |
| CN113895428B (en) * | 2021-10-19 | 2024-01-23 | 深圳市万集科技有限公司 | Parking method and device, computer readable storage medium and terminal equipment |
| CN114228701B (en) * | 2021-11-30 | 2023-10-20 | 岚图汽车科技有限公司 | Parking control method and device based on sensor data fusion |
| US11776404B2 (en) | 2022-02-07 | 2023-10-03 | International Business Machines Corporation | Ad-hoc network optimization by parking allocation |
| CN114758494B (en) * | 2022-03-25 | 2023-05-30 | 西安电子科技大学广州研究院 | Traffic parameter detection system and method based on communication perception multi-source data fusion |
| CN114802215B (en) * | 2022-05-31 | 2024-04-19 | 重庆长安汽车股份有限公司 | Automatic parking system and method based on calculation force sharing and edge calculation |
| CN115100852A (en) * | 2022-06-09 | 2022-09-23 | 智能汽车创新发展平台(上海)有限公司 | High-availability roadside fusion sensing system and method for serving intelligent networked automobile |
| CN115171421A (en) * | 2022-06-22 | 2022-10-11 | 上海智能网联汽车技术中心有限公司 | Intelligent parking lot system based on vehicle-road cooperation and parking and departure implementation method thereof |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107054466A (en) * | 2016-02-11 | 2017-08-18 | 通用汽车环球科技运作有限责任公司 | Parking assistance system and its application method for vehicle |
| CN107074233A (en) * | 2014-10-27 | 2017-08-18 | 罗伯特·博世有限公司 | For the method for the automatic parking process for performing vehicle |
| KR102073929B1 (en) * | 2018-08-02 | 2020-02-05 | (주)유비벨록스모바일 | Vehicle Emergency Log system using blockchain network |
| CN111640330A (en) * | 2020-05-29 | 2020-09-08 | 深圳市元征科技股份有限公司 | Anti-collision method based on edge calculation and related device |
| CN111976718A (en) * | 2020-07-13 | 2020-11-24 | 浙江大华汽车技术有限公司 | Automatic parking control method and system |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011209070A (en) * | 2010-03-29 | 2011-10-20 | Daihatsu Motor Co Ltd | Image processor |
| CN108512880B (en) * | 2017-02-28 | 2021-02-23 | 上海诺基亚贝尔股份有限公司 | Communication method and communication device |
| EP3401891B1 (en) * | 2017-05-09 | 2022-12-28 | Deutsche Telekom AG | Distributed consensus networks supporting mobile edge computing |
| CN109949598A (en) * | 2019-04-17 | 2019-06-28 | 江苏小白兔网络科技有限公司 | A kind of automated parking system and the parking method suitable for the parking system |
| CN110660221A (en) * | 2019-10-09 | 2020-01-07 | 浙江省交通规划设计研究院有限公司 | Information interaction method and device based on vehicle-road cooperative system |
| CN111341136A (en) * | 2020-02-11 | 2020-06-26 | 浙江吉利汽车研究院有限公司 | Passenger-riding parking method, system and storage medium based on vehicle-road cooperation |
| CN111311944A (en) * | 2020-02-19 | 2020-06-19 | 江苏大学 | Parking lot management system and method under autonomous passenger-riding parking environment |
| CN111768647A (en) * | 2020-05-29 | 2020-10-13 | 同济大学 | Autonomous parking method and device based on mobile edge calculation |
| CN112002139A (en) * | 2020-07-24 | 2020-11-27 | 南京市德赛西威汽车电子有限公司 | Unmanned intelligent parking method and system based on V2X technology |
-
2020
- 2020-12-04 CN CN202011402894.9A patent/CN112562409B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107074233A (en) * | 2014-10-27 | 2017-08-18 | 罗伯特·博世有限公司 | For the method for the automatic parking process for performing vehicle |
| CN107054466A (en) * | 2016-02-11 | 2017-08-18 | 通用汽车环球科技运作有限责任公司 | Parking assistance system and its application method for vehicle |
| KR102073929B1 (en) * | 2018-08-02 | 2020-02-05 | (주)유비벨록스모바일 | Vehicle Emergency Log system using blockchain network |
| CN111640330A (en) * | 2020-05-29 | 2020-09-08 | 深圳市元征科技股份有限公司 | Anti-collision method based on edge calculation and related device |
| CN111976718A (en) * | 2020-07-13 | 2020-11-24 | 浙江大华汽车技术有限公司 | Automatic parking control method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112562409A (en) | 2021-03-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112562409B (en) | Autonomous parking system and method based on multi-access edge calculation | |
| US11881101B2 (en) | Intelligent road side unit (RSU) network for automated driving | |
| CN110603181B (en) | Intelligent driving vehicle yielding method and device and vehicle-mounted equipment | |
| RU2733015C1 (en) | Real-time vehicle control | |
| Bevly et al. | Lane change and merge maneuvers for connected and automated vehicles: A survey | |
| EP3357049B1 (en) | Transmission of targeted roadway alerts | |
| RU2734732C1 (en) | Traffic network blocking tracking during operational control of autonomous vehicle | |
| CN111902782A (en) | Centralized shared autonomous vehicle operation management | |
| CN115016474A (en) | Control method, road side equipment, cloud control platform and system for cooperative automatic driving of vehicle and road | |
| CN213461826U (en) | Autonomous parking system based on multi-access edge calculation | |
| KR102386960B1 (en) | Connected Automated Vehicle Road Systems and Methods | |
| US20200272159A1 (en) | Method and vehicle control system for intelligent vehicle control about a roundabout | |
| US20220375335A1 (en) | Autonomous Vehicle and Cloud Control System | |
| CN114501385A (en) | Collaborative automatic driving system applied to intelligent network connection traffic system | |
| Yue et al. | Evolution of road traffic congestion control: A survey from perspective of sensing, communication, and computation | |
| CN113844465B (en) | Automatic driving method and system | |
| Iovine et al. | Safe human-inspired mesoscopic hybrid automaton for autonomous vehicles | |
| Boubakri et al. | High definition map update for autonomous and connected vehicles: A survey | |
| US11897503B2 (en) | Method and apparatus for detecting unexpected control state in autonomous driving system | |
| Pechinger et al. | Benefit of smart infrastructure on urban automated driving-using an av testing framework | |
| CN110599790B (en) | Method for intelligent driving vehicle to get on and stop, vehicle-mounted equipment and storage medium | |
| US11961403B2 (en) | Lane monitoring during turns in an intersection | |
| EP3943352A1 (en) | Driving control method, apparatus, device, medium, and system | |
| US20220105955A1 (en) | Metrics for Evaluating Autonomous Vehicle Performance | |
| CN112991741B (en) | Traffic flow prediction method and device |
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 |