Max Robotics — Global Service Robot Directory + US Certification

About

Felix Duvallet is a robotics researcher whose work sits at the intersection of human-robot interaction, natural language processing, and autonomous navigation. Best known for his pioneering contributions to language-driven robot control, Duvallet has dedicated much of his career to enabling robots to understand and act upon natural language instructions in real-world environments — a challenge with profound implications for deploying robots alongside untrained human collaborators. His most influential work centers on imitation learning and language grounding for robot navigation. Papers such as "Imitation Learning for Natural Language Direction Following Through Unknown Environments" (52 citations) and "Learning Models for Following Natural Language Directions in Unknown Environments" (67 citations) demonstrate his sustained effort to make human-robot communication intuitive and accessible, even in previously unseen surroundings. His research on grounding spatial relations for outdoor navigation further extends these capabilities beyond controlled lab settings. Beyond language, Duvallet has made notable contributions to physical human-robot interaction, particularly through his highly cited work on fluid handover controllers (67 citations), which drew inspiration from natural human behavior. His early work on imitation learning for multi-robot task allocation and his development of the student-taught "Fun With Robots" course at Carnegie Mellon reflect both his technical breadth and his commitment to robotics education and accessibility.