Adaptive Reinforcement Learning Strategy with Sliding Mode Control for Unknown and Disturbed Wheeled Inverted Pendulum
- PDF / 1,163,706 Bytes
- 12 Pages / 594.77 x 793.026 pts Page_size
- 13 Downloads / 191 Views
ISSN:1598-6446 eISSN:2005-4092 http://www.springer.com/12555
Adaptive Reinforcement Learning Strategy with Sliding Mode Control for Unknown and Disturbed Wheeled Inverted Pendulum Phuong Nam Dao* and Yen-Chen Liu Abstract: This paper develops a novel adaptive integral sliding-mode control (SMC) technique to improve the tracking performance of a wheeled inverted pendulum (WIP) system, which belongs to a class of continuous time systems with input disturbance and/or unknown parameters. The proposed algorithm is established based on an integrating between the advantage of online adaptive reinforcement learning control and the high robustness of integral sliding-mode control (SMC) law. The main objective is to find a general structure of integral sliding mode control law that can guarantee the system state reaching a sliding surface in finite time. An adaptive/approximate optimal control based on the approximate/adaptive dynamic programming (ADP) is responsible for the asymptotic stability of the closed loop system. Furthermore, the convergence possibility of proposed output feedback optimal control was determined without the convergence of additional state observer. Finally, the theoretical analysis and simulation results validate the performance of the proposed control structure. Keywords: Adaptive reinforcement learning control, approximate/adaptive dynamic programming (ADP), integral sliding mode control (SMC), output feedback control, wheeled inverted pendulum (WIP).
1.
INTRODUCTION
In recent years, the motion control as well as motion/force control problems of wheeled inverted pendulum (WIP) systems have received much attention in many fields, such as industry and transportation, exploration as described in [1, 2]. A WIP system is an inverted pendulum mounted on a mobile platform subjected to nonholonomic constraints. Due to the under-actuated description, i.e., the number of control inputs is less than the number of the controlled degree of freedom, it is difficult to employ the conventional robotic approaches for WIP systems. The fact is that the mobile platform forward velocity dynamics cannot be separately controlled from the tilt angle of inverted pendulum dynamics. Moreover, the presence of unstable balance, nonholonomic constraint forces, dynamic uncertainties and external disturbances in WIP systems lead to the challenges in control design. The authors in [3, 4] established the separation technique based on the nonholonomic description of vehicle to separate WIP systems obtaining the reduced dynamics. The mentioned control objective was not only classical motion control but also motion/force control by obtaining the description of constraint coefficient [5, 6]. After sep-
arating a WIP system into three subsystems comprising linear velocity subsystem (υ), and heading angular velocity subsystem (ϕ), tilt angle subsystem (θ ), the tracking problems of heading angular velocity - tilt angle frame were implemented previously using nonlinear as well as optimal control design such as robust adaptive algorit
Data Loading...
