CN111949037A - Automatic driving system and method for internet vehicle - Google Patents
Automatic driving system and method for internet vehicle Download PDFInfo
- Publication number
- CN111949037A CN111949037A CN202010870277.5A CN202010870277A CN111949037A CN 111949037 A CN111949037 A CN 111949037A CN 202010870277 A CN202010870277 A CN 202010870277A CN 111949037 A CN111949037 A CN 111949037A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- module
- cloud
- automatic driving
- application
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 57
- 230000006855 networking Effects 0.000 claims description 34
- 238000004891 communication Methods 0.000 claims description 30
- 230000008569 process Effects 0.000 claims description 25
- 239000002245 particle Substances 0.000 claims description 24
- 238000004422 calculation algorithm Methods 0.000 claims description 23
- 238000012544 monitoring process Methods 0.000 claims description 20
- 238000013439 planning Methods 0.000 claims description 15
- 238000003860 storage Methods 0.000 claims description 15
- 238000001514 detection method Methods 0.000 claims description 13
- 230000007246 mechanism Effects 0.000 claims description 10
- 238000005516 engineering process Methods 0.000 claims description 9
- 238000005070 sampling Methods 0.000 claims description 9
- 238000012423 maintenance Methods 0.000 claims description 8
- 230000003068 static effect Effects 0.000 claims description 8
- 230000008447 perception Effects 0.000 claims description 2
- 238000007726 management method Methods 0.000 abstract description 14
- 238000004519 manufacturing process Methods 0.000 abstract description 8
- 238000004364 calculation method Methods 0.000 abstract description 5
- 230000006870 function Effects 0.000 description 11
- 238000011161 development Methods 0.000 description 6
- 238000009826 distribution Methods 0.000 description 6
- 230000002085 persistent effect Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 230000001133 acceleration Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 4
- 238000013461 design Methods 0.000 description 4
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000000903 blocking effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000012952 Resampling Methods 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000000747 cardiac effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 210000001503 joint Anatomy 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000002688 persistence Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0238—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors
- G05D1/024—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors in combination with a laser
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0214—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with safety or protection criteria, e.g. avoiding hazardous areas
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0223—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving speed control of the vehicle
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0225—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving docking at a fixed facility, e.g. base station or loading bay
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0257—Control of position or course in two dimensions specially adapted to land vehicles using a radar
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Aviation & Aerospace Engineering (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Optics & Photonics (AREA)
- Electromagnetism (AREA)
- Traffic Control Systems (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
Abstract
The invention discloses an automatic driving system of a networked vehicle, wherein an information platform of the automatic driving system is used for providing data sharing service for automatic driving related application; the application system is used for solving the driving problem of a certain scene; the cloud control system realizes automatic driving control and management; the internet vehicle body executes the command sent by the cloud control system and continuously reports the state of the internet vehicle body. The internet vehicle body of the automatic driving system of the internet vehicle provided by the invention is simplified, a plurality of complicated control logics and sensors are removed, the cloud control system realizes standardized unified commands, the manufacturing cost is low, and the automatic driving system of the internet vehicle is suitable for wide popularization. The invention also discloses an automatic driving method of the internet vehicle, which solves the problems that in the prior art, the automatic driving vehicle needs a large amount of positioning calculation, so that analytic equipment such as a sensor is too complex, the manufacturing cost is high, and the practicability is low.
Description
Technical Field
The invention relates to the technical field of automatic driving, in particular to an automatic driving system and method for an internet vehicle.
Background
At present, the automatic driving technology gets more and more extensive attention, and the machine vision technology based on the deep learning method becomes one of the most popular researches in the field of vehicle-mounted automatic driving, wherein one realization mode is to directly utilize a camera to obtain image information and utilize a deep neural network to map the image information to driving operation so as to realize complete automatic driving. However, the weather conditions, illumination and the like greatly interfere with the information acquired by the camera, so that the automatic driving technical route realized based on the camera has great potential safety hazards.
In the prior art, the automatic driving process of the vehicle which is responsible for sensing data processing and action decision-making is still arranged on the vehicle, so that the vehicle needs to be provided with a high-performance processor, and the manufacturing cost of the vehicle is increased. However, in the face of huge traffic conditions and various road conditions, huge data volume and increasingly complex algorithm models tend to appear. In such a case, the data processor mounted on the vehicle with limited space and energy is limited in the computing power, and thus has no practical application value. The vehicles are regarded as main bodies which independently walk, and each vehicle bears respective driving tasks and safety responsibilities, so that the high efficiency and the safety of traffic are difficult to guarantee.
In view of the above, it is desirable to design an apparatus and method for solving the problems of high manufacturing cost of the vehicle and low efficiency and safety of the vehicle as an independent subject during operation due to high configuration of the sensor and the data processor of the autonomous vehicle in the prior art.
Disclosure of Invention
In view of the above-mentioned drawbacks, the present invention provides an online automatic driving system and method for solving the problems of high vehicle manufacturing cost and low efficiency and safety of the vehicle as an independent main body during operation due to high configuration of the sensor and the data processor of the automatic driving vehicle in the prior art.
The invention provides an automatic driving system of a networked vehicle, which comprises:
the application system is used for realizing travel service under a certain specific scene;
the information platform is electrically connected with a series of application systems and is provided with a data sharing module;
the cloud control system is electrically connected with the information platform and is provided with a tracking module, and the tracking module is used for controlling the vehicle to run along a given track;
the internet vehicle body is provided with a terminal system, and the terminal system is electrically connected with the cloud control system.
Preferably, the application system comprises:
the application networking module is electrically connected with the information platform and the cloud control system respectively;
the motion planning module is electrically connected with the application networking module;
the application storage module is electrically connected with the application networking module;
the application monitoring module is electrically connected with the application networking module and is used for monitoring road information in the automatic driving process;
and the environment module is respectively electrically connected with the application networking module and the motion planning module and is used for supporting module replacement between application scenes.
Preferably, the cloud control system includes:
the vehicle cloud networking module is electrically connected with the information platform;
the internet communication module is respectively and electrically connected with the vehicle cloud internet module and the internet vehicle body;
the vehicle cloud storage module is respectively and electrically connected with the vehicle cloud internet module and the internet vehicle communication module, and is provided with a vehicle cloud memory database and a vehicle cloud relation database;
and the vehicle cloud monitoring module is electrically connected with the internet communication module.
