Max Robotics — Global Service Robot Directory + US Certification

About

Shromona Ghosh is a researcher working at the intersection of formal methods, machine learning, and autonomous systems safety. Their work addresses one of the most pressing challenges in modern robotics and AI: ensuring that complex, learning-enabled systems behave reliably and safely in the real world. Ghosh's most influential contributions span two complementary directions. Their 2019 work bridging Hamilton-Jacobi safety analysis with reinforcement learning (85 citations) tackles the fundamental tension between rigorous control-theoretic safety guarantees and the flexibility of modern learning-based approaches, offering a principled framework for safe autonomous operation. Equally impactful is their development of Scenic, a probabilistic programming language designed for scenario specification and data generation in cyber-physical systems (83 citations across multiple versions), which has become a notable tool for training and testing ML-based systems against rare and challenging conditions. Ghosh also contributed to SOTER, a runtime assurance framework that helps developers build safety guarantees into robotic systems even when relying on third-party or learned components. Together, these projects reflect a cohesive research vision: making autonomous and robotic systems not only capable, but verifiably safe—an increasingly critical goal as such systems enter real-world deployment.