Robot learning · Manipulation · Physical AI
I’m a CS (AI/ML) undergraduate at VIT Pune, interested in how robots learn to perceive and act through imitation learning and reinforcement learning. My work spans vision-language-action models, real robot deployment, and ROS 2 systems.
Website · Résumé · LinkedIn · Email
During my e-Yantra summer internship at IIT Bombay, I worked on a bi-manual LeRobot SO-101 setup—from RGB-D integration and data collection to policy training and hardware deployment. I explored SmolVLA, pi0.5, OpenVLA, and GR00T.
| Project | What I worked on | Explore |
|---|---|---|
| VLA + RL navigation | High-level VLA perception paired with local Q-learning for navigation using low-cost sensors. | Code · Paper · Demos |
| Husky A300 in Isaac Sim | Articulated robot setup, differential-drive teleoperation, and ROS 2 integration with odometry, transforms, and RViz. | Code |
| Krishi Drone | ROS 2, PID flight control, plant detection, and waypoint-based missions for autonomous greenhouse spraying. | Demo |
Q-Learning with VLA Perception for Real-World Navigation Using Low-Cost Sensors
Atlantis Press · ICAIML-AE 2026 · Advances in Intelligent Systems Research
Also published in machine learning
Adaptive TabNet–β-VAE Fusion Ensemble Closes Uncertainty Gap in Fraud Detection
Springer Cham · ICAIN 2025 · Lecture Notes in Networks and Systems