Grounding Mundane Inference in Perception

We describe a uniform technique for representing both sensory data and the attentional state of an agent using a subset of modal logic with indexicals. The resulting representation maps naturally into feed-forward parallel networks or can be implemented on stock hardware using bit-mask instructions. The representation has circuit-semantics" 34, 32 , but can e ciently represent propositions containing modals, unary predicates, and functions. We describe an example using Kludge, a vision-based mobile robot programmed to perform simple natural language instructions involving fetching and following tasks.

• Type: Journal
• Year: 1998
• Where: AROBOTS
• Authors: Ian Horswill
• Keywords: AROBOTS 1998, Feed-forward Parallel Networks, Uniform Technique, Vision-based Mobile Robot