Assumption-Based Planning

TL;DR

This paper introduces Assumption-Based Planning, a multi-agent approach where agents collaboratively develop plans through conjecture and refutation cycles, reasoning under uncertainty without negotiation.

Contribution

It presents a novel planning method based on defeasible reasoning and argumentation dialogues among agents, differing from classical planning approaches.

Findings

Agents can produce reasonable proposals based on their knowledge.

Planning involves conjecture/refutation cycles rather than negotiation.

The approach handles complex environments and partial knowledge.

Abstract

The purpose of the paper is to introduce a new approach of planning called Assumption-Based Planning. This approach is a very interesting way to devise a planner based on a multi-agent system in which the production of a global shared plan is obtained by conjecture/refutation cycles. Contrary to classical approaches, our contribution relies on the agents reasoning that leads to the production of a plan from planning domains. To take into account complex environments and the partial agents knowledge, we propose to consider the planning problem as a defeasible reasoning where the agents exchange proposals and counter-proposals and are able to reason about uncertainty. The argumentation dialogue between agents must not be viewed as a negotiation process but as an investigation process in order to build a plan. In this paper, we focus on the mechanisms that allow an agent to produce `reasonable' proposals according to its knowledge.