EnergyAction：基于能量模型的单臂到双臂策略组合
EnergyAction: Unimanual to Bimanual Composition with Energy-Based Models
将单臂操作策略建模为能量模型并通过能量组合实现双臂协调，其能量约束下的时序-空间协调机制与自适应去噪步数策略，可为视觉-动作联合生成中的多策略融合与推理效率提供可复用思路。
原文依据 model individual unimanual policies as EBMs and leverage their compositional properties to compose left and right arm actions
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期，单臂操作策略借助充足的训练数据与成熟的模型架构，在多种机器人任务上取得了显著成功。然而，由于缺乏双臂示范数据以及双臂动作协调的复杂性，将这些能力扩展到双臂操作仍然具有挑战性。现有方法要么依赖大规模双臂数据集，要么无法有效利用预训练的单臂策略。为解决这一局限，我们提出 EnergyAction，一种通过能量模型（EBMs）以组合方式将单臂操作策略迁移至双臂任务的新框架。具体而言，我们的方法包含三项关键创新。第一，我们将各个单臂策略建模为 EBM，并利用其组合性质来组合左臂与右臂动作，从而将单臂策略融合为双臂策略。第二，我们通过能量约束引入一种基于能量的时序-空间协调机制，确保生成的双臂动作既具有时序一致性又具备空间可行性。第三，我们提出两种能量感知的去噪策略，根据动作质量评估动态调整去噪步数。这些策略在保证生成高质量动作的同时，相比固定步数去噪方法保持了更优的计算效率。实验结果表明，EnergyAction 能够有效地将单臂知识迁移至双臂任务，在仅需极少双臂数据的情况下，于仿真与真实世界任务上均取得优越性能。
英文原文摘要 1660 字符
Recent advances in unimanual manipulation policies have achieved remarkable success across diverse robotic tasks through abundant training data and well-established model architectures. However, extending these capabilities to bimanual manipulation remains challenging due to the lack of bimanual demonstration data and the complexity of coordinating dual-arm actions. Existing approaches either rely on extensive bimanual datasets or fail to effectively leverage pre-trained unimanual policies. To address this limitation, we propose EnergyAction, a novel framework that compositionally transfers unimanual manipulation policies to bimanual tasks through the Energy-Based Models (EBMs). Specifically, our method incorporates three key innovations. First, we model individual unimanual policies as EBMs and leverage their compositional properties to compose left and right arm actions, enabling the fusion of unimanual policies into a bimanual policy. Second, we introduce an energy-based temporal-spatial coordination mechanism through energy constraints, ensuring the generated bimanual actions are both temporal coherence and spatial feasibility. Third, we propose two different energy-aware denoising strategies that dynamically adapt denoising steps based on action quality assessment. These strategies ensure the generation of high-quality actions while maintaining superior computational efficiency compared to fixed-step denoising approaches. Experimental results demonstrate that EnergyAction effectively transfers unimanual knowledge to bimanual tasks, achieving superior performance on both simulated and real-world tasks with minimal bimanual data.