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.
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
- The iRobot Roomba s9+ and Braava m6 are the robots you should trust to clean your house wellon November 19, 2019 at 5:15 pm
First up: iRobot's top-end home cleaning robots, the Roomba s9+ robot vacuum, and the Braava m6 robot mop and floor sweeper. Both of these represent the current peak of iRobot's technology, and while ...
- Companies Adjust Financial Communications to Resonate With Humans and Robotson November 19, 2019 at 12:41 pm
The target audience isn’t just human analysts and investors: Machine-learning tools, perception studies and speech recognition are also used by finance and investor-relations executives seeking to ...
- XPO Logistics Expands Use of Intelligent Robotics in the UK Ahead of Holiday Shopping Seasonon November 19, 2019 at 6:17 am
The robots guide employees to the correct inventory area, validate the items picked and transport them to designated packing stations. The technology uses machine learning to double productivity rates ...
- XACT Robotics Appoints Industry Veteran Brian L. Allen as its Vice President of Sales and Marketingon November 19, 2019 at 3:00 am
Brian recently served as Senior Vice President of Business Development for HeartSciences, where he led the global market release of the cardiac industry's first wavelet signal processed ...
- The robotic pooch from Boston Dynamics’ viral videos is ready for real workon November 18, 2019 at 5:00 pm
For years, people have joked that Boston Dynamics is more a maker of viral videos than of robots. The company has ... While Spot was learning how to navigate around the construction site, its human ...
- Will A Robot Be Interviewing You For Your Next Job?on November 18, 2019 at 9:16 am
For example, there is a fear that since AI may involve “machine learning,” the robot may develop assumptions over time regarding the suitability ... and the levels of sophistication of this technology ...
- Fazt Tech provides an overview of robotics, machine learning, and the future of manufacturingon November 18, 2019 at 6:19 am
Machine learning is the next step towards true automation and enhanced levels of efficiency in the manufacturing industry. A relatively new technology still under development, it nonetheless ...
- Learning about space-age surgeryon November 18, 2019 at 12:12 am
Students got to see medical robotics in action as the hospital gave live demonstrations of its new state-of-the-art surgical robot. Students learned how the technology helps surgeons achieve more ...
- Women in Technology (WIT) honors its Women of the Yearon November 16, 2019 at 3:00 am
“I love learning,” she said. “I am a very competitive person ... for 19 years and was instrumental in bringing FIRST Lego League to Georgia and FIRST Robotics to Georgia and her native Tennessee.
- Recycling robots raise millions from top venture firms to rescue an industry in turmoilon November 14, 2019 at 3:38 pm
Given the economic reality, recyclers are turning to AMP’s technology — a combination of computer vision, machine learning and robotic automation to improve efficiencies at their facilities. That’s ...
via Google News and Bing News