#科技头条#【机器人预见未来?科学家提供了机器人更好完成任务的新方案】

#科技头条#【机器人预见未来?科学家提供了机器人更好完成任务的新方案】据报道,科学家通过采用视觉预见技术(visual foresight),让机器人可以操纵以前从未碰到过的物体,并在采取动作之前通过机器人的摄像头预见接下来的动作情景,尽管这种情景的呈像只能是未来的几秒钟,且画面相对简单。但这项技术将可能在自动驾驶汽车预测事故方面大放异彩。

The robots that can 'see into their future': Scientists create machines that imagine the consequences of their actions to better handle objects

  • Robots can manipulate objects they have never encountered before
  • In the future, this technology could help self-driving cars anticipate events
  • Robots predict what their cameras will see if they perform particular movements
Scientists have created a robot called Vestri (pictured) that can learn like a baby and predicts future outcomes

Scientists have created a robot called Vestri (pictured) that can learn like a baby and predicts future outcomes

HOW DOES IT LEARN?

This new technology, called 'visual foresight' means robots can work out how to manipulate objects they have never encountered before.

The robot relies on a deep learning technology called dynamic neural advection (DNA).

This DNA-based model predicts how pixels in an image will move from one frame to the next based on the robot's actions.

The robot pushes objects on a table, then uses the learned prediction model to choose motions that will move an object to a desired location.

Robots use the learned model from raw camera observations to teach themselves how to avoid obstacles and push objects around obstructions.

Crucially, the robot can learn to perform these tasks without any help from humans or prior knowledge about physics, its environment or what the objects are.

The machines are the work of computer scientists from UC Berkeley.

Using the visual technology, the robots can predict what their cameras will see if they perform a particular sequence of movements.

These robotic imaginations are still relatively simple for now and made only several seconds into the future.

However, they are enough for the robot to figure out how to move objects around on a table without disturbing obstacles.

Crucially, the robot can learn to perform these tasks without any help from humans or prior knowledge about physics, its environment or what the objects are.

That's because the visual imagination is learned entirely from scratch from unattended and unsupervised exploration, where the robot plays with objects on a table.

After this play phase, the robot builds a predictive model of the world, and can use this model to manipulate new objects that it has not seen before.

Read more: http://www.dailymail.co.uk/sciencetech/article-5148065/New-robots-future-learn-just-like-babies.html#ixzz50X1MmOoU
Follow us: @MailOnline on Twitter | DailyMail on Facebook


发表评论

登录 后发表评论.



无觅相关文章插件