SViP：基于对象中心运动原语的双手视觉运动策略排序
SViP: Sequencing Bimanual Visuomotor Policies with Object-Centric Motion Primitives
AI总结：
SViP通过将视觉运动策略与任务和运动规划结合，利用语义场景图划分示范并生成参数化原语，仅需20个示范即可实现分布外泛化，优于现有生成式模仿学习方法。
摘要：
模仿学习（IL），特别是在利用高维视觉输入进行策略训练时，已被证明在复杂的双手操作任务中直观且有效。然而，视觉运动策略的泛化能力仍然有限，尤其是在可用的示范数据集较小时。视觉运动策略中的累积误差显著阻碍了其完成长时域任务的能力。为解决这些限制，我们提出了SViP，一个将视觉运动策略无缝集成到任务与运动规划（TAMP）中的框架。SViP使用语义场景图监控器将人类示范划分为双手和单手操作。利用关键场景图中的连续决策变量来训练切换条件生成器。该生成器产生参数化的脚本化原语，即使在遇到分布外观测时也能确保可靠的性能。仅使用20个真实世界示范，我们展示了SViP使视觉运动策略能够在无需对象姿态估计器的情况下，跨分布外初始条件进行泛化。对于以前未见过的任务，SViP利用TAMP公式中的约束建模，自动发现有效的解决方案以实现目标。在真实世界实验中，SViP优于最先进的生成式IL方法，表明其对于更复杂任务具有更广泛的适用性。项目网站：https://sites.google.com/view/svip-bimanual
英文摘要：
Imitation learning (IL), particularly when leveraging high-dimensional visual inputs for policy training, has proven intuitive and effective in complex bimanual manipulation tasks. Nonetheless, the generalization capability of visuomotor policies remains limited, especially when small demonstration datasets are available. Accumulated errors in visuomotor policies significantly hinder their ability to complete long-horizon tasks. To address these limitations, we propose SViP, a framework that seamlessly integrates visuomotor policies into task and motion planning (TAMP). SViP partitions human demonstrations into bimanual and unimanual operations using a semantic scene graph monitor. Continuous decision variables from the key scene graph are employed to train a switching condition generator. This generator produces parameterized scripted primitives that ensure reliable performance even when encountering out-of-the-distribution observations. Using only 20 real-world demonstrations, we show that SViP enables visuomotor policies to generalize across out-of-distribution initial conditions without requiring object pose estimators. For previously unseen tasks, SViP automatically discovers effective solutions to achieve the goal, leveraging constraint modeling in TAMP formulism. In real-world experiments, SViP outperforms state-of-the-art generative IL methods, indicating wider applicability for more complex tasks. Project website: https://sites.google.com/view/svip-bimanual
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。
