Reliability-Guided Depth Fusion for Glare-Resilient Navigation Costmaps

2026-04-14

AI Summary

Specular glare often induces depth measurement artifacts—such as holes and spikes—in RGB-D sensors, which accumulate in occupancy grid cost maps as spurious obstacles. This work addresses this issue by formulating it as a depth reliability estimation task and introduces a lightweight Depth Reliability Map (DRM) estimator. Furthermore, a Reliability-Guided Fusion (RGF) mechanism is devised to dynamically modulate the weight of depth measurements during occupancy updates based on their estimated reliability. The proposed approach substantially suppresses false obstacle generation in reflective environments while better preserving free space. Evaluated on RealSense D435 and Jetson Orin Nano platforms, the method incurs only minimal computational overhead and significantly enhances both the robustness of indoor navigation and the accuracy of cost maps.

Technology Category

• Intelligent Robots: State Estimation
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Computer Vision: 3D Computer Vision

Application Category

• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Specular glare on reflective floors and glass surfaces frequently corrupts RGB-D depth measurements, producing holes and spikes that accumulate as persistent phantom obstacles in occupancy-grid costmaps. This paper proposes a glare-resilient costmap construction method based on explicit depth-reliability modeling. A lightweight Depth Reliability Map (DRM) estimator predicts per-pixel measurement trustworthiness under specular interference, and a Reliability-Guided Fusion (RGF) mechanism uses this signal to modulate occupancy updates before corrupted measurements are accumulated into the map. Experiments on a real mobile robotic platform equipped with an Intel RealSense D435 and a Jetson Orin Nano show that the proposed method substantially reduces false obstacle insertion and improves free-space preservation under real reflective-floor and glass-surface conditions, while introducing only modest computational overhead. These results indicate that treating glare as a measurement-reliability problem provides a practical and lightweight solution for improving costmap correctness and navigation robustness in safety-critical indoor environments.

Problem

• specular glare
• depth corruption
• occupancy-grid costmaps
• phantom obstacles
• RGB-D sensing

Innovation

• Depth Reliability Map
• Reliability-Guided Fusion
• specular glare
• costmap construction
• RGB-D fusion