Bootstrap Perception Under Hardware Depth Failure for Indoor Robot Navigation

TL;DR

This paper introduces a bootstrap perception system for indoor robot navigation that effectively combines LiDAR and learned monocular depth to overcome hardware depth failures, improving obstacle detection and navigation success.

Contribution

The system leverages sensor failure patterns to calibrate monocular depth without external data, enhancing obstacle coverage and navigation reliability in challenging indoor environments.

Findings

Obstacle coverage increased by 55-110% over LiDAR alone.

A lightweight student model runs at 218 FPS on Jetson Orin Nano.

Achieved 9/10 navigation success with zero collisions in simulation.

Abstract

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.