Piloted driving vehicle training method based on virtual environment and depth double-Q network
A virtual environment and automatic driving technology, applied in the direction of probability network, neural learning method, based on specific mathematical models, etc., can solve the problems of poor robustness, labor-intensive data collection, and variation, etc., to achieve strong robustness, The training process is fast and stable, avoiding a large amount of workload and the effect of high requirements for human manipulation
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0039] Hereinafter, the algorithm steps are described in conjunction with the accompanying drawings to describe the specific embodiments of the present invention, so that those skilled in the art can better understand the present invention.
[0040] The present invention proposes an automatic driving car training method based on a virtual environment and a deep double-Q network, such as figure 1 As shown, achieved through the following steps:
[0041] Step 1: Refer to the real track, preset environmental parameters, and build a virtual environment of the car track suitable for intensive learning training based on Unity;
[0042] In this embodiment, running under the Linux system, downloading and configuring Unity and OpenAI gym. Using the game engine sandbox in Unity, according to the size of the physical car, set a two-way street with a road attribute width of 60cm, the size of the car in the virtual environment is set to a ratio of 1:16, and the frame skipping parameter in the Uni...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap