Collision avoidance in multi-robot systems based on multi-layered reinforcement learning
✍ Scribed by Yoshikazu Arai; Teruo Fujii; Hajime Asama; Hayato Kaetsu; Isao Endo
- Publisher
- Elsevier Science
- Year
- 1999
- Tongue
- English
- Weight
- 812 KB
- Volume
- 29
- Category
- Article
- ISSN
- 0921-8890
No coin nor oath required. For personal study only.
✦ Synopsis
It is important for a robot to acquire adaptive behaviors for avoiding surrounding robots and obstacles in complicated environments. Although the introduction of a learning scheme is expected to be one of the solutions for this purpose, a large size of memory and a large calculation cost are required to handle useful information such as motions of robots. In this paper, we introduce the multi-layered reinforcement learning method. By dividing a learning curriculum into multiple layers, the number of expected situations can be reduced. It is shown that real robots can adaptively avoid collision with each other and to obstacles in a complicated situation.