Research on robot motion control based on local weighted kNN-TD reinforcement learning
Fei Han, Jin Lu, Yuequan Yang, Zhiqiang Cao, Tianping Zhang · 2012
Learning is an important capability for an individual robot, which provides an effective way for understanding, planning, and decision-making in a complex environment. For robot motion control, a local weighted k-nearest neighbors states selection method based on environment information and task information is presented. Based on this method, TD reinforcement learning algorithm is combined to reduce the misclassified probability of kNN-TD method, which is finally verified by the simulations.