CN110930811B - System suitable for unmanned decision learning and training - Google Patents
System suitable for unmanned decision learning and training Download PDFInfo
- Publication number
- CN110930811B CN110930811B CN201911093164.2A CN201911093164A CN110930811B CN 110930811 B CN110930811 B CN 110930811B CN 201911093164 A CN201911093164 A CN 201911093164A CN 110930811 B CN110930811 B CN 110930811B
- Authority
- CN
- China
- Prior art keywords
- module
- vehicle
- training
- main processor
- virtual reality
- 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
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B9/00—Simulators for teaching or training purposes
- G09B9/02—Simulators for teaching or training purposes for teaching control of vehicles or other craft
- G09B9/04—Simulators for teaching or training purposes for teaching control of vehicles or other craft for teaching control of land vehicles
- G09B9/05—Simulators for teaching or training purposes for teaching control of vehicles or other craft for teaching control of land vehicles the view from a vehicle being simulated
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- General Physics & Mathematics (AREA)
- Processing Or Creating Images (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The application belongs to the technical field of artificial intelligence, and particularly relates to a system suitable for unmanned decision learning and training. Because the existing method designs an algorithm frame, trains by using big data or trains/verifies according to a set of established rules, the efficiency is low, and the cost is high. A system suitable for unmanned decision learning and training is provided, the system comprising a virtual reality/machine learning unit; the virtual reality/machine learning unit comprises a main processor module, the main processor module is connected with a virtual reality presenting module, the main processor module is connected with a vehicle operation electromechanical module, the vehicle operation electromechanical module is connected with a steering wheel, the vehicle operation electromechanical module is connected with gears, and the vehicle operation electromechanical module is connected with an accelerator/brake. The method solves the problem of how to train the algorithm quickly in the unmanned technology, improves the driving capability of the vehicle, and is particularly suitable for artificial intelligence learning.
Description
Technical Field
The application belongs to the technical field of artificial intelligence, and particularly relates to a system suitable for unmanned decision learning and training.
Background
The cost of researching unmanned driving is very high, on one hand, unmanned driving is a series of complex algorithms related to the comprehensive application of related technologies in multiple fields, such as vehicle positioning, object detection, tracking, path planning and the like, and on the other hand, an automatic driving laboratory and a laboratory field are needed to verify related algorithms, otherwise, the researched algorithms cannot be verified and really applied. Particularly, the external environment of an unmanned automobile after real road getting on is quite complex and changeable, and in order to enable the unmanned automobile to cope with the complex situations, one method is to enable the automobile to collect data under the actual road conditions on the premise that people are responsible for driving safety, then analyze the collected scene data, and design a corresponding algorithm to enable the brain of the automobile to know how to process the data when the brain meets similar situations next time. This method is costly and long-term. The other method is to train and verify the perception and decision algorithm of the unmanned automobile under different scenes through a simulation mode. There are even a few open source autopilot simulation platforms, including Carla, AirSim, Udacity self-driving car simulator, Apollo, and Autoware, among others. These simulation platforms are mainly divided into two categories: the first type is to simulate the environment, perception and vehicle based on synthesized data, most of the perception is perception at image level, and the simulator is mainly used for the initial development of perception and planning algorithms, such as Carla, AirSim and Udacity self-driving car simulator; the other type is playback based on real data, wherein the real data comprises data of various sensors such as images, lidar, radar and the like, the simulator is mainly used for testing the performance of information fusion algorithms and different parts of the vehicle in unmanned driving, and Apollo and Autoware belong to the simulator.
In the existing unmanned simulation platform, the data problem in the algorithm research is only solved no matter the playback of the generated virtual data or the real data is based on. Because the existing method designs an algorithm framework, trains by using big data or trains/verifies according to a set of established rules, the existing method has little help to the core-driving skill of unmanned driving or an intelligent decision algorithm, and has low efficiency and higher cost. This is probably one of the reasons for the "long tail" effect in the development of driverless technology.
Disclosure of Invention
1. Technical problem to be solved
Based on the existing unmanned simulation platform, the data problem in the algorithm research is only solved no matter based on the generated virtual data or the playback of the real data during training or testing. Because the existing method designs an algorithm framework, trains by using big data or trains/verifies according to a set of formulated rules, the system is suitable for unmanned decision learning and training for the problems of little help of unmanned core-driving skills or intelligent decision algorithm, low efficiency and high cost.
