I am an M.S.E. Robotics student at the University of Pennsylvania, dedicated to building intelligent autonomous systems. With a strong technical foundation in C++ and ROS2, I develop robust software for robot perception and navigation. Currently, my research focuses on Generative World Models, exploring how agents can leverage predictive dynamics for smarter decision-making in complex environments.
Conducted research on world models for agent-centric prediction and decision-making, including current and latent dynamics formulations. Developed and trained flow and diffusion based generative models for controllable sequence generation, and implemented preliminary energy-based model variants
Implemented sensor calibration and EKF for sensor fusion, contributed to holonomy analysis, 2.5D planning, and off-road simulation with sensor integration. Developed computer vision modules for visual SLAM and subject tracking in rough off-road conditions
Implemented autonomous yard patrols using a quadruped robot, enabling waypoint navigation, dynamic obstacle avoidance, sensor-based image capture, and web-based monitoring and control. Created full-stack AI guest check-in system, supporting visitor/employee appointments and real-time status tracking.
Developed a Python web scraper using Scrapy to extract and process over 100 million data hashes, storing results in PostgreSQL. Authorized a comprehensive SRS document outlining system functionalities, technical requirements, and project scope.
Developed a planar boxing-arm simulator that uses Model Predictive Control with iLQR to generate fast, contact-rich attack, block, and parry motions between two opposing robotic arms. The system demonstrates real-time trajectory optimization and adaptive defensive behaviors.
Developed three deep leanring using different architecures to detect deepfake auido from real audio to prevent malicious AI generated content from deceiving unsuspecting victims.
Implemented UNet3+ model for advanced electricity detection using satellite data on African settlements. The dataset used comes from the IEEE GRSS 2021 ESD dataset composing of 98 tiles representing a 64KM area.
Created a Minecraft clone from scratch using OpenGL, featuring custom rendering, texturing, and player physics. The game allows players to build, destroy, and move around, closely mimicking the mechanics of the original game.
HackDavis 2023 winner, this project enhances biker safety by integrating LED blinker lights, a rear-view vehicle detection and alert system, and an emergency contact messaging system directly into the helmet.
