Title :
Behavior-based reinforcement learning control for robotic rehabilitation training
Author :
Fancheng Meng ; Keyan Fan
Author_Institution :
Sch. of Autom., Beijing Inst. of Technol., Beijing, China
Abstract :
A behavior-based reinforcement learning controller (BRL) is developed for robotic rehabilitation training systems with time-varying properties. This adaptive BRL control system consists of an event-based planner layer, a behavior decision-making layer, and a control execution layer. In the adaptive BRL, the event-based planner layer is used to create a representative database and generate a real optimal desired trajectory for each patient, and then the behavior decision-making layer utilizes multiple behavior modules to select an optimal control behavior, which is transmitted to the control execution layer. In addition, to avoid the conflicts and the competition of different control behaviors, a self-adjusting shaping algorithm is proposed for BRL. Simulation experiments verify that the feasibility of the proposed BRL framework.
Keywords :
adaptive control; learning systems; medical robotics; patient rehabilitation; time-varying systems; trajectory control; adaptive BRL control system; behavior decision-making layer; behavior-based reinforcement learning control; control execution layer; event-based planner layer; robotic rehabilitation training; self-adjusting shaping algorithm; time-varying property; trajectory generation; Decision making; Learning (artificial intelligence); Medical treatment; Robot kinematics; Training; Trajectory; Actor critic; Behavior-based Reinforcement-learning control; Robotic rehabilitation system; Shaping;
Conference_Titel :
Control and Decision Conference (CCDC), 2015 27th Chinese
Conference_Location :
Qingdao
Print_ISBN :
978-1-4799-7016-2
DOI :
10.1109/CCDC.2015.7162691