外观
论文arXiv 2609.3657529 天前
EquivDP3：用于数据高效人形机器人loco-manipulation的SIM(3)不变点云编码器
针对人形机器人少演示视觉运动泛化，EquivDP3以SIM(3)等变VNN点云编码器构建分层扩散策略，并在模拟IsaacLab基准验证数据效率。
宇树 G1原文链接：EquivDP3: A SIM(3)-Invariant Point-Cloud Encoder for Data-Efficient Humanoid Loco-Manipulation（arXiv 2609.36575 · 发布日期：2026-09-29）
EquivDP3: A SIM(3)-Invariant Point-Cloud Encoder for Data-Efficient Humanoid Loco-Manipulation
针对人形机器人少演示视觉运动泛化，EquivDP3以SIM(3)等变VNN点云编码器构建分层扩散策略，并在模拟IsaacLab基准验证数据效率。
核心要点
- 人形loco-manipulation策略需从少量演示泛化到物体位姿和光照变化。
- 高层扩散规划器用SIM(3)等变VNN编码点云，低层由冻结RL步态策略和手臂微分IK执行。
- 5-10个演示时成功率67.1%，高于四个非等变基线38.2-52.4%。
- 去除点云的本体感知对照显示差距来自感知；额外延迟仅0.8 ms/命令块。
验证范围与局限：验证范围为43关节Unitree G1人形机器人在两个模拟IsaacLab基准中的实验。
英文摘要 (Abstract)
Visuomotor policies for humanoid loco-manipulation must generalize across object poses and lighting from only a handful of demonstrations. 3D Diffusion Policy (DP3) conditions a diffusion-based action generator on point-cloud features, but its PointNet-style encoder has no built-in equivariance to the rotations, translations, and scalings (SIM(3)) that manipulation tasks respect. EquiBot closed this gap for wheeled manipulators with a SIM(3)-equivariant Vector Neuron Network (VNN) encoder. We extend this to a substantially more complex embodiment, the 43-joint Unitree G1 humanoid, and propose EquivDP3: a two-stage policy where a high-level diffusion planner with a SIM(3)-equivariant VNN encoder emits 6 Hz whole-body command chunks, executed at 50 Hz by a frozen, pre-trained RL locomotion policy and a differential inverse-kinematics module for the arms, trained end-to-end by behavior cloning. Across two simulated IsaacLab benchmarks and four non-equivariant baselines (5-100 demonstrations, in- and out-of-distribution), EquivDP3's advantage concentrates in the low-data regime: at 5-10 demonstrations it reaches 67.1% success versus 38.2-52.4% for the baselines, while by 50-100 all encoders converge (74.3-85.2%) and the ordering is no longer meaningful. A proprioception-only control confirms this gap is genuinely perceptual: with the point cloud removed, success drops to 31% vs. 60% (EquivDP3) at 5 demonstrations and 78% vs. 99% at 10, but vanishes by 50-100, showing the high-data plateau reflects a benchmark ceiling, not five encoders learning the same invariance. The encoder costs only 0.8 ms of extra latency per action chunk over the PointNet encoder it replaces. Baking geometric symmetry into a hierarchical diffusion policy's perception backbone is a practical, nearly free way to improve data efficiency for humanoid loco-manipulation when demonstrations are scarce.
作者：Abu Hanif Muhammad Syarubany, Chang D. Yoo
来源
本页事实对应的公开页面，以原文为准。