2. Technical scheme
To achieve the above objects, the present application provides a system suitable for unmanned decision learning and training, the system comprising a virtual reality/machine learning unit;
the virtual reality/machine learning unit comprises a main processor module, the main processor module is connected with a virtual reality presenting module, the main processor module is connected with a vehicle operation electromechanical module, the vehicle operation electromechanical module is connected with a steering wheel, the vehicle operation electromechanical module is connected with a gear, and the vehicle operation electromechanical module is connected with an accelerator/brake;
the main processor module is used for simulating various driving scenes and learning the driving skills of the vehicle operator in various scenes through various parameters,
the virtual reality presentation module is used for displaying various simulated driving scenes to a vehicle operator,
the vehicle control electromechanical module collects various operation information of a vehicle operator in real time, simultaneously records the operation information corresponding to road condition parameters in a virtual environment, and sends the operation information to the main processor module,
the steering wheel is used for simulating the operation of the vehicle,
the gear is used for simulating the operation of the vehicle,
the throttle/brake is used for simulating vehicle operation.
Another embodiment provided by the present application is: the main processor module comprises a machine learning algorithm submodule and a virtual reality scene generator which are connected with each other, the machine learning algorithm submodule is connected with the vehicle control electromechanical module,
the virtual reality scene generator is used for sending current parameters of a scene to the machine learning algorithm submodule, the machine learning algorithm submodule is used for receiving samples of the vehicle control electromechanical module, and the machine learning algorithm submodule is used for learning driving skills of a vehicle operator in various scenes through various parameters.
Another embodiment provided by the present application is: the current parameters of the scene include road conditions and location.
Another embodiment provided by the present application is: the main processor module is a server or a distributed system.
Another embodiment provided by the present application is: the virtual reality presentation module is a head-mounted VR display, a projection display or a computer display.
Another embodiment provided by the present application is: the machine learning algorithm sub-module is a traditional expert system, a neuron network or a deep learning algorithm module.
Another embodiment provided by the present application is: the model learned by the machine learning algorithm submodule can be directly used for unmanned decision and control.
Another embodiment provided by the present application is: the dynamic chassis is used for simulating the movement of a vehicle body; the dynamic chassis is connected with the main processor module.
Another embodiment provided by the present application is: the dynamic chassis comprises a motion simulation device, and the motion simulation device is a three-axis driving platform, a four-axis driving platform or a multi-axis driving platform;
the dynamic chassis is used for simulating the motion states of vehicles under various weather, season and road conditions.
Another embodiment provided by the present application is: the connection is a local area network connection or a field bus connection.
3. Advantageous effects
Compared with the prior art, the system suitable for unmanned decision learning and training provided by the application has the beneficial effects that:
the system is suitable for unmanned decision learning and training, and aims at how to realize rapid learning human decision intelligence in unmanned and auxiliary driving technologies, and the learned skills are deployed into an unmanned system or an ADAS system so as to improve unmanned/ADAS decision skills and passenger experience.
The system suitable for unmanned decision learning and training is characterized in that the driving experience of a person in a complex virtual environment is fused into the learning of an intelligent decision algorithm on the basis of driving simulation so as to rapidly improve the decision capability of an unmanned vehicle. Based on the content of the application, the unmanned driving algorithm can be learned, and the driving skill can be quickly learned by the students in driving schools, so that the learning is shortened. Thereby reducing resources and costs.
The system suitable for unmanned decision learning and training solves the problem of how to train an algorithm quickly in an unmanned technology, improves vehicle driving capability, and especially realizes artificial intelligence learning.
The system suitable for unmanned decision learning and training combines the simulated driving device with the virtual reality technology, and the driving skills of the driver are integrated into the unmanned decision algorithm learning through the acquisition of the driving parameters of the experienced driver in various challenging environments, so that the unmanned decision algorithm can be rapidly learned. The method and the system not only save the cost of acquiring the actual road condition data, but also integrate the driving experience of people into the artificial intelligence learning compared with the existing simulation platform, and can greatly promote the convergence speed of the algorithm.
Drawings
FIG. 1 is a schematic diagram of a system suitable for unmanned decision learning and training of the present application;
FIG. 2 is a schematic diagram of a system data flow suitable for unmanned decision learning and training according to the present application.
