Simultaneous localization and mapping using neural network
No Thumbnail Available
Date
2020
Journal Title
Journal ISSN
Volume Title
Publisher
UMT Lahore
Abstract
Simultaneous Localization and Mapping (SLAM) algorithm is designed using a Neural Network (NN) to map any unknown environment simultaneously provide the pose of robot in the generated map with respect to its initial origin position using IMU sensor and Encoders. We use the Extended Kalman Filter (EKF) for pose estimation and NN to provide navigation and path planning in an unknown environment. This project also provides a universal obstacle avoidance while autonomously navigating in the environ- ment. By integrating the SLAM with EKF and NN, we also improve the efficiency of navigation. The application of this project is autonomous vacuum cleaning, autonomous car parking and autonomous aerial mapping in the dynamic environment. The GUI in- terface of robot mapping and localization of the robot is provided by Robot Operating System (ROS). The unsupervised leaning method is used to train the NN model using virtual data set from the internet, simulation and some real data from the testing Light Detection and Ranging (LIDAR) sensor.