Preferably, the internet protocol car body further comprises an actuating mechanism, the actuating mechanism is electrically connected with the terminal system, and the terminal system comprises:
the terminal networking module is electrically connected with the cloud control system;
the detection module is electrically connected with the terminal networking module and is used for detecting the physical state of the detection module in real time and feeding the physical state back to the cloud control system;
the anti-collision module is electrically connected with the detection module and is used for detecting short-distance obstacle information and sending out an operation stop instruction;
the decision-making module is electrically connected with the anti-collision module and the terminal networking module respectively;
and the bus communication module is electrically connected with the execution mechanism and the decision module respectively.
The invention also provides an automatic driving method of the internet vehicle, which comprises the following specific steps:
step 4, the application program system sends the driving path to a vehicle-end cloud server and stores the driving path into a cloud platform database, and the vehicle-end cloud server analyzes the driving path into a vehicle driving control command after acquiring the vehicle driving path;
and 5, the vehicle-end cloud server acquires the positioning data of the vehicle in real time, and operates the vehicle to run according to the vehicle running control instruction until the vehicle reaches the target position.
Preferably, the step 1 specifically comprises the following steps:
step 1.1, establishing a cloud platform based on an RPC technology, wherein the cloud platform provides a data description service based on a web interface;
step 1.2, a developer registers login and information maintenance on a cloud platform server, wherein the information maintenance comprises entering and maintaining an application page and configuring shared data;
and step 1.3, registering and logging in a cloud platform client by a user, inputting keywords on a web page, and searching corresponding data description.
Preferably, the step 3 specifically comprises the following steps:
step 3.1, constructing a static map, and determining the position of the vehicle on the static map;
step 3.2, calibrating the vehicle positioning position according to the information of the grid map;
and 3.3, planning a path and navigating the vehicle according to the information of the topological map.
Preferably, the step 5 specifically comprises the following steps:
step 5.1, calculating by combining the planned path to generate a vehicle tracking instruction, and operating the vehicle to enter the planned track;
step 5.2, solving the problem of pose tracking by adopting a laser scan profiler software package, enabling the sensor to become an independent positioning device, and performing local pose tracking after the vehicle enters a planned track;
and 5.3, carrying out global position estimation by using a Monte Carlo positioning algorithm and a KLD sampling method.
Preferably, the step 5.1 comprises the following specific steps:
step 5.1.1, establishing a global coordinate system according to the track map, and positioning the coordinates of the vehicle under the global coordinate system;
step 5.1.2, finding the closest point of the vehicle to the reference track to position the position of the vehicle on the reference path;
step 5.1.3, selecting a fixed pre-aiming distance, and then finding the farthest point on the reference path in the pre-aiming distance to determine the point as a target point;
step 5.1.4, converting the target point into a vehicle coordinate system;
step 5.1.5, calculating the curvature and the corner of the front wheel;
and 5.1.6, updating the position of the vehicle, returning to the step 5.1.1, and repeating the steps until the end of the planned track is reached.
Preferably, said step 5.3 is in particular:
step 5.3.1, selecting a weighted particle sample by adopting a KLD sampling method;
step 5.3.2, in the prediction process, according to the weight of the particles from Bel(s)t-1) Randomly extracting particles from the sample
Then obtaining new particles according to the pose motion information output by the laser scan mather software package
Step 5.3.3, in the updating process, updating the particles according to the sensor perception data
Corresponding probability
Step 5.3.4, Bel(s) according to the time t-1t-1) Estimate Bel(s) at time tt)；
Step 5.3.5, at Bel(s)t) Selecting the maximum weight value from the N samples
Corresponding position
As an estimate of the current position of the mobile object.
According to the scheme, the information platform of the internet automatic driving system is used for providing data sharing service for automatic driving related application; the application system is an automatic driving application under each scene or a related application serving automatic driving and is used for solving the driving problem of a certain scene; the cloud control system is a complete system for automatic driving control and management, and provides automatic driving control service for the outside; the internet vehicle body is an execution carrier, executes commands sent by the cloud control system and continuously reports the state of the internet vehicle body. The internet vehicle body is simplified, a plurality of complicated control logics and sensors are removed, the cloud control system realizes standardized unified commands, the vehicle only needs to translate the control commands sent from the cloud into corresponding execution commands according to a specific command format, the manufacturing cost is low, the effect is obvious, and the internet vehicle is suitable for wide popularization. The invention also provides an automatic driving method of the internet, which solves the problems that in the prior art, the automatic driving vehicle needs a large amount of positioning calculation, so that analytic equipment such as a sensor is too complex, the manufacturing cost is high, and the practicability is low.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic block diagram of a structure of an internet automatic driving system according to an embodiment of the present invention;
fig. 2 is a first process block diagram of an internet vehicle automatic driving method according to an embodiment of the present invention;
fig. 3 is a process block diagram ii of an automatic driving method for internet vehicles according to an embodiment of the present invention;
fig. 4 is a process block diagram three of an internet automatic driving method provided by the embodiment of the invention;
fig. 5 is a process block diagram of an automatic driving method of an internet vehicle according to an embodiment of the present invention.
In the figure:
1. an application system; 2. an information platform; 3. a cloud control system; 4. a network connection vehicle body; 41. a terminal system; 42. an actuator; 411. a terminal networking module; 412. a detection module; 413. an anti-collision module; 414. a decision-making module; 415. and a bus communication module.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1
Referring to fig. 1 to 5, an embodiment of an automatic driving system for a networked vehicle according to the present invention will now be described. The automatic driving system of the internet connection vehicle comprises an application system 1, an information platform 2, a cloud control system 3 and an internet connection vehicle body 4, wherein the application system 1 is used for realizing travel service in a certain specific scene; the information platform 2 is electrically connected with a series of application systems 1 and is provided with a data sharing module; the cloud control system 3 is electrically connected with the information platform 2 and is provided with a tracking module, and the tracking module is used for controlling the vehicle to run along a given track; the internet vehicle body 4 is provided with a terminal system 41, and the terminal system 41 is electrically connected with the cloud control system 3.
The information platform 2 is used to provide data sharing services for the autopilot-related applications. The information platform 2 provides all data associated with the user for the accessed application system 1, and the application system 1 needs to support all users on the information platform 2, that is, the users on the information platform 2 can directly access the application system 1 without re-registration, and the application system 1 needs to provide all data manipulation of the information platform 2 user. In this way, no data barrier is available whether to apply improvement services or research institutes.
