About

I am currently working as a full-time Robotics Research Engineer II at the Robotics Institute at Carnegie Mellon University. I currently work on the MMPUG Project - Multi-Modal Perception Uber Good advised by Prof. Matthew Travers and my research focuses on SLAM and Perception framework for heterogenous fleet of robots used for to rapidly map, navigate, search and rescue in unstructured environments.

I graduated with a Master's in Computer Engineering from Carnegie Mellon University in May 2023. My current interests lie in Robotics - broadly in the intersection of Perception, SLAM, Deep Learning, and Path planning. I previously worked as a Research Assistant at the AirLab at Robotics Institute, Carnegie Mellon University advised by Prof. Sebastian Scherer. Prior to that, I worked as a Research Assistant under the Guidance of Prof. Bhiksha Raj in the domain of Deep Learning.

I have four years of professional work experience in a state owned Design and Manufacturing company, where I worked as a Development Engineer. I got an opportunity to work on several challenging projects from two major development teams that were a part of the company’s core technologies. I have worked extensively in System Integration and Sub-system design of Autonomous Marine Defence Systems. I have also Designed and developed various Commercial simulators that are Virtual Reality based.

Know more

Education

Carnegie Mellon University- Pittsburgh, PA
- Master of Science in Electrical and Computer Engineering- Applied
  May 2023
- CGPA: 3.95/4
- Relevant Courses : Deep Learning, Computer Vision, Deep Learning for Robotics, Visual Learning and Recognition, Machine Learning for Signal Processing, Estimation Detection and Learning
- Current Coursework : Deep Learning for 3D Vision, Path Planning, SLAM and Autonomous Driving.
Ramaiah Institute of Technology- Bangalore, India
- Bachelor of Engineering in Electronics and Communication
  June 2017
- CGPA: 9.03/10
Indian Institue of Science
- Proficiency Course in Embedded Systems Design
  Nov 2018

Experience

● Robotics Institute, Carnegie Mellon University

Robotics Research Engineer II

May 2023- Present

Currently working on a high-speed heterogeneous multi-robot system used to rapidly map, navigate, search, and rescue in unstructured environments.
Work focused on development, testing, and deployment of SLAM and Perception framework on a heterogeneous fleet of robots comprising fast-moving RC cars and quadrupedal robot.

● The AirLab at Carnegie Mellon University

Graduate Research Assistant

Dec 2022- Present

Research Focused on Navigation and guidance for Autonomous Drone exploration advised by Prof. Sebastian Scherer.
Multi-view Wide-Angle State Estimation and Reconstruction for Autonomous Flight to estimate the relative motion and create 360 depth maps to enable a drone to fly autonomously.
Implemented ORB SLAM-3 visual odometry, for State Estimation and Reconstruction utilizing the drone’s Stereo fisheye multi-camera(6) feed.
Working on Visual Odometry for navigation as part of the Autonomy stack for autonomous drones .

The AirLab at CMU

● School of Computer Science, CMU

Graduate Teaching Assistant - Fall 2022 and Spring 2023

May 2022- Present

Teaching Assistant for CMU’s flagship course Introduction to Deep Learning - 11785 under Prof. Bhiksha Raj. Contributed to curriculum design, assignment drafting, and course planning.
Covering MLP, CNN, RNN, Attention, Transformers, GAN's, Auto-Encoders, and VAE, with practical applications using PyTorch.
Prepared and presented lectures and recitations, conducted office hours, supported term projects, helped students with course materials, graded assignments, and quizzes in classes totaling over 350 students.

Graduate Research Assistant

Aug 2022- Present

Graduate Research assistant advised by Prof. Bhiksha Raj.
My research is focused in Learning Strategies for unsupervised adaptations on test dataset through the use of Deep Neural Networks.

● Voaige Inc, Pittsburgh, PA

Robotic Software Development Intern

May 2022- Aug 2022

Led a team of 2 in the conceptualization and development of DeepSpace platform, a framework for adaptive real-time programming, control, monitoring, and task sequencing of a novel vision-enabled pick and place General Purpose Robotic Arm.
Built a point cloud preprocessing pipeline with Intel Realsense, PCL, and gRPC for filtering and downsampling point cloud data for real-time streaming.
Conceptualized and integrated the system architecture for sub-system communication and data storage.
Integrated real-time Point-Cloud streaming from RealSense Camera using gRPC framework for real-time Monitoring, programming, and Task Sequencing in Unity.
Wrote production-level, low-latency python and C# code for Communicating with ROS-based controller; extended existing SDK to support gRPC for a 6 DOF UFactory X-Arm.

Team at Voaige was featured on Venture Bridge 2022.

● Visual Intel Studio, CyLab, CMU

Graduate Research Assistant

Jan 2022- May 2022

Researched, designed, and developed ‘Emergency Medical Service’ project under Prof. Yang Cai, to provide Simulated Medical Training of Laryngoscopy using Augmented Reality as a training tool to enhance the teaching of residents, frontline workers and students in emergency clinical encounters and procedures.

● Bharat Electronics Limited, Bangalore-India

Design and Development Engineer

Oct 2017- Jan 2022

System Integration and Sub-System Design of autonomous Marine Defense Systems such as Anti-torpedo/rocket countermeasure systems. Involved in interfacing a compendium of sensors to provide multi-sensor track correlation and target management of underwater targets to generate an accurate fire control solution using Deep learning.
Proposed and implemented a simulation software for predicting Azimuth and Elevation angles for Automatic target designation and engagement from ship-borne robotic Rocket and Torpedo launchers that reduced testing and integration time 10 folds.
Introduced and executed an extensible software called “External Simulator Interface” to provide Naval Tactical Simulation of sensors such as Active/Passive Sonar, Radar that predict underwater targets using Deep Learning that reduced integration and testing time
Led a three-member project team in the conceptualization, design, and development of three commercial training simulators that provide hazard perception training, testing, and evaluation of drivers.
Developed core components and scripts to provide hardware-accelerated realistic vehicle dynamics and render a fully immersive 3D visual system. Integration of HTC VIVE, 3 DOF motion Platforms and Leap Tracking devices to deliver a realistic user experience.
Created a User interface to facilitate logging of manufacturing data of 2.5 Million Electronic Voting Machines(EVM) to provide component level traceability and tracking in a secure mass manufacturing setup. Established a Digital CA facility to ensure data integrity in the EVM’s.