Mr. Edwin Jegam, HR - Head Corporate Accounts TCS, presented the "TCS Best Student Project Award 2016" to Srivenkata Krishnan S., Sundarrajan G., Kiran Kassyap S. of the Department of Computer Science and Engineering, for the project titled, “A Robust Approach for Improving the Accuracy of IMU based Indoor Mobile Robot Localization”, guided by Dr. Vidhya Balasubramanian, Associate Professor, the Department of Computer Science and Engineering, Amrita School of Engineering, Coimbatore on 30th September, 2016.
Students presented this work in ICINCO 2016–the 13th International Conference on Informatics in Control, Automation and Robotics on 29th to 31st of July, 2016, in Lisbon, Portugal. The award carried a Cash Prize and One Gold Medal for each student.
The details of the project are as follows:
Title: A Robust Approach for Improving the Accuracy of IMU based Indoor Mobile Robot Localization
Team : Srivenkata Krishnan S., Sundarrajan G., Kiran Kassyap S.
Guide: Dr. Vidhya Balasubramanian
Abstract: Indoor localization is a vital part of autonomous robots. Obtaining accurate indoor localization is difficult in challenging indoor environments where external infrastructures are unreliable and maps keep changing. In such cases. the robot should be able to localize using its on board sensors. IMU sensors are most suitable due to their cost effectiveness. In this project, a novel approach that aims to improve the accuracy of IMU based robotic localization was proposed and implemented. This approach analyses the performance of gyroscope and encoders under different scenarios, and integrates them by exploiting their advantages. In addition, the angle computed by robots to avoid obstacles as they navigate is used as an additional source of orientation estimate and appropriately integrated, using a complementary filter. We show that such an approach improves the localization accuracy significantly, while keeping costs low.