外观
论文arXiv 2609.290921 个月前
DAWN：基于深度去噪世界模型的噪声鲁棒四足跑酷
原文链接：DAWN: Noise-Robust Quadruped Parkour via Depth-Denoising World Models（arXiv 2609.29092 · 发布日期：2026-09-24）
DAWN: Noise-Robust Quadruped Parkour via Depth-Denoising World Models
为提升视觉腿足运动的深度噪声鲁棒性，DAWN将去噪与对比对齐融入世界模型，并在Unitree Go1跑酷上验证。
核心要点
- 现有视觉腿足运动训练假设深度干净，部署依赖手调滤波，参数不透明且噪声会显著降低性能。
- DAWN向编码器输入带噪深度、以干净深度重建，并用对比学习对齐带噪与干净深度的潜状态。
- 无需手动滤波校准，DAWN在Unitree Go1上零样本通过18 cm楼梯、70 cm沟和45 cm台阶。
- 消融显示去噪与对比对齐分别作用于重建和表征，结合后带来可叠加增益；视频和代码已公开。
验证范围与局限：验证范围为Unitree Go1上的零样本四足跑酷，使用原始深度观测通过楼梯、沟和台阶等障碍。
英文摘要 (Abstract)
Vision-based legged locomotion methods assume clean depth at training time and rely on hand-tuned post-processing filters at deployment. However, filter parameters are rarely disclosed, hindering reproducibility, and performance degrades substantially when depth noise is left unaddressed. Building noise robustness directly into the learning pipeline would eliminate this dependency. While such robustness has been explored for proprioceptive inputs, analogous approaches for depth perception remain largely absent in legged locomotion. We propose DAWN (Denoising and Alignment in World models for Noise-robustness), a noise-robust perception framework for legged locomotion, which builds noise robustness directly into a world model via two modifications: (1) feeding noisy depth to the encoder while keeping clean depth as the reconstruction target, forcing the model to implicitly denoise its input; and (2) applying contrastive learning to align the latent states of noisy and clean depth. Importantly, DAWN is not tied to a specific noise model, requiring no manual tuning to the noise distribution at deployment. Furthermore, it incurs no additional inference cost over existing world model-based methods. Without any manual filter calibration -- relying solely on the learned noise-robust representation -- DAWN achieves zero-shot quadruped parkour on a Unitree Go1: traversing stairs up to 18 cm, clearing gaps up to 70 cm, and mounting steps up to 45 cm from raw depth observations. Ablation studies show that denoising and contrastive alignment contribute at complementary levels -- reconstruction and representation, respectively -- and yield additive gains when combined. Videos and code are available at: https://dawn-parkour.github.io/
作者：Yohan Choi, Min-Jun Kim, Jin-Sung Kim, Yong-Jae Kim, Youn‐Hee Han
来源
本页事实对应的公开页面，以原文为准。