Max Robotics — Global Service Robot Directory + US Certification

About

Jan Issac’s research lies at the intersection of robotic perception, motion generation, and manipulation under uncertainty. His major contributions include pioneering the development of Riemannian Motion Policies (RMPs)—a mathematically elegant framework for modular, real-time motion generation that integrates perception and control in geometrically consistent ways. His work on RMPflow, with over 34 combined citations, provides a principled method for synthesizing multi-task motion policies that handle complex, dynamic environments. Issac also made significant strides in closing the sim-to-real gap, proposing an adaptive simulation randomization technique that uses real-world rollouts to fine-tune policy transfer, a paper that has garnered 46 citations. His earlier work on probabilistic articulated real-time tracking (69 citations) enables precise end-effector pose estimation by fusing joint measurements with depth data, a critical capability for robust manipulation. Notably, his 2018 paper “Real-Time Perception Meets Reactive Motion Generation” (107 citations) underscores the importance of tightly coupling continuous perception with reactive control to handle noisy sensing and unpredictable dynamics. Through these contributions, Issac has advanced the field’s ability to deploy robots in unstructured, real-world settings, making his work essential reading for researchers in robot learning and control.