Robot motion control method and device based on actor-critic method
A technology of robot motion and control method, applied in the field of machine learning
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0045] Embodiment 1: A robot motion control method. The video data is collected by a camera, and the video data is processed to obtain the current position information of the robot, obstacle distribution information, and given destination information. The map is obtained by analyzing the video data. The position of the robot is regarded as the state x of the robot, and the movement direction of the robot is regarded as the action u; figure 1 As shown, specific control methods include learning process and motion control.
[0046] The learning process includes the following steps:
[0047] 1 state transition
[0048] According to the environment model, the robot state is transferred, and then the actions that should be performed in the new state are selected according to the behavior strategy. The behavior strategy adopts a completely random strategy, that is, the selection probabilities of all actions in any state are equal and the sum is 1.
[0049] 2Calculate the off strategy factor...
Example Embodiment
[0074] This embodiment 801.4
[0075] Off-PAC1242.4
[0076] OPGTD2(λ)1125.2
[0077] SARSA1747.8
[0078] In the method of the present invention, the result obtained by changing different μ values:
[0079] VOPAC
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