Automated Generation of Robotic Planning Domains from Observations

TL;DR

This paper presents a novel method for automatically generating robotic planning domains from human demonstrations, enabling robots to plan and execute complex tasks with high success rates, reducing manual domain specification effort.

Contribution

The paper introduces an automated approach to generate planning domains from demonstrations, including segmentation, recognition, and extraction of actions, preconditions, and effects, facilitating robot planning without manual domain modeling.

Findings

92% success rate with a single demonstration

100% success rate when combining multiple demonstrations

Effective for previously unknown stacking goals

Abstract

Automated planning enables robots to find plans to achieve complex, long-horizon tasks, given a planning domain. This planning domain consists of a list of actions, with their associated preconditions and effects, and is usually manually defined by a human expert, which is very time-consuming or even infeasible. In this paper, we introduce a novel method for generating this domain automatically from human demonstrations. First, we automatically segment and recognize the different observed actions from human demonstrations. From these demonstrations, the relevant preconditions and effects are obtained, and the associated planning operators are generated. Finally, a sequence of actions that satisfies a user-defined goal can be planned using a symbolic planner. The generated plan is executed in a simulated environment by the TIAGo robot. We tested our method on a dataset of 12 demonstrations collected from three different participants. The results show that our method is able to generate executable plans from using one single demonstration with a 92% success rate, and 100% when the information from all demonstrations are included, even for previously unknown stacking goals.