让机器人在复杂户外地形上稳定行走，靠视觉预判落脚点并保持身体对称。
SSR: Scaling Surefooted and Symmetric Humanoid Traversal to the Open World
- 通过预判下一步落脚点，引导脚步走向稳定区域防滑倒。
- 在真实多变地形上实现安全稳定行走，包括台阶、大缝隙和高平台。
- 适合需要长期户外自主移动的仿人机器人场景。
将仿人机器人行进能力扩展至开放世界是其实现人类环境实用部署的关键，但依然面临挑战。机器人需利用视觉在高度动态运动中确保异质地形上的安全可靠落脚，并生成协调自然的整体动作。我们提出SSR，一种高效的端到端框架，基于第一视角视觉实现仿人机器人行进，联合学习上述能力。SSR引入想象落脚点引导机制，学习预测即将进行的摆动脚接触点并评估其支撑性，从而引导触地前摆动向稳定区域，减少边缘滑移。同时采用等变潜在空间对称增强，在高维视觉观测下高效诱导双侧协调；并使用地形特异性多判别器运动先验，促进跨场景的人类式行为表现。大量实验表明，SSR在多样真实地形上实现安全、稳定且高质量的行走，包括结构各异的楼梯、宽缝隙及高平台等极端挑战，并可在开放室外环境中实现可靠的长时程行进。
原文摘要 · Abstract (English)
Extending humanoid traversal to the open world is key to practical deployment in human environments, but remains challenging. The robot must use vision to ensure safe and reliable foot placement on heterogeneous terrain under highly dynamic motion, while producing coordinated, natural whole-body behaviors. We propose SSR, an efficient end-to-end framework for egocentric vision-based humanoid traversal that jointly learns these capabilities. SSR introduces imagined foothold guidance, which learns to model forthcoming swing-foot contacts and evaluates their support to guide pre-touchdown swings toward stable regions, reducing edge slips. It further employs equivariant latent-space symmetry augmentation to efficiently induce bilateral coordination under high-dimensional visual observations, and uses terrain-specific multi-discriminator motion priors to encourage human-like behavior across scenes. Extensive experiments show that SSR achieves safe, stable, and high-quality locomotion on diverse real-world terrains, including stairs with varied structures and extreme challenges such as wide gaps and high platforms, while enabling reliable long-horizon traversal in open outdoor environments.
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。