Active Collaborative Visual SLAM exploiting ORB Features

TL;DR

This paper introduces an efficient active collaborative visual SLAM method using aerial and ground robots, improving environment exploration and mapping by optimizing frontier filtering and guiding robots to revisit goal positions, resulting in increased coverage.

Contribution

The paper presents a novel visual AC-SLAM approach with a new frontier filtering technique and a robot guidance strategy to enhance exploration efficiency and map accuracy.

Findings

Achieved 59% increase in area coverage in simulations.

Implemented in ROS and evaluated on public datasets.

Outperformed similar methods in exploration efficiency.

Abstract

In autonomous robotics, a significant challenge involves devising robust solutions for Active Collaborative SLAM (AC-SLAM). This process requires multiple robots to cooperatively explore and map an unknown environment by intelligently coordinating their movements and sensor data acquisition. In this article, we present an efficient visual AC-SLAM method using aerial and ground robots for environment exploration and mapping. We propose an efficient frontiers filtering method that takes into account the common IoU map frontiers and reduces the frontiers for each robot. Additionally, we also present an approach to guide robots to previously visited goal positions to promote loop closure to reduce SLAM uncertainty. The proposed method is implemented in ROS and evaluated through simulations on publicly available datasets and similar methods, achieving an accumulative average of 59% of increase in area coverage.