Max Robotics — Global Service Robot Directory + US Certification

About

H. Sebastian Seung is a pioneering researcher in robotics and artificial intelligence, with key contributions spanning reinforcement learning, bipedal locomotion, and swarm robotics. His groundbreaking work on "Stochastic policy gradient reinforcement learning on a simple 3D biped" (270 citations) demonstrated a revolutionary learning system that enables robots to acquire robust walking policies from scratch in under 20 minutes, achieving rapid convergence through real-world trials. Seung further advanced legged locomotion with his work on passive dynamic walkers (188 citations), developing minimal-degree-of-freedom robots capable of stable 3D walking, supported by reduced-order dynamic models. His innovative approach extends to swarm robotics, where "Anthills built to order" (32 citations) explores bio-inspired collective construction, drawing from social insect behavior to automate fabrication without centralized control. More recently, Seung has tackled critical safety challenges in human-robot interaction through acoustic collision detection and localization (22 citations), and advanced off-policy reinforcement learning for continuous action domains (15 citations). His work on learning in intelligent embedded systems (11 citations) demonstrates early recognition of the need for adaptive, biologically-inspired algorithms. Seung's research consistently bridges theory and practice, developing algorithms that learn rapidly from limited data while achieving robust real-world performance.