Autonomous Environment Recognition by Robotic Manipulators

概要

論文の詳細を見る
This paper discusses methods of autonomus environment recognition and action by a robotic manipulator working with dynamic interaction to the enviroment, e.g., assembling. A method automatically recognizes the contacting situation with the work site from the sensor outputs and the robotic manipulator motion. The autonomous recognition then discriminates the constraint conditions at manopulator hand using the self-organizing map that is a kind of unsupervisedlearning of neural networks. The discrimination of the constraint conditions is successfully demonstraed by a numerical simulation of a 3-link SCARA type manipulator. Another is for the cognitive action. Some approaches based on the reinforcement learnin are proposed. They give models of cognitive actions and aproaches to so-called frame problem obstructing efficient learning and action.
IEEEの論文
2001-08-00