论文arXiv 2611.257882 天前
通道条件导航:轮足机器人27分钟示教实现88.6%越障成功率
本文由 AI 根据公开内容整理,可能有误,请以原文为准:Collision-Free Is Not Enough: Passage-Conditioned Navigation for Wheeled-Legged Robots(arXiv 2611.25788)
核心内容
针对轮足机器人在未知环境中因定位噪声导致固定步态失效的痛点,研究团队提出通道条件导航(Passage-Conditioned Navigation)框架。该方法摒弃传统依赖精确机器人模型或大量试错的路径规划范式,仅需27分钟单次人工示教即可提取关键地形过渡信息。在真实部署中,该系统助力机器人在2026全球开源AI挑战赛2999份提交中脱颖而出获得第三名,成为该任务唯一全自主完赛决赛选手,验证了其在复杂非结构化地形中的工程鲁棒性。
技术核心在于将每次成功越障存储为独立事件,并在局部重规划后强制执行入口约束:若当前位置偏离示教轨迹超过10 cm或10°,机器人自动转向或后退重试。仿真测试显示,在学习策略配合下,受扰楼梯攀爬零跌落(基线9次),被推离1.2 m后平均回归误差仅0.14 m;真机在271 m、7.0 m高差多障碍赛道完成全部6次运行。该方案适用于巡检巡逻等重复路线场景,解决了无模型条件下固定技能机器人的地形适应难题。
关键看点
- 低样本示教:仅需27分钟单次教学即可提取所有台阶与边缘的通过技能,无需预置机器人动力学模型或大规模强化学习训练数据
- 入口门控机制:在局部重规划后强制执行姿态校验,当位置偏差超10 cm或角度偏差超10°时触发自动转向或后退重试逻辑
- 抗扰动性能:在定位噪声干扰下,越障动作保持在安全阈值内的比例从24.1%显著提升至88.6%,大幅降低固定步态失效风险
- 实赛验证:在271 m长、7.0 m高差的真实多障碍赛道完成6次全自动运行,获2026全球开源AI挑战赛季军且为该任务唯一完赛者
工程与产业观察
该工作证明了在非结构化地形重复作业场景中,基于事件记忆的几何约束比端到端模型更具工程性价比。对于缺乏高精度本体模型的轮足机器人,通过低成本示教建立‘路径-姿态’耦合约束,能有效弥补感知与控制间的语义鸿沟,为工业巡检与安防巡逻提供了可快速部署的鲁棒导航范式。
英文摘要 (Abstract)
A collision-free detour can still bring a legged robot to the next stair or ledge a few centimetres or degrees off, and a fixed locomotion skill, factory or learned, can stall or fall. Existing methods prevent this with a robot model or extensive trial and error, but on a new site with unknown skills neither is available, so they cannot be used. We find that a single 27-minute teaching session already supplies what these methods have to derive or learn: for every stair and ledge, one crossing the skill has completed. Our method, passage-conditioned navigation, makes the route remember how each transition was entered, not only where the path went. It stores each taught crossing as an event and, without training or a robot model, enforces it after every local replan: before each ledge, an entry gate makes the robot turn or back up and retry if it is more than 10 cm or 10{\deg} off the taught crossing. Under localization noise, with path, gait schedule, and sensing unchanged, this raises the share of disturbed ledge crossings that stay within these limits from 24.1% to 88.6%. In contact simulation with our learned policies, a robot pushed off course before stairs never falls in 180 climbs, against 9 falls when the stored direction is ignored; pushed 1.2 m away, it rejoins the route, ending on average 0.14 m from it (1.10 m without rejoining), and finishes as often as an undisturbed robot. This suits any robot with fixed skills that repeats a route over terrain transitions, as in inspection and patrol, where one wrong entry can end the task. We deployed it in competition on a real wheeled-legged robot: over 271 m of multi-obstacle terrain spanning 7.0 m of elevation, it completed all six runs, won third place at the 2026 Global Open-source AI Challenge, which drew 2,999 submissions, and was the only finalist in its task to finish fully autonomously.
作者:Wai Ka Sun, Waiyiu Pong, Bowen Wang
外部来源
本页事实对应的公开页面,以原文为准。(点击将离开本站)