I'm Junior Software Engineer @ Aegeus Technologies building autonomous
robots for robotic dry cleaning at the Solar Parks so as to minimize
the soiling losses . Before joining Aegeus Technologies , I worked as
Project Intern @ Robotics Lab ,Department of Electrical Engineering , IIT Roorkee , where I worked on the reinforcement
learning based control of the UR5 Robotic Arm .
I hold an Integrated B.Tech - M.Tech degree in Power & Energy Engineering
from the Central University of Karnataka , where I secured an "O" grade ( Outstanding ) and received a free-ship award for my academic
performance . I also have multiple certifications and internships
in the field of Robotics and Machine Learning .I am passionate
and ethusiastic about Robotics and Machine Learning . I am always
open to new opportunities and challenges that can help me grow
and make a positive impact .
Baleshwar Mahto
+91 7760816342
baleshwar.cuk@gmail.com
Integrated B.Tech - M.Tech in Power & Energy Engineering• July 2017 - June 2022
1.Secured "O" grade ( Outstanding ) in M.Tech @ Department of Electrical Engineering.
2.Courses : Python , C , Data Structures & Algorithms , Machine Learning , Electrical Machines , Power Electronics , Digital Electronics , Analog Electronics.
3.Technical member of Enigma AI Club & IEEE volunteer and Student member.
3.Free-ship awardee ( Tuition Fee refund ) for academic excellence.
4.Nominated (Our team) for the Smart India Hackathon 2020 after competing at the University level .
5.Led the team "3Coders" in 24 hour long IEEEXtreme 13.0 Programming competition.
6.Led the team "8Spiders" in 24 hour long IEEEXtreme 12.0 Programming Competition.
Junior Software Engineer • Feb 2023 - Present
1.Shreem Autonomous Robot :
- Co-implemented Epsilon Star algorithm in Python
for online coverage path planning of unknown environment to navigate
autonomously in an inclined rectangular island of solar panels .
- Derived mathematically the angle of inclined solar panels with ground
in terms of roll and pitch angles provided by IMU ( Inertial Measurement
Unit ) sensor to compute the required traction for auto-hold functionality
on inclined solar panels.
- Done research work and read research papers in related domains and suggested
optimal method for development .
2.Unicorn Fully-automatic Robot :
- Assisted Lead Engineer in troubleshooting 42 control panels ( Control Unit )
of the Unicorn fully-automatic robot .
- Created root cause analysis ( RCA ) report on the failures of the control panels
at that specific site and suggested optimal methods to further stablize it .
- Contributed code to multiple Unicorn robot related projects for new features enhancement
and enabling wireless communication between the robot and remote monitoring station .
(Modbus RTU & LoRaWAN )
Researcher ( Deep Learning ) • Aug 2021 - July 2022
1.Solar Energy Generation Forecasting : Enhanced the accuracy of the
solar energy generation forecasting on the Greek dataset using NeuralProphet
by 0.017 and 0.034 in terms of Mean Absolute Error ( MAE ) and Root Mean
Square Error ( RMSE ) respectively.
2.Web App for User Interaction : Developed a web app for interacting with
the solar energy generation forecasting model using Flask web framework
and deployed the forecasting model on Heroku cloud.
3.Research Work : Done research work and read research papers published
between 2016 to 2021 to find various machine learning algorithms to forecast
solar energy generation .
Project Intern @ Robotics Lab ( Reinforcement Learning ) • Dec 2020 - June 2021
UR5 Robotic Arm Trajectory Planning : Applied Q-learning algorithm to make the end effector of UR5 to move in a circular trajectory using openai_ros package in Robotic Operating System ( ROS) Kinetic version .Trained the reinforcement learning agent for 6-7 hours in the online Contruct platform and found the agent to learn
Summer Research Intern ( Computer Vision ) • Feb 2021 - April 2021
1.Automatic License Plate detection and Recognition System ( ALPR ) :
Labelled ~ 250 images of License Plate to train a custom object detection model .
Applied Tesseract OCR for License plate recognition and was able to improve its
performance by using image processing techniques.
2.Deployment of detection model :Deployed YOLO v4 model having weight size
of 244 MB in Raspberry PI 3B of 1GB RAM using Darknet framework .
Design Innovation Center ( DIC ) Winter Intern • Dec 2019
Discrete-time Sliding Mode Controller Design : Researched about the latest papers on sliding mode control . Designed a discrete-time sliding mode controller for a two-wheeled mobile robot , which is a kind of autonomous guided vehicle , for path tracking of basic paths , namely circular path and straight line path .