In the figure: the system comprises a main processor module, a 2-virtual reality presentation module, a 3-vehicle control electromechanical module, a 4-steering wheel, a 5-gear, a 6-accelerator/brake, a 7-machine learning algorithm submodule, an 8-virtual reality scene generator and a 9-dynamic chassis.
Detailed Description
Hereinafter, specific embodiments of the present application will be described in detail with reference to the accompanying drawings, and it will be apparent to those skilled in the art from this detailed description that the present application can be practiced. Features from different embodiments may be combined to yield new embodiments, or certain features may be substituted for certain embodiments to yield yet further preferred embodiments, without departing from the principles of the present application.
Referring to fig. 1-2, the present application provides a system suitable for unmanned decision learning and training, the system comprising a virtual reality/machine learning unit;
the virtual reality/machine learning unit comprises a main processor module 1, wherein the main processor module 1 is connected with a virtual reality presenting module 2, the main processor module 1 is connected with a vehicle operation electromechanical module 3, the vehicle operation electromechanical module 3 is connected with a steering wheel 4, the vehicle operation electromechanical module 3 is connected with a gear 5, and the vehicle operation electromechanical module 3 is connected with an accelerator/brake 6;
the main processor module 1 is used for simulating various driving scenes and learning the driving skills of the vehicle operator in various scenes through various parameters,
the virtual reality presenting module 2 is used for displaying various simulated driving scenes to a vehicle operator,
the vehicle control electromechanical module 3 collects various operation information of a vehicle operator in real time, simultaneously records the operation information corresponding to road condition parameters in a virtual environment, and sends the operation information to the main processor module,
the steering wheel 4, used to simulate vehicle operation,
the gear 5 is used for simulating the operation of the vehicle,
and the accelerator/brake 6 is used for simulating vehicle operation.
Further, the main processor module comprises a machine learning algorithm submodule 7 and a virtual reality scene generator 8 which are connected with each other, the machine learning algorithm submodule 7 is connected with the vehicle operation electromechanical module 3,
the virtual reality scene generator 8 is used for sending current parameters of a scene to the machine learning algorithm submodule 7, the machine learning algorithm submodule 7 is used for receiving samples of the vehicle operation electromechanical module 3, and the machine learning algorithm submodule 7 is used for learning driving skills of a vehicle operator in various scenes through various parameters.
Further, the current parameters of the scene include road conditions and location.
Further, the main processor module 1 is a server or a distributed system.
Further, the virtual reality presenting module 2 is a head-mounted VR display, a projection display or a computer display.
Further, the machine learning algorithm sub-module 7 is a conventional expert system, a neural network or a deep learning algorithm module.
Further, the model learned by the machine learning algorithm sub-module 7 can be directly used in unmanned decision and control.
Further, the device also comprises a dynamic chassis 9, wherein the dynamic chassis 9 is used for simulating the movement of the vehicle body; the dynamic chassis is connected with the main processor module.
Further, the dynamic chassis 9 includes a motion simulation device, and the motion simulation device is a three-axis driving platform, a four-axis driving platform or a multi-axis driving platform;
the dynamic chassis 9 is used for simulating the motion state of the vehicle under various weather, season and road conditions.
Further, the connection is a local area network connection or a field bus connection.
The connection of each component of the system can be a local area network, a field bus and the like;
the vehicle operation electromechanical module 3 is used for receiving various vehicle operation information of a vehicle operator, and the main processor module 1 is connected with the virtual reality presenting module 2, the vehicle operation electromechanical module 3 and the dynamic chassis 9 according to corresponding data interfaces. When the driving operation is simulated, the main processor module 1 simulates various driving scenes through the built-in virtual reality scene generator 8 and displays the driving scenes to a vehicle operator through the virtual reality presentation device, the vehicle operator realizes the simulation of the movement of the vehicle in the virtual reality scene through various vehicle operation interfaces such as the steering wheel 4, the gear 5, the accelerator/brake 6 and the like according to the presented driving scenes, meanwhile, the vehicle operation electromechanical module 3 samples various operations of the vehicle by the vehicle operator according to a certain period and sends the various operations to the machine learning algorithm submodule 7 built in the main processor module 1, and the virtual reality scene generator 8 sends the current parameters (such as road conditions, positions and the like) of the scenes to the machine learning algorithm submodule 7 at the same time. The main processor module 1 simulates the motion state of the vehicle through the dynamic chassis 9 according to the operation of the current vehicle operator and the current scene, so that the vehicle operator has a presence feeling. The machine learning algorithm submodule 7 learns the driving skills of the vehicle operator in various scenes through various parameters.
