Max Robotics — Global Service Robot Directory + US Certification

About

Nawid Jamali is a leading researcher in robotic fabric manipulation, tactile perception, and visuospatial reasoning. His work bridges the gap between high-level task planning and low-level physical interaction, with a focus on enabling robots to handle deformable objects—a notoriously difficult challenge in robotics. Jamali’s most influential contributions include deep imitation learning for sequential fabric smoothing (109 citations), where he trained policies to flatten and fold fabrics using RGB-D data, with applications spanning surgery, manufacturing, and home robotics. He also pioneered deep transfer learning for robot bed-making (81 citations), demonstrating how pick points can be learned from depth images to generalize across fabric colors and textures. His VisuoSpatial Foresight framework (71 citations) extended visual prediction to multi-step, multi-task fabric manipulation, while his work on learning dense visual correspondences in simulation (55 citations) enabled sim-to-real transfer for folding and smoothing. Beyond fabrics, Jamali advanced tactile perception through active exploration strategies (58 citations) and visuotactile 6D pose estimation (51 citations), integrating vision and touch for in-hand object manipulation. His designs for tactile fingertips on the iCub hand (42 citations) and event-driven tactile sensor encoding (42 citations) have improved real-time sensing and data efficiency. With over 500 citations across his top papers, Jamali’s research is shaping the future of autonomous robots that can handle the soft, unpredictable materials central to everyday life.