Et-Seed: Efficient trajectory-Level SE(3) equivariant diffusion Policy

Transformed Observation Equivariant Action Sequence 3D Diffusion Policy ET-SEED (Ours) Figure 1: ET-SEED is a visual imitation learning algorithm that marries SE(3) equivariant visual representations with diffusion policies. (a) ET-SEED achieve surprising efficiency and spatial generalization than baselines. (b) When the input object observation is rotated or translated, the output action sequence change equivariantly. (c) Visualizations of simulation environments.