Papers
5
Total Citations
16
H-Index
3
About
Carol Young’s research lies at the intersection of human-robot interaction and autonomous manipulation, with a focus on developing learning algorithms that enable robots to predict and react to human intention with both adaptiveness and consistency. Her major contributions include pioneering work on avoiding “chatter” in online co-learning algorithms—a critical issue where a robot’s predictions oscillate without stabilizing during human interaction. She also introduced a novel architecture for autonomous physical security using moving sensors, reducing false alarms and human oversight. More recently, Young has advanced field robotics by applying physics-informed neural networks to realize generalized optimal motion primitives, allowing robots to manipulate objects under uncertainty. Her work on the dual expert algorithm, which balances adaptiveness and consistency in selecting reactions to human movements, has been foundational. While her papers have garnered modest citation counts (2–4 each), they represent early, high-impact contributions to adaptive robotics and human-robot collaboration. Young’s research is particularly notable for its rigorous theoretical grounding, as seen in her formal analysis of expert-based learning algorithms, and its practical implications for real-world robotic systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2Autonomous Detection and Assessment with Moving Sensors4 citations · 2020
- 3
- 4A learning algorithm to select consistent reactions to human movements3 citations · 2016
- 5