Configurable autonomy applicable to humanoid manipulation in unstructured and communication-limited environment
Yu Ohara, Masaki Murooka, Ryohei Ueda, Shunichi Nozawa, Yohei Kakiuchi, Kei Okada, Masayuki Inaba
- Year
- 2015
- Citations
- 7
Abstract
In recent years, humanoids have been expected to play an important part in disaster response due to safety concerns. For disaster response, humanoids should do tasks in unknown and unstructured environments possibly with limited communications. Firstly this paper presents a robot operating system in which complementary integration of autonomous and manual functions is achieved. In our system operator can change the level of automation depending on the situation: operator can modify the result of recognition in 3D Viewer, and can transfer from auto motion generating mode to manual control mode at any time with inheriting some motion parameters. Secondly for the purpose of overcoming communication-limit in disaster site, we propose the method of generating robot motion with little communication between operator and robot. Even when communication is limited, our System can convey necessary information to user by processing past data, always transferring small important data, and showing future motion plans.
Keywords
Related papers
Statistical Learning Theory
Yuhai Wu, Vladimir Vapnik
1999
Artificial intelligence: a modern approach
1995
Applied Nonlinear Control
Jean-Jacques Slotine, Weiping Li
1991
A new optimizer using particle swarm theory
R.C. Eberhart, James Kennedy
2002