Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Active Collaborative Visual SLAM exploiting ORB Features

Muhammad Farhan Ahmed, Vincent Frémont, Isabelle Fantoni

TL;DR

An efficient frontiers filtering method that takes into account the common IoU map frontiers and reduces the frontiers for each robot is proposed and an approach to guide robots to previously visited goal positions to promote loop closure and reduce SLAM uncertainty is presented.

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.

Active Collaborative Visual SLAM exploiting ORB Features

TL;DR

An efficient frontiers filtering method that takes into account the common IoU map frontiers and reduces the frontiers for each robot is proposed and an approach to guide robots to previously visited goal positions to promote loop closure and reduce SLAM uncertainty is presented.

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.
Paper Structure (10 sections, 2 equations, 7 figures, 2 tables, 3 algorithms)

This paper contains 10 sections, 2 equations, 7 figures, 2 tables, 3 algorithms.

Table of Contents

  1. INTRODUCTION
  2. RELATED WORK
  3. Active Collaborative SLAM
  4. Frontiers-based exploration
  5. METHODOLOGY
  6. IoU frontiers Management
  7. Frontier and reward management Server
  8. Re-localization method
  9. SIMULATION RESULTS
  10. CONCLUSIONS

Figures (7)

  • Figure 1: The architecture of resultant system with local (yellow), IoU (green), server (red) and MapMerger (gray) nodes.
  • Figure 2: \ref{['fig: plugin_map:1a']} and \ref{['fig: plugin_map:1b']} environments used and the overlapped resulting O.G map from UAV indicating path (black dots), start(black circle), end (gray circle) positions. \ref{['fig: plugin_map:1c']} showing resulting merged O.G and Octo-map of the H.E.
  • Figure 3: % area of map in H.G and W.E environments.
  • Figure 4: Area of IoU map in H.E and W.E environments.
  • Figure 5: Robot_0 all points (red), Robot_1 all points (blue), Robot_0 points after IoU filtering (orange), Robot_1 points after IoU filtering (green), running average all points (black dots), running average IoU filtered points (gray dots).
  • ...and 2 more figures