Shared control of telerobot systems using artificial intelligence algorithms

Abstract

The technology of teleoperation essentially applies to various operations in hostile environments where human can hardly work. To develop force information-based telerobotic control algorithms which composes essential functionality for telerobot systems to perform dexterous tasks in uncertain environments, the thesis deals with the following issues: First, a novel design method of a compliance controller for telerobot systems interacting with environments having unknown stiffness is presented. The neurofuzzy compliance model(NFCM)-based control presented herein is a control scheme designed to automatically determine the suitable compliance for a given task. A NFCM, composed of a fuzzy logic controller and a rule learning mechanism, is used as a compliance controller. The fuzzy logic controller receives contact force as inputs and generates corresponding corrective motions as outputs. The rule learning mechanism, composed of two neurons, trains rule base of the fuzzy logic controller until the given task is successfully performed by using a reinforcement learning algorithm. The scheme does not require any prior knowledge on the slave arm dynamics, slave arm controller and the environment, and thus, it can be easily applied to the compliance control of telerobot systems. The effectiveness of the proposed scheme is verified through a series of experiments. Second, a novel method for selecting the force reflection gain in position- force type bilateral telerobot systems is presented. The force reflection gain greatly affects the task performance of a bilateral teleoperation system; too small gain results in poor task performance while too large gain results in system instability. The maximum boundary of the gain guaranteeing the stability greatly depends upon characteristics of the elements in the system such as: a master arm which is combined with the human operator``s hand, and the environments where the slave arm contacts. In normal practice, therefore, it is ...