Date: Feb 6

Time: 2-2:50pm
Room: WEB L102

Title: Interactive Policy Summarization: Explaining Robot Behavior to Human Users

Abstract: We are steadily moving towards a future where humans work with robotic assistants, robotic teammates, and even robotic tutors. Yet, human users often have little knowledge of how robots work or will respond in a new situation. To ensure safe and effective use of robots, training human users regarding the robots that they work with is imperative. In pursuit of this imperative, this talk will introduce AI Teacher: an explainable AI algorithm that summarizes robot policies via demonstrations, aiming to improve human understanding of robot behaviors. By leveraging human’s natural ability to model others (Theory of Mind), the AI Teacher algorithm reduces the number of interactions it takes for humans to arrive at predictive models of robot behavior. To effectively explain robot policies, the manner in which informative summaries are communicated is just as crucial as generating them. Hence, next, the talk will delve into recent experiments examining the impact of explanation modalities on humans’ comprehension of robot behavior. The talk will conclude with implications of this research for the development of systems aimed at training humans to collaborate effectively with robots.

Bio: Vaibhav Unhelkar is an Assistant Professor of Computer Science at Rice University, where he leads the Human-Centered AI and Robotics group. Unhelkar has developed algorithms to enable fluent human-robot collaboration and, with industry collaborators, deployed robots among humans. Ongoing research in his group includes development of algorithms and systems to model human behavior, train human-robot teams, and improve transparency of AI systems. Unhelkar received his doctorate in Autonomous Systems at MIT (2020) and completed his undergraduate education at IIT Bombay (2012). He serves as an Associate Editor for IEEE Robotics and Automation Letters and is the recipient of JPMC AI Early Career Researcher Award and AAMAS 2022 Best Program Committee Member Award. Before joining Rice, Unhelkar worked as a robotics researcher at X, the Moonshot Factory (formerly, Google X).

Related Papers:

· Qian, Peizhu, and Vaibhav Unhelkar. “Evaluating the role of interactivity on improving transparency in autonomous agents.” In Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems, pp. 1083-1091. 2022.

· Rong, Yao, Tobias Leemann, Thai-Trang Nguyen, Lisa Fiedler, Peizhu Qian, Vaibhav Unhelkar, Tina Seidel, Gjergji Kasneci, and Enkelejda Kasneci. “Towards human-centered explainable AI: A survey of user studies for model explanations.” IEEE Transactions on Pattern Analysis and Machine Intelligence (2023).

· Qian, Peizhu, and Vaibhav Unhelkar. “Evaluating the role of interactivity on improving transparency in autonomous agents.” In Companion of the 19th ACM/IEEE International Conference on Human-Robot Interaction. 2024.