Token Communication-Assisted Collaborative Embodied Artificial Intelligence: Concepts, Framework, and Opportunities

2026-10-01

AI Summary

This study addresses the challenge of efficient multimodal communication among collaborative embodied agents in dynamic environments by proposing a unified token-based communication framework. In this framework, tokens serve as both communication carriers and reasoning units. By integrating generative foundation models, compact codebooks, and syntactic rules, it achieves semantic-level compressed transmission with high-fidelity reconstruction, alongside a task-adaptive communication protocol. Experimental evaluations on cooperative transport tasks demonstrate that the proposed method significantly reduces communication bit overhead while preserving task execution efficiency. Furthermore, it exhibits strong robustness against noise.

Abstract

Collaborative embodied artificial intelligence (CEAI) enables multiple physical agents to perceive, reason, and act cooperatively in dynamic environments. Effective communication is essential for CEAI, yet CEAI agents must exchange not only large multimodal observations but also task-relevant insights, intents, and interactive information over long horizons. This article investigates token communication (TokCom) as a native intelligence interface for CEAI, in which tokens serve jointly as compact semantic carriers for communication and fundamental inference units for generative foundation models (GFMs). We first discuss how TokCom supports insight sharing, intent alignment, and interactive control among embodied agents. We then propose a TokCom-assisted CEAI framework driven by a task-adaptive communication protocol. Comprising a compact codebook, syntax rules, and contextual examples, this protocol guides GFM-based transceivers to distill messages into compact tokens and reconstruct them after wireless transmission. A case study on collaborative object transport demonstrates that the proposed TokCom framework substantially reduces the source payload bit consumption while preserving task efficiency and showing robustness under noisy channels. Finally, we outline future research directions.

Problem

• Collaborative Embodied AI
• Token Communication
• Multi-agent Communication
• Generative Foundation Models
• Semantic Communication

Innovation

• Token Communication
• Collaborative Embodied AI
• Generative Foundation Models
• Task-Adaptive Protocol
• Semantic Communication