Embodied AI Agents: Modeling the World
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915373133070336 |
|---|---|
| author | Fung, Pascale Bachrach, Yoram Celikyilmaz, Asli Chaudhuri, Kamalika Chen, Delong Chung, Willy Dupoux, Emmanuel Gong, Hongyu Jégou, Hervé Lazaric, Alessandro Majumdar, Arjun Madotto, Andrea Meier, Franziska Metze, Florian Morency, Louis-Philippe Moutakanni, Théo Pino, Juan Terver, Basile Tighe, Joseph Tomasello, Paden Malik, Jitendra |
| author_facet | Fung, Pascale Bachrach, Yoram Celikyilmaz, Asli Chaudhuri, Kamalika Chen, Delong Chung, Willy Dupoux, Emmanuel Gong, Hongyu Jégou, Hervé Lazaric, Alessandro Majumdar, Arjun Madotto, Andrea Meier, Franziska Metze, Florian Morency, Louis-Philippe Moutakanni, Théo Pino, Juan Terver, Basile Tighe, Joseph Tomasello, Paden Malik, Jitendra |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_22355 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Embodied AI Agents: Modeling the World Fung, Pascale Bachrach, Yoram Celikyilmaz, Asli Chaudhuri, Kamalika Chen, Delong Chung, Willy Dupoux, Emmanuel Gong, Hongyu Jégou, Hervé Lazaric, Alessandro Majumdar, Arjun Madotto, Andrea Meier, Franziska Metze, Florian Morency, Louis-Philippe Moutakanni, Théo Pino, Juan Terver, Basile Tighe, Joseph Tomasello, Paden Malik, Jitendra Artificial Intelligence 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. |
| title | Embodied AI Agents: Modeling the World |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2506.22355 |