Max Robotics — Global Service Robot Directory + US Certification

About

Joseph Lorenzetti is a robotics researcher whose work lies at the intersection of control theory, optimization, and safety-critical systems. His primary contributions focus on developing computationally tractable methods for complex planning and control problems, particularly those involving contact dynamics and adversarial interactions. Lorenzetti’s most influential work, "Reach-Avoid Games Via Mixed-Integer Second-Order Cone Programming" (2018, 18 citations), provides a powerful framework for solving reach-avoid games—a key problem in multi-robot systems, human-robot interaction, and safety-critical applications. He has also advanced the field of manipulation and locomotion through his work on bilevel optimization for planning through contact (2019, 2022), offering a semidirect method that efficiently handles the challenging dynamics of physical interaction. In soft robotics, Lorenzetti developed reduced-order finite element models for optimal control (2021, 4 citations), enabling high-fidelity yet computationally feasible controllers for continuous-deformation robots. His research on scalable filtering for graph-coupled hidden Markov models (2019, 3 citations) further demonstrates his versatility, addressing large-scale spatial processes such as robot swarms and disease epidemics. Through these contributions, Lorenzetti has established himself as a rising figure in robotics and control, with his work cited across multiple domains and recognized for its practical impact on real-world autonomous systems.