Designing Intent Communication for Agent-Human Collaboration

2025-10-23

AI Summary

Existing intent communication methods are rigid, task-specific, and poorly generalizable—primarily because “what to convey” is not systematically integrated with “when and how to convey it.” This work introduces the first three-dimensional design space for intent communication, orthogonally modeling *content*, *timing*, and *modality* along the dimensions of transparency, abstraction level, and modality. This unified framework enables adaptive, multimodal communication strategy generation across diverse tasks, environments, and user preferences. We instantiate and empirically validate our approach in three canonical human-robot collaboration scenarios: bystander interaction, collaborative task execution, and shared control. By bridging the theoretical gap between intent modeling and communication implementation, our method yields scalable, reusable, and human-intuitive strategies that significantly improve both safety and efficiency in human-robot collaboration.

Technology Category

• Intelligent Robots: Human-Robot Interaction
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Multiagent Systems: Agent Communication

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

As autonomous agents, from self-driving cars to virtual assistants, become increasingly present in everyday life, safe and effective collaboration depends on human understanding of agents' intentions. Current intent communication approaches are often rigid, agent-specific, and narrowly scoped, limiting their adaptability across tasks, environments, and user preferences. A key gap remains: existing models of what to communicate are rarely linked to systematic choices of how and when to communicate, preventing the development of generalizable, multi-modal strategies. In this paper, we introduce a multidimensional design space for intent communication structured along three dimensions: Transparency (what is communicated), Abstraction (when), and Modality (how). We apply this design space to three distinct human-agent collaboration scenarios: (a) bystander interaction, (b) cooperative tasks, and (c) shared control, demonstrating its capacity to generate adaptable, scalable, and cross-domain communication strategies. By bridging the gap between intent content and communication implementation, our design space provides a foundation for designing safer, more intuitive, and more transferable agent-human interactions.

Problem

• Designing adaptable intent communication for human-agent collaboration
• Bridging the gap between intent content and communication implementation
• Creating generalizable multimodal strategies across diverse interaction scenarios

Innovation

• Multidimensional design space for intent communication
• Integrates transparency, abstraction, and modality dimensions
• Generates adaptable cross-domain human-agent strategies