Kimberlee Chestnut Chang

Papers

Total Citations

H-Index

About

Dr. Kimberlee Chestnut Chang is a leading researcher at the intersection of human-robot interaction and interpretable artificial intelligence, whose work is shaping the future of safe, collaborative autonomy. Her primary research areas include human-robot teaming, reinforcement learning for continuous control, and the development of explainable AI systems for safety-critical domains. Dr. Chang’s most influential contribution, the 2023 paper “Human-Robot Teaming: Grand Challenges” (37 citations), provides a foundational framework for the field, identifying key obstacles and opportunities in designing robots that can effectively collaborate with humans in dynamic environments. She has also pioneered work in interpretable reinforcement learning, addressing the critical need for transparency in learned policies used in legally-regulated and high-stakes applications such as autonomous driving and robotic surgery. Her 2023 paper on this topic, while early in its citation trajectory, underscores her commitment to bridging the gap between powerful machine learning methods and the accountability required for real-world deployment. Dr. Chang’s research is essential reading for anyone interested in building AI systems that are not only capable but also trustworthy and aligned with human values.