Example 1:
a server with a GPU graphic accelerator is connected to a computer display screen, and the vehicle simulation system can be composed of a simulation steering wheel 4 module, a gear 5 module and a brake/accelerator 6 module which are commercially available. Various road scenes are generated by using a 3D modeling tool, an experienced driver operates the vehicle simulation modules in the generated simulation scenes, output information of each vehicle simulation module is sent to a server in real time, the server corresponds current road parameters and the like in the simulation scenes to operation parameters of the driver, and the current road parameters and the like are used as input training samples of a machine learning algorithm submodule 7 arranged in the server to carry out learning training on the algorithm modules.
Example 2:
2 computers are used for forming a distributed computing system based on a local area network, one of the computers is used as a main control computer for virtual reality simulation driving, the corresponding display of the main control computer is a head-mounted VR display device so as to display various road conditions, and meanwhile, the main control computer controls a three-axis dynamic chassis 9 to simulate the movement of a vehicle under various road conditions, so that a driver can obtain the driving experience of telepresence; the other computer is used as a main processor of the machine learning algorithm submodule 7, receives the operation parameters of the simulated driving and various road condition parameters sent by a main control computer of the virtual reality simulated driving, and takes the parameters as input training samples of the computer to perform learning training on the algorithm module.
Example 3:
2 servers are assembled to form a distributed system based on a high-speed local area network, one server is used as a main control computer for virtual reality simulation driving, the corresponding display is a head-mounted VR display device to display various road conditions, and meanwhile, the main control computer controls a six-axis dynamic chassis 9 to simulate the movement of a vehicle under various road conditions, so that a driver can obtain the driving experience of telepresence; and the other server with the GPU accelerator card is used as a main processor of the machine learning algorithm submodule 7, receives operation parameters of the simulated driving and various road condition parameters sent by a main control computer of the virtual reality simulated driving, uses the parameters as input training samples of the deep neuron network, evaluates driving results of each time by adopting certain evaluation indexes, and performs learning training on a driving decision model by using the evaluation results as samples.
The application can be used in the field of vehicle-ground wireless communication and has certain help for the vehicle-ground wireless communication.
The system suitable for unmanned decision learning and training combines the simulated driving device with the virtual reality technology, and the driving skills of the driver are integrated into the unmanned decision algorithm learning through the acquisition of the driving parameters of the experienced driver in various challenging environments, so that the unmanned decision algorithm can be rapidly learned. The method and the system not only save the cost of acquiring the actual road condition data, but also integrate the driving experience of people into the artificial intelligence learning compared with the existing simulation platform, and can greatly promote the convergence speed of the algorithm.
Although the present application has been described above with reference to specific embodiments, those skilled in the art will recognize that many changes may be made in the configuration and details of the present application within the principles and scope of the present application. The scope of protection of the application is determined by the appended claims, and all changes that come within the meaning and range of equivalency of the technical features are intended to be embraced therein.
Claims (9)
1. A system adapted for unmanned decision learning and training, characterized by: the system includes a virtual reality/machine learning unit;
the virtual reality/machine learning unit comprises a main processor module, the main processor module is connected with a virtual reality presenting module, the main processor module is connected with a vehicle operation electromechanical module, the vehicle operation electromechanical module is connected with a steering wheel, the vehicle operation electromechanical module is connected with a gear, and the vehicle operation electromechanical module is connected with an accelerator/brake;
the main processor module is used for simulating various driving scenes and learning the driving skills of the vehicle operator in various scenes through various parameters,
the virtual reality presentation module is used for displaying various simulated driving scenes to a vehicle operator,
the vehicle control electromechanical module collects various operation information of a vehicle operator in real time, simultaneously records the operation information corresponding to road condition parameters in a virtual environment, and sends the operation information to the main processor module,
the steering wheel is used for simulating the operation of the vehicle,
the gear is used for simulating the operation of the vehicle,
the accelerator/brake is used for simulating vehicle operation;
the main processor module comprises a machine learning algorithm submodule and a virtual reality scene generator which are connected with each other, the machine learning algorithm submodule is connected with the vehicle control electromechanical module,
the virtual reality scene generator is used for sending current parameters of a scene to the machine learning algorithm submodule, the machine learning algorithm submodule is used for receiving samples of the vehicle control electromechanical module, and the machine learning algorithm submodule is used for learning driving skills of a vehicle operator in various scenes through various parameters.
