Publication detail

Walking Gait of Four-Legged Robot Obtained Throug Q Learning

BŘEZINA, T., HOUŠKA, P., SINGULE, V.

Original Title

Walking Gait of Four-Legged Robot Obtained Throug Q Learning

English Title

Walking Gait of Four-Legged Robot Obtained Throug Q Learning

Type

conference paper

Language

Czech

Original Abstract

The possible method of walking policy obtaining of four-legged robot through Q-learning is discussed in the contribution. Q-learning is implemented using architecture represented by nondeterministic state machine that defines both possible discrete states and admissible transitions between them. Discrete state is designed as indicators vector of goals achievement by single simultaneously activated instances of two basic controllers. Only simultaneous activations that guarantee static stability of robot are admissible even in the case when single activations cold not achieve its goals. The controllers attempt to achieve its goals using on-line minimization process. Q-learning sequentially improves an estimation of future benefit from usage of admissible simultaneous activations in single discrete states. Walking policy is generated through activations with the highest estimation of future benefit.

English abstract

The possible method of walking policy obtaining of four-legged robot through Q-learning is discussed in the contribution. Q-learning is implemented using architecture represented by nondeterministic state machine that defines both possible discrete states and admissible transitions between them. Discrete state is designed as indicators vector of goals achievement by single simultaneously activated instances of two basic controllers. Only simultaneous activations that guarantee static stability of robot are admissible even in the case when single activations cold not achieve its goals. The controllers attempt to achieve its goals using on-line minimization process. Q-learning sequentially improves an estimation of future benefit from usage of admissible simultaneous activations in single discrete states. Walking policy is generated through activations with the highest estimation of future benefit.

Key words in English

mechatronics, walking robots, machine learning, Q-learning

Authors

BŘEZINA, T., HOUŠKA, P., SINGULE, V.

RIV year

2003

Released

12. 5. 2003

Publisher

Institute of Theoretical and Applied Mechanics, Academy of Sciences of the Czech Republic, Prague

Location

Praha

ISBN

80-86246-18-3

Book

Engeneering Mechanics 2003

Edition number

1

Pages from

36

Pages to

37

Pages count

2

BibTex

@inproceedings{BUT7626,
  author="Tomáš {Březina} and Pavel {Houška} and Vladislav {Singule}",
  title="Walking Gait of Four-Legged Robot Obtained Throug Q Learning",
  booktitle="Engeneering Mechanics 2003",
  year="2003",
  number="1",
  pages="2",
  publisher="Institute of Theoretical and Applied Mechanics, Academy of Sciences of the Czech Republic, Prague",
  address="Praha",
  isbn="80-86246-18-3"
}