智慧計算學門發展趨勢暨學門交流

"In this talk we present our work on predicting long-horizon sequence of actions from short-observation contexts. In a demonstration with a robotic manipulator, we show that predicting human intention in this way leads to effective collaboration between humans and robots."

Katia Sycara is the Edward Fredkin Research Professor in the School of Computer Science at Carnegie Mellon University and a Research Professor at the Robotics Institute. She is a leading expert in artificial intelligence, multi-agent systems, and human-agent collaboration.

Her research spans AI autonomy, distributed intelligent systems, and trust in human-AI interaction, with applications in robotics, defense, and large-scale information systems. She has been a pioneer in agent-based systems and has made significant contributions to semantic web technologies and collaborative AI.

Professor Sycara has received numerous honors, including recognition as a Fellow of the Association for the Advancement of Artificial Intelligence and the Institute of Electrical and Electronics Engineers. She has also served in key advisory roles for government and international research initiatives, and her work has had a lasting impact on the development of intelligent, cooperative systems.

"Theory of Mind entails predicting the evolving beliefs of other actors often under conditions of partial observability. Predicting the actions of others based on what you believe they believe to be true rather than your own beliefs can improve accuracy and therefore coordination. We describe three studies in which team performance is improved by incorporating Theory of Mind. In the first, human agent teams perform a bomb defusal task in which agents have access to different tools which must be applied in particular sequences. An advisor models the beliefs of the human participant to identify situations to intervene in which the human is expected to make the wrong decision. In the second study LLMs coordinate to perform the task and when prompted to update models of one another's beliefs reach a solution in half the time. In the third study OverCooked players infer the roles of their teammates to predict their actions allowing few-shot adaptation."

Michael Lewis is a Professor at the School of Computing and Information at the University of Pittsburgh. Trained in engineering psychology, his research focuses on human-computer interaction, human-agent teaming, and swarm robotics. He investigates how humans interact with complex autonomous systems, with particular emphasis on trust, decision-making, and coordination in multi-agent environments.

His work integrates artificial intelligence, visualization, and human factors to improve the effectiveness of human-AI collaboration. Professor Lewis has led and contributed to numerous research projects supported by agencies such as DARPA, NSF, and other U.S. government organizations. He has published extensively in leading journals and conferences in human-machine systems, robotics, and AI.