Tharun Vadakke Puthanveettil

I'm a robotics graduate student at the University of Maryland, College Park.

Previously, I was a researcher at the Robotics Innovations Lab, Indian Institute of Science where I work on 'Human Collaborative Agricultural Robots'.

I've also worked as the AI Team Lead of the innovation team at Wipro Limited, handling cutting edge technologies like AI, IoT, AR, VR, Robotics, and Automation

Email / CV / Bio / Google Scholar / Linkedin / Github / Honours & Certifications

Projects & Research

My areas of interest are Machine Learning, Computer Vision, Robotics and Cognitive Science. The following are some of my works in the mentioned domains.

	Autonomous Weeding Robot(Ongoing) video A robotic manipulator based precision weeding robot for optimizing the usage of pesticides in indoor farms.
	RAMI Cascade Campaign(IROS21) - FBM1: ORB SLAM based drone localization video An aerial robotic solution for asset Inspection and Management (I&M).
	RAMI Cascade Campaign(IROS21) - FBM2: YoloR based Surface Defect Detection video An aerial robotic solution for asset Inspection and Management (I&M).
	Monocular Depth Estimation using Transfer Learning video A Deep Learning based solution for estimating depth using monocular cameras.
	Virtual Try-on project page / video An advanced AI solution to bring down trial room drops and to provide the customer with a style quotient evaluator.
	AI Cricket Coach project page An AI-backed solution that can classify bowl types based on video feeds and provide batsmen with end-to-end coaching assistance in an enhancedWebVR environment.
	my Style project page / video An end-to-end AI-powered shopping app.
	RL Driven Cricket Game Simulation project page A 2D Cricket game simulation engine where an RL based bowler(agent) learns to bowl as per different batting styles and fielder distributions on the field, ensuring that it gives away as minimal run as possible to the batsman and at the same time takes the maximum number of wickets down.
	A Univariate Data Analysis Approach for Rainfall Forecasting GoogleScholar The main objective of this work is to create an efficient, easy-to-implement rainfall forecast system that can promptly warn and alert the people of any unexpected downpours.
	A Comparative Study of Various Classification Techniques to Determine Water Quality GoogleScholar The work focuses on determining the water quality using different classification techniques such as Decision Tree (DT), K-nearest neighbour (KNN) and Support Vector Machine (SVM) on the ground water samples of Madhya Pradesh, India.
	Prediction of Rainfall Using Data Mining Techniques GoogleScholar In this work, we use regression techniques and statistical modelling to predict the rainfall intensity of Coonoor in Nilgiris district, Tamil Nadu. It is a comparative study of various regression techniques based on the Relative error.
	Wall climbing robot using soft robotics GoogleScholar The aim of this paper is to develop a lightweight wall climbing robot which is based on the soft-robotics concept. The robot is a prototype for inspection applications aboard the pipe inspections both inside and outside the pipe.

Take a look at Jon Barron's source code for the template of this website.