1A1-E30 Memory Representation and Control for Efficient Learning of Reaching Motions
Yuki Yoshihara, Shingo Shimoda, Hidenori Kimura · The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec) · 2010
Humans can rapidly adapt to unexpectedly changing environment and achieve various tasks. Specifically, the number of trials for adaptation is small when current situation is similar to the memorized ones, suggesting evaluation of similarity would be a key component to boost learning speed. Here, we develop a model for learning reaching motions which can store various visio-motor transformations with respect to a situation, and can recall them depending on similarity of the situation. Simulation results demonstrate that only one trial is needed to coordinate a multi-joint arm, even though no kinematic or dynamic properties are given a-priori.