Continuous Robot Control Research Articles

A Bioinspired Neurodynamics-Based Approach to Tracking Control of Mobile Robots

Tracking control is a fundamentally important issue for robot and motor systems, where smooth velocity commands are desirable for safe and effective operation. In this paper, a novel biologically inspired tracking control approach to real-time navigation of a nonholonomic mobile robot is proposed by integrating a backstepping technique and a neurodynamics model. The tracking control algorithm is derived from the error dynamics analysis of the mobile robot and the stability analysis of the closed-loop control system. The stability of the robot control system and the convergence of tracking errors to zeros are guaranteed by a Lyapunov stability theory. Unlike some existing tracking control methods for mobile robots whose control velocities suffer from velocity jumps, the proposed neurodynamics-based approach is capable of generating smooth continuous robot control signals with zero initial velocities. In addition, it can deal with situations with a very large tracking error. The effectiveness and efficiency of the proposed neurodynamics-based tracking control of mobile robots are demonstrated by experimental and comparison studies.

学習とロボット 強化学習による実ロボットの運動制御

For learning behaviors of real robotic systems, we propose a method to extend reinforcement learning to the domain of continuous robot control problems. Reinforcement learning methods are applicable to a variety of fields, however generally they can handle only discrete states and actions and they sometimes require impractical amount of time to learn practical problems. In the proposing method, one of the connectionist models CMAC is employed for utility networks in order to represent continuous states and control variables. In order to fully utilize experiences and progress fast learning, experience sequences are stored while actual actuation and they are replayed with priorities afterall. As a testbed, the learning system is applied in simulation to the control of swing amplitude of a two-link brachiation robot which is hardly constrained with dynamics.