Multimodal Grounding for Embodied AI via Augmented Reality Headsets for Natural Language Driven Task Planning

TL;DR

This paper demonstrates how augmented reality headsets can facilitate multimodal grounding in embodied AI, enabling effective human-robot collaboration for industrial inspection tasks, and analyzes the robustness of prompts used in such systems.

Contribution

It introduces the novel use of AR headsets for multimodal grounding in embodied AI and applies this approach to industrial tasks, highlighting new applications and challenges.

Findings

Successful human-robot teaming in industrial inspections

Identification of prompt robustness issues in EAI systems

Quantitative and qualitative analysis of multimodal grounding

Abstract

Recent advances in generative modeling have spurred a resurgence in the field of Embodied Artificial Intelligence (EAI). EAI systems typically deploy large language models to physical systems capable of interacting with their environment. In our exploration of EAI for industrial domains, we successfully demonstrate the feasibility of co-located, human-robot teaming. Specifically, we construct an experiment where an Augmented Reality (AR) headset mediates information exchange between an EAI agent and human operator for a variety of inspection tasks. To our knowledge the use of an AR headset for multimodal grounding and the application of EAI to industrial tasks are novel contributions within Embodied AI research. In addition, we highlight potential pitfalls in EAI's construction by providing quantitative and qualitative analysis on prompt robustness.