Stephen Gordon

Papers

Total Citations

H-Index

About

Stephen Gordon’s research lies at the intersection of cognitive robotics, human-robot interaction, and artificial intelligence, with a focus on enabling robots to learn, reason, and collaborate more effectively. His most influential work introduces a framework for robots to learn affordance relations—the possibilities for action offered by objects—through internal rehearsal, a process that mimics human cognitive simulation. This approach, detailed in his 2008 paper (31 citations), represents a significant step toward developing truly cognitive robots capable of generalizing from experience rather than relying on pre-programmed rules. Gordon also advanced cognitive control architectures for task execution, implementing these ideas in the humanoid robot ISAC to enable adaptive learning from partial instructions (14 citations). His contributions extend to multi-robot systems, where he investigated visualization techniques to enhance human operators’ situational awareness during team activities (12 citations). Through this work, Gordon has helped bridge the gap between low-level robotic control and high-level cognitive processes, demonstrating how robots can use internal models to plan actions and learn affordances—a foundational capability for autonomous systems that must operate in unstructured, real-world environments.