Acquisition by robots of danger-avoidance behaviors using probability-based reinforcement learning

Autor:	Tsuyoshi Nakamura, Masayoshi Kanoh, Tohgoroh Matsui, Daiki Takeyama
Rok vydání:	2015
Předmět:	business.industry Computer science Reinforcement learning Robot Mobile robot Artificial intelligence Space (commercial competition) Behavior-based robotics business Robot learning Robot control
Zdroj:	FUZZ-IEEE
DOI:	10.1109/fuzz-ieee.2015.7337999
Popis:	Robots are being used more and more in dangerous environments such as space and disaster areas. However, when robots are at risk in dangerous environments, the time during which robot operators can issue risk avoidance instructions is limited. Therefore, robots should be able to acquire behaviors that enable them to autonomously avoid danger. In this paper, we present a probability-based reinforcement learning (PrRL) method and apply it to robot behavior acquisition.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::b9fa06d6647f7235b748508c46c043d2 https://doi.org/10.1109/fuzz-ieee.2015.7337999 Zobrazit plný text záznamu