Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Sensor Fusion for Autonomous Indoor UAV Navigation in Confined Spaces

Alice James, Avishkar Seth, Endrowednes Kuantama, Subhas Mukhopadhyay, Richard Han

TL;DR

This work presents a promising navigation accuracy, with errors as low as 0.4 meters, and mapping quality characterized by a Root Mean Square Error (RMSE) of just 0.13 m, while maintaining energy efficiency and balanced resource allocation, addressing a crucial concern in UAV applications.

Abstract

In this paper, we address the challenge of navigating through unknown indoor environments using autonomous aerial robots within confined spaces. The core of our system involves the integration of key sensor technologies, including depth sensing from the ZED 2i camera, IMU data, and LiDAR measurements, facilitated by the Robot Operating System (ROS) and RTAB-Map. Through custom designed experiments, we demonstrate the robustness and effectiveness of this approach. Our results showcase a promising navigation accuracy, with errors as low as 0.4 meters, and mapping quality characterized by a Root Mean Square Error (RMSE) of just 0.13 m. Notably, this performance is achieved while maintaining energy efficiency and balanced resource allocation, addressing a crucial concern in UAV applications. Flight tests further underscore the precision of our system in maintaining desired flight orientations, with a remarkable error rate of only 0.1%. This work represents a significant stride in the development of autonomous indoor UAV navigation systems, with potential applications in search and rescue, facility inspection, and environmental monitoring within GPS-denied indoor environments.

Sensor Fusion for Autonomous Indoor UAV Navigation in Confined Spaces

TL;DR

This work presents a promising navigation accuracy, with errors as low as 0.4 meters, and mapping quality characterized by a Root Mean Square Error (RMSE) of just 0.13 m, while maintaining energy efficiency and balanced resource allocation, addressing a crucial concern in UAV applications.

Abstract

In this paper, we address the challenge of navigating through unknown indoor environments using autonomous aerial robots within confined spaces. The core of our system involves the integration of key sensor technologies, including depth sensing from the ZED 2i camera, IMU data, and LiDAR measurements, facilitated by the Robot Operating System (ROS) and RTAB-Map. Through custom designed experiments, we demonstrate the robustness and effectiveness of this approach. Our results showcase a promising navigation accuracy, with errors as low as 0.4 meters, and mapping quality characterized by a Root Mean Square Error (RMSE) of just 0.13 m. Notably, this performance is achieved while maintaining energy efficiency and balanced resource allocation, addressing a crucial concern in UAV applications. Flight tests further underscore the precision of our system in maintaining desired flight orientations, with a remarkable error rate of only 0.1%. This work represents a significant stride in the development of autonomous indoor UAV navigation systems, with potential applications in search and rescue, facility inspection, and environmental monitoring within GPS-denied indoor environments.

Paper Structure

This paper contains 11 sections, 8 figures, 1 table, 1 algorithm.

Table of Contents

  1. Introduction
  2. Background
  3. System Overview
  4. Sensor Fusion for Mapping
  5. Sensors
  6. SLAM Visualization in RVIZ
  7. Experimental Validation
  8. System Network - RQT graphs
  9. Distance measurements
  10. Flight tests
  11. Conclusion

Figures (8)

  • Figure 1: The aerial robot used for indoor SLAM
  • Figure 2: The System Block Diagram of the Autonomous UAV
  • Figure 3: The ROS Visualisation output for SLAM implementation performed by connecting the ground station laptop to the UAV's unique ROS Master IP address
  • Figure 4: The RQT Graph showing active ROS nodes and topics obtained from the ZED 2i camera along with RVIZ output
  • Figure 5: The RQT graph showing the active ROS nodes, ROS topics and TF for the LiDAR, Hector Slam, and MAVROS packages along with the RVIZ output.
  • ...and 3 more figures