Alphabet X’s “Everyday Robot” project is making machines that learn as they go
The news: Alphabet X, the company’s early research and development division, has unveiled the Everyday Robot project, whose aim is to develop a “general-purpose learning robot.” The idea is to equip robots with cameras and complex machine-learning software, letting them observe the world around them and learn from it without needing to be taught every potential situation they may encounter.
For now: The early prototype robots are learning how to sort trash. It sounds mundane, but it’s tough to get robots to identify different types of objects, and then how to grasp them. Alphabet X claims that its robots are currently putting less than 5% of trash in the wrong place, versus an error rate of 20% among the office’s humans.
The big idea: Robots are expensive and confined to performing very specific, specialized tasks. Getting robots that can operate safely and autonomously in messy, complex human environments like homes or offices is one of the biggest challenges in robotics right now.
The concept of combining robotics and AI is something a lot of companies are already working on, to varying degrees of success. The goal of the Everyday Robot project—building a robot that can learn to operate in many different situations—is hugely ambitious, and even if successful, this sort of capability is many years away from being realized.
拓展人生
新闻:该公司的早期研发部门AlphabetX推出了
新闻:该公司的早期研发部门Alphabet X推出了Everyday Robot项目,该项目旨在开发“通用学习机器人”。该想法是为机器人配备相机和复杂的机器学习软件,让他们观察周围的世界并从中学习,而无需教会他们可能遇到的每种潜在情况。
现在:早期的型机器人正在学习如何分类垃圾。听起来平凡,但要让机器人识别不同类型的物体,然后抓紧它们是很难的。 Alphabet X声称,其机器人目前在错误的位置放置的垃圾少于5%,而办公室人员的错误率为20%。
Alphabet X’s “Everyday Robot” project is making machines that learn as they go
The news: Alphabet X, the company’s early research and development division, has unveiled the Everyday Robot project, whose aim is to develop a “general-purpose learning robot.” The idea is to equip robots with cameras and complex machine-learning software, letting them observe the world around them and learn from it without needing to be taught every potential situation they may encounter.
For now: The early prototype robots are learning how to sort trash. It sounds mundane, but it’s tough to get robots to identify different types of objects, and then how to grasp them. Alphabet X claims that its robots are currently putting less than 5% of trash in the wrong place, versus an error rate of 20% among the office’s humans.
The big idea: Robots are expensive and confined to performing very specific, specialized tasks. Getting robots that can operate safely and autonomously in messy, complex human environments like homes or offices is one of the biggest challenges in robotics right now.
The concept of combining robotics and AI is something a lot of companies are already working on, to varying degrees of success. The goal of the Everyday Robot project—building a robot that can learn to operate in many different situations—is hugely ambitious, and even if successful, this sort of capability is many years away from being realized.
分享:
相关帖子