Max Robotics — Global Service Robot Directory + US Certification

About

Benoit Landry is a robotics and control researcher whose work sits at the intersection of optimization, machine learning, and safety-critical systems. His research tackles some of the most pressing challenges in modern robotics: ensuring that autonomous systems behave reliably and provably correctly in complex environments. Landry's most influential contribution, "Lyapunov-stable neural-network control" (2021, 95 citations), addresses a critical gap in deep reinforcement learning by introducing formal stability guarantees for neural-network controllers — a breakthrough that bridges the gap between empirical performance and theoretical rigor. His work on bilevel optimization, including a differentiable augmented Lagrangian method (2019) and its application to planning through contact (2022), has provided roboticists with powerful general-purpose tools for solving hierarchically structured problems common in manipulation and motion planning. Landry has also contributed to game-theoretic safety through his work on reach-avoid games using mixed-integer second-order cone programming (2018), with applications in multi-robot systems and human-robot interaction. Beyond theoretical contributions, his practical work includes vision-based autonomous disinfection systems developed in response to the COVID-19 pandemic. Collectively, his research demonstrates a commitment to making autonomous systems both mathematically sound and real-world deployable.