PDDLStream: Integrating Symbolic Planners and Blackbox Samplers via Optimistic Adaptive Planning

Caelan Reed Garrett, Tomás Lozano-Pérez, Leslie Pack Kaelbling

PosterID: 36
picture_as_pdf PDF
library_books Slides
library_books Poster
menu_book BibTeX
Many planning applications involve complex relationships defined on high-dimensional, continuous variables. For example, robotic manipulation requires planning with kinematic, collision, visibility, and motion constraints involving robot configurations, object poses, and robot trajectories. These constraints typically require specialized procedures to sample satisfying values. We extend PDDL to support a generic, declarative specification for these procedures that treats their implementation as black boxes. We provide domain-independent algorithms that reduce PDDLStream problems to a sequence of finite PDDL problems. We also introduce an algorithm that dynamically balances exploring new candidate plans and exploiting existing ones. This enables the algorithm to greedily search the space of parameter bindings to more quickly solve tightly-constrained problems as well as locally optimize to produce low-cost solutions. We evaluate our algorithms on three simulated robotic planning domains as well as several real-world robotic tasks.

Session Am3: Search & Hybrid Planning
Canb 10/28/2020, 10:00 – 11:00
10/30/2020, 03:00 – 04:00
Paris 10/28/2020, 00:00 – 01:00
10/29/2020, 17:00 – 18:00
NYC 10/27/2020, 19:00 – 20:00
10/29/2020, 12:00 – 13:00
LA 10/27/2020, 16:00 – 17:00
10/29/2020, 09:00 – 10:00