Max Robotics — Global Service Robot Directory + US Certification

About

Mohammad Javad Khojasteh is a researcher working at the intersection of robotics, control theory, and machine learning, with a particular focus on safety-critical systems and multi-agent environments. His most influential contributions center on the development and extension of Control Barrier Functions (CBFs), a mathematically rigorous framework for guaranteeing safety in autonomous systems. His 2020 work on Robust Control Barrier Functions with Learned Uncertainties — garnering nearly 90 citations — addressed a critical limitation in existing multi-agent safety frameworks by incorporating learned uncertainty models, enabling robots to operate reliably in real-world environments populated by heterogeneous, unpredictable agents. This contribution represents a meaningful bridge between formal control-theoretic safety guarantees and data-driven machine learning techniques. Khojasteh has also explored safe exploratory planning using Gaussian Processes and Neural Control Contraction Metrics, tackling the challenge of robots learning unknown disturbance functions while avoiding unsafe regions. More broadly, his 2022 work on networked estimation and control examines how information flows through communication networks in systems ranging from smart grids to autonomous vehicles. Collectively, his research advances the frontier of building autonomous systems that are simultaneously adaptive, safe, and certifiably reliable in complex, uncertain environments.