暂停注册
 找回密码
 暂停注册

潮韵传媒

搜索

查看: 33679 | 回复: 3

CHP
发表于: 2018-5-13 23:24:33 | 显示全部楼层

马上注册,结交更多好友,享用更多功能,让你轻松玩转社区。

您需要 登录 才可以下载或查看,没有帐号?暂停注册

x
转:Facebook helped create an AI scavenger hunt that could lead to the first useful home robots

Artificial-intelligence programs could develop some much-needed common sense by competing in scavenger hunts inside virtual homes filled with simulated coffee tables, couches, lamps, and other everyday things.  
在放置着仿真咖啡桌、沙发、台灯和其他日常物品的虚拟住宅里,人工智能程序通过完成寻物游戏学会它们特别需要的常识。
Researchers at Facebook and Georgia Tech developed the scavenger-hunt challenge. The contest requires a virtual agent to look for something in a simulated home after parsing a natural-language question. An agent would be placed in room of a virtual home at random and asked something like “What color is the car?” or “Where is the coffee table?” Finding the answer requires an agent to understand the question and then explore the virtual space in search of the relevant object.  
Facebook和佐治亚理工学院的研究人员开发了这个寻物挑战赛。比赛要求一个虚拟主体解析完一个自然语言问题后,在一个模拟住宅里寻找某件物品。一个主体可能会被随机安排到一个虚拟住宅中的某个房间,被要求回答诸如“这辆车是什么颜色?”或“咖啡桌在哪里?”的问题。要找到答案,主体必须理解这个问题,然后在这个虚拟空间里寻找相关物品。 “The goal is to build intelligent systems that can see, talk, plan, and reason,” says Devi Parikh, a computer scientist at Georgia Tech and Facebook AI Research (FAIR), who developed the contest with her colleague and husband, Dhruv Batra.
佐治亚理工学院及Facebook人工智能研究项目(FAIR)的计算机科学家戴维·帕里克(Devi Parikh)和她的同事兼丈夫德鲁弗·巴特拉(Dhruv Batra)开发了这个挑战赛。她说:“我们的目标是建造能看会说、能做规划和推理的人工智能系统。” Parikh, Batra, and their collaborators developed an agent that combines several different forms of machine learning to answer questions about a home. The agent also learns a rudimentary form of common sense by figuring out, through lots of trial and error, the best places to look for a particular object. For instance, over time, the agent learns that cars are usually found in the garage, and it understands that garages can usually be found by going out the front or back door.
帕里克、巴特拉和他们的合作方创造了一个虚拟主体,它会结合几种不同形式的机器学习来回答关于一个住宅的问题,这个主体还学会了基本的常识,它通过大量试错学会判断哪里最有可能找到某个特定物品。例如,随着时间的推移,这个主体学会了通常汽车能在车库里找到,而且它知道从前门或后门出去就能找到车库。
The approach relies on reinforcement learning, a form of machine learning inspired by animal behavior, as well as imitation learning, a technique that lets algorithms learn by observation. The virtual homes were created by researchers at FAIR and UC Berkeley.  
这种方法是基于增强学习(一种从动物行为得到启发的机器学习)和模仿学习(一种让算法通过观察学习的技术)实现的。FAIR和加州大学伯克利分校的研究人员练手设计了这些虚拟住宅。
An agent navigating a virtual home.
一个正在探索虚拟住宅的主体。
A growing number of researchers are experimenting with virtual environments for training AI programs. The approach is seen as a way to broaden the intelligence of AI and overcome fundamental limitations. While there has been remarkable progress in AI lately, it has tended to involve computers doing a single task, like recognizing faces in images or playing a board game. What’s more, AI programs are generally trained on still images rather than in 3-D settings.  
越来越多的研究人员通过在虚拟环境进行实验来训练人工智能程序。这一手段被视为拓展人工智能的智能水平及克服根本性局限的方式之一。虽然人工智能近期取得了显著进展,但它通常被用于执行单种任务,比如识别图片中的人脸或下棋。此外,人工智能通常是基于静态图片进行训练,而不是在三维的环境中。 As early AI research showed, it simply isn’t practical to hand-code such knowledge into a system. So the solution will most likely be for AI programs to learn such knowledge for themselves.
早期的人工智能研究表明,将这种知识手动编入一个系统是不实际的。因此,最有可能的解决方案就是让人工智能程序自学。
Microsoft has released an environment called Malmo, which is based on the game Minecraft. Researchers at the Allen Institute for AI (Ai2) in Seattle developed another 3-D virtual environment for training AI agents. This environment also reflects basic physics, and it allows agents to take simple actions. The Ai2 researchers have proposed a similar set of natural-language challenges for agents in their environment.  微软已经发布了Malmo,一个基于Minecraft游戏的平台。西雅图的艾伦人工智能研究所(Ai2)开发了另一个用于训练人工智能主体的三维虚拟环境。这个环境还能反映基本的物理原理,主体可以执行简单的行动。Ai2的研究人员计划为其环境中的主体设计一组类似的自然语言挑战赛。
Roozbeh Mottaghi, the lead researcher behind the Ai2 project, says it is crucial for these virtual environments to become more realistic if we want AI agents to learn properly inside them. Currently, this isn’t really practical. “Designing a single realistic-looking room might take months, and it is costly,” he says. “And defining realistic physical properties for every object is very challenging.”  
Ai2项目背后的首席研究员鲁斯贝·莫塔吉(Roozbeh Mottaghi)表示,如果我们想让人工智能主体在这些虚拟环境中好好学习,它们一定要变得更逼真。目前,这还不太实际。他说:“设计一个逼真的房间大概需要几个月的时间,而且成本很高。为每件物品设定逼真的物理特性是非常有挑战性的。”
In the near term the work could help make chatbots and personal assistants less stubbornly dumb. Progress on more open-ended tasks, such as understanding natural language, has been slower. A machine can be taught to repeat patterns in text, but coping with the ambiguity of language usually requires some common-sense knowledge of the real world. The common sense developed by exploring virtual environments could help chatbots and personal assistants converse without making so many errors.  
短期内,这种平台有助于让聊天机器人和个人助手不再那么愚笨。对于更加开放的任务(比如理解自然语言),进展一直都比较缓慢。机器能学会重复文本形式的规律,但是处理语言的多重含义通常需要一些关于现实世界的常识。通过探索虚拟环境获得的常识可能会帮助聊天机器人和个人助手在对话中少犯错误。  Facebook knows this challenge firsthand. The company launched a general-purpose virtual assistant, called M, in 2015. But it relied on humans to take over when the underlying software failed to understand a command or query. The product never really took off, and it was discontinued last year.  Facebook对这一挑战有亲身体会。该公司于2015年发布了一款通用虚拟助手,叫做M。但是,当这款软件无法理解一个指令或问题时,还是要由人类介入。该产品没有真正实现发展,去年就被终止了。 The research may also feed into more futuristic projects. Imagine asking a Roomba to go vacuum the bedroom. Even if the machine could understand your voice and see its surroundings, it has no idea what a bedroom is, or where one might be found. But future home robots might use AI software that has learned such simple facts about ordinary homes by exploring lots of virtual homes first.  
这个研究也有可能推动更有未来感的项目。想象一下,你让Roomba扫地机器人去清扫卧室,即便它能听懂你的声音,看到周围的环境,但它依然不明白卧室是什么,也不知道在哪能找到卧室。但是,未来的家庭机器人可能会用上这样的人工智能软件,通过事先探索大量虚拟住宅,学会一些关于普通住宅的简单常识。
“We are clearly headed into an age of assistive agents,” says Batra. Referring to Amazon’s Echo device and rumors that the company is working on a home robot, he adds, “These things will develop eyes, and after that they will follow you around.”
巴特拉说:“我们显然进入了一个助手机器人的时代。”他提到了亚马逊的Echo以及关于该公司正在开发一个家庭机器人的传言,他补充说道:“这些东西会拥有眼睛,之后就可以跟着你到处走了。”