The information platform 2 stores and retrieves basic user information, retrieves and tracks user application behavior data, and maintains application information. The storage of the user basic information mainly refers to the storage of user attribute information. The information platform 2 is not responsible for storing a large amount of data, and the information service information platform 2 adopts a web management interface for data detailed description and use introduction of the application system 1 of the developer. The application information is mainly to solve the auditing of application access and how to retrieve application services from a unified APP portal.
The application system 1 is mainly an automatic driving application in each scene or a related application serving automatic driving, and is used for solving a problem of a certain scene, for example, a parking lot application is used for solving a parking problem of a parking lot. In some scenarios, some applications may have specific environmental sensors, for example, when the application is used in a parking lot, the parking lot needs to include an environmental sensing module for acquiring sensing data, and the sensing data may be directly used by the cloud control system 3 to realize automatic driving.
The cloud control system 3 is a complete system for automatic driving control and management, and the cloud control system 3 controls the vehicle to track so as to realize automatic driving. Heavy vehicle end logic is put at the cloud end to be realized, and the control system setting of the vehicle and the cost of the vehicle are simplified. The cloud control system 3 is used for application service access and vehicle control, the application service access is mainly responsible for accessing applications and using interfaces provided by services, and the vehicle control is mainly used for controlling vehicles, for example, automatic driving.
The cloud control system 3 is registered on the information platform 2, the information of the external application service to be cooperated is obtained through the information platform 2, the information butt joint with the external application service is realized, and both sides obtain the application identification code which the opposite side agrees to access. And then obtain the data and service support of the other party through the application identification code in each Web request. After the cloud control system 3 obtains the vehicle running path, the path is analyzed into a vehicle running control command, meanwhile, positioning data of the vehicle is obtained in real time from an external application in the vehicle running process, and a planned path is combined to calculate and generate a vehicle tracking command, so that the vehicle is guaranteed to run safely in the planned path. The cloud control system 3 provides basic information of the vehicle for the information platform 2, so that the automatic driving can exert the value in different application scenes, the service of the automatic driving vehicle is expanded, the deep vehicle using experience of a user is realized, and the system is suitable for internet transportation travel. The cloud control system 3 simultaneously manages the service functions of vehicle registration, vehicle online and the like, and the system order is ensured.
The tracking module, namely the Auto drive module, realizes the tracking running function of the vehicle, and is a core module for the cloud control system 3 to realize the automatic driving function. And the tracking module controls the vehicle to travel along the track according to the travel track sent by the application system 1 and the real-time position of the vehicle. The Auto drive module comprises various tracking control algorithms, controls the vehicle to accurately track the given track, such as a PID algorithm, a Follow-the-karot algorithm, a Pure Pursuit algorithm and the like, and can continuously increase the tracking control algorithms.
The internet vehicle body 4 is the final execution carrier, and mainly the execution mechanism 42 executes the command sent by the cloud control system 3 and continuously reports the state of the internet vehicle body. The internet vehicle body 4 is simplified, a plurality of complicated control logics and sensors are removed, the cloud control system 3 realizes standardized unified commands, and the vehicle only needs to translate the control commands sent by the cloud into corresponding execution commands according to a specific command format of the vehicle. The internet vehicle body 4 is started, namely, the internet vehicle body 4 is connected with the cloud control system 3 to obtain the road driving right, and the internet vehicle body 4 accurately executes the control instruction of the cloud end to realize physical displacement.
Example 2
As a specific implementation manner of the embodiment of the present invention, please refer to fig. 1 to 5 together, the structure of the online vehicle automatic driving system provided in this embodiment is basically the same as that of embodiment 1, and the difference is that the application system 1 includes an application online module, a motion planning module, an application storage module, an application monitoring module and an environment module, wherein the application online module is electrically connected to the information platform 2 and the cloud control system 3, respectively; the motion planning module is electrically connected with the application networking module; the application storage module is electrically connected with the application networking module; the application monitoring module is electrically connected with the application networking module and is used for monitoring road information in the automatic driving process; the environment module is respectively electrically connected with the application networking module and the motion planning module and is used for supporting module replacement among application scenes. The modularized design of the cloud control system 3 reduces the coupling of the program, is beneficial to the parallel development and the rapid iteration of the program, and realizes the replaceability of the program module.
The application networking module is responsible for introducing external services, acquires data support from the application storage module after acquiring an external request, calls the motion planning module, the application monitoring module and the environment module to assist in request processing, realizes cooperation with other applications, and completes interaction with users.
The application networking module, namely the application Web module, responds to an external HTTP request, wherein the external services comprise an information platform 2, a cloud control system 3 and other value-added service applications. The module acquires user data of the platform, acquires data and service support of other value-added service applications, simultaneously opens related data to the information platform 2, displays automatic driving information to a user through the module application, receives an automatic driving instruction of the user and the like.
The application Web module is used for acquiring user data of the information platform 2 and sending automatic driving journey data to the information platform 2; and the system is used for sending the path planned for the internet connection vehicle body 4 to the cloud control system 3 and acquiring real-time positioning information of the internet connection vehicle body 4. Specifically, when the information platform 2 has a new user registration, the information platform 2 performs statistics and broadcasts user data to the application system 1 at regular time. The application Web module converts information sent from the cloud platform into a series of user data, stores the user data into a database, and simultaneously quantitatively sends the automatic driving data to the information platform 2.
The motion planning module, namely the Core module, can realize service logic analysis, such as intelligent allocation of automatic driving paths, analysis and processing of automatic driving data and the like. And each service logic under the large module of the Core module is divided into various small modules, so that the service granularity is refined, the program coupling is reduced, and the program replaceability and expandability are realized. The Core module has the main function of realizing dynamic scientific planning of an automatic driving path, can realize intensive parking and efficient vehicle taking when applied to an automatic parking scene of a parking lot, improves the capacity of the parking lot, avoids collision accidents in the process of vehicle taking and storing, and increases the economic benefit of the parking lot.
The application storage module, namely the application Database module, is responsible for completing the management operation of data, so that the data sharing is realized, and the module coupling degree is reduced. The application Database module comprises an application memory Database and a persistent relational Database. The memory database realizes high-performance reading and writing, and periodically persists the content of the memory database to a disk by using the relational database. The memory database has high access performance, meets the high requirement of the access of the data on the real-time performance, and can use a Redis memory database as an exemplary memory database. The persistent relational database manages persistent data conveniently, and an exemplary persistent relational database may use a MySQL database.
