research Imitation Learning Learning contact-rich manipulation from human demonstrations — hybrid trajectory-and-force imitation, variable compliance from a few demos, and diffusion policies. Active Compliance Control Making rigid, position-controlled industrial arms behave compliantly — learned force control, variable compliance via deep RL, and deployment at the World Robot Summit. Passive Compliance (Soft Robots) Compliance built into the hardware — soft wrists, tactile sensing, and soft hands that absorb contact uncertainty before the controller ever sees it. Vision-Language and Task and Motion Planning Turning natural-language instructions and scene observations into executable robot plans — the ViLaIn interpreters and one-shot vision-language guided motion generation. Cooking Robotics Cooking as a benchmark for contact-rich, long-horizon manipulation — safe knife skills learned in simulation, and task and motion planning that gets a whole dish from instruction to plate. Universal Robots ROS1 Control Collection of utilities for easily controlling Universal Robots either on the Gazebo simulator or the real robots. internship WRS2020 Robotic Assembly Challenge. Robotic Industrial Assembly Challenge at WRS2020 World Robot Summit. As part of the O2AC team, we achieve the 3rd place. GSoC & Moveit: Simultaneous Trajectory Execution 2022 Google Summer of Code participant. Open Source Project with MoveIt on the feature Simultaneous Trajectory Execution fun OpenBotV MVP - Robotics 4.0 Educational robot: First prototype of robot arm, and corresponding Android app.
