Learning in behavioural robotics

• Main Author: Jones, E. L.
• Published: University of Edinburgh 1999
• Subjects: 006.3
• Online Access: http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.653135

The research described in this thesis examines how machine learning mechanisms can be effectively used in a behavioural robot system to improve the reliability of the system and reduce the development workload, without reducing the flexibility of the system. The justification for this is that for a robot to be performing effectively it is frequently necessary to have gained experience of its performance under a particular configuration before that configuration can be altered to produce a performance improvement. Machine learning mechanisms can automate this activity of testing, evaluating and then changing. From studying how other researchers have developed working robot systems the activities which require most effort and experimentation are: the selection of the optimal parameter settings; the establishment of the action-sensor couplings which are necessary for the effective handling of uncertainty; and choosing which way to achieve a goal. One way to implement the first two kinds of learning is to specify a model of the coupling or the interaction of parameters and results, and from that model derive an appropriate learning mechanism that will find an optimal parametrisation for that model that will enable good performance to be obtained. From this starting point it has been possible to show how equal, or better performance can be obtained by using learning mechanisms which are neither derived from nor require a model of the task being learned. Instead, by combining iteration and a task specific profit function it is possible to use a generic behavioural module based on a learning mechanism to achieve the task.