Humanoid robot gait on sloping floors using reinforcement learning
N/D
Tipo de produção
Artigo de evento
Data de publicação
2016-01-05
Texto completo (DOI)
Periódico
Communications in Computer and Information Science
Editor
Texto completo na Scopus
Citações na Scopus
2
Autores
SILVA, I. J.
PERICO, D. H.
HOMEM, T. P. D.
VILAO, C. O.
Reinaldo Bianchi
Flavio Tonidandel
Orientadores
Resumo
© Springer International Publishing AG 2016.Climbing ramps is an important ability for humanoid robots: ramps exist everywhere in the world, such as in accessibility ramps and building entrances. This works proposes the use of Reinforcement Learning to learn the action policy that will make a robot walk in an upright position, in a lightly sloped terrain. The proposed architecture of our system is a two-layer combination of the traditional gait generation control loop with a reinforcement learning component. This allows the use of an accelerometer to generate a correction for the gait, when the slope of the floor where the robot is walking changes. Experiments performed on a real robot showed that the proposed architecture is a good solution for the stability problem.
Citação
SILVA, I. J.; PERICO, D. H.; HOMEM, T. P. D.; VILAO, C. O.; BIANCHI, R.; TONIDANDEL, F. Humanoid robot gait on sloping floors using reinforcement learning. Communications in Computer and Information Science, v. 619, p. 228-246, 2016.
Palavras-chave
Keywords
Gait pattern stabilization; Humanoid robots; Reinforcement learning
Assuntos Scopus
Action policies; Gait generation; Gait pattern; Humanoid robot; Proposed architectures; Sloped terrains; Stability problem; Upright position