English

Few-shot Adaptation for Manipulating Granular Materials Under Domain Shift

Robotics 2023-10-27 v3

Abstract

Autonomous lander missions on extraterrestrial bodies will need to sample granular material while coping with domain shift, no matter how well a sampling strategy is tuned on Earth. This paper proposes an adaptive scooping strategy that uses deep Gaussian process method trained with meta-learning to learn on-line from very limited experience on the target terrains. It introduces a novel meta-training approach, Deep Meta-Learning with Controlled Deployment Gaps (CoDeGa), that explicitly trains the deep kernel to predict scooping volume robustly under large domain shifts. Employed in a Bayesian Optimization sequential decision-making framework, the proposed method allows the robot to use vision and very little on-line experience to achieve high-quality scooping actions on out-of-distribution terrains, significantly outperforming non-adaptive methods proposed in the excavation literature as well as other state-of-the-art meta-learning methods. Moreover, a dataset of 6,700 executed scoops collected on a diverse set of materials, terrain topography, and compositions is made available for future research in granular material manipulation and meta-learning.

Keywords

Cite

@article{arxiv.2303.02893,
  title  = {Few-shot Adaptation for Manipulating Granular Materials Under Domain Shift},
  author = {Yifan Zhu and Pranay Thangeda and Melkior Ornik and Kris Hauser},
  journal= {arXiv preprint arXiv:2303.02893},
  year   = {2023}
}
R2 v1 2026-06-28T09:02:43.141Z