Automatic parking trajectory planning method based on deep enhanced learning
A technology of automatic parking and enhanced learning, which is applied to simulators of space navigation conditions, space navigation equipment, instruments, etc., can solve the problems of vehicle position control error accumulation, unsatisfactory accuracy and reliability, and difficulty in precise control , to improve the accuracy and reliability of the
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0024] Embodiment: An automatic parking trajectory planning method based on deep reinforcement learning of this embodiment, such as image 3 As shown, including the following steps:
[0025] ① Obtain parking space information and the relative position of the vehicle and the parking space through the on-board camera, use different colors to indicate the obstacles and vehicles in the obtained image, and mark a sufficiently small and narrow virtual parking space for parking training parking space (side parking When parking, the length of the virtual parking space is 1.2 times the length of the vehicle; when parking in reverse, the width of the virtual parking space is 1.2 times the width of the vehicle), to establish a two-dimensional virtual parking environment;
[0026] ②In the case of low speed, that is, the vehicle speed is below 10km / h, simulate the parking motion of the vehicle, set the steering wheel angle range between -40° and 40°, equally divided, and take a corresponding ste...
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