Optimizing robot planning domains to reduce search time for long-horizon planning

TL;DR

This paper presents a method to optimize robotic planning domains by selecting the most frequently used operators from demonstrations, significantly reducing search time for long-horizon planning tasks.

Contribution

It introduces a domain slimming technique based on operator frequency to improve planning efficiency in robotic systems.

Findings

Reduced search time for long-horizon planning goals

Effective domain size reduction without sacrificing plan quality

Iterative expansion improves planning success rate

Abstract

We have recently introduced a system that automatically generates robotic planning operators from human demonstrations. One feature of our system is the operator count, which keeps track of the application frequency of every operator within the demonstrations. In this extended abstract, we show that we can use the count to slim down domains with the goal of decreasing the search time for long-horizon planning goals. The conceptual idea behind our approach is that we would like to prioritize operators that have occurred more often in the demonstrations over those that were not observed so frequently. We, therefore, propose to limit the domain only to the most popular operators. If this subset of operators is not sufficient to find a plan, we iteratively expand this subset of operators. We show that this significantly reduces the search time for long-horizon planning goals.