And the application monitoring module is used for managing and monitoring the negative cardiac automatic driving environment of the Manage module, and comprises monitoring and alarming the real-time state of the automatic driving environment.
The Environment module, namely the Environment module, is a common module in all application scenes of automatic driving of the vehicle, well supports module replacement between the application scenes, and is responsible for providing basic Environment sensing data for the cloud control system 3 and providing data support for realizing automatic driving. The Environment module comprises a Map module and a Route module. The modular design is beneficial to reuse and replacement of Environment modules. The Map management module, namely the Map module, is responsible for carrying out function management such as processing and conversion on a Map, wherein the conversion function of the Map can process a radar Map into a coordinate Map through an Open CV, and the vehicle positioning coordinates correspond to the radar Map so as to realize real-time display of the vehicle position in the Map; and the path planning module, namely the Route module, plans the path for the vehicle according to the map of the vehicle, the real-time positioning data and the target positioning position.
In this embodiment, the cloud control system 3 includes a vehicle cloud networking module, a networking vehicle communication module, a vehicle cloud storage module and a vehicle cloud monitoring module, wherein the vehicle cloud networking module is electrically connected with the information platform 2; the internet communication module is respectively and electrically connected with the vehicle cloud internet module and the internet vehicle body 4; the vehicle cloud storage module is respectively and electrically connected with the vehicle cloud networking module and the networking communication module, and is provided with a vehicle cloud memory database and a vehicle cloud relation database; the vehicle cloud monitoring module is electrically connected with the internet communication module.
The vehicle cloud networking module, that is, the vehicle cloud Web module, is responsible for responding to the Restful request, receiving the Http request, for example, other servers call open interfaces through Http, and the interfaces acquire the current state and the current position of the vehicle and the automatic driving service, and further include a request sent by the client of the information platform 2.
The car cloud Web module uses http (hyper text transport protocol) communication protocol, and also uses Restful interface specification. The HTTP communication protocol facilitates data communication between applications and introduction of foreign services. The Restful specification unifies Web interfaces, reduces code amount, simplifies system design, and provides an architecture style criterion for constructing a Web program with high performance, simplicity and portability. The vehicle cloud Web module realizes automatic driving and is applied to various specific scenes.
The internet communication module, i.e. the I/O module, realizes the functions of high-performance TCP/IP connection and data receiving and sending, and then stores the received data through the interface of the application storage module. The data sent to the I/O module comprises a vehicle and a networking sensor on the vehicle, the data received by IO are directly output to the application storage module, and efficient writing is achieved by utilizing memory data storage. And the module for sending data to the outside through the I/O is an Autodrive module.
The I/O communication module uses the TCP communication protocol and a high performance MINA framework. The TCP communication protocol ensures the reliability and stability of communication and can uniformly process communication data with various formats. The MINA framework is designed based on Java NIO, namely an IO mechanism which is synchronous and non-blocking, and the multiplexer is responsible for managing connection requests of clients, polling whether I/O requests exist or not, and creating a thread for each I/O request if the I/O requests exist. The NIO mode is suitable for a multi-short-connection-number architecture and accords with the condition of multi-client request of a vehicle cloud control system 3. Meanwhile, the MINA framework skillfully adopts a loose coupling framework to flexibly load a filter mechanism, and unit testing is easier to realize; the number of threads can be customized to improve the performance of running on the multiprocessor; and the calling is completed in a callback mode, so that the use of the thread is easier. The MNA framework enables the IO communication module to achieve high performance and high scalability.
In order to simplify the vehicle and reduce the communication load, the screened internet vehicle body 4 mainly uploads the basic information, vehicle ready information, vehicle motion state and vehicle operation state of the vehicle to the cloud control system 3. The internet vehicle body 4 can send basic vehicle information to the cloud control system 3 in modes of scanning two-dimensional codes or bar codes and the like, registration operation of the internet vehicle body 4 is completed, and the basic vehicle information is used for placement and path planning of the internet vehicle body 4. The vehicle ready information is used for informing the vehicle-end cloud server that the vehicle is ready, can realize communication with the cloud control system 3, and receives management and automatic driving control of the cloud control system 3. The internet vehicle body 4 starts to send motion state information of the vehicle such as speed, acceleration and direction in real time after being started, and the cloud control system 3 calculates according to the motion state information of the vehicle, real-time positioning of the vehicle and a planned path of the vehicle to obtain a vehicle tracking control instruction, so that the intelligent vehicle runs according to the planned path. The vehicle operation state comprises operation state information such as vehicle fault codes and the environment in the vehicle, and the cloud control system 3 distributes maintenance personnel for the faulty vehicle after receiving the fault code information and stores historical faults and leaves a record.
The vehicle cloud storage module, namely the vehicle cloud Database module, comprises a vehicle cloud memory Database and a persistent relational Database. The cloud control system 3 is required to store not only data with few modification and query operations, such as vehicle basic information, but also real-time vehicle motion state information and real-time vehicle running state information, which are frequently accessed and have high requirements for real-time performance. And the vehicle cloud memory database performs high-performance data storage and examination operation. The vehicle cloud memory database can be a Redis database. The Redis database has high-efficiency reading and writing efficiency and rich data structures, supports high-level functions such as sequencing and the like, supports data persistence and can regularly brush data on a disk. Relational databases facilitate flexible management of persistent data. The relational database may be a MySQL database. The MySQL database is light and efficient; open source, free and good expansibility; the portability is high, the system can run under a Windows or Linux platform, supports multiple languages, and can be better matched with server software development; the standardized database operation language is used, and the development difficulty is low.
The vehicle cloud monitoring module, namely the vehicle cloud management module, realizes vehicle management and vehicle monitoring. The vehicle management comprises the functional business of adding, deleting, changing, checking and the like of the vehicle and the related accessories of the vehicle. Vehicle monitoring includes monitoring and alerting of the real-time status of the vehicle. And when the monitored real-time state is not in the threshold range, triggering an alarm event, calling a corresponding processing method and simultaneously sending the alarm event to the information platform 2 client for displaying. Alarm events are described by human pre-defined thresholds, error codes, events, and stored.