2. A system adapted for unmanned decision learning and training as defined in claim 1, wherein: the current parameters of the scene include road conditions and location.
3. A system adapted for unmanned decision learning and training as defined in claim 1, wherein: the main processor module is a server or a distributed system.
4. A system adapted for unmanned decision learning and training as defined in claim 1, wherein: the virtual reality presentation module is a head-mounted VR display, a projection display or a computer display.
5. A system adapted for unmanned decision learning and training as defined in claim 1, wherein: the machine learning algorithm sub-module is a traditional expert system, a neuron network or a deep learning algorithm module.
6. A system adapted for unmanned decision learning and training as defined in claim 5, wherein: the model learned by the machine learning algorithm submodule can be directly used for unmanned decision and control.
7. A system suitable for unmanned decision learning and training as claimed in any one of claims 1 to 6, wherein: the dynamic chassis is used for simulating the movement of a vehicle body; the dynamic chassis is connected with the main processor module.
8. A system adapted for unmanned decision learning and training as defined in claim 7, wherein: the dynamic chassis comprises a motion simulation device, and the motion simulation device is a three-axis driving platform, a four-axis driving platform or a multi-axis driving platform;
the dynamic chassis is used for simulating the motion states of vehicles under various weather, season and road conditions.
9. A system adapted for unmanned decision learning and training as defined in claim 7, wherein: the connection is a local area network connection or a field bus connection.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911093164.2A CN110930811B (en) | 2019-11-11 | 2019-11-11 | System suitable for unmanned decision learning and training |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911093164.2A CN110930811B (en) | 2019-11-11 | 2019-11-11 | System suitable for unmanned decision learning and training |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110930811A CN110930811A (en) | 2020-03-27 |
| CN110930811B true CN110930811B (en) | 2020-10-16 |
Family
ID=69853704
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911093164.2A Active CN110930811B (en) | 2019-11-11 | 2019-11-11 | System suitable for unmanned decision learning and training |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110930811B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111915956B (en) * | 2020-08-18 | 2022-04-22 | 湖南汽车工程职业学院 | Virtual reality car driving teaching system based on 5G |
| CN112859810A (en) * | 2021-01-13 | 2021-05-28 | 自行科技(武汉)有限公司 | ADAS algorithm verification method and device based on Carla platform |
| CN113110442B (en) * | 2021-04-09 | 2024-01-16 | 深圳阿米嘎嘎科技有限公司 | Multi-skill movement control method, system and medium for quadruped robot |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1640727A1 (en) * | 2004-09-23 | 2006-03-29 | Innalabs Technologies, Inc. | Magnetofluidic accelerometer |
| CN102184659A (en) * | 2011-06-09 | 2011-09-14 | 公安部交通管理科学研究所 | Automobile traffic safety simulation driving education training system |
| CN202720794U (en) * | 2012-07-09 | 2013-02-06 | 山东建筑大学 | Intelligent driving practicing system |
| CN206541476U (en) * | 2017-01-20 | 2017-10-03 | 长安大学 | Traffic driver training instrument based on VR glasses |
| CN107316543A (en) * | 2017-08-23 | 2017-11-03 | 合肥龙图腾信息技术有限公司 | A kind of intelligent Driving Test system based on VR technologies |
| CN107506830A (en) * | 2017-06-20 | 2017-12-22 | 同济大学 | Towards the artificial intelligence training platform of intelligent automobile programmed decision-making module |
| CN107564363A (en) * | 2017-09-05 | 2018-01-09 | 百度在线网络技术（北京）有限公司 | A kind of method and apparatus for driving model switching |
| CN108877377A (en) * | 2018-07-05 | 2018-11-23 | 池州智栋信息技术有限公司 | A kind of simulated automotive driving machine |
| CN109299732A (en) * | 2018-09-12 | 2019-02-01 | 北京三快在线科技有限公司 | The method, apparatus and electronic equipment of unmanned behaviour decision making and model training |
| CN109448482A (en) * | 2018-10-23 | 2019-03-08 | 扬州大学 | A kind of automatic Pilot experience platform based on virtual reality |
| CN109791295A (en) * | 2016-07-25 | 2019-05-21 | 奇跃公司 | Use enhancing and the imaging of virtual reality glasses modification, display and visualization |
-
2019
