Skip to content

论文arXiv 2611.177306 天前

ERA系统实现无深度传感器零样本导航,VLFM成功率升至61.7% ​

本文由 AI 根据公开内容整理,可能有误,请以原文为准:ERA: Error-Resistant Autonomous Object Navigation with Predicted Depth(arXiv 2611.17730)

核心内容 ​

针对3D基础模型预测深度在零样本导航中因视图依赖误差累积导致探索中断的痛点,研究提出免训练对象导航系统ERA。该系统摒弃物理深度传感器,仅依靠RGB图像与位姿预测几何信息。在三项基准测试中,ERA在无深度传感器免训练方法中取得SOTA性能,并将VLFM算法在同一预测深度条件下的成功率从10.8%大幅提升至61.7%,且已在真实机器人平台完成部署验证。

ERA核心采用“带误移动”(Move with Error)范式,利用运动获取新视角以修正地图误差。技术实现上引入可修正占用图(Revisable Occupancy)机制,支持从可达视点持续探索,确保在无前沿边界时搜索不终止,并在停止前跨视角验证目标。该架构有效解决了纯视觉预测深度建图的不一致性,为低成本具身智能体在未知环境中的鲁棒导航提供了无需额外训练的工程化解决方案。

关键看点 ​

  • 核心范式:提出Move with Error机制,利用机器人主动运动获取新视角,动态修正RGB预测深度的视图依赖误差
  • 性能跃升:在相同预测深度条件下,将VLFM导航成功率从10.8%提升至61.7%,刷新无深度传感器免训练方法SOTA
  • 关键技术:采用可修正占用图与可达视点探索策略,解决传统前沿探索因地图误差导致的搜索提前终止问题
  • 工程验证:系统完全免训练且无需物理深度传感器,仅依赖RGB与位姿输入,并已成功部署于真实机器人平台

工程与产业观察 ​

ERA证明了通过算法层面的主动纠错机制,可有效弥补单目RGB预测深度的几何缺陷,降低对昂贵深度传感器的硬件依赖。其“带误移动”范式为具身智能体在感知不确定环境下的鲁棒导航提供了新思路,对推动低成本、轻量化服务机器人的零样本部署具有重要工程参考价值。

英文摘要 (Abstract) ​

Depth and 3D foundation models can predict geometry from RGB images, allowing zero-shot object navigation without a depth sensor. However, when predicted depth is mapped as if it came from a sensor, view-dependent errors accumulate in the map, remove exploration goals, and end the search before the agent can observe and correct them. We propose ERA, a training-free object navigation system that replaces the depth sensor with depth predicted from RGB images and poses. ERA follows a paradigm we call Move with Error: movement provides new views that correct map errors, and the corrected map enables further movement. It realizes this paradigm with revisable occupancy and with exploration from reachable viewpoints, which continues the search when no frontier remains, and verifies the target across views before stopping. On three benchmarks, ERA achieves state-of-the-art performance among training-free methods without depth sensors. Its map and exploration components also raise VLFM's success from 10.8% to 61.7% under the same predicted depth. We further deploy ERA on a real robot.

作者:Shunyang Huang, Shuo Wang, Wenyuan Xie, Mingyu Lin, Yue Ding, Hongtao Lu

基于本页技术方向关联的整机参数、核心零部件、实测报告与同赛道选型横评。

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)

  1. arXiv 2611.17730:ERA: Error-Resistant Autonomous Object Navigation with Predicted Depth ↗访问 2026-11-16