Hierarchical Intention Tracking with Switching Trees for Real-Time Adaptation to Dynamic Human Intentions during Collaboration

Abstract--During collaborative tasks, human behavior is guided by multiple levels of intentions that evolve over time, such as task sequence preferences and interaction strategies. T o adapt to these changing preferences and promptly correct any inaccurate estimations, collaborative robots must accurately track these dynamic human intentions in real time. We propose a Hierarchical Intention Tracking (HIT) algorithm for collaborative robots to track dynamic and hierarchical human intentions effectively in real time. HIT represents human intentions as intention trees with arbitrary depth, and probabilistically tracks human intentions by Bayesian filtering, upward measurement propagation, and downward posterior propagation across all levels. We develop a HIT-based robotic system that dynamically switches between Interaction-Task and V erification-Task trees for a collaborative assembly task, allowing the robot to effectively coordinate human intentions at three levels: task-level (subtask goal locations), interaction-level (mode of engagement with the robot), and verification-level (confirming or correcting intention recognition). Our user study shows that our HIT-based collaborative robot system surpasses existing collaborative robot solutions by achieving a balance between efficiency, physical workload, and user comfort while ensuring safety and task completion. Post-experiment surveys further reveal that the HIT-based system enhances the user trust and minimizes interruptions to user's task flow through its effective understanding of human intentions across multiple levels. The video demonstrating our experiments is available at https://youtu.be/Y5kg7QC41yw. I. Introduction Robots require an effective understanding of human intentions to collaborate both safely and efficiently with humans. During long-term tasks, human intentions continuously evolve along with task progress. When handling a complex task, humans typically break down the task into milestones and sub-tasks at varying levels of granularity, leading to a hierarchical structure of human intentions. During collaboration, humans often maintain multiple intentions with different semantics simultaneously. For instance, they may prefer specific subtask sequences or modes of interaction with the robot (e.g.