research Limits of imitation learning for high-precision insertion BSc thesis · ACT and Diffusion Policy on 30k simulated demos (UR5e, Isaac Lab) AI for Industry Challenge — cable insertion Research internship · IL/RL policies and a sim-to-real stack for the Intrinsic & Open Robotics challenge Action-conditioned video world model PSIML 2026 · teaching a video diffusion model to follow robot actions on BAIR Robotic table tennis: intercepting a thrown ball with a Franka Panda In progress · MoveIt baseline in Gazebo, nonlinear MPC under development (ROS 1, CasADi, acados) coursework EKF localization with lidar features ROS 2 · TurtleBot3 · own split-and-merge line extraction Inference, planning and RL from scratch Particle filters, Bayesian networks, Q-learning and REINFORCE in NumPy