Action selection in continuous state and action spaces by cooperation and competition of extended kohonen maps

This paper presents an action selection framework based on an assemblage of self-organizing neural networks called Cooperative Extended Kohonen Maps. This framework encapsulates two features that significantly enhance a robot’s action selection capability: self-organization in the continuous state and action spaces to provide smooth, efficient and fine motion control; action selection via the cooperation and competition of Extended Kohonen Maps to achieve more complex motion tasks. Qualitative tests demonstrate the capability of our action selection method for both singleand multi-robot motion tasks. Categories and Subject Descriptors I.2 [Computing Methodologies]: Artificial Intelligence; I.2.6 [Artificial Intelligence]: Learning—connectionism and neural nets; I.2.9 [Artificial Intelligence]: Robotics General Terms Algorithms, Design, Experimentation, Performance Keywords action selection, motion control, neural networks

• Type: Conference
• Year: 2003
• Where: ATAL
• Authors: Kian Hsiang Low, Wee Kheng Leow, Marcelo H. Ang
• Keywords: Action Selection, Action Selection Framework, ATAL 2003, Extended Kohonen Maps