Read More.

Call for Paper - December – 2022 Edition   

(SJIF Impact Factor: 5.966) (IJIFACTOR 3.8, RANKING: A+) (PIF: 3.460)

IJATCA solicits original research papers for the December – 2022 Edition.
Last date of manuscript submission is December 30, 2022.

                                                   

Simulation of an autonomous vehicle localization


Volume: 4 Issue: 5
Year of Publication: 2017
Authors: Sakthi Karthik B, Sundar Ganesh C S



Abstract

The main goal of this project is to simulate the localization of a car-like autonomous vehicle when the Global Positioning System on the vehicle fails. GPS is an important component that helps in the locating the position of the vehicle in the world. Sometimes the GPS may fail to lead to accidents or erratic motion in the case of autonomous vehicles. An effective methodology is required to locate the vehicle in the world even after the failure of the GPS and for parking the car in a safe location nearby. The Vehicle uses a Lidar from which the point cloud of obstacles surrounding the vehicle is obtained. Using several filters, only the static obstacles like the Traffic signal post are clipped. The vehicle is assumed to be at the stop line whose global coordinates are known. From the filtered point cloud data, the coordinates of the static reference points with respect to the vehicle are obtained. By using Parallelogram Law of Vectors, the global coordinates of the reference points are calculated. Then as the vehicle moves, the global coordinates of the vehicle is calculated from the corresponding local coordinates of the reference points with respect to the car. The Autonomous vehicle is modeled and imported in simulation software called Gazebo which runs alongside Robot Operating System. The Autonomous vehicle is mounted with a Velodyne HDL-32E Lidar, which is also modeled and imported in Gazebo. Point Cloud Library provides various filters required for processing the point cloud data. The Programming language used is python. Robot Operating System bridges between Gazebo and the algorithm developed.

References

  1. Lentin Joseph, Mastering ROS for Robotics Programming: Design, build and simulate complex robots using Robot Operating System and master its out-of-the-box functionalities. 2015

  2. Morgan Quigley, Brian Gerkey, William D. Smart, Programming Robots with ROS: A Practical Introduction to the Robot Operating System. 2015

  3. Anis Koubaa (eds.), Robot Operating System (ROS): The Complete Reference(1). 2016

  4. Jason M. OKane, A Gentle Introduction to ROS. 2015

  5. S. Argamon-Engelson, \"Using image signatures for place recognition\", Pattern Recognit. Lett., (19)pp. 941-951, 1998.

  6. T. Bailey, Mobile robot localisation and mapping in extensive outdoor environments, Univ. Sydney, 2002.

  7. T. Bailey, \"Constrained initialisation for bearing-only SLAM\", Proc. IEEE Int. Conf. Robotics Automation, pp. 1966-1971, 2003.

  8. Alexander Cunningham, Kai M. Wurm, Wolfram Burgard, Frank Dellaert, \"Fully distributed scalable smoothing and mapping with robust multi-robot data association\", Robotics and Automation (ICRA) 2012 IEEE International Conference on, pp. 1093-1100, 2012.

  9. Maxime Lhuillier, \"Fusion of GPS and structure-from-motion using constrained bundle adjustments\", Computer Vision and Pattern Recognition (CVPR) 2011 IEEE Conference on, pp. 3025-3032, 2011.

  10. D. R. Wong, M.P. Hayes, A. Bainbridge-Smith, \"IMU-aided SURF feature matching for relative pose estimation\", Image and Vision Computing New Zealand (IVCNZ) 2010 25th International Conference of, pp. 1-6,2010.

Keywords

Automatic Vehicle Detection System, Cloud Computing, Gazebo, Robot operating System .




© 2022 International Journal of Advanced Trends in Computer Applications
Foundation of Computer Applications (FCA), All right reserved.
Vision & Mission | Privacy Policy | Terms and Conditions