Grounding Mundane Inference in Perception

  • Authors:
  • Ian Douglas Horswill

  • Affiliations:
  • The Institute for the Learning Sciences, Northwestern University, 1890 Maple Avenue, Evanston, IL 60201. E-mail: ian@cs.nwu.edu

  • Venue:
  • Autonomous Robots - Special issue on autonomous agents
  • Year:
  • 1998

Quantified Score

Hi-index 0.02

Visualization

Abstract

We describe a uniform technique for representing both sensory data andthe attentional state of an agent using a subset of modal logic withindexicals. The resulting representation maps naturally intofeed-forward parallel networks or can be implemented on stock hardwareusing bit-mask instructions. The representation has“circuit-semantics” (Nilsson, 1994, Rosenschein and Kaelbling, 1986),but can efficiently represent propositions containing modals, unarypredicates, and functions. We describe an example using Kludge, avision-based mobile robot programmed to perform simple naturallanguage instructions involving fetching and following tasks.