V-IRL: Grounding Virtual Intelligence in Real Life

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Yang, Jihan, Ding, Runyu, Brown, Ellis, Qi, Xiaojuan, Xie, Saining
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913434860257280
author Yang, Jihan
Ding, Runyu
Brown, Ellis
Qi, Xiaojuan
Xie, Saining
author_facet Yang, Jihan
Ding, Runyu
Brown, Ellis
Qi, Xiaojuan
Xie, Saining
contents There is a sensory gulf between the Earth that humans inhabit and the digital realms in which modern AI agents are created. To develop AI agents that can sense, think, and act as flexibly as humans in real-world settings, it is imperative to bridge the realism gap between the digital and physical worlds. How can we embody agents in an environment as rich and diverse as the one we inhabit, without the constraints imposed by real hardware and control? Towards this end, we introduce V-IRL: a platform that enables agents to scalably interact with the real world in a virtual yet realistic environment. Our platform serves as a playground for developing agents that can accomplish various practical tasks and as a vast testbed for measuring progress in capabilities spanning perception, decision-making, and interaction with real-world data across the entire globe.
format Preprint
id arxiv_https___arxiv_org_abs_2402_03310
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle V-IRL: Grounding Virtual Intelligence in Real Life
Yang, Jihan
Ding, Runyu
Brown, Ellis
Qi, Xiaojuan
Xie, Saining
Artificial Intelligence
Computer Vision and Pattern Recognition
There is a sensory gulf between the Earth that humans inhabit and the digital realms in which modern AI agents are created. To develop AI agents that can sense, think, and act as flexibly as humans in real-world settings, it is imperative to bridge the realism gap between the digital and physical worlds. How can we embody agents in an environment as rich and diverse as the one we inhabit, without the constraints imposed by real hardware and control? Towards this end, we introduce V-IRL: a platform that enables agents to scalably interact with the real world in a virtual yet realistic environment. Our platform serves as a playground for developing agents that can accomplish various practical tasks and as a vast testbed for measuring progress in capabilities spanning perception, decision-making, and interaction with real-world data across the entire globe.
title V-IRL: Grounding Virtual Intelligence in Real Life
topic Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2402.03310