Max Robotics — Global Service Robot Directory + US Certification

About

Sanket Gaurav is a roboticist whose research bridges intuitive human-robot interaction and intelligent control systems. His primary contributions lie in goal-predictive teleoperation, where he pioneered methods to infer human intent from noisy, low-cost sensors like the Microsoft Kinect. His most cited work (2017, 20 citations) introduced a framework that predicts operator goals despite sensor imprecision, dramatically improving teleoperation reliability. Expanding on this, Gaurav developed deep correspondence learning for VR-based teleoperation (2019, 13 citations), enabling operators to control robots through immersive 3D workspaces rather than traditional 2D views—a leap in intuitive control. He further advanced human-robot collaboration by discriminatively learning inverse optimal control models (2019, 9 citations) to predict human intentions from partial action sequences, enhancing safety and efficiency in shared tasks. Most recently, Gaurav tackled a challenging domestic application: teaching robots to mop like humans from video demonstrations (2023, 3 citations), addressing the difficulty of hand-coding adaptive cleaning behaviors. Across these works, his cumulative impact exceeds 47 citations, demonstrating a clear trajectory from sensor-noise mitigation to practical, human-inspired robot learning. Gaurav’s research consistently focuses on making robotic systems more accessible, intuitive, and capable of learning from natural human demonstrations.