# Excavation Reinforcement Learning Using Geometric Representation

arXiv: https://arxiv.org/abs/2201.11292 · HTML: https://mlsanity.com/paper/2201.11292/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jan 2022.

## Built on by (most cited first, 7 of 7)

- [Cyclic Policy Distillation: Sample-Efficient Sim-to-Real Reinforcement Learning with Domain Randomization](https://mlsanity.com/paper/2207.14561/) (2022)
- [Learning Excavation of Rigid Objects with Offline Reinforcement Learning](https://mlsanity.com/paper/2303.16427/) (2023)
- [Progressive-Resolution Policy Distillation: Leveraging Coarse-Resolution Simulations for Time-Efficient Fine-Resolution Policy Learning](https://mlsanity.com/paper/2412.07477/) (2024)
- [Learning Tool-Aware Adaptive Compliant Control for Autonomous Regolith Excavation](https://mlsanity.com/paper/2509.05475/) (2025)
- [Interactive Shaping of Granular Media Using Reinforcement Learning](https://mlsanity.com/paper/2509.06469/) (2025)
- [3D Operation of Autonomous Excavator based on Reinforcement Learning through Independent Reward for Individual Joints](https://mlsanity.com/paper/2406.19848/) (2024)
- [Document Image Rectification Bases on Self-Adaptive Multitask Fusion](https://mlsanity.com/paper/2505.06038/) (2025)

## Abstract (arXiv)

Excavation of irregular rigid objects in clutter, such as fragmented rocks and wood blocks, is very challenging due to their complex interaction dynamics and highly variable geometries. In this paper, we adopt reinforcement learning (RL) to tackle this challenge and learn policies to plan for a sequence of excavation trajectories for irregular rigid objects, given point clouds of excavation scenes. Moreover, we separately learn a compact representation of the point cloud on geometric tasks that do not require human labeling. We show that using the representation reduces training time for RL, while achieving similar asymptotic performance compare to an end-to-end RL algorithm. When using a policy trained in simulation directly on a real scene, we show that the policy trained with the representation outperforms end-to-end RL. To our best knowledge, this paper presents the first application of RL to plan a sequence of excavation trajectories of irregular rigid objects in clutter.