Dec 072017
 

via UC Berkeley

UC Berkeley researchers have developed a robotic learning technology that enables robots to imagine the future of their actions so they can figure out how to manipulate objects they have never encountered before. In the future, this technology could help self-driving cars anticipate future events on the road and produce more intelligent robotic assistants in homes, but the initial prototype focuses on learning simple manual skills entirely from autonomous play.

[Read more: Fed up, two UC Berkeley students launch tool to spot Twitter bots]

Using this technology, called visual foresight, 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 – predictions made only several seconds into the future – but 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.

“In the same way that we can imagine how our actions will move the objects in our environment, this method can enable a robot to visualize how different behaviors will affect the world around it,” said Sergey Levine, assistant professor in Berkeley’s Department of Electrical Engineering and Computer Sciences, whose lab developed the technology. “This can enable intelligent planning of highly flexible skills in complex real-world situations.”

The research team will perform a demonstration of the visual foresight technology at the Neural Information Processing Systems conference in Long Beach, California, on December 5.

At the core of this system is a deep learning technology based on convolutional recurrent video prediction, or dynamic neural advection (DNA). DNA-based models predict how pixels in an image will move from one frame to the next based on the robot’s actions. Recent improvements to this class of models, as well as greatly improved planning capabilities, have enabled robotic control based on video prediction to perform increasingly complex tasks, such as sliding toys around obstacles and repositioning multiple objects.

“In that past, robots have learned skills with a human supervisor helping and providing feedback. What makes this work exciting is that the robots can learn a range of visual object manipulation skills entirely on their own,” said Chelsea Finn, a doctoral student in Levine’s lab and inventor of the original DNA model.

With the new technology, a 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.

“Humans learn object manipulation skills without any teacher through millions of interactions with a variety of objects during their lifetime. We have shown that it possible to build a robotic system that also leverages large amounts of autonomously collected data to learn widely applicable manipulation skills, specifically object pushing skills,” said Frederik Ebert, a graduate student in Levine’s lab who worked on the project.

Since control through video prediction relies only on observations that can be collected autonomously by the robot, such as through camera images, the resulting method is general and broadly applicable. In contrast to conventional computer vision methods, which require humans to manually label thousands or even millions of images, building video prediction models only requires unannotated video, which can be collected by the robot entirely autonomously. Indeed, video prediction models have also been applied to datasets that represent everything from human activities to driving, with compelling results.

“Children can learn about their world by playing with toys, moving them around, grasping, and so forth. Our aim with this research is to enable a robot to do the same: to learn about how the world works through autonomous interaction,” Levine said. “The capabilities of this robot are still limited, but its skills are learned entirely automatically, and allow it to predict complex physical interactions with objects that it has never seen before by building on previously observed patterns of interaction.”

The Berkeley scientists are continuing to research control through video prediction, focusing on further improving video prediction and prediction-based control, as well as developing more sophisticated methods by which robots can collected more focused video data, for complex tasks such as picking and placing objects and manipulating soft and deformable objects such as cloth or rope, and assembly.

Learn more: New robots can see into their future

 

The Latest on: Robotic learning technology
  • Boosting student performance with robot learning
    on December 16, 2017 at 8:15 am

    Remote learning is a growing means of delivering education. A downside is with student engagement. This can be overcome, according to new research, when robotic assistants are used. The Michigan State University research has concluded that online students ... […]

  • Collaborative robots learning to work with people
    on December 15, 2017 at 10:20 am

    OSAKA -- Panasonic has developed control technology for so-called collaborative-type robots that can undertake work such as carrying baggage in cooperation with humans. With the new technology, 1,000 kinds of human movements were first registered so that ... […]

  • SD Times news digest: MicroStrategy 10.10, Talend’s new developer courses, and UC Berkeley future learning robots
    on December 11, 2017 at 10:37 am

    Researchers at UC Berkeley develop technology that allows robots to see into their future Researchers ... Unity releases new beta of Unity machine learning agents The machine learning team at Unity has announced the release of v0.2 beta of Unity machine ... […]

  • Students acquire coding skills with robots, games, computers
    on December 5, 2017 at 5:41 pm

    Osmo coding games, Bloxels, Dash Robots ... a goal Wollenburg said the technology team across the school district tries to accomplish. “I don’t believe in failing,” said Wollenburg. “I believe in [students] learning from whatever it is they ... […]

  • What does the rise of the robots mean for education?
    on December 5, 2017 at 11:02 am

    Pearson and its research partners have discovered that robots aren’t automatically replacing humans. Instead, what’s happening is that technology is affecting ... new approach to the business of learning. Of course, Pearson isn’t the only company ... […]

  • Artificially Intelligent Robot Predicts Its Own Future by Learning Like a Baby
    on December 5, 2017 at 8:00 am

    A robotic learning system developed by researchers at Berkeley ... to discover ways of moving objects through time and space. Called Vestri, and using technology called visual foresight, the system can manipulate objects it’s never encountered before ... […]

  • Learning technique allows robots to consider their future
    on December 5, 2017 at 4:37 am

    Developed by a team at the University of California, Berkeley, the technology could help self-driving cars anticipate future events on the road and produce more intelligent robotic assistants in homes. The initial prototype focuses on learning simple ... […]

  • Robot learning improves student engagement
    on December 1, 2017 at 7:41 am

    The technology, Greenhow added, also has implications for telecommuters working remotely and students with disabilities or who are ill. MSU's College of Education started using robot learning in 2015. Greenhow and Benjamin Gleason, a former MSU doctoral ... […]

via Google News and Bing News

Other Interesting Posts

Leave a Reply

%d bloggers like this: