Combining Answer Set Programming and POMDPs for Knowledge Representation and Reasoning on Mobile Robots

TL;DR

This paper presents a novel architecture combining Answer Set Programming and POMDPs to improve knowledge representation and reasoning in mobile robots operating under uncertainty and partial observability.

Contribution

It introduces an integrated approach that uses declarative programming with probabilistic reasoning to handle incomplete knowledge and sensor uncertainty in robotic tasks.

Findings

Effective in representing incomplete domain knowledge

Enables belief revision with minimal human input

Successfully tested on mobile robots in indoor environments

Abstract

For widespread deployment in domains characterized by partial observability, non-deterministic actions and unforeseen changes, robots need to adapt sensing, processing and interaction with humans to the tasks at hand. While robots typically cannot process all sensor inputs or operate without substantial domain knowledge, it is a challenge to provide accurate domain knowledge and humans may not have the time and expertise to provide elaborate and accurate feedback. The architecture described in this paper combines declarative programming and probabilistic reasoning to address these challenges, enabling robots to: (a) represent and reason with incomplete domain knowledge, resolving ambiguities and revising existing knowledge using sensor inputs and minimal human feedback; and (b) probabilistically model the uncertainty in sensor input processing and navigation. Specifically, Answer Set Programming (ASP), a declarative programming paradigm, is combined with hierarchical partially observable Markov decision processes (POMDPs), using domain knowledge to revise probabilistic beliefs, and using positive and negative observations for early termination of tasks that can no longer be pursued. All algorithms are evaluated in simulation and on mobile robots locating target objects in indoor domains.