FURI | Spring 2020

An Investigation of the Different Approaches of Autonomous Traversal

Data icon, disabled. Four grey bars arranged like a vertical bar chart.

The objective of this research is to design an algorithm that helps a mobile robot navigate in unmapped terrain through the aid of computer vision, GPS coordinates and path planning. An approach that utilizes coordinate frame transformation and the SLAM (Simultaneous Localization and Mapping) method is studied. It provides a way for the robot to perform path planning and obstacle avoidance, potentially during rescue or discovery missions. More artificial intelligence subfields, such as reinforcement learning, could also be applied to improve the algorithm in the future for a more robust algorithm to serve the purpose of different missions.