Year

2005

Degree Name

Master of Engineering (Research)

Department

School of Electrical, Computer and Telecommunication Engineering - Faculty of Engineering

Abstract

Acquisition of the behavioural skills of a human operator and recreating them in an intelligent autonomous system has been a critical but rather challenging step in the development of complex intelligent autonomous systems. A systematic and generic method for realising this process will greatly simplify the development, commissioning and maintenance of autonomous systems. A human operator automatically employs tacit skills to perform a dynamic real time task. Application of conventional knowledge acquisition systems is not sufficient to acquire the employed skills as the operator is typically unable to provide an accurate and complete description of the employed skills and their sequence. The feasibility of acquiring the human behavioural skills has been explored in this thesis. The work has been carried out in the context of transferring those skills to a biped robot. The focus has been on the human postural and locomotor movements. A fuzzy clustering method is developed and applied to identify different movements of the human hand. The motion is measured by a dual-axis accelerometer and a gyroscope mounted on the hand. The gyroscope is used to locate the position and configuration of the hand, whereas the accelerometer measures the kinematic parameters of the movement. The covariance and the mean of the data produced by the sensors are used as features in the clustering process. The clustering method is applied to the data produced from the human wrist movements to identify the sequence of the motion primitives embedded in them. Furthermore, the relationship between these primitives in the context of the performed task is reconstructed using a Hidden Markov Model. The progress made and the results obtained are reported and a critical review of the outcomes produced is carried out.

02Whole.pdf (1155 kB)

Share

COinS