# Few-shot Adaptation for Manipulating Granular Materials Under Domain Shift

arXiv: https://arxiv.org/abs/2303.02893 · HTML: https://mlsanity.com/paper/2303.02893/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Mar 2023.

## Built on by (most cited first, 5 of 5)

- [Tactile-based Object Retrieval From Granular Media](https://mlsanity.com/paper/2402.04536/) (2024)
- [Localized Graph-Based Neural Dynamics Models for Terrain Manipulation](https://mlsanity.com/paper/2503.23270/) (2025)
- [Interactive Shaping of Granular Media Using Reinforcement Learning](https://mlsanity.com/paper/2509.06469/) (2025)
- [Few-shot Scooping Under Domain Shift via Simulated Maximal Deployment Gaps](https://mlsanity.com/paper/2408.02949/) (2024)
- [Response to Promises and Pitfalls of Deep Kernel Learning](https://mlsanity.com/paper/2509.21228/) (2025)

## Abstract (arXiv)

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.