Embodied AI Agents: Modeling the World

TL;DR

This paper explores the development of embodied AI agents that perceive, learn, and act within their environments, emphasizing the importance of world models for reasoning, planning, and human collaboration.

Contribution

It introduces the concept of comprehensive world models for embodied AI agents, integrating perception, reasoning, and mental modeling for improved interaction and autonomy.

Findings

World models enable better reasoning and planning in embodied agents.

Integration of multimodal perception improves environmental understanding.

Mental world modeling enhances human-agent collaboration.

Abstract

This paper describes our research on AI agents embodied in visual, virtual or physical forms, enabling them to interact with both users and their environments. These agents, which include virtual avatars, wearable devices, and robots, are designed to perceive, learn and act within their surroundings, which makes them more similar to how humans learn and interact with the environments as compared to disembodied agents. We propose that the development of world models is central to reasoning and planning of embodied AI agents, allowing these agents to understand and predict their environment, to understand user intentions and social contexts, thereby enhancing their ability to perform complex tasks autonomously. World modeling encompasses the integration of multimodal perception, planning through reasoning for action and control, and memory to create a comprehensive understanding of the physical world. Beyond the physical world, we also propose to learn the mental world model of users to enable better human-agent collaboration.