arXiv cs.AI· Fei Xia, Amir Zamir, Zhi-Yang He, Alexander Sax, Jitendra Malik, Silvio Savarese·· 12 小时前AI 评分22
Gibson 虚拟环境：面向具身智能体的真实世界感知
Gibson Env: Real-World Perception for Embodied Agents
AI 导读
研究者提出 Gibson 虚拟环境，用于为具身智能体开发真实世界感知能力，其虚拟化真实空间而非人工设计场景，涵盖 572 栋完整建筑中超过 1400 个楼层空间。该环境具备真实世界语义复杂性，并内置名为 Goggles 的合成机制，使训练好的模型无需额外域适应即可部署到真实世界。智能体在其中具有具身形态，并受物理与空间约束。
正文 · 原文
Abstract:Developing visual perception models for active agents and sensorimotor control are cumbersome to be done in the physical world, as existing algorithms are too slow to efficiently learn in real-time and robots are fragile and costly. This has given rise to learning-in-simulation which consequently casts a question on whether the results transfer to real-world. In this paper, we are concerned with the problem of developing real-world perception for active agents, propose Gibson Virtual Environment for this purpose, and showcase sample perceptual tasks learned therein. Gibson is based on virtualizing real spaces, rather than using artificially designed ones, and currently includes over 1400 floor spaces from 572 full buildings. The main characteristics of Gibson are: I. being from the real-world and reflecting its semantic complexity, II. having an internal synthesis mechanism, "Goggles", enabling deploying the trained models in real-world without needing further domain adaptation, III. embodiment of agents and making them subject to constraints of physics and space.
| Comments: | Access the code, dataset, and project website at this http URL . CVPR 2018 (spotlight) |
| Subjects: | Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Graphics (cs.GR); Machine Learning (cs.LG); Robotics (cs.RO) |
| Cite as: | arXiv:1808.10654 [cs.AI] |
| (or arXiv:1808.10654v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.1808.10654 arXiv-issued DOI via DataCite |
|
| Journal reference: | CVPR 2018 |
Submission history
From: Amir Zamir [view email]
[v1]
Fri, 31 Aug 2018 09:56:43 UTC (9,382 KB)
[v2]
Tue, 20 Oct 2026 17:37:11 UTC (15,337 KB)
来源：arXiv cs.AI · arxiv.org