In this embodiment, the internet vehicle body 4 further includes an executing mechanism 42, the executing mechanism 42 is electrically connected to the terminal system 41, the terminal system 41 includes a terminal internet module 411, a detecting module 412, an anti-collision module 413, a decision module 414 and a bus communication module 415, wherein the terminal internet module 411 is electrically connected to the cloud control system 3; the detection module 412 is electrically connected with the terminal networking module 411, and the detection module 412 is used for detecting the physical state of the detection module in real time and feeding the physical state back to the cloud control system 3; the anti-collision module 413 is electrically connected with the detection module 412, and the anti-collision module 413 is used for detecting short-distance obstacle information and sending out an operation stop instruction; the decision module 414 is electrically connected to the anti-collision module 413 and the terminal networking module 411 respectively; the bus communication module 415 is electrically connected to the execution mechanism 42 and the decision module 414, respectively.
The internet vehicle body 4 detects the physical state (such as speed, acceleration and positioning coordinates) of the internet vehicle body in real time, sends the state heartbeat to the cloud control system 3, and accurately executes a control instruction of the cloud, so that accurate physical displacement is realized, and the safety of a traffic road is ensured. The anti-collision module 413 detects short-distance obstacles to deal with sudden road conditions, and once the vehicle detects abnormal obstacles on the road in front, the vehicle can wait for cloud dispatching or the road returns to normal only by stopping. The detection module 412 performs vehicle physical information monitoring, such as speed, acceleration, and electrical quantity information. The cloud control system 3 grasps physical information of all vehicles in the traffic network, so as to perform real-time scheduling and control, such as vehicle change, acceleration and deceleration, or battery replacement when going to a charging station.
In the embodiment, the information platform 2 adopts a K/V key value pair form to store and solve the problem of uncertainty of the platform data format, and is suitable for flexibly storing structured and unstructured data. Because the support of the NoSQL on unstructured and semi-structured data enables the development to be simple in many specific scenes, for the business which is weakly dependent on the SQL, the introduction of the NoSQL not only reduces the cost per se, but also increases the expansibility and the performance of the system. The information platform 2 comprises a server and a client, wherein the client is a service object of the platform, specifically comprises an externally accessed intelligent traffic related application, an application management client provided for a developer and a client APP of a trip application portal provided for a common user; the server comprises a data sharing support module, a console service module and a portal APP service module, wherein the data sharing support module is used for providing data sharing for the application. The data sharing module mainly realizes a uniform data sharing interface. The console service module provides functions of application registration, application management, data management and the like for the control client. The portal APP server side mainly achieves functions of maintaining application information, recommending applications and the like.
The developer client mainly realizes registration login and information maintenance of a developer, and has the main functions of inputting and maintaining an application page and configuring shared data for the developer; the client APP mainly realizes login and registration of a common user and jumps to each application as an application entrance. The application system 1 makes full use of data and services under the information platform 2, can reduce the development period, concentrates on specific fields, and reduces the application cost.
After the user logs in the information platform 2 client, the client communication module binds the user, the vehicle id and the session, and after the user selects the destination, the destination map id and the session are also bound. After the user presses the automatic driving button, the sensing module of the internet vehicle body 4 continuously acquires the positioning data production positioning coordinate of the internet vehicle body, stores the positioning coordinate into the memory database and sends the positioning coordinate to the cloud control system 3. The Core module plans a proper parking position for the vehicle, reads the latest positioning data of the vehicle from the database, and plans an optimal driving path between the vehicle position and the parking position. And then the vehicle-end cloud communication module sends the path to the vehicle-end cloud and stores the path in a database. The intelligent unmanned parking lot application system 1 continuously acquires and calculates the real-time vehicle position, and sends the real-time vehicle position coordinates to the vehicle-end cloud server until the vehicle reaches the planned position.
Example 3
Referring to fig. 1 to 5, an embodiment of an automatic driving method for a internet vehicle according to the present invention will now be described. The automatic driving method of the internet vehicle comprises the following specific steps:
s1, a cloud platform is established and opened, a developer registers an application program system on the cloud platform and configures information, a user registers and logs in the cloud platform, and data sharing is carried out in the cloud platform;
the specific implementation steps of the step can be as follows:
s1.1, establishing a cloud platform based on an RPC technology, wherein the cloud platform provides a data description service based on a web interface;
the cloud platform provides a data description service based on a web interface to unify the description of data. The cloud platform adopts Remote Procedure Call (RPC) service based on Nety to realize the sending and receiving of data. RPC is an intermediary technology that requests services from a remote computer program over a network without having to know the underlying network technology. An IO model under a Java environment comprises a plurality of frames, an NIO frame (No-block IO) which is a common synchronous non-blocking framework is adopted for carrying out server back-end development, and the problem that RPC development is complex due to the fact that details such as TCP package sticking, network communication abnormity, link processing and the like need to be considered when a TCP/HTTP server is realized is solved. The main NIO frames are mainly Nety and Mina. Nety has all the characteristics of Mina, and currently, Nety has a more active community and is maintained more frequently.
S1.2, a developer registers login and information maintenance on a cloud platform server, wherein the information maintenance comprises entering and maintaining an application page and configuring shared data;
the specific process of the developer configuring the application data to realize the sharing of the data comprises the following steps:
s1.2.1, applying for APPID, wherein the APPID is uniformly generated and distributed by a cloud platform, and each APPID corresponds to one application on the platform and is the unique identifier of the application;
s1.2.2, filling basic information of the application, wherein the basic information comprises information such as the name, the category, LOGO, keywords and the like of the application, and the category and the keywords are convenient for a user to search and inquire;
s1.2.3, filling shared data information of the application, wherein the shared data information comprises basic information description of data fields uploaded by the application, frequency of data uploaded by the application, data format uploaded by the application and the like;
s1.2.4, after the application is submitted and checked, once the data information generated when the user uses the application is generated, the application data can be uploaded to the cloud platform, the application data information of the application related user can be retrieved on the cloud platform, and the related data information can be downloaded.
S1.3, a user registers and logs in at a cloud platform client, keywords are input into a web page, and corresponding data description is searched.
S2, when the vehicle-mounted sensor is used, an application program in a required scene is selected at the client, an automatic driving instruction is issued in the application program, and meanwhile, the vehicle-mounted sensor acquires vehicle positioning information, stores the vehicle positioning information and sends the vehicle positioning information to a vehicle cloud server;
s3, the application program system plans a proper parking position for the vehicle according to the destination information selected by the user, reads the latest positioning data of the vehicle from the database of the vehicle-side cloud server, plans an optimal driving path between the vehicle position and the parking position, divides and refines the driving path into a series of coordinate points, and smoothes the path coordinate points, so that the vehicle can run more stably and safely;
the specific implementation steps of the step can be as follows:
s3.1, constructing a static map, and determining the position of the vehicle on the static map;
the specific implementation steps of the step can be as follows:
s3.1.1, building a grid map of the parking lot based on the GMapping method of the laser radar;
the GMapping algorithm is a Rao-Blackwellized Particle Filter (RBPF) SLAM algorithm based on a laser radar and a milemeter, and is the SLAM algorithm which is most widely applied in the field of robots. Odometers are a method of using data obtained from a motion sensor to estimate the change in the position of an object over time. The adaptive resampling technique in the GMapping algorithm minimizes the impact of particle depletion problems. When the technology is used for calculating the particle distribution, the uncertainty of the pose of the moving object in the prediction stage of particle filtering is reduced, and the requirement on the number of particles is reduced.
Grid maps are maps where sensors such as lidar are used for location. Grid maps are composed of a series of grids containing static elements, such as walls, obstacles, pillars, etc., that permanently occupy space within a parking lot.
S3.1.2, establishing a topological map on the grid map;
the topological map is used for providing topological information to the automatic driving system and is a second-layer map added on the static map. The topological map is composed of points and lines and comprises elements of parking space positions, lane lines, intersections and the like, wherein the elements can describe drivable areas in the parking lot.
S3.1.3, aligning the grid map and the topological map.
S3.2, calibrating the vehicle positioning position according to the information of the grid map;
specifically, a laser scanner mather software package is used for replacing a speedometer, and the laser radar is enabled to be an independent indoor positioning device, so that additional devices are reduced as far as possible. Given two scan point sets X ═ X1，K，xnP ═ P1，K，pnThe ICP algorithm is used to find the translation t and rotation R to minimize the sum of squared differences between the point sets,
the Laser scan simulator software package can provide pose estimation only by depending on Laser scanning equipment, adopts an Iterative Closest Point (ICP) variant algorithm based on a Point-to-Line Metric, and is a rapid increment Laser scanning matching algorithm.
And S3.3, planning a path and navigating the vehicle according to the information of the topological map.
Specifically, the key idea in applying RBPF to SLAM is based on the sensor observations z of the mobile robot1:t＝z1，K，ztAnd a track measurement u1:t-1＝u1，K，ut-1Calculating information about the map m and the trajectory x1:t＝x1，K，xtA posteriori probability p (x)1:t,m|z1:t,u1:t-1) The GMapping algorithm utilizes p (x)1:t,m|z1:t,u1:t-1)＝p(m|x1:t,z1:t)*p(x1:t|z1:t,u1:t-1) And (4) factorizing to obtain a track calculation map, wherein the GMapping algorithm depends on a milemeter. When the GMaping algorithm is used, the -rate parameter setting of the grid map is particularly important for the influence of the output map. For example, the best mapping effect can be obtained by setting the resolution of the grid map to lcm based on the ranging accuracy and the ranging range of the radar.
S4, the application program system sends the driving path to the vehicle-end cloud server and stores the driving path into the cloud platform database, and the vehicle-end cloud server analyzes the driving path into a vehicle driving control command after acquiring the vehicle driving path;
and S5, the vehicle-end cloud server acquires the positioning data of the vehicle in real time, and operates the vehicle to run according to the vehicle running control instruction until the vehicle reaches the target position.
The sensor localization problem is divided into local pose tracking and global position estimation. The former means that the initial pose of the moving object is known, and the position of the moving object in the map is estimated according to the observation information of the sensor; if the initial pose of the moving object is unknown, or the pose of the moving object is changed during the tracking process, i.e., without notification of the moving object, as a global positioning estimation problem.
The specific implementation steps of the step can be as follows:
s5.1, calculating by combining the planned path to generate a vehicle tracking instruction, and operating the vehicle to enter the planned track;
based on the vehicle kinematic model, the center of the rear wheel is a tangent point, the vehicle body is a tangent line, and the vehicle runs back to the reference track along an arc by controlling the deflection angle of the front wheel. The specific implementation steps of the step can be as follows:
s5.1.1, establishing a global coordinate system according to the track map, and positioning the coordinates of the vehicle under the global coordinate system;
s5.1.2, finding the closest point of the vehicle on the reference track to locate the position of the vehicle on the reference path;
s5.1.3, selecting a fixed pre-aiming distance, and finding the farthest point on the reference path in the pre-aiming distance to determine the point as the target point;
s5.1.4, converting the target point into a vehicle coordinate system;
s5.1.5, calculating curvature and front wheel turning angle;
s5.1.6, updating the vehicle position, and returning to S5.1.1 to repeat the steps until the end of the planned track is reached. Specifically, G is set as a target point on a planned path within a pre-aiming distance, and the center position of a rear wheel of the vehicle is set as MrThe turning radius of the vehicle is R, the rotation center of the vehicle is P, and the axis of the vehicle body and the straight line ldIs alpha, so thatrPG is 2 alpha, obtaining
Where k is the curvature of the turning arc. After the curvature of the arc of the expected turn is obtained through calculation, the relation between the deflection angle of the front wheel and the curvature is obtained through calculation:
s5.2, solving the problem of pose tracking by adopting a laser scan profiler software package, enabling the sensor to become an independent positioning device, and performing local pose tracking after the vehicle enters a planned track;
s5.3, carrying out global position estimation by using a Monte Carlo positioning algorithm (MCL) and a KLD sampling method.
Specifically, the posterior probability distribution of the position of the moving object is represented by N weighted particles, and the posterior probability of the position of the moving object is obtained
Wherein,
are possible positions of the mobile object and,
is a moving object located
Is also the weight of sample i.
MCL is a probabilistic algorithm for performing mobile object dislocation sub-tracking on a grid map using a particle filtering algorithm. At the beginning of the Monte Carlo positioning algorithm, if the initial position is not specified, N points are randomly selected from the position space of the moving object, and the probability corresponding to each point is set to be 1/N. The positioning process is divided into a prediction process and an update process. The two processes are repeated continuously, and incremental positioning of the moving object is realized.
The KLD sampling method adjusts the sampling times according to the KL distance between the approximate distribution and the real distribution based on the samples, wherein the KL distance is a common measurement of the approximation degree of two probability distributions.
