Active Visual Localization for Multi-Agent Collaboration: A Data-Driven Approach

TL;DR

This paper presents a data-driven method for active visual localization in multi-agent systems, improving viewpoint selection to enhance localization accuracy across diverse viewpoints in simulation and real-world scenarios.

Contribution

It introduces a novel data-driven approach for viewpoint selection in active visual localization, outperforming existing methods in multi-agent collaboration contexts.

Findings

Data-driven approach outperforms existing methods in simulations.

Method achieves higher localization accuracy in real-world tests.

Approach effectively handles viewpoint changes in multi-agent settings.

Abstract

Rather than having each newly deployed robot create its own map of its surroundings, the growing availability of SLAM-enabled devices provides the option of simply localizing in a map of another robot or device. In cases such as multi-robot or human-robot collaboration, localizing all agents in the same map is even necessary. However, localizing e.g. a ground robot in the map of a drone or head-mounted MR headset presents unique challenges due to viewpoint changes. This work investigates how active visual localization can be used to overcome such challenges of viewpoint changes. Specifically, we focus on the problem of selecting the optimal viewpoint at a given location. We compare existing approaches in the literature with additional proposed baselines and propose a novel data-driven approach. The result demonstrates the superior performance of the data-driven approach when compared to existing methods, both in controlled simulation experiments and real-world deployment.