用几何不变性提升机器人推抓协同能力，让复杂场景抓取成功率大幅提高。
Push-Grasp Policy Learning Using Equivariant Models and Grasp Score Optimization
- 利用SE(2)不变性建模推抓动作的几何结构
- 推抓联合成功率在仿真中提升49%，真实场景提升35%
- 适合需要主动重排物体的复杂抓取任务
在杂乱环境中，因周围物体遮挡导致目标物体无法直接抓取，是机器人抓取的难点。通过结合推和抓的策略，可主动重排场景以利于目标获取。然而现有方法常忽略任务中的丰富几何结构，限制了其在高度杂乱环境下的表现。为此，我们提出等变推抓网络（Equivariant Push-Grasp Network），实现推抓策略的联合学习。贡献包括：（1）利用SE(2)-等变性提升推与抓的表现；（2）基于抓取得分优化的训练策略，简化联合学习过程。实验表明，该方法在仿真中抓取成功率较强基线提升49%，在真实场景中提升35%，显著推动了推抓策略学习的发展。
原文摘要 · Abstract (English)
Goal-conditioned robotic grasping in cluttered environments remains a challenging problem due to occlusions caused by surrounding objects, which prevent direct access to the target object. A promising solution to mitigate this issue is combining pushing and grasping policies, enabling active rearrangement of the scene to facilitate target retrieval. However, existing methods often overlook the rich geometric structures inherent in such tasks, thus limiting their effectiveness in complex, heavily cluttered scenarios. To address this, we propose the Equivariant Push-Grasp Network, a novel framework for joint pushing and grasping policy learning. Our contributions are twofold: (1) leveraging SE(2)-equivariance to improve both pushing and grasping performance and (2) a grasp score optimization-based training strategy that simplifies the joint learning process. Experimental results show that our method improves grasp success rates by 49% in simulation and by 35% in real-world scenarios compared to strong baselines, representing a significant advancement in push-grasp policy learning.
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。