Max Robotics — Global Service Robot Directory + US Certification

About

Emo Todorov is a leading researcher at the intersection of computational neuroscience, robotic control, and reinforcement learning, with seminal contributions to trajectory optimization and biologically inspired motor control. His most influential work centers on Differential Dynamic Programming (DDP), particularly his 2014 paper on control-limited DDP, which has garnered over 440 citations and demonstrated that trajectory optimization methods can achieve real-time control of complex systems, including full humanoid robots. This work helped establish trajectory optimization as a cornerstone technique in modern robotics. Todorov has also pioneered the integration of trajectory optimization with function approximation, exploring how neural networks and classical control methods can be combined to overcome each other's limitations. A recurring theme throughout his research is tendon-driven control — drawing inspiration from biological motor systems to advance robotic manipulation. His work on the ACT Hand and biomechanical models of the human finger applies path integral reinforcement learning to tackle the high-dimensional, nonlinear challenges inherent in tendon-driven systems. His investigations into variable impedance control further reflect his commitment to bridging neuroscience and robotics, pushing toward robots that learn adaptive, human-like movement with appropriate compliance and precision.