PRIME: Scaffolding Manipulation Tasks With Behavior Primitives for Data-Efficient Imitation Learning
Tian Gao, Soroush Nasiriany, Huihan Liu, Quantao Yang, Yuke Zhu
Abstract
Imitation learning has shown great potential for enabling robots to acquire complex manipulation behaviors. However, these algorithms suffer from high sample complexity in long-horizon tasks, where compounding errors accumulate over the task horizons. We present PRIME (<underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">PR</u>imitive-based <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">IM</u>itation with data <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">E</u>fficiency), a behavior primitive-based framework designed for improving the data efficiency of imitation learning. PRIME scaffolds robot tasks by decomposing task demonstrations into primitive sequences, followed by learning a high-level control policy to sequence primitives through imitation learning. Our experiments demonstrate that PRIME achieves a significant performance improvement in multi-stage manipulation tasks, with 10–34% higher success rates in simulation over state-of-the-art baselines and 20–48% on physical hardware.
BibTeX
@inproceedings{ral2024_primescaffolding,
title = {PRIME: Scaffolding Manipulation Tasks With Behavior Primitives for Data-Efficient Imitation Learning},
author = {Tian Gao and Soroush Nasiriany and Huihan Liu and Quantao Yang and Yuke Zhu},
booktitle = {RA-L 2024},
year = {2024}
}