Temporal Planning with Incomplete Knowledge and Perceptual Information

TL;DR

This paper introduces a novel temporal planning approach that handles incomplete knowledge, sensing actions, numeric constraints, and non-determinism, extending PDDL and demonstrating effective performance on new benchmark domains.

Contribution

It presents a new planning method combining contingent and temporal planning with an extended PDDL for incomplete knowledge and sensing, along with new evaluation domains.

Findings

Effective handling of incomplete knowledge and sensing actions.

Successful extension of PDDL for complex planning scenarios.

Good performance on newly proposed benchmark domains.

Abstract

In real-world applications, the ability to reason about incomplete knowledge, sensing, temporal notions, and numeric constraints is vital. While several AI planners are capable of dealing with some of these requirements, they are mostly limited to problems with specific types of constraints. This paper presents a new planning approach that combines contingent plan construction within a temporal planning framework, offering solutions that consider numeric constraints and incomplete knowledge. We propose a small extension to the Planning Domain Definition Language (PDDL) to model (i) incomplete, (ii) knowledge sensing actions that operate over unknown propositions, and (iii) possible outcomes from non-deterministic sensing effects. We also introduce a new set of planning domains to evaluate our solver, which has shown good performance on a variety of problems.