The specific implementation steps of the step can be as follows:
s5.3.1, selecting a weighted particle sample by adopting a KLD sampling method;
specifically, let P ═ P (P)i1,2, K, n) and Q ═ Q (Q)iI ═ 1,2, K, n) are 2 probability distributions, then the KL distance of P, Q is:
s5.3.2, in the prediction process, according to the weight of the particles from Bel(s)t-1) Randomly extracting particles from the sample
Then obtaining new particles according to the pose motion information output by the laser scan mather software package
S5.3.3, in the updating process, the particles are updated according to the sensor sensing data
Corresponding probability
S5.3.4 repeating the above two processes according to Bel(s) at time t-1t-1) Estimate Bel(s) at time tt)；
S5.3.5, in Bel(s)t) Selecting the maximum weight value from the N samples
Corresponding position
As an estimate of the current position of the mobile object.
The MCL algorithm is based on particle filtering, has the advantages of simplicity in implementation, high positioning accuracy, less computing resources and the like, and solves the particle depletion problem by adopting a self-adaptive sampling technology based on KLD (Kullback-Leibler Distance).
The embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same or similar parts among the embodiments are referred to each other. Details which are not described in detail in the embodiments of the invention belong to the prior art which is known to the person skilled in the art.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. An internet vehicle autopilot system, comprising:
the system comprises an application system (1) and a control system, wherein the application system is used for realizing travel service under a certain specific scene;
the information platform (2) is electrically connected with a series of application systems (1) and is provided with a data sharing module;
the cloud control system (3) is electrically connected with the information platform (2) and is provided with a tracking module, and the tracking module is used for controlling the vehicle to run along a given track;
the internet vehicle body (4) is provided with a terminal system (41), and the terminal system (41) is electrically connected with the cloud control system (3).
2. The networked automatic driving system according to claim 1, wherein the application system (1) comprises:
the application networking module is electrically connected with the information platform (2) and the cloud control system (3) respectively;
the motion planning module is electrically connected with the application networking module;
the application storage module is electrically connected with the application networking module;
the application monitoring module is electrically connected with the application networking module and is used for monitoring road information in the automatic driving process;
and the environment module is respectively electrically connected with the application networking module and the motion planning module and is used for supporting module replacement between application scenes.
3. The networked vehicle automatic driving system according to claim 1, wherein the cloud control system (3) comprises:
the vehicle cloud networking module is electrically connected with the information platform (2);
the internet communication module is respectively and electrically connected with the vehicle cloud internet module and the internet vehicle body (4);
the vehicle cloud storage module is respectively and electrically connected with the vehicle cloud internet module and the internet vehicle communication module, and is provided with a vehicle cloud memory database and a vehicle cloud relation database;
and the vehicle cloud monitoring module is electrically connected with the internet communication module.
4. The automatic driving system of the internet vehicle according to claim 1, wherein the internet vehicle body (4) further comprises an actuator (42), the actuator (42) is electrically connected with the terminal system (41), and the terminal system (41) comprises:
the terminal networking module (411) is electrically connected with the cloud control system (3);
the detection module (412) is electrically connected with the terminal networking module (411), and the detection module (412) is used for detecting the physical state of the detection module in real time and feeding the physical state back to the cloud control system (3);
a collision avoidance module (413) electrically connected to the detection module (412), the collision avoidance module (413) configured to detect short-range obstacle information and issue a stop command;
a decision module (414) electrically connected to the collision avoidance module (413) and the terminal networking module (411), respectively;
and the bus communication module (415) is electrically connected with the execution mechanism (42) and the decision module (414) respectively.
5. The automatic driving method of the internet vehicle is characterized by comprising the following specific steps:
step 1, establishing and opening a cloud platform, registering an application program system and configuring information on the cloud platform by a developer, registering and logging in a user on the cloud platform, and sharing data in the cloud platform;
step 2, when the vehicle-mounted sensor is used, an application program in a required scene is selected at a client side, an automatic driving instruction is issued in the application program, and meanwhile, the vehicle-mounted sensor acquires vehicle positioning information, stores the vehicle positioning information and sends the vehicle positioning information to a vehicle-side cloud server;
step 3, the application program system plans a proper parking position for the vehicle according to the destination information selected by the user, reads the latest positioning data of the vehicle from the database of the vehicle-side cloud server, and plans an optimal driving path between the vehicle position and the parking position;
step 4, the application program system sends the driving path to a vehicle-end cloud server and stores the driving path into a cloud platform database, and the vehicle-end cloud server analyzes the driving path into a vehicle driving control command after acquiring the vehicle driving path;
and 5, the vehicle-end cloud server acquires the positioning data of the vehicle in real time, and operates the vehicle to run according to the vehicle running control instruction until the vehicle reaches the target position.
6. The automatic driving method for the internet connected vehicle according to claim 5, wherein the specific steps of the step 1 comprise:
step 1.1, establishing a cloud platform based on an RPC technology, wherein the cloud platform provides a data description service based on a web interface;
step 1.2, a developer registers login and information maintenance on a cloud platform server, wherein the information maintenance comprises entering and maintaining an application page and configuring shared data;
and step 1.3, registering and logging in a cloud platform client by a user, inputting keywords on a web page, and searching corresponding data description.
7. The automatic driving method for the internet connected vehicle according to claim 5, wherein the specific steps in the step 3 comprise:
step 3.1, constructing a static map, and determining the position of the vehicle on the static map;
step 3.2, calibrating the vehicle positioning position according to the information of the grid map;
and 3.3, planning a path and navigating the vehicle according to the information of the topological map.
8. The automatic driving method for the internet connected vehicle according to claim 5, wherein the specific steps in the step 5 comprise:
step 5.1, calculating by combining the planned path to generate a vehicle tracking instruction, and operating the vehicle to enter the planned track;
step 5.2, solving the problem of pose tracking by adopting a laser scan profiler software package, enabling the sensor to become an independent positioning device, and performing local pose tracking after the vehicle enters a planned track;
and 5.3, carrying out global position estimation by using a Monte Carlo positioning algorithm and a KLD sampling method.
