Automatic Extension of a Symbolic Mobile Manipulation Skill Set
Julian F\"orster, Lionel Ott, Juan Nieto, Roland Siegwart, Jen Jen, Chung

TL;DR
This paper presents a method for autonomous robots to automatically extend their symbolic skill set, enabling better adaptation to environmental changes and improving task success rates in simulation.
Contribution
It introduces strategies for generalizing skills, completing action sequences, and discovering preconditions to enhance symbolic planning adaptability.
Findings
29% higher success rate compared to baseline
68% faster runtime in simulation
Effective skill set extension in object rearrangement tasks
Abstract
Symbolic planning can provide an intuitive interface for non-expert users to operate autonomous robots by abstracting away much of the low-level programming. However, symbolic planners assume that the initially provided abstract domain and problem descriptions are closed and complete. This means that they are fundamentally unable to adapt to changes in the environment or task that are not captured by the initial description. We propose a method that allows an agent to automatically extend its skill set, and thus the abstract description, upon encountering such a situation. We introduce strategies for generalizing from previous experience, completing sequences of key actions and discovering preconditions to ensure the efficiency of our skill sequence exploration scheme. The resulting system is evaluated in simulation on object rearrangement tasks. Compared to a Monte Carlo Tree Search…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
