硬件深度传感器失效时，用残存数据自校准实现室内导航
Bootstrap Perception Under Hardware Depth Failure for Indoor Robot Navigation
- 利用失效传感器的残存数据自校准单目深度，填补感知空缺
- 在走廊和动态人群场景中，障碍物覆盖提升55%至110%
- 轻量模型可部署于边缘设备，零碰撞完成导航任务
我们提出一种在硬件深度传感器失效条件下，用于室内机器人导航的自启动感知系统。在走廊数据中，飞行时间相机在反光表面会丢失高达78%的深度像素，而仅靠2D LiDAR无法探测扫描平面以上的障碍物。本系统利用该故障的自参照特性：传感器保留的有效像素可将学习得到的单目深度校准到真实尺度，从而在无需外部数据的情况下自我补全感知。系统构建了故障感知的传感层级结构，在传感器正常时保持保守，在故障时主动填充：始终以LiDAR为几何基准，保留有效硬件深度，仅在必要时引入学习深度。在走廊及动态行人测试中，选择性融合使代价地图障碍物覆盖率相比仅用LiDAR提高55%-110%。一个轻量级蒸馏后的学生模型可在Jetson Orin Nano上以218 FPS运行，在闭环仿真中实现9/10导航成功率且零碰撞，性能接近真值深度基线，成本仅为基础模型的极小部分。
原文摘要 · Abstract (English)
We present a bootstrap perception system for indoor robot navigation under hardware depth failure. In our corridor data, the time-of-flight camera loses up to 78% of its depth pixels on reflective surfaces, yet a 2D LiDAR alone cannot sense obstacles above its scan plane. Our system exploits a self-referential property of this failure: the sensor's surviving valid pixels calibrate learned monocular depth to metric scale, so the system fills its own gaps without external data. The architecture forms a failure-aware sensing hierarchy, conservative when sensors work and filling in when they fail: LiDAR remains the geometric anchor, hardware depth is kept where valid, and learned depth enters only where needed. In corridor and dynamic pedestrian evaluations, selective fusion increases costmap obstacle coverage by 55-110% over LiDAR alone. A compact distilled student runs at 218\,FPS on a Jetson Orin Nano and achieves 9/10 navigation success with zero collisions in closed-loop simulation, matching the ground-truth depth baseline at a fraction of the foundation model's cost.
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。