Anticipatory Task and Motion Planning: Improved Rearrangement in Persistent Continuous-Space Environments
Roshan Dhakal, Duc M. Nguyen, Tom Silver, Xuesu Xiao, Gregory J. Stein
Abstract
We consider a sequential task and motion planning (<sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">tamp</small>) setting in which a robot is assigned continuous-space rearrangement-style tasks one-at-a-time in an environment that persists between each. Lacking advance knowledge of future tasks, existing (myopic) planning strategies unwittingly introduce side effects that impede completion of subsequent tasks: e.g., by blocking future access or manipulation. We present <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">anticipatory task and motion planning</i>, in which estimates of expected future cost from a learned model inform selection of plans generated by a model-based <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">tamp</small> planner so as to avoid such side effects, choosing configurations of the environment that both complete the task and reduce overall cost. Simulated many-task deployments in navigation-among-movable-obstacles and cabinet-loading domains yield improvements of 32.7% and 16.7% average per-task cost respectively. When given time in advance to <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">prepare</i> the environment, our learning-augmented planning approach yields improvements of 83.1% and 22.3%. Finally, we also demonstrate anticipatory <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">tamp</small> on a real-world Fetch mobile manipulator.
BibTeX
@inproceedings{ral2026_anticipatorytask,
title = {Anticipatory Task and Motion Planning: Improved Rearrangement in Persistent Continuous-Space Environments},
author = {Roshan Dhakal and Duc M. Nguyen and Tom Silver and Xuesu Xiao and Gregory J. Stein},
booktitle = {RA-L 2026},
year = {2026}
}