Man-machine cooperative dynamic obstacle avoidance method and system based on deep reinforcement learning
A technology of dynamic obstacle avoidance and enhanced learning, applied in the fields of motor vehicles, control/regulation systems, non-electric variable control, etc. High stability effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0060] Such as Figure 1-28 The shown method for dynamic obstacle avoidance of smart cars based on deep reinforcement learning method includes the following steps:
[0061] S1. Obtain the simulated perception image of the smart car at time t I t ;
[0062] S2, will simulate the perception image I t Input the neural network model, and the neural network model outputs the state characteristics of the smart car at time t s t And the probability of performing each action;
[0063] S3. Select the action a of the smart car at time t according to the probability distribution corresponding to each action t And output, among which, according to the ε-greedy strategy, the execution action a of the smart car at time t is determined from each action t ,specific:
[0064] Select the action of the smart car in the ratio of (1-ε) according to the action of the neural network model to interact with the environment, and randomly select the action of the smart car in the ratio of ε, at this time, the ac...
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