Dyna-QUF: Dyna-Q based univector field navigation for autonomous mobile robots in unknown environments
来源期刊：中南大学学报(英文版)2013年第5期
论文作者：VIET Hoang-huu CHOI Seung-yoon CHUNG Tae-choong
文章页码：1178 - 1188
Key words：Dyna-Q; mobile robot; reinforcement learning; univector field
Abstract: A novel approach was presented to solve the navigation problem of autonomous mobile robots in unknown environments with dense obstacles based on a univector field method. In an obstacle-free environment, a robot is ensured to reach the goal position with the desired posture by following the univector field. Contrariwise, the univector field cannot guarantee that the robot will avoid obstacles in environments. In order to create an intelligent mobile robot being able to perform the obstacle avoidance task while following the univector field, Dyna-Q algorithm is developed to train the robot in learning moving directions to attain a collision-free path for its navigation. Simulations on the computer as well as experiments on the real world prove that the proposed algorithm is efficient for training the robot in reaching the goal position with the desired final orientation.
VIET Hoang-huu, CHOI Seung-yoon, CHUNG Tae-choong
(Department of Computer Engineering, Kyung Hee University, 1-Seocheon-Dong,
Giheung-Gu, Yongin-Si, Gyeonggi-Do, 446-701, Korea)
Abstract:A novel approach was presented to solve the navigation problem of autonomous mobile robots in unknown environments with dense obstacles based on a univector field method. In an obstacle-free environment, a robot is ensured to reach the goal position with the desired posture by following the univector field. Contrariwise, the univector field cannot guarantee that the robot will avoid obstacles in environments. In order to create an intelligent mobile robot being able to perform the obstacle avoidance task while following the univector field, Dyna-Q algorithm is developed to train the robot in learning moving directions to attain a collision-free path for its navigation. Simulations on the computer as well as experiments on the real world prove that the proposed algorithm is efficient for training the robot in reaching the goal position with the desired final orientation.
Key words:Dyna-Q; mobile robot; reinforcement learning; univector field
