# 无需运动先验的地形穿越：部署保真度下的专家路由人形机器人运动

> 原文链接：https://robotics.hellobike.com/papers/2026-10-07-2610-14061
> 频道：papers | 更新日期：2026-10-07 | 标签：arxiv, cs.RO
> 核心摘要：该系统以地形分类路由五专家并用模型规划细化落脚点，在部署保真仿真中验证人形机器人复杂地形穿越。

# 无需运动先验的地形穿越：部署保真度下的专家路由人形机器人运动

::: v-pre
> 原文链接：[Terrain Traversal Without Motion Priors: Expert-Routed Humanoid Locomotion at Deployment Fidelity](https://arxiv.org/abs/2610.14061)（arXiv 2610.14061 · 发布日期：2026-10-07）

**Terrain Traversal Without Motion Priors: Expert-Routed Humanoid Locomotion at Deployment Fidelity**

该系统以地形分类路由五专家并用模型规划细化落脚点，在部署保真仿真中验证人形机器人复杂地形穿越。

## 核心要点

- 现有感知式人形移动多依赖动作捕捉重定向、生成式运动先验和蒸馏流程。
- 方法用感知高程网格分类地形路由五个专家，并对每个落脚点做模型规划与连续细化。
- 在85米五段航点路线中端到端成功18/20，四个单段均20/20成功。
- 消融去除混合与细化在楼梯和跨栏段为0%；连续细化使72.4%落脚跨越网格边界。

**验证范围与局限**：验证在部署保真仿真器中完成，任务为85米五段航点路线及五个单段评分，摘要未报告真机实验。

## 英文摘要 (Abstract)

State-of-the-art perceptive humanoid locomotion is mostly built on retargeted motion capture, a generative motion prior, and a distillation stage. We report a complete system that does not require this pipeline for a humanoid to cross varied terrain. In its place, we provide a five-expert mixture routed by a terrain classifier over a sensed elevation grid, and target every foothold with a model-based planner, refined by six closed-form-gradient steps on an interpolated terrain-cost field instead of picked from a fixed grid. Driven through the same perception-to-actuation software a robot would run, inside a second, deployment-fidelity simulator, it crosses an $85$\,m five-segment waypoint course $18$ of $20$ times end-to-end ($90\%$, Wilson $95\%$ CI $70$--$97$) and succeeds $20/20$ on four of five segments scored alone, where an ablated configuration without the mixture and without refinement reaches $0\%$ on both the stair and the hurdle segment. The continuous refinement moves $72.4\%$ of foot placements across at least one grid-cell boundary, which produces real sub-grid correction. We also ran matched component studies to report what does not account for it: one expert equals five on the training distribution, four label-free routers collapse to near-uniform activation, and a self-supervised terrain embedding loses to the privileged label.

作者：Thanh Ly, Chien Le, Truong-Duy Dang, Duy Khuong Nguyen, Duy-Dung Le, Vien Anh Ngo, An T. Le
:::

## 原始参考来源 (Sources)

- [arXiv 2610.14061：Terrain Traversal Without Motion Priors: Expert-Routed Humanoid Locomotion at Deployment Fidelity](https://arxiv.org/abs/2610.14061)