EquiBim: 学习双臂操作的对称等变策略
EquiBim: Learning Symmetry-Equivariant Policy for Bimanual Manipulation
AI总结：
本文提出EquiBim框架，通过强制对称性等变性提升双臂操作的性能和鲁棒性，适用于多种感知与动作表示。
摘要：
机器人模仿学习在从演示中学习复杂操作行为方面取得了显著成功。然而，许多现有机器人学习方法并未显式考虑机器人系统的物理对称性，导致在对称观测下出现不对称或不一致的行为。本文引入EquiBim，一种针对双臂操作的对称等变策略学习框架，通过训练过程中强制观测与动作之间的双侧等变性。该方法将物理对称性建模为观测和动作空间上的群作用，并在对称变换下对策略预测施加等变约束。该框架具有模型无关性，可无缝集成到多种模仿学习流程中，适用于多种感知模态和动作表示，包括点云和图像基策略，以及末端执行器空间和关节空间参数化。我们在RoboTwin双臂机器人平台上评估了EquiBim，并在仿真中评估了多种感知和动作配置。我们进一步在真实世界双臂系统上验证了该方法。在仿真和物理实验中，该方法在分布偏移下均能提升性能和鲁棒性。这些结果表明，显式强制物理对称性为双臂机器人学习提供了一个简单而有效的归纳偏差。
英文摘要：
Robotic imitation learning has achieved impressive success in learning complex manipulation behaviors from demonstrations. However, many existing robot learning methods do not explicitly account for the physical symmetries of robotic systems, often resulting in asymmetric or inconsistent behaviors under symmetric observations. This limitation is particularly pronounced in dual-arm manipulation, where bilateral symmetry is inherent to both the robot morphology and the structure of many tasks. In this paper, we introduce EquiBim, a symmetry-equivariant policy learning framework for bimanual manipulation that enforces bilateral equivariance between observations and actions during training. Our approach formulates physical symmetry as a group action on both observation and action spaces, and imposes an equivariance constraint on policy predictions under symmetric transformations. The framework is model-agnostic and can be seamlessly integrated into a wide range of imitation learning pipelines with diverse observation modalities and action representations, including point cloud-based and image-based policies, as well as both end-effector-space and joint-space parameterizations. We evaluate EquiBim on RoboTwin, a dual-arm robotic platform with symmetric kinematics, and evaluate it across diverse observation and action configurations in simulation. We further validate the approach on a real-world dual-arm system. Across both simulation and physical experiments, our method consistently improves performance and robustness under distribution shifts. These results suggest that explicitly enforcing physical symmetry provides a simple yet effective inductive bias for bimanual robot learning.
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。
