About Me
I'm a Robotics Engineer with a Master's degree from Worcester Polytechnic Institute, specializing in Computer Vision, Deep Learning, and Machine Learning. Currently based in Redmond, WA, I focus on developing innovative vision systems and automation solutions for industrial applications. My expertise spans machine vision integration, object detection, anomaly detection, and robotic systems development.
Work Experience
Application Automation Engineer
March 2025 - Present
- Implemented an edge-based state machine control system for Pack bench operations, coordinating I/O devices and visual indicators to streamline packaging processes and improve operator efficiency.
- Developed a dual-camera OCR system with synchronized capture and depth sensor to verify Go-Cart routing by detecting labels, extracting barcodes and site codes, checking fill level and presence/absence, and matching side-view against top-view results with 2-3 second cycle time.
- Developed a pipeline for detecting non-conveyable boxes in the Bulk-Sort flow using YOLO and a RealSense camera.
- Deployed vision systems such as scan tunnels and sorting solutions for vendors like Amazon warehouses and FedEx.
- Designed and implemented a pipeline for projector-camera calibration.
Vision Engineer
July 2024 - Feb 2025
- Developed synthetic good images using DCGAN's and evaluated the performance of EfficientAD models for anomaly detection by comparing results on original and synthetic dataset.
- Developed a pipeline to generate synthetic images replicating industrial anomalies, such as scratches.
- Led the setup and integration of vision systems for a battery module production lines.
- Developed vision software to automate battery module production, achieving a target of 1000 module per shift.
- Created a web interface for real-time communication between cameras and HMI systems.
- Commissioned and evaluated machine vision systems with 2D and 3D Matrox cameras.
Vision Engineer
June 2023 - May 2024
- Refined and translated a C++ pipeline to Python for robotic laser detection, leveraging OpenCV for enhanced image processing capabilities.
- Developed and curated a customized dataset of 500 images for training and validating an object detection model.
- Integrated production-level Object detection models like YOLOv8 to achieve precise center-finding, significantly enhancing the accuracy of robotic placements in subsequent operations.
- Executed various vision tasks such as gauging, barcode reading, OCR, defect detection, part verification, pattern matching, sorting, Flexibowl picking, and 3D inspections.
- Conducted feasibility studies and prototyped, commissioned, and evaluated machine vision systems for 8 companies.
Calvary Robotics, USA
Robotics Engineering Coop
Sept 2022 - Jan 2023
- Created web interface using React framework integrated with ROS to monitor the robots.
- Developed computer vision pipeline for object detection and pose estimation of the robot.
Research Assistant
May 2022 - Aug 2022
- Research work focuses on an Ensemble Learning Methodology combining multiple existing robotics grasp synthesis algorithms to obtain comparatively better grasp quality.
- Train individual experts like Generative grasping, Residual-Net on Cornell dataset. Compare grasping performance of Ensemble architecture of these experts by evaluating diversity metrics.
Graduate Learning Assistant
Sept 2021 - Aug 2022
- Conduct office hours and lab sessions. Grade assignments for 5 courses (Applied Statistics, Calculus IV, Geometric Concepts, Probability and Discrete Mathematics).
Key Projects
Multi-Task Self-Supervised Learning for Image Segmentation
PyTorch | OpenCV | Numpy
- Developed unified encoder-decoder architecture to perform Depth estimation and Surface Normalization with Semantic Segmentation to boost performance on NYU2D dataset.
- Performed experiments using different weighting techniques (Grid search, Uncertainty weighting). Grid Search offering good trade-off as MIOU increased from 0.751 to 0.806, achieving 7.3% increase.
View on GitHub
Lidar-Camera Sensor Fusion
Open3D | YOLOv4 | OpenCV | Numpy
- Calibrated camera using checkerboard pattern by mapping 3D world coordinates to image coordinates and then estimated parameters of camera through the processes of calculating intrinsic and extrinsic parameters.
- Implemented low-level (Point-Pixel) fusion and mid-level (Box to Box) fusion of LiDAR 3D points with 2D image detections using pretrained YOLOv4 network.
View on GitHub
Crime Pattern Detection Analysis
TensorFlow | Numpy
- Built a Time-series regression model with regularization techniques to predict crime rate for succeeding years.
- Implemented multiple classification (SVM, KNN, Decision Tree, SoftMax) and regression models for homicide prediction, used Ensemble learning method on classification methods and obtained an accuracy of 88.92%.
View on GitHub
Leaf Diseases Classification based on CNN
TensorFlow | OpenCV | Numpy | Keras | Arduino UNO
- Created a Sequential model to distinguished plants as healthy or diseased. Resulted in 83% accuracy.
- Developed an IoT (Internet of Things) based smart agriculture system for monitoring soil environment.
View on GitHub
Path Planning on WPI Campus Map
C++ | Python
- Found feasible paths and compared distance metrics using discrete and sampling-based algorithms such as BFS, DFS, A*, Dijkstra's, PRM, RRT and RRT*.
View on GitHub
Solidworks | MATLAB | Simulink
Sept 2021 - Dec 2021 | GitHub
- Designed and fabricated 2 connected 1 Degree of Freedom robot using various spring mechanisms.
- Optimized the design parameters for the system on MATLAB Simulink and provided the required torque using an Admittance Sliding controller to the exo-skeleton system.
Medical Simulation Station for Neuro-Intervention, Med-Man Lab WPI
Solidworks | Arduino UNO
Sept 2021 - Feb 2022
- Designed using Solidworks and built a 3-DOF system with 2 cameras to track a tube inserted into a human body.
- Controlled the motors using Arduino to position the camera along with the movement of the tube.
Solidworks
Oct 2016 - Jan 2020 | Newsletter
- Worked in the chassis subsystem on Hybrid-electric and combustion prototype. Promoted to chassis module head and led team of 5 people.
- Designed using Solidworks and fabricated fixture assembly for series-hybrid electric prototype.
- Developed a compact battery box design using Solidworks for stacking Lithium-ion batteries.
Education
Worcester Polytechnic Institute (WPI) - USA
MS Robotics
GPA: 4.0/4.0
May 2023
R.V. College of Engineering (RVCE) - India
BE in Mechanical Engineering
GPA: 8.0/10.0
Sept 2020
Skills & Expertise
Programming & OS
Python, C++, MATLAB, ROS (Noetic), ROS2, Ubuntu
Development Tools
PyTorch, TensorFlow, Keras, Scikit-learn, OpenCV, Open3D, Labelme, CUDA, Ultralytics, OpenGL, Gazebo, Git, Rviz, Solidworks, AutoCAD, Simulink
Machine Vision Tools
Cognex Insight, Cognex VisionPro Deep Learning, Keyence, ifm, Fanuc iRVision, Matrox
Relevant Coursework
Machine Learning, Deep Learning, Computer Vision, Sensor Fusion, Motion Planning, Robot Dynamics & Controls, Design of Machine Elements, Kinematic and Dynamics of Machines