Downloads & Free Reading Options - Results

One problem in robot control is how to obtain accurate high speed trajectory tracking when the payload varies throughout the performance of the task. A solution to the problem is one requirement for realizing a manipulator capable of duplicating human performance. A manipulator with the ability to emulate human performance is one prerequisite for achieving Air Force Robotic Telepresence program objectives. A new form of adaptive model-based control is proposed and experimentally evaluated. An Adaptive Model-Based Neural Network Controller (AMBNNC) uses multilayer perceptron artificial neural networks to estimate the payload during high speed manipulator motion. The payload estimate adapts the feedforward compensator to unmodeled system dynamics and payload variations. The neural nets are trained through repetitive training on trajectory tracking error data. The AMBNNC is experimentally evaluated on the third link of a PUMA-560 manipulator. Tracking performance is evaluated for a wide range of payload and trajectory conditions and compared to a non-adaptive model-based controller. The superior tracking accuracy of the AMBNNC demonstrates the potential of the proposed technique. Keywords: Robot, Robotics, Robot control, Adaptive control, Pattern recognition, Parameter estimation, Theses. (AW)