Dr Nick Hawes

Reader in Autonomous Intelligent Robotics

School of Computer Science
University of Birmingham
Edgbaston, Birmingham, B15 2TT
United Kingdom

Email: n.a.hawes@cs.bham.ac.uk
Twitter: @hawesie
Phone: +44 (0) 121 41 43739
Office: 133 (first floor, back right)
Office Hours: Mon 12:00, Tues 11:00 (term-time only)
Availability: Doodle MeetMe
[young14effects] Jay Young and Nick Hawes. Effects of Training Data Variation and Temporal Representation in a QSR-Based Action Prediction System. In AAAI Spring Symposium 2014 on Qualitative Representations for Robots. March 2014. [pdf] [bib]
Abstract. Understanding of behaviour is a crucial skill for Artificial Intelligence systems expected to interact with external agents -- whether other AI systems, or humans, in scenarios involving co-operation, such as domestic robots capable of helping out with household jobs, or disaster relief robots expected to collaborate and lend assistance to others. It is useful for such systems to be able to quickly learn and re-use models and skills in new situations. Our work centres around a behaviour-learning system utilising Qualitative Spatial Relations to lessen the amount of training data required by the system, and to aid generalisation. In this paper, we provide an analysis of the advantages provided to our system by the use of QSRs. We provide a comparison of a variety of machine learning techniques utilising both quantitative and qualitative representations, and show the effects of varying amounts of training data and temporal representations upon the system. The subject of our work is the game of simulated RoboCup Soccer Keepaway. Our results show that employing QSRs provides clear advantages in scenarios where training data is limited, and provides for better generalisation performance in classifiers. In addition, we show that adopting a qualitative representation of time can provide significant performance gains for QSR systems.
Download:  pdf pdf (476 KB)  bib bib
Links: [Google Scholar] [CiteSeer]