Max Robotics — Global Service Robot Directory + US Certification

About

Farbod Farshidian is a leading robotics researcher whose work sits at the intersection of optimal control, model predictive control (MPC), and legged robotics. His research has fundamentally advanced how robots perceive, plan, and move through complex, unstructured environments — with a particular emphasis on quadrupedal locomotion and mobile manipulation. Farshidian's most influential contributions center on real-time nonlinear MPC frameworks that unify trajectory optimization and feedback control. His 2016 paper on fast nonlinear MPC (205 citations) established a foundational approach still widely referenced today, while his 2023 work on perceptive locomotion through nonlinear MPC (237 citations) demonstrated how robots can navigate rough terrain using rich sensory feedback. His trajectory optimization methods have enabled robots to automatically discover gaits, plan whole-body motions through contacts, and execute collision-free loco-manipulation tasks with remarkable versatility. A recurring theme across his portfolio is bridging the gap between model-based precision and real-world robustness — including hybrid approaches that combine learning-based locomotion policies with model-based manipulation. With multiple papers exceeding 100 citations and a cumulative citation count well above 1,100, Farshidian's work has had measurable impact on both academic research and the practical deployment of agile robotic systems.