Team Anveshak, University Rover Challenge, Utah

Abstract

We build a remote operated all-terrain rover, complete with a robotic manipulator and digger, with an in-built autonomous navigation module. We were one of the 3 teams from India to get selected for University Rover Challenge held by Mars Society in Utah, and finished 29th out of more than 70 teams from across the world at URC 2017 in our debut attempt. As part of the Softwarew Team, I developed novel heuristics for path planning for autonomous 6 wheel drive systems. I also developed ROS meta-packages in C++ and Python, interfacing the robotic manipulator and on-board drive systems for seamless control. I implemented Computer Vision algorithms for identification and estimation of object distance, and a custom built radar using ultrasonic sensors.

Avatar
Ganga Meghanath
Data & Applied Scientist

My research interests include Reinforcement Learning, Deep Learning, Game Theory, Vision & Robotics.