Max Robotics — Global Service Robot Directory + US Certification

About

Anish Shankar is a leading roboticist pushing the boundaries of agile, real-world machine learning, with a primary focus on high-speed, human-interactive systems. His most impactful work centers on the grand challenge of robotic table tennis, where he has systematically advanced the field from foundational sim-to-real transfer to achieving a historic milestone: the first learned robot agent to reach amateur human-level competitive performance. Shankar’s major contributions include the development of highly optimized perception and control subsystems that enable a robot to engage in hundreds of rallies and precisely return balls to desired targets. He is a key proponent of the i-Sim2Real paradigm, which tightly integrates human interaction loops into simulation training to bridge the reality gap for dynamic tasks. His work on agile catching, using whole-body Model Predictive Control and blackbox policy learning, further demonstrates his expertise in mastering tasks that require split-second reactions. With over 55 citations for his core table tennis studies, including a landmark 2025 paper, Shankar’s research is not only a technical tour de force but also a compelling case study in building robotic systems that can learn and compete alongside humans.