用对称性减少机器人操作演示需求，提升数据效率
ET-SEED: Efficient Trajectory-Level SE(3) Equivariant Diffusion Policy
- 基于空间对称性设计轨迹级等变扩散模型
- 仅需少量示范即可完成复杂物体操作，泛化能力更强
- 适合需要少样本学习的机器人操控场景
模仿学习，如扩散策略，在多种机器人操作任务中已被证明有效。然而，为保证策略鲁棒性和泛化能力，通常需要大量示范数据。为降低对示范数据的依赖，我们利用空间对称性，提出 ET-SEED——一种高效的轨迹级 SE(3) 等变扩散策略模型，用于生成复杂机器人操作中的动作序列。此前的等变扩散模型要求马尔可夫过程中每一步都满足等变性，导致训练困难。本文从理论上扩展了等变马尔可夫核，并简化了等变扩散过程的条件，从而在端到端框架下显著提升了训练效率。我们在涉及刚体、带关节物体和可变形物体的代表性任务上评估了 ET-SEED，实验表明该方法具备更优的数据效率与操作能力，且仅需少量示范即可泛化至未见构型。
原文摘要 · Abstract (English)
Imitation learning, e.g., diffusion policy, has been proven effective in various robotic manipulation tasks. However, extensive demonstrations are required for policy robustness and generalization. To reduce the demonstration reliance, we leverage spatial symmetry and propose ET-SEED, an efficient trajectory-level SE(3) equivariant diffusion model for generating action sequences in complex robot manipulation tasks. Further, previous equivariant diffusion models require the per-step equivariance in the Markov process, making it difficult to learn policy under such strong constraints. We theoretically extend equivariant Markov kernels and simplify the condition of equivariant diffusion process, thereby significantly improving training efficiency for trajectory-level SE(3) equivariant diffusion policy in an end-to-end manner. We evaluate ET-SEED on representative robotic manipulation tasks, involving rigid body, articulated and deformable object. Experiments demonstrate superior data efficiency and manipulation proficiency of our proposed method, as well as its ability to generalize to unseen configurations with only a few demonstrations. Website: https://et-seed.github.io/
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。