Max Robotics — Global Service Robot Directory + US Certification

About

Susmit Jha is a leading researcher at the intersection of machine learning, formal methods, and robotics, whose work focuses on building trustworthy and verifiable autonomous systems. His key research areas include learning from demonstrations, certified control, and trusted machine learning for safety-critical applications. Jha’s most influential work, "Learning Task Specifications from Demonstrations" (2017, 42 citations), pioneered methods for decomposing complex real-world tasks into sub-tasks using demonstrations, offering formal guarantees that are crucial for robotics applications. He further advanced safe autonomy with "Learning Certified Control using Contraction Metric" (2020, 15 citations), which provides provable convergence and tracking error bounds for robots operating under disturbances. Jha also introduced the paradigm of "Trusted Machine Learning" (2018, 6 citations), proposing model, data, and reward repair to ensure safety and liveness in high-stakes domains like self-driving cars and surgical robotics. Additionally, he co-organized the influential Dagstuhl Seminar on "Machine Learning and Formal Methods" (2018), bridging two critical communities. With a career dedicated to marrying learning with formal guarantees, Jha’s work is essential reading for researchers building reliable AI for the physical world.