用坐标框架提升机器人分层策略的对称性与泛化能力
Hierarchical Equivariant Policy via Frame Transfer
- 高阶代理输出作为低阶代理的坐标系，提供强归纳偏置
- 在仿真和真实场景中均实现顶尖性能，减少示范依赖
- 适合需要长程规划与精细控制的复杂机器人任务
近期分层策略学习进展表明，将系统分解为高层与底层代理可实现高效的长时序推理与精确的细粒度控制。然而，层级间接口仍研究不足，现有方法常忽略领域对称性，导致需大量示范才能获得鲁棒性能。为此，我们提出分层等变策略（HEP），引入帧传递接口，使高层代理输出成为低层代理的坐标参考系，既保留灵活性又提供强归纳偏置。同时，我们将领域对称性整合至两层，并理论证明系统整体具备等变性。HEP在复杂机器人操作任务中达到当前最优表现，仿真与真实场景均有显著提升。
原文摘要 · Abstract (English)
Recent advances in hierarchical policy learning highlight the advantages of decomposing systems into high-level and low-level agents, enabling efficient long-horizon reasoning and precise fine-grained control. However, the interface between these hierarchy levels remains underexplored, and existing hierarchical methods often ignore domain symmetry, resulting in the need for extensive demonstrations to achieve robust performance. To address these issues, we propose Hierarchical Equivariant Policy (HEP), a novel hierarchical policy framework. We propose a frame transfer interface for hierarchical policy learning, which uses the high-level agent's output as a coordinate frame for the low-level agent, providing a strong inductive bias while retaining flexibility. Additionally, we integrate domain symmetries into both levels and theoretically demonstrate the system's overall equivariance. HEP achieves state-of-the-art performance in complex robotic manipulation tasks, demonstrating significant improvements in both simulation and real-world settings.
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。