Anticipatory Task and Motion Planning

TL;DR

This paper introduces anticipatory task and motion planning that uses learned models to predict future costs, enabling robots to plan actions that avoid side effects and improve efficiency in multi-task environments, demonstrated in simulation and real-world tests.

Contribution

It presents a novel anticipatory planning method that integrates learned predictions to enhance multi-task robot planning, reducing costs and side effects.

Findings

Simulated multi-task deployments showed 32.7% and 16.7% cost improvements.

When given environment preparation time, improvements increased to 83.1% and 22.3%.

Successfully demonstrated on a real-world Fetch mobile manipulator.

Abstract

We consider a sequential task and motion planning (tamp) 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 anticipatory task and motion planning, in which estimates of expected future cost from a learned model inform selection of plans generated by a model-based tamp planner so as to avoid such side effects, choosing configurations of the environment that both complete the task and minimize overall cost. Simulated multi-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 prepare the environment, our learning-augmented planning approach yields improvements of 83.1% and 22.3%. Both showcase the value of our approach. Finally, we also demonstrate anticipatory tamp on a real-world Fetch mobile manipulator.