Anthony Dearden

Papers

Total Citations

215

H-Index

About

Anthony Dearden’s research lies at the intersection of developmental robotics, motor learning, and cognitive architectures, with a focus on how robots can autonomously acquire complex skills. His most influential contribution is the concept of learning forward models—internal predictive models that allow a robot to anticipate the consequences of its own actions. This work, detailed in his highly cited 2005 paper (114 citations), provides a foundational mechanism for intelligent, goal-directed behavior in autonomous systems. Dearden further advanced the field by bridging self-exploration and social learning. His 2005 paper on hierarchical learning by imitation (97 citations) explores a developmental pathway where robots first learn through “motor babbling” and then use that self-knowledge to imitate others, effectively combining asocial and social learning strategies. This framework enables robots to be more adaptive and autonomous in human environments. While his 2008 paper on developmental learning of internal models has fewer citations, it synthesizes these ideas into a cohesive architecture. Dearden’s work is notable for integrating insights from developmental psychology into robotics, offering a principled approach to building robots that learn progressively, much like human infants.