Back to Search
Start Over
Data-Efficient and Safe Learning for Humanoid Locomotion Aided by a Dynamic Balancing Model
- Source :
- IEEE Robotics and Automation Letters. 5:4376-4383
- Publication Year :
- 2020
- Publisher :
- Institute of Electrical and Electronics Engineers (IEEE), 2020.
-
Abstract
- In this letter, we formulate a novel Markov Decision Process (MDP) for safe and data-efficient learning for humanoid locomotion aided by a dynamic balancing model. In our previous studies of biped locomotion, we relied on a low-dimensional robot model, commonly used in high-level Walking Pattern Generators (WPGs). However, a low-level feedback controller cannot precisely track desired footstep locations due to the discrepancies between the full order model and the simplified model. In this study, we propose mitigating this problem by complementing a WPG with reinforcement learning. More specifically, we propose a structured footstep control method consisting of a WPG, a neural network, and a safety controller. The WPG provides an analytical method that promotes efficient learning while the neural network maximizes long-term rewards, and the safety controller encourages safe exploration based on step capturability and the use of control-barrier functions. Our contributions include the following (1) a structured learning control method for locomotion, (2) a data-efficient and safe learning process to improve walking using a physics-based model, and (3) the scalability of the procedure to various types of humanoid robots and walking.<br />Comment: 8 pages, 7 figures
- Subjects :
- FOS: Computer and information sciences
0209 industrial biotechnology
Control and Optimization
Biomedical Engineering
02 engineering and technology
Computer Science - Robotics
03 medical and health sciences
020901 industrial engineering & automation
0302 clinical medicine
Artificial Intelligence
Control theory
Reinforcement learning
Structured prediction
Artificial neural network
Mechanical Engineering
Control engineering
Computer Science Applications
Human-Computer Interaction
Control and Systems Engineering
Scalability
Robot
Computer Vision and Pattern Recognition
Markov decision process
Robotics (cs.RO)
030217 neurology & neurosurgery
Humanoid robot
Subjects
Details
- ISSN :
- 23773774
- Volume :
- 5
- Database :
- OpenAIRE
- Journal :
- IEEE Robotics and Automation Letters
- Accession number :
- edsair.doi.dedup.....c998710a87bb57586f4bc03b1eb35536