用遮蔽重建提升点云强化学习，更好处理变形物体
PointPatchRL -- Masked Reconstruction Improves Reinforcement Learning on Point Clouds
- 将点云分块后用Transformer处理，构建新强化学习框架
- 在复杂操作任务中超越主流无模型与基于模型的基线
- 适合研究点云感知、机器人抓取与动态物体建模的学者
通过摄像头感知环境对机器人强化学习至关重要。图像虽易获取，但难以提取关键几何信息，尤其面对形变或几何多变的物体。点云天然表征几何结构，可融合多视角颜色与位置数据。尽管点云深度学习近年成果丰硕，但其在强化学习中的应用仍不足，现有研究仅采用最简编码架构。本文提出PointPatchRL（PPRL），基于将点云划分为重叠区块、进行令牌化并使用Transformer处理的通用范式。相比以往用于强化学习的点云架构，PPRL表现显著提升。进一步引入遮蔽重建进行表征学习，实验表明该方法在含形变物体和几何变化的复杂操作任务中，优于强基准的无模型与基于模型方法。视频与代码见https://alrhub.github.io/pprl-website。
原文摘要 · Abstract (English)
Perceiving the environment via cameras is crucial for Reinforcement Learning (RL) in robotics. While images are a convenient form of representation, they often complicate extracting important geometric details, especially with varying geometries or deformable objects. In contrast, point clouds naturally represent this geometry and easily integrate color and positional data from multiple camera views. However, while deep learning on point clouds has seen many recent successes, RL on point clouds is under-researched, with only the simplest encoder architecture considered in the literature. We introduce PointPatchRL (PPRL), a method for RL on point clouds that builds on the common paradigm of dividing point clouds into overlapping patches, tokenizing them, and processing the tokens with transformers. PPRL provides significant improvements compared with other point-cloud processing architectures previously used for RL. We then complement PPRL with masked reconstruction for representation learning and show that our method outperforms strong model-free and model-based baselines on image observations in complex manipulation tasks containing deformable objects and variations in target object geometry. Videos and code are available at https://alrhub.github.io/pprl-website
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。