Harsh Mahesheka

I am senior undergraduate of Electrical Engineering at Indian Institute of Technology (BHU), Varanasi with minor in Computer Science Engineering. I am currently working under Dr. Abhinav Valada at University of Freiburg. Previously, I have worked at Open Robotics under Google Summer of Code Programs and under Dr. Madhav Krishna at Robot Research Center, IIIT Hyderabad

The desire to build robust and adaptive autonomous systems that can work alongside humans to solve complex real-world tasks motivates me to study robotics. My research usually focuses more on Reinforcement Learning, Computer Vision and Robotics. Besides trying to make robots work, I enjoy clash of arguments in the form of debates.

harsh.mahesheka.eee20@iitbhu.ac.in

News

[Aug 2023] : Presented my Houshold Bot Project at G20 Summit at Varanasi, India.
[May 2023] : Started Research Internship at Robot Learning Lab, University of Freiburg.
[Feb 2023] : Got nominated for DAAD WISE Scholarship and IUSSTF-Viterbi India Program.
[June 2022] : Appointed as Secretary of Robotics Club, IIT BHU.
[May 2022] : Started Research Internship at Robotics Research Center, IIIT Hyderabad.
[May 2022] : Got Selected for Google Summer of Code Program at Open Robotics.
[March 2021] : Stood first in Robotics Conclave and Scientist of Utopia at Technex (Annual Technical Fest of IIT BHU).
[Nov 2020] : Started Integrated BTech + Mtech in Electrical Engineering at IIT BHU

Experiences

Robot Learning Lab, University of Freiburg

DAAD-WISE Research Internship Under Dr. Abhinav Valada

Developed an RL-based planner to generate base velocities for mobile manipulators, enabling them to achieve end-effector goal poses provided by teleoperator. Utilized the planner to streamline the collection of demonstations for kinesthetic learning. Also, Created an interface that enables the use of the HSR robot with the Nvidia Issac simulator for training and testing Deep Reinforcement Learning planners.

Robotics Research Center, IIIT Hyderabad

Research Internship Under Dr. K. Madhava Krishna

Worked on RL-based Global Planner trained to reduce localisation drift by avoiding symmetric or featureless areas. Created platform for training and testing DRL global planners on ROS-compatible simulations. Also, worked on grounding waypoints on annotated maps by analyzing complex language commands in Indoor Environment.

Google Summer of Code - Open Robotics

Student Developer at Open Robotics

Created tool for generating template packages for gazebo simulato and macros for installing and sourcing worlds, models, plugins etc. in gazebo robotics simulator. These tools were designed to streamline the process of creating and deploying new packages, making it easier for researchers and developers to build and test their robotic systems.