SurveilNav: Collaborative Object Goal Navigation with Robot and Surveillance System

2026-06-23

AI Summary

This work addresses the challenge of efficient navigation for a single robot in large-scale environments, where limited perceptual range and blind spots from fixed onboard cameras hinder performance. To overcome these limitations, the authors propose SurveilNav, a novel framework that unifies active camera scheduling, joint 2D/3D mapping, vision-language model (VLM)-driven value estimation, and collaborative goal verification within a single architecture. By integrating the robot’s dynamic local perception with the static global viewpoints provided by surveillance systems, SurveilNav enables multi-perspective cooperative navigation. Evaluated on a new indoor collaborative navigation dataset built upon Habitat-Sim, the method significantly outperforms existing approaches in HM3D environments, achieving state-of-the-art results in both exploration efficiency and navigation success rate, with strong applicability to large-scale search, domestic assistance, and emergency response scenarios.

Abstract

With the growing deployment of surveillance systems in factories, offices, and homes, integrating them with robots offers a promising direction for collaborative and efficient task execution. However, existing approaches largely focus on single-robot scenarios and struggle with multi-view collaboration in large-scale environments. In this paper, we present a novel indoor collaborative object navigation dataset built on Habitat-Sim, featuring 206 cameras across 74 floors. The dataset enables systematic evaluation of an agent's ability to exploit multi-view surveillance information. To address the limitations of single-robot perception, we propose SurveilNav, a collaborative navigation framework that integrates active camera scheduling, joint 2D/3D mapping, VLM-based value estimation, and collaborative target verification. By synergizing the robot's dynamic local perception with the static global view of surveillance, this architecture effectively overcomes both the limited perception range of single agents and the inherent blind spots of fixed cameras, resolving inefficient exploration. Experimental results on the HM3D dataset demonstrate that SurveilNav substantially outperforms existing methods, achieving state-of-the-art performance in both exploration efficiency and navigation success rate. Moreover, the system shows strong potential for applications in large-scale search, home environments, and rescue missions.

Problem

• object goal navigation
• surveillance system
• multi-view collaboration
• large-scale environment
• robot perception

Innovation

• collaborative navigation
• surveillance-robot integration
• active camera scheduling
• joint 2D/3D mapping
• VLM-based value estimation