An incremental constraint-based framework for task and motion planning

Abstract

We present a new constraint-based framework for task and motion planning (TMP). Our approach is extensible, probabilistically complete, and offers improved performance and generality compared with a similar, state-of-the-art planner. The key idea is to leverage incremental constraint solving to efficiently incorporate geometric information at the task level. Using motion feasibility information to guide task planning improves scalability of the overall planner. Our key abstractions address the requirements of manipulation and object rearrangement. We validate our approach on a physical manipulator and evaluate scalability on scenarios with many objects and long plans, showing order-of-magnitude gains compared with the benchmark planner and improved scalability from additional geometric guidance. Finally, in addition to describing a new method for TMP and its implementation on a physical robot, we also put forward requirements and abstractions for the development of similar planners in the future.

Description
Advisor
Degree
Type
Journal article
Keywords
Citation

Dantam, Neil T., Kingston, Zachary K., Chaudhuri, Swarat, et al.. "An incremental constraint-based framework for task and motion planning." The International Journal of Robotics Research, (2018) Sage: https://doi.org/10.1177/0278364918761570.

Has part(s)
Forms part of
Rights
This is an author's peer-reviewed final manuscript, as accepted by the publisher. The published article is copyrighted by the authors.
Link to license
Citable link to this page