MS student in Robotics Engineering at Worcester Polytechnic Institute (WPI), specializing in control theory, optimization, and learning for physical systems (robotic manipulators, quadrotors etc). Transitioned from a B.Tech in Instrumentation & Control Engineering (NIT Tiruchirappalli), with doctoral work in manipulation and whole-body control as the next step.

"Sic Parvis Magna"

• 🔭 Currently: Directed Research at the WPI Manipulation and Environmental Robotics Lab, conducting research on force manipulability analysis on tendon-driven continuum robots
• 🌱 Coursework: Robot Control, Vision-Based Robotic Manipulation
• 🎓 B.Tech, Instrumentation & Control Engineering, NIT Tiruchirappalli — CGPA 8/10, NITT Undergraduate STEM Research Fellow
• 📫 Portfolio · LinkedIn · shreehan1912@gmail.com

Manipulator kinematics & dynamics · impedance/whole-body control · trajectory planning · multi-objective design optimization (NSGA-II) · singularity analysis · learning-based control

Perception & Control Pipeline for Redundant Manipulators 6-DOF Cartesian impedance controller for the Franka Emika Panda (3.8mm peak / 0.14mm steady-state tracking error), two-camera 3D localization (1.4mm, 0.1° yaw), pick-and-place at 100% success across 50 trials. MuJoCo Python ROS 2

7-DOF Redundant Manipulator for Space Applications — B.Tech thesis, xTerra Robotics deliverable DH kinematics, NSGA-II multi-objective link-length optimization (2.825m reach, 79.9% well-conditioned workspace), RNEA torque analysis, damped-least-squares IK with adaptive Gaussian damping (100% convergence). MATLAB MuJoCo Python

Adaptive Control of Quadrotor UAVs TD3/DDPG agents tuning PID gains under an LQG-shaped reward, 60% lower tracking error vs. baseline. PyTorch Python Gymnasium

Fuzzy-Tuned LQR for Cruise Missile Autopilot Feedback linearization + Mamdani fuzzy inference for online LQR adaptation, 28.9% robustness improvement over offline tuning. MATLAB Simulink

System Identification and Control of Mobile Robot N4SID discrete-time state-space modeling with Ziegler-Nichols PID tuning. MATLAB Simulink

More on my portfolio →

• Adaptive PID Control for Quadrotor UAVs Using Feedback Linearization and Deep Reinforcement Learning — IEEE NEIICON 2026 (Accepted)
• Deep Reinforcement Learning Framework for Adaptive Control of Swing-up Inverted Pendulum — 5th ICEEA (Accepted)
• Bio-Inspired Optimization of LQR Controllers for Feedback-Linearized Cruise Missiles — 9th ICISC (Published, IEEE Xplore)

_{Thanks for stopping by — always happy to talk manipulator design, optimization, or control.}