Accelerating long-horizon planning with affordance-directed dynamic grounding of abstract skills

K. Elimelech, Z. Kingston, W. Thomason, M. Y. Vardi, and L. E. Kavraki, “Accelerating long-horizon planning with affordance-directed dynamic grounding of abstract skills,” in IEEE International Conference on Robotics and Automation, 2024.

Abstract

Long-horizon task planning is important for robot autonomy, especially as a subroutine for frameworks such as Integrated Task and Motion Planning. However, task planning is computationally challenging and struggles to scale to realistic problem settings. We propose to accelerate task planning over an agent’s lifetime by integrating learned abstract skills: a generalizable planning experience encoding introduced in earlier work. In this work, we contribute a practical approach to planning with skills by introducing a novel formalism of planning in a skill-augmented domain. We also introduce and formulate the notion of a skill’s affordance, which indicates its predicted benefit to the solution, and use it to guide the planning and skill grounding processes. Together, our observations yield an affordance-directed, lazy-search planning algorithm, which can seamlessly compose skills and actions to solve long-horizon planning problems. We evaluate our planner in an object rearrangement domain, where we demonstrate performance benefits relative to a state-of-the-art task planner.

PDF preprint: http://kavrakilab.org/publications/elimelech2024skills.pdf