ExplainabilityTrustworthinessSafetycs.AI
Joint Mind Modeling for Explanation Generation in Complex Human-Robot Collaborative Tasks
Xiaofeng Gao, Ran Gong, Yizhou Zhao, Shu Wang, Tianmin Shu, Song-Chun Zhu
July 24, 2020
IEEE International Symposium on Robot and Human Interactive Communication
47 citations
2 influential
Key Takeaways
-
Robots can improve collaboration by understanding human mental states: The research demonstrates that when robots build models of what humans are thinking—their goals, beliefs, and desires—they can communicate more effectively, similar to how human teammates naturally work together by inferring each other's intentions.
-
Explanations of robot reasoning enhance both task performance and trust: In a real-time cooking task study, the robot's explanations of its own decision-making significantly improved both how well the human-robot team completed the task and how users perceived the robot, suggesting that transparency about AI reasoning matters in practice.
-
"Mind-aware" communication reduces misunderstandings in collaborative work: By continuously updating its understanding of what the human user knows and intends (through Bayesian inference), the robot can tailor its explanations to address gaps in shared understanding, minimizing the kind of miscommunications that derail teamwork.
-
This approach bridges a gap in human-robot interaction design: Rather than robots simply following pre-programmed instructions, this framework enables robots to communicate pedagogically—like a good human teammate would—by recognizing what information the human partner actually needs at each moment.
Abstract
Human collaborators can effectively communicate with their partners to finish a common task by inferring each other's mental states (e.g., goals, beliefs, and desires). Such mind-aware communication minimizes the discrepancy among collaborators' mental states, and is crucial to the success in human ad-hoc teaming. We believe that robots collaborating with human users should demonstrate similar pedagogic behavior. Thus, in this paper, we propose a novel explainable AI (XAI) framework for achieving human-like communication in human-robot collaborations, where the robot builds a hierarchical mind model of the human user and generates explanations of its own mind as a form of communications based on its online Bayesian inference of the user's mental state. To evaluate our framework, we conduct a user study on a real-time human-robot cooking task. Experimental results show that the generated explanations of our approach significantly improves the collaboration performance and user perception of the robot. Code and video demos are available on our project website: https://xfgao.github.io/xCookingWeb/.