Aerial-Ground collaborative sensing: Third-Person view for teleoperation

TL;DR

This paper presents a MAV-based system that autonomously provides third-person views for ground robots, improving teleoperation in GPS-denied environments during time-critical Search and Rescue operations.

Contribution

It introduces a novel MAV system that offers seamless third-person perspective support for multiple ground robots using local visual servoing and global localization.

Findings

System successfully supports multiple ground robots in real-world scenarios

Enhances teleoperation performance in GPS-denied environments

Enables flexible visual detection and return-home functions

Abstract

Rapid deployment and operation are key requirements in time critical application, such as Search and Rescue (SaR). Efficiently teleoperated ground robots can support first-responders in such situations. However, first-person view teleoperation is sub-optimal in difficult terrains, while a third-person perspective can drastically increase teleoperation performance. Here, we propose a Micro Aerial Vehicle (MAV)-based system that can autonomously provide third-person perspective to ground robots. While our approach is based on local visual servoing, it further leverages the global localization of several ground robots to seamlessly transfer between these ground robots in GPS-denied environments. Therewith one MAV can support multiple ground robots on a demand basis. Furthermore, our system enables different visual detection regimes, and enhanced operability, and return-home functionality. We evaluate our system in real-world SaR scenarios.