SuperEx: Enhancing Indoor Mapping and Exploration using Non-Line-of-Sight Perception

2025-10-12

AI Summary

Existing indoor exploration systems rely on line-of-sight (LOS) sensing, necessitating physical traversal of occluded regions for mapping—leading to inefficiency when prior assumptions are invalid. This work pioneers the integration of non-line-of-sight (NLOS) perception into the robot mapping-exploration loop. We propose a hybrid physics-informed and data-driven approach for structural reconstruction of occluded regions: leveraging single-photon LiDAR time-of-flight histograms, incorporating empty-space pruning and a two-stage reconstruction pipeline, and exploiting architectural spatial regularity to enhance prediction robustness. Evaluated on complex simulated environments and the real-world KTH floorplan dataset, our method improves map completeness by 12% under ≤30% coverage, while significantly outperforming conventional LOS-based exploration in efficiency. The core contribution is the first demonstration of active occlusion-aware perception and high-fidelity implicit modeling under low-coverage conditions—breaking the fundamental LOS constraint in robotic exploration.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Low Level & Physics-based Vision
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Efficient exploration and mapping in unknown indoor environments is a fundamental challenge, with high stakes in time-critical settings. In current systems, robot perception remains confined to line-of-sight; occluded regions remain unknown until physically traversed, leading to inefficient exploration when layouts deviate from prior assumptions. In this work, we bring non-line-of-sight (NLOS) sensing to robotic exploration. We leverage single-photon LiDARs, which capture time-of-flight histograms that encode the presence of hidden objects - allowing robots to look around blind corners. Recent single-photon LiDARs have become practical and portable, enabling deployment beyond controlled lab settings. Prior NLOS works target 3D reconstruction in static, lab-based scenarios, and initial efforts toward NLOS-aided navigation consider simplified geometries. We introduce SuperEx, a framework that integrates NLOS sensing directly into the mapping-exploration loop. SuperEx augments global map prediction with beyond-line-of-sight cues by (i) carving empty NLOS regions from timing histograms and (ii) reconstructing occupied structure via a two-step physics-based and data-driven approach that leverages structural regularities. Evaluations on complex simulated maps and the real-world KTH Floorplan dataset show a 12% gain in mapping accuracy under < 30% coverage and improved exploration efficiency compared to line-of-sight baselines, opening a path to reliable mapping beyond direct visibility.

Problem

• Enhancing indoor mapping with non-line-of-sight perception
• Overcoming inefficiency from occluded regions in robot exploration
• Integrating NLOS sensing into mapping-exploration loop

Innovation

• Using single-photon LiDAR for non-line-of-sight perception
• Integrating NLOS sensing into mapping-exploration loop directly
• Carving empty regions and reconstructing occupied structure