- 2019-11-11 CN CN201911093164.2A patent/CN110930811B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1640727A1 (en) * | 2004-09-23 | 2006-03-29 | Innalabs Technologies, Inc. | Magnetofluidic accelerometer |
| CN102184659A (en) * | 2011-06-09 | 2011-09-14 | 公安部交通管理科学研究所 | Automobile traffic safety simulation driving education training system |
| CN202720794U (en) * | 2012-07-09 | 2013-02-06 | 山东建筑大学 | Intelligent driving practicing system |
| CN109791295A (en) * | 2016-07-25 | 2019-05-21 | 奇跃公司 | Use enhancing and the imaging of virtual reality glasses modification, display and visualization |
| CN206541476U (en) * | 2017-01-20 | 2017-10-03 | 长安大学 | Traffic driver training instrument based on VR glasses |
| CN107506830A (en) * | 2017-06-20 | 2017-12-22 | 同济大学 | Towards the artificial intelligence training platform of intelligent automobile programmed decision-making module |
| CN107316543A (en) * | 2017-08-23 | 2017-11-03 | 合肥龙图腾信息技术有限公司 | A kind of intelligent Driving Test system based on VR technologies |
| CN107564363A (en) * | 2017-09-05 | 2018-01-09 | 百度在线网络技术（北京）有限公司 | A kind of method and apparatus for driving model switching |
| CN108877377A (en) * | 2018-07-05 | 2018-11-23 | 池州智栋信息技术有限公司 | A kind of simulated automotive driving machine |
| CN109299732A (en) * | 2018-09-12 | 2019-02-01 | 北京三快在线科技有限公司 | The method, apparatus and electronic equipment of unmanned behaviour decision making and model training |
| CN109448482A (en) * | 2018-10-23 | 2019-03-08 | 扬州大学 | A kind of automatic Pilot experience platform based on virtual reality |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110930811A (en) | 2020-03-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104765280B (en) | The three-dimensional aobvious control comprehensive training system of no-manned plane three-dimensional | |
| CN110930811B (en) | System suitable for unmanned decision learning and training | |
| CN112232490B (en) | Visual-based depth simulation reinforcement learning driving strategy training method | |
| CN110427682A (en) | A kind of traffic scene simulation experiment platform and method based on virtual reality | |
| CN108681264A (en) | A kind of intelligent vehicle digitalized artificial test device | |
| CN109461342B (en) | Teaching system for unmanned motor vehicle and teaching method thereof | |
| CN105654808A (en) | Intelligent training system for vehicle driver based on actual vehicle | |
| CN101251958A (en) | Method for implementing automobile driving analog machine facing to disciplinarian | |
| CN106373453A (en) | Intelligent immersive high-speed train virtual driving behavior evaluation method and simulation system | |
| CN110320883A (en) | A kind of Vehicular automatic driving control method and device based on nitrification enhancement | |
| CN109726804A (en) | A kind of intelligent vehicle driving behavior based on driving prediction field and BP neural network personalizes decision-making technique | |
| CN112015164A (en) | Intelligent networking automobile complex test scene implementation system based on digital twin | |
| CN113327479A (en) | Motor vehicle driving intelligent training system based on MR technology | |
| Wang et al. | Towards next generation of pedestrian and connected vehicle in-the-loop research: A digital twin co-simulation framework | |
| Fouladinejad et al. | Modeling virtual driving environment for a driving simulator | |
| Pouyanfar et al. | Roads: Randomization for obstacle avoidance and driving in simulation | |
| Hong et al. | System configuration of Human-in-the-loop Simulation for Level 3 Autonomous Vehicle using IPG CarMaker | |
| CN113219944B (en) | Intelligent vehicle control strategy test platform for mixed traffic flow working condition | |
| Kowol et al. | A-eye: Driving with the eyes of ai for corner case generation | |
| Maas et al. | Simulator setup according to use case scenarios-A human-oriented method for virtual development | |
| CN115202479A (en) | Man-machine co-driving simulation system of man-in-loop and application thereof | |
| CN114969092A (en) | Driving simulation system based on unreal engine and simulation experiment method | |
| Feng et al. | Autonomous RC-car for education purpose in iSTEM projects | |
| Feng et al. | Research on Testing System for an Intelligent and Connected Vehicle | |
| Ball et al. | Engaging Students in an Automotive Autonomy Sensor Processing Class: Incorporating active learning and high-fidelity, physics-based autonomy simulation into class projects |
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 |