COMBO-Grasp：学习基于约束的操作以实现双臂遮挡抓取
COMBO-Grasp: Learning Constraint-Based Manipulation for Bimanual Occluded Grasping
AI总结：
本文提出 COMBO-Grasp，通过价值函数引导协调约束稳定策略与 RL 抓取策略，并结合师生蒸馏部署点云策略，显著提升双臂遮挡抓取成功率。
摘要：
本文解决遮挡机器人抓取的挑战，即在由于表面碰撞等环境约束导致期望抓取位姿在运动学上不可行的情况下进行抓取。传统机器人操作方法难以应对人类在这些情况下常用的非预抓或双臂策略的复杂性。最先进的强化学习（RL）方法由于任务固有的复杂性而并不适用。相比之下，从演示中学习需要收集大量专家演示，而这通常并不可行。受人类双手协作以稳定和重新定向物体的双臂操作策略启发，本文转而聚焦于一种双臂机器人设置来应对该挑战。具体而言，我们提出了面向双臂遮挡抓取的基于约束的操作方法 COMBO-Grasp（Constraint-based Manipulation for Bimanual Occluded Grasping），这是一种基于学习的方法，利用两个协同策略：一个使用自监督数据集训练、用于生成稳定位姿的约束策略，以及一个使用 RL 训练、用于重新定向并抓取目标物体的抓取策略。一项关键贡献在于价值函数引导的策略协调。具体来说，在抓取策略的 RL 训练期间，约束策略的输出会通过来自联合训练价值函数的梯度进行优化，从而改善双臂协调和任务性能。最后，COMBO-Grasp 采用师生策略蒸馏，以便在真实环境中有效部署基于点云的策略。实证评估表明，与具有竞争力的基线方法相比，COMBO-Grasp 显著提高了任务成功率，并成功泛化到仿真和真实环境中未见过的物体。
英文摘要：
This paper addresses the challenge of occluded robot grasping, i.e. grasping in situations where the desired grasp poses are kinematically infeasible due to environmental constraints such as surface collisions. Traditional robot manipulation approaches struggle with the complexity of non-prehensile or bimanual strategies commonly used by humans in these circumstances. State-of-the-art reinforcement learning (RL) methods are unsuitable due to the inherent complexity of the task. In contrast, learning from demonstration requires collecting a significant number of expert demonstrations, which is often infeasible. Instead, inspired by human bimanual manipulation strategies, where two hands coordinate to stabilise and reorient objects, we focus on a bimanual robotic setup to tackle this challenge. In particular, we introduce Constraint-based Manipulation for Bimanual Occluded Grasping (COMBO-Grasp), a learning-based approach which leverages two coordinated policies: a constraint policy trained using self-supervised datasets to generate stabilising poses and a grasping policy trained using RL that reorients and grasps the target object. A key contribution lies in value function-guided policy coordination. Specifically, during RL training for the grasping policy, the constraint policy's output is refined through gradients from a jointly trained value function, improving bimanual coordination and task performance. Lastly, COMBO-Grasp employs teacher-student policy distillation to effectively deploy point cloud-based policies in real-world environments. Empirical evaluations demonstrate that COMBO-Grasp significantly improves task success rates compared to competitive baseline approaches, with successful generalisation to unseen objects in both simulated and real-world environments.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
