Max Robotics — Global Service Robot Directory + US Certification

About

Karankumar Patel is a robotics researcher whose work sits at the intersection of perception, manipulation, and human-robot interaction. His primary contributions lie in three interconnected areas: tactile sensing, 6D pose estimation, and intention estimation for teleoperation. In his most cited work (51 citations), Patel tackles the difficult problem of in-hand 6D object pose estimation by fusing vision and tactile sensor data, overcoming the occlusion challenges that plague purely vision-based methods during robotic grasping. He also developed a principled probabilistic approach to crowd navigation, deriving interaction densities from first principles to enable real-time human-robot interaction. More recently, Patel has applied hierarchical deep learning to estimate user intentions during teleoperated assembly tasks, a critical capability for shared control in manufacturing. His work on estimating tactile sensor output from depth data further demonstrates his innovative approach to reducing the need for physical contact in tactile sensing. Patel’s research is notable for its theoretical grounding—deriving models from first principles—while maintaining practical applicability in real-time robotic systems. His contributions advance the fundamental challenge of enabling robots to perceive, understand, and collaborate with humans in complex, dynamic environments.