Task planning is the problem of finding a discrete sequence of actions to achieve a goal. Unfortunately, task planning in robotic domains is computationally challenging. To address this, in our prior work, we explained how knowledge from a successful task solution can be cached for later use, as an “abstract skill.” Such a skill is represented as a trace of states (“road map”) in an abstract space and can be matched with new tasks on-demand. This paper explains how one can use a library of abstract skills, derived from past planning experience, to reduce the computational cost of solving new task planning problems. As we explain, matching a skill to a task allows us to decompose it into independent sub-tasks, which can be quickly solved in parallel. This can be done automatically and dynamically during planning. We begin by formulating this problem of “planning with skills” as a constraint satisfaction problem. We then provide a hierarchical solution algorithm, which integrates with any standard task planner. Finally, we experimentally demonstrate the computational benefits of the approach for reach-avoid tasks.
Efficient Task Planning Using Abstract Skills and Dynamic Road Map Matching
Springer Proceedings in Advanced Robotics
The International Symposium of Robotics Research ; 2022 ; Geneva, Switzerland September 25, 2022 - September 30, 2022
2023-03-08
17 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Automatic Cross-domain Task Plan Transfer by Caching Abstract Skills
Springer Verlag | 2022
|Matching of Digital Road Networks suited for Navigation and Transport Planning
British Library Conference Proceedings | 2000
|An efficient temporal logic for robotic task planning
NTRS | 1989
|Decentralized dynamic task planning for heterogeneous robotic networks
British Library Online Contents | 2015
|