State Aggregation through Reasoning in Answer Set Programming (2016)
Ginevra Gaudioso, Matteo Leonetti, and Peter Stone
For service robots gathering increasing amounts of information, the ability to realize which bits are relevant and which are not for each task is going to be crucial. Abstraction is, indeed, a fundamental characteristic of human intelligence, while it is still a challenge for AI. Abstraction through machine learning can inevitably only work in hindsight: the agent can infer whether some information was pertinent from experience. However, service robots are required to be functional and effective quickly, and their users often cannot let the robot explore the environment long enough. We propose a method to perform state aggregation through reasoning in answer set programming, which allows the robot to determine if a piece of information is irrelevant for the task at hand before taking the first action. We demonstrate our method on a simulated mobile service robot, carrying out tasks in an office environment.
In Proceedings of the IJCAI Workshop on Autonomous Mobile Service Robots (WSR 16), New York City, NY, USA, July 2016.

Matteo Leonetti Postdoctoral Alumni matteo [at] cs utexas edu
Peter Stone Faculty pstone [at] cs utexas edu