Interpretation of Emergent Communication in Heterogeneous Collaborative Embodied Agents
This work addresses the challenge of understanding communication in AI agents for researchers in embodied AI and human-robot interaction, though it is incremental as it builds on existing communication mechanisms.
The paper tackles the problem of interpretability and perceptual grounding in emergent communication between heterogeneous embodied AI agents by introducing the CoMON collaborative navigation task, and demonstrates that the learned communication can be grounded to agent observations and spatial structures.
Communication between embodied AI agents has received increasing attention in recent years. Despite its use, it is still unclear whether the learned communication is interpretable and grounded in perception. To study the grounding of emergent forms of communication, we first introduce the collaborative multi-object navigation task CoMON. In this task, an oracle agent has detailed environment information in the form of a map. It communicates with a navigator agent that perceives the environment visually and is tasked to find a sequence of goals. To succeed at the task, effective communication is essential. CoMON hence serves as a basis to study different communication mechanisms between heterogeneous agents, that is, agents with different capabilities and roles. We study two common communication mechanisms and analyze their communication patterns through an egocentric and spatial lens. We show that the emergent communication can be grounded to the agent observations and the spatial structure of the 3D environment. Video summary: https://youtu.be/kLv2rxO9t0g