9. The automatic driving method for the internet connected vehicle according to claim 8, wherein the specific step of the step 5.1 comprises the following steps:
step 5.1.1, establishing a global coordinate system according to the track map, and positioning the coordinates of the vehicle under the global coordinate system;
step 5.1.2, finding the closest point of the vehicle to the reference track to position the position of the vehicle on the reference path;
step 5.1.3, selecting a fixed pre-aiming distance, and then finding the farthest point on the reference path in the pre-aiming distance to determine the point as a target point;
step 5.1.4, converting the target point into a vehicle coordinate system;
step 5.1.5, calculating the curvature and the corner of the front wheel;
and 5.1.6, updating the position of the vehicle, returning to the step 5.1.1, and repeating the steps until the end of the planned track is reached.
10. The automatic driving method for the internet vehicle according to claim 9, wherein the step 5.3 is specifically:
step 5.3.1, selecting a weighted particle sample by adopting a KLD sampling method;
step 5.3.2, in the prediction process, according to the weight of the particles from Bel(s)t-1) Randomly extracting particles from the sample
Then obtaining new particles according to the pose motion information output by the laser scan mather software package
Step 5.3.3, in the updating process, updating the particles according to the sensor perception data
Corresponding probability
Step 5.3.4, Bel(s) according to the time t-1t-1) Estimate Bel(s) at time tt)；
Step 5.3.5, at Bel(s)t) Selecting the maximum weight value from the N samples
Corresponding position
As an estimate of the current position of the mobile object.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010870277.5A CN111949037A (en) | 2020-08-26 | 2020-08-26 | Automatic driving system and method for internet vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010870277.5A CN111949037A (en) | 2020-08-26 | 2020-08-26 | Automatic driving system and method for internet vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111949037A true CN111949037A (en) | 2020-11-17 |
Family
ID=73367540
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010870277.5A Withdrawn CN111949037A (en) | 2020-08-26 | 2020-08-26 | Automatic driving system and method for internet vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111949037A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113132457A (en) * | 2021-03-02 | 2021-07-16 | 西安电子科技大学 | Automatic method and system for converting Internet of things application program into RESTful service on cloud |
| CN113655790A (en) * | 2021-08-05 | 2021-11-16 | 阿波罗智联(北京)科技有限公司 | Vehicle control method, device, equipment, storage medium and program product |
| CN113686595A (en) * | 2021-09-26 | 2021-11-23 | 国汽智控(北京)科技有限公司 | Vehicle durability test method and device, cloud control platform and system |
| WO2022104747A1 (en) * | 2020-11-20 | 2022-05-27 | 华为技术有限公司 | Method and apparatus for accessing io devices |
| CN114999228A (en) * | 2022-06-01 | 2022-09-02 | 北京易航远智科技有限公司 | Anti-collision method for automatic driving vehicle in severe weather |
-
2020
- 2020-08-26 CN CN202010870277.5A patent/CN111949037A/en not_active Withdrawn
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022104747A1 (en) * | 2020-11-20 | 2022-05-27 | 华为技术有限公司 | Method and apparatus for accessing io devices |
| CN113132457A (en) * | 2021-03-02 | 2021-07-16 | 西安电子科技大学 | Automatic method and system for converting Internet of things application program into RESTful service on cloud |
| CN113132457B (en) * | 2021-03-02 | 2022-06-14 | 西安电子科技大学 | Automatic method and system for converting Internet of things application program into RESTful service on cloud |
| CN113655790A (en) * | 2021-08-05 | 2021-11-16 | 阿波罗智联(北京)科技有限公司 | Vehicle control method, device, equipment, storage medium and program product |
| CN113686595A (en) * | 2021-09-26 | 2021-11-23 | 国汽智控(北京)科技有限公司 | Vehicle durability test method and device, cloud control platform and system |
| CN113686595B (en) * | 2021-09-26 | 2024-05-28 | 国汽智控(北京)科技有限公司 | Vehicle endurance test method, device, cloud control platform and system |
| CN114999228A (en) * | 2022-06-01 | 2022-09-02 | 北京易航远智科技有限公司 | Anti-collision method for automatic driving vehicle in severe weather |
| CN114999228B (en) * | 2022-06-01 | 2022-12-16 | 北京易航远智科技有限公司 | Anti-collision method for automatic driving vehicle in severe weather |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111949037A (en) | Automatic driving system and method for internet vehicle | |
| EP3759562B1 (en) | Camera based localization for autonomous vehicles | |
| US11537127B2 (en) | Systems and methods for vehicle motion planning based on uncertainty | |
| US11842530B2 (en) | Systems and methods for latent distribution modeling for scene-consistent motion forecasting | |
| CN111309015A (en) | Transformer substation inspection robot positioning navigation system integrating multiple sensors | |
| CN110471411A (en) | Automatic Pilot method and servomechanism | |
| US11762094B2 (en) | Systems and methods for object detection and motion prediction by fusing multiple sensor sweeps into a range view representation | |
| WO2020139961A1 (en) | Distributed system task management using a simulated clock | |
| DE112018005907T5 (en) | INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING PROCESS, PROGRAM AND MOVABLE BODY | |
| DE102020106204A1 (en) | Technologies for managing a world model of a monitored area | |
| US11397610B2 (en) | Architecture for simulation clock-based simulation of distributed systems | |
| CN113479195A (en) | Method for automatic valet parking and system for carrying out said method | |
| WO2021178513A1 (en) | Systems and methods for integrating radar data for improved object detection in autonomous vehicles | |
| US11620838B2 (en) | Systems and methods for answering region specific questions | |
| WO2020139967A1 (en) | Distributed system execution using a serial timeline | |
| US11391587B1 (en) | Assessing the impact of blockages on autonomous vehicle services | |
| US11820397B2 (en) | Localization with diverse dataset for autonomous vehicles | |
| CN110780325B (en) | Method and device for positioning moving object and electronic equipment | |
| US20230031130A1 (en) | Open door reconstruction for sensor simulation | |
| CN115675528A (en) | Automatic driving method and vehicle based on similar scene mining | |
| US20220413510A1 (en) | Targeted driving for autonomous vehicles | |
| CN115577314A (en) | Intelligent automobile cooperative control system based on multi-sensor information fusion | |
| Cho et al. | Autonomous vehicle technology development: A patent survey based on main path analysis | |
| Donzia et al. | Implementation of Autoware Application to real-world Services Based Adaptive Big Data Management System for Autonomous Driving | |
| Kloeker et al. | Corridor for new mobility Aachen-D\" usseldorf: Methods and concepts of the research project ACCorD |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20201117 |
|
| WW01 | Invention patent application withdrawn after publication |