Autonomous Unmanned Ground Vehicle

Abstract

Automation technologies are bringing revolutionary changes in the world. Autonomous driving is subject to high academic research as well as high investments from the corporate sector. Demand for unmanned ground vehicles in industry, agriculture, and military has increased due to advances in manufacturing and automation. Waypoint guidance and navigation are indispensable fields in the research in autonomous vehicles. Following user defined paths and seeking goal locations is the main objective in waypoint guidance. In this work, an autonomous Unmanned Ground Vehicle (UGV) is commanded to drive itself along a path defined by a series of waypoints, which will be user- defined through a mapping interface. In autonomous navigation, the UGV use Sharp IR proximity sensors, GPS receivers and monocular and stereo vision cameras to circumvent obstacles and navigate through a path defined by GPS waypoints. It has to autonomously navigate through its surroundings and execute its mission hence including obstacle detection and avoidance. This report consists of implementing a system that can detect any obstacles in the way in real-time. Autonomous UGV are poised for accelerated adoption, with an ability to create and keep a map of their environment based on the input form the variety of sensors located at multiple parts of the UGV. The software then processes all these sensory inputs, determining the instructions to be sent for the UGV’s actuation. UGV uses VIO for state estimation, convolutional neural networks and computer vision for perception and stereo vision-based 3D object detection for localization of obstacles, along with path planning algorithms to plan the local and global path, which is followed by the actuation of low- level controller. All these technologies enable efficient autonomous navigation