English

The Planner Optimization Problem: Formulations and Frameworks

Artificial Intelligence 2023-03-15 v2 Robotics

Abstract

Identifying internal parameters for planning is crucial to maximizing the performance of a planner. However, automatically tuning internal parameters which are conditioned on the problem instance is especially challenging. A recent line of work focuses on learning planning parameter generators, but lack a consistent problem definition and software framework. This work proposes the unified planner optimization problem (POP) formulation, along with the Open Planner Optimization Framework (OPOF), a highly extensible software framework to specify and to solve these problems in a reusable manner.

Keywords

Cite

@article{arxiv.2303.06768,
  title  = {The Planner Optimization Problem: Formulations and Frameworks},
  author = {Yiyuan Lee and Katie Lee and Panpan Cai and David Hsu and Lydia E. Kavraki},
  journal= {arXiv preprint arXiv:2303.06768},
  year   = {2023}
}

Comments

4 pages (+2 pages references, +6 pages appendix)