Robot ambulation control method based on confirmation learning theory
Patent Information
- Authority / Receiving Office
- CN · China
- Current Assignee / Owner
- SOUTH CHINA UNIV OF TECH
- Publication Date
- 2008-12-10
- Estimated Expiration
- Not applicable · inactive patent
Smart Images
Figure 1 Figure 2 Figure 3
Abstract
Description
technical field
[0001] The invention relates to a humanoid robot walking control method, in particular to a robot gait learning and control method based on deterministic learning theory. Background technique
[0002] Today, with the rapid development of science and technology, robot systems have been widely used in many fields, such as medical treatment, industry, and so on. With the widespread application of robotic systems, intelligence and humanization have become an important direction of its development. Gait control of biped robots is a hot topic in the field of robot control. The inherent instability of the biped robot itself, the high-order coupling dynamics and the multi-stage nature of its gait make its walking control a very challenging subject.
[0003] With the development of neural computing science, neural networks have made great achievements in classification problems, pattern recognition, digital signal processing and many other fields. At present, there...