Abstract

<p>Over the last decade, navigation and Simultaneous Localization and Mapping (SLAM) have become key players in developing robust mobile robots. Several SLAM approaches utilizing camera, laser scan, sonar and fusion of sensors were developed and improved by a number of researchers. In this thesis, comparisons of these methods were evaluated, especially those offering low cost benefits, and low computation and memory consumption. The aim of this thesis was to select the most reliable and cost-efficient approach for indoor autonomous robotic applications. Currently, there are numerous studies that have optimized these SLAM methods; however, they still suffer from various complications such as scale drifting and excessive computation. This study performed different experiments to observe these challenges in realworld environments. A modified Pioneer robot was used to implement the selected SLAM system and furthermore, perform obstacle avoidance and path planning in indoor office environments. The results and tests show the reliable performance of Gmapping after tuning its parameter and set right configurations.</p>

Highlights

  • Over the past decades, mobile robot applications have been a source of attention

  • The main conclusion derived was that visionbased Simultaneous Localization and Mapping (SLAM) approaches suffered from scale drifting, lost track of the robot and relied on a high computation in comparison to Light Imaging Detection and Ranging (LIDAR)-based approaches

  • LIDAR-based SLAMs are preferable as it met our requirement of limited hardware for this project

Read more

Summary

Introduction

Mobile robot applications have been a source of attention. There are several major areas of interests such as mapping of indoor and outdoor environments, localizing the robot in a pre-mapped environment, and performing both tasks simultaneously which is called Simultaneous Localization and Mapping (SLAM) [1]. There is a dramatic increase in mobile robotic research where new algorithms are being proposed to address SLAM and navigation challenges. Recent studies in the Robot Operating System (ROS), SLAM, Navigation stacks, layered Costmap, obstacle avoidance, and other optimization techniques, make it possible to process more data with limited processing power and memory. These findings improve the overall result by developing other approaches such as utilizing sensor fusion. It is important not to assume that these techniques will work in all cases

Overview of the Project
Section 2. Literature Review and Previous Works
Simultaneous Localization and Mapping
Introduction to SLAM
Vision-Based SLAM Algorithms
Semi-direct Visual Odometry (SVO)
Dense Piecewise Planar Tracking and Mapping SLAM
Large Scale Direct SLAM
Direct Sparse Odometry
ORB SLAM
Stereo Parallel Tracking and Mapping
LIDAR-based SLAM Algorithms
KartoSLAM
Core SLAM
Lago SLAM
Cartographer
HectorSLAM
Gmapping
Pre-mapping
Loop Closure
Section 3. Implementation Techniques
Hardware System
Software System
RPLIDAR Setup on ROS
Pioneer 2DX Setup on ROS
Localization
Navigation Stack
Section 4. Conducted Tests and Results
Challenges and Observations
Small and Narrow Obstacles and Different Surfaces
Glass Detection Challenge
Stairs Detection and Mapping Challenge
Loop Closure Challenge
Disaster Area’s Pre-mapping Practical Objection
Dynamic Environments
Sensor Fusion
Conclusion and Future Work
Future Work
A.13. Move Base Launch File
A.14. Configuration Files
A.15. Navigation Launch File

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.