外观
论文arXiv 2610.1837315 天前
DR-VLA：通过域不变场景表示从第一视角网络视频学习类人四足导航
原文链接：DR-VLA: Learning Human-Like Quadruped Navigation from Egocentric Web Videos via Domain-Invariant Scene Representations（arXiv 2610.18373 · 发布日期：2026-10-13）
DR-VLA: Learning Human-Like Quadruped Navigation from Egocentric Web Videos via Domain-Invariant Scene Representations
DR-VLA用域不变场景表示从第一视角网络视频迁移人类导航经验，并在EgoLynx-Robot和NAVSIM v1上验证。
核心要点
- 面向户外配送四足机器人，解决复杂场景理解、变化预判与社会合规导航的数据瓶颈。
- 采用Mixture-of-Transformers框架，结合视觉语言理解、潜在世界建模与flow-matching动作专家。
- 先在EgoLynx-Web无动作标签预训练，再用EgoLynx-Robot适配并预测可执行轨迹。
- 在EgoLynx-Robot测试集上QNS约提升5%，FHE降低14.6%；DISR优于五种通用视觉表示。
验证范围与局限：验证范围为EgoLynx-Robot留出测试划分和NAVSIM v1，主要指标含伪闭环QNS与开环FHE。
英文摘要 (Abstract)
Quadruped robots performing outdoor deliveries must interpret complex scenes, anticipate changes, and navigate in socially compliant ways. Robot demonstrations are costly to collect at the scale needed for generalization. Egocentric web videos offer abundant human navigation experience, but differences in viewpoint and motion make this experience difficult to transfer to robots. We introduce DR-VLA, a Mixture-of-Transformers framework that transfers human navigation experience through a domain-invariant scene representation (DISR). The framework combines vision-language understanding and latent world modeling with a flow-matching action expert. We introduce EgoLynx, comprising 10,000 hours of curated egocentric web video (EgoLynx-Web) and 2,000 clips of teleoperated robot navigation collected during real-world deliveries (EgoLynx-Robot). We pretrain the understanding and world experts on EgoLynx-Web without action labels, then adapt the model to robot observations and train the action expert on EgoLynx-Robot to predict executable trajectories. We also propose the Quadruped Navigation Score (QNS), a pseudo-closed-loop metric combining safety, instruction compliance, comfort, and progress. On the held-out EgoLynx-Robot test split, DR-VLA improves QNS by approximately 5% and reduces open-loop final heading error (FHE) by 14.6%, each relative to the best competing result for that metric. Ablations show that web-video pretraining improves generalization and that the model's key components contribute to performance. As a future-prediction target, DISR outperforms five generic visual representations and yields performance close to task-specific 3D perception without dedicated geometric labels or point clouds for target construction. Trained separately on NAVSIM v1 without web pretraining, DR-VLA achieves 92.1 PDMS, suggesting that the framework also applies to autonomous driving.
作者：Jun Tian, Yingjie Niu, Ruo Chen, Hongyi Lin, Chao Li
来源
本页事实对应的公开页面，以原文为准。