I am a final-year Robotics & Mechatronics undergraduate working toward robot learning for locomotion across morphologies. My current research learns recovery policies for a wheeled Mars rover trapped in deformable granular terrain: mobility when contact is uncertain and no hand-designed escape recipe exists.
I want to carry that problem from wheels to quadrupeds to bipeds, where richer contact and stricter balance make model-based controllers fail more sharply. I am drawn to reinforcement learning, learning-based control, and Sim2Real, and to putting simulation-trained policies on hardware. I am currently seeking a PhD, MS, or Research Assistant position in robot learning.
Wheel entrapment in loose regolith has crippled real planetary missions (e.g., NASA's Spirit rover). We learn a maneuver-agnostic recovery policy in deformable granular dynamics, restoring mobility without a prescribed escape recipe.
A bare-metal flight controller on an STM32F103, closing six control loops at 250 Hz with no RTOS and no flight stack. Five sensors fused into an attitude and position estimate, feeding a rate-PID cascade. Built in 2023 and flown and upgraded across my undergraduate years.
A full kinematics and dynamics stack written from first principles in NumPy, validated against official URDFs for both a UR5e and a 7-DOF KUKA iiwa. Cross-checking exposed a DH sign error worth 1.998 m; corrected, model and URDF agree to 1.5e-7.
A software-in-the-loop maritime-patrol drone over Chattogram port: PX4 SITL and Gazebo render the flight while a ROS 2 planner routes exclusion-aware waypoints that never enter a no-fly zone, driven from a browser ground station with a live chase-camera feed.
An APPO agent trained with Sample-Factory to survive in a first-person 3D environment, learning to navigate and collect health packs from raw pixel input.
A 31.8 × 54 m digital-twin warehouse benchmarking PPO, SAC, and TD3 for autonomous navigation on a Clearpath Jackal under realistic LiDAR and localization noise.
A vectorised Python flocking simulation with five steering rules, measured order parameters, and obstacle avoidance. Boids coloured by heading show alignment as colour convergence — a rainbow collapses to a single hue.