跳转到指定楼层
支持潮阳论坛发展就多多发帖吧!发帖是分享,回帖是一种美德!
孙哗助
发表于: 2018-5-13 23:42:26 | 显示全部楼层

其实我就冒个泡
支持潮阳论坛发展就多多发帖吧!发帖是分享,回帖是一种美德!
支持潮阳论坛(www.cy0754.com)发展就多多发帖吧!没有帖子的论坛就如同一潭死水,没有生气!哪怕只是一句简单的回复也是对发帖者莫大的鼓舞和支持也是社区发展的动力!发帖是分享,回帖是一种美德!
回复 支持 反对

使用道具 举报

砖富八斗
发表于: 2018-5-17 09:21:54 | 显示全部楼层

占位
支持潮阳论坛发展就多多发帖吧!发帖是分享,回帖是一种美德!
回复 支持 反对

使用道具 举报

狐狸猫猫
发表于: 2018-5-19 14:03:58 | 显示全部楼层

冒泡灌水拿潮币
支持潮阳论坛发展就多多发帖吧!发帖是分享,回帖是一种美德!
回复 支持 反对

使用道具 举报

*滑块验证:
您需要登录后才可以回帖 登录 | 暂停注册

本版积分规则

主题:777 | 回复:5057

手机版

指尖上的潮阳,潮阳论坛手机客户端!

官方微信

扫描二维码,参与官方微信有奖活动,好礼拿不停!

订阅QQ邮件

第一手潮坛快讯,尊享VIP邮件推送服务,不错过每一条潮阳消息!

||

快速回复 返回顶部 返回列表