A New Reinforcement Learning Based Adaptive Sliding Mode Control Scheme for Free-Floating Space Robotic Manipulator

Abstract

This paper presents a new adaptive small chattering sliding mode control (SCSMC) scheme that uses reinforcement learning (RL) and time-delay estimation (TDE) for the motion control of free-floating space robotic manipulators (FSRM) subject to model uncertainty and external disturbance. The proposed sliding mode control scheme can achieve small chattering effects and improve the tracking accuracy by using a new adaptive law for the switching gain and a RL-based robust term to handle the control inputs. In SCSMC, the complicated multiple-input-multiple-output (MIMO) uncertain system of FSRM is transformed into multiple single-input-single-output (SISO) known subsystems with bounded estimation errors by the TDE technique and state feedback compensation. Subsequently, once the sliding variable is inside the designed manifold, the derivative of the switching gain for each subsystem becomes a negative hyperbolic tangent function of the associated sliding variable, which offers the ability to reduce chattering by decreasing the switching gain. Moreover, the RL based robust term for each subsystem is designed to avoid the loss of tracking accuracy caused by the aforementioned switching gain drop. The tracking errors are proven to be uniformly-ultimately-bounded (UUB) with an arbitrarily small bound by using the Lyapunov theory. The effectiveness of the proposed control scheme is verified by numerical simulations.

Keywords

• Reinforcement learning
• sliding mode control
• space robotic manipulator
• time delay estimation