Predicting Situated Behaviour Using Sequences of Abstract Spatial Relations.

摘要

The ability to understand behaviour is a crucial skill for Ar-tificial Intelligence systems that are expected to interact with external agents such as humans or other AI systems. Such systems might be expected to operate in co-operative or team-based scenarios, such as domestic robots capable of helping out with household jobs, or disaster relief robots expected to collaborate and lend assistance to others. Conversely, they may also be required to hinder the activities of malicious agents in adversarial scenarios. In this paper we address the problem of modelling agent behaviour in domains expressed in continuous, quantitative space by applying qualitative, re-lational spatial abstraction techniques. We employ three com-mon techniques for Qualitative Spatial Reasoning – the Re-gion Connection Calculus, the Qualitative Trajectory Calcu-lus and the Star calculus. We then supply an algorithm based on analysis of Mutual Information that allows us to find the set of abstract, spatial relationships that provide high degrees of information about an agent’s future behaviour. We employ the RoboCup soccer simulator as a base for movement-based tasks of our own design and compare the predictions of our system against those of systems utilising solely metric rep-resentations. Results show that use of a spatial abstraction-based representation, along with feature selection mecha-nisms, allows us to outperform metric representations on the same tasks.