UC Berkeley researchers have developed algorithms that enable robots to learn motor tasks through trial and error using a process that more closely approximates the way humans learn, marking a major milestone in the field of artificial intelligence.
They demonstrated their technique, a type of reinforcement learning, by having a robot complete various tasks — putting a clothes hanger on a rack, assembling a toy plane, screwing a cap on a water bottle, and more — without pre-programmed details about its surroundings.
“What we’re reporting on here is a new approach to empowering a robot to learn,” said Professor Pieter Abbeel of UC Berkeley’s Department of Electrical Engineering and Computer Sciences. “The key is that when a robot is faced with something new, we won’t have to reprogram it. The exact same software, which encodes how the robot can learn, was used to allow the robot to learn all the different tasks we gave it.”
The latest developments will be presented on Thursday, May 28, in Seattle at the International Conference on Robotics and Automation (ICRA). Abbeel is leading the project with fellow UC Berkeley faculty member Trevor Darrell, director of the Berkeley Vision and Learning Center. Other members of the research team are postdoctoral researcher Sergey Levine and Ph.D. student Chelsea Finn.
The work is part of a new People and Robots Initiative at UC’s Center for Information Technology Research in the Interest of Society (CITRIS). The new multi-campus, multidisciplinary research initiative seeks to keep the dizzying advances in artificial intelligence, robotics and automation aligned to human needs.
“Most robotic applications are in controlled environments where objects are in predictable positions,” said Darrell. “The challenge of putting robots into real-life settings, like homes or offices, is that those environments are constantly changing. The robot must be able to perceive and adapt to its surroundings.”
Conventional, but impractical, approaches to helping a robot make its way through a 3D world include pre-programming it to handle the vast range of possible scenarios or creating simulated environments within which the robot operates.
Instead, the UC Berkeley researchers turned to a new branch of artificial intelligence known as deep learning, which is loosely inspired by the neural circuitry of the human brain when it perceives and interacts with the world.
“For all our versatility, humans are not born with a repertoire of behaviors that can be deployed like a Swiss army knife, and we do not need to be programmed,” said Levine. “Instead, we learn new skills over the course of our life from experience and from other humans. This learning process is so deeply rooted in our nervous system, that we cannot even communicate to another person precisely how the resulting skill should be executed. We can at best hope to offer pointers and guidance as they learn it on their own.”
In the world of artificial intelligence, deep learning programs create “neural nets” in which layers of artificial neurons process overlapping raw sensory data, whether it be sound waves or image pixels. This helps the robot recognize patterns and categories among the data it is receiving. People who use Siri on their iPhones, Google’s speech-to-text program or Google Street View might already have benefited from the significant advances deep learning has provided in speech and vision recognition.
Applying deep reinforcement learning to motor tasks has been far more challenging, however, since the task goes beyond the passive recognition of images and sounds.
“Moving about in an unstructured 3D environment is a whole different ballgame,” said Finn. “There are no labeled directions, no examples of how to solve the problem in advance. There are no examples of the correct solution like one would have in speech and vision recognition programs.”
The Latest on: Deep Learning
via Google News
The Latest on: Deep Learning
- Learn AI and deep learning with this bundle, for a price you chooseon August 16, 2019 at 11:15 am
AI and deep learning are transforming the way we understand software, used across a broad range of industries to produce hardware like self-driving cars, personal assistant computers, and decision ...
- DeepCC: a novel deep learning-based framework for cancer molecular subtype classificationon August 16, 2019 at 10:57 am
Molecular subtyping of cancer is a critical step towards more individualized therapy and provides important biological insights into cancer heterogeneity. Although gene expression signature-based ...
- Squirrel AI Learning by Yixue Group Learning Won Best Paper & Best Student Paper Award at ACM KDD International Symposium on Deep Learning on Graphon August 16, 2019 at 2:41 am
ANCHORAGE, Alaska, Aug. 14, 2019 /PRNewswire/ -- The first international symposium on deep learning on graph: methods and applications (DLG 2019) was held in Anchorage, Alaska, the US on August 5 ...
- Towards perturbation prediction of biological networks using deep learningon August 16, 2019 at 2:10 am
The mapping of the physical interactions between biochemical entities enables quantitative analysis of dynamic biological living systems. While developing a precise dynamical model on biological ...
- Global Closed-circuit Television (CCTV) Camera Market 2019-2023| Introduction of Deep Learning Technology to Boost Growth| Technavioon August 15, 2019 at 9:47 am
Technavio has published a new market research report on the global closed-circuit television (CCTV) camera market from 2019-2023 (Graphic: Business Wire) The growing demand for IP-based CCTV cameras ...
- A day at the beach: Deep learning for a childon August 14, 2019 at 2:34 pm
The beach offers a wide open playscape where children are fuelled by curiosity. Whether at the beach or elsewhere outdoors, it helps to take a moment to see the world through the lens of a child ...
- Master data analytics and deep learning with this $35 Python certification bundleon August 13, 2019 at 10:02 am
Python is one of the easiest programming languages to learn, but mastering it allows you to build apps and games or even take advantage of neural networks for deep learning. But first, you’ll need to ...
- Global Deep Learning Market Outlook 2019-2025: Anticipating a CAGR of 42.3%on August 12, 2019 at 8:34 am
Dublin, Aug. 12, 2019 (GLOBE NEWSWIRE) -- The "Deep Learning - Market Analysis, Trends, and Forecasts" report has been added to ResearchAndMarkets.com's offering. Deep Learning market worldwide is ...
- Sightcorp deep learning method improves biometric face detection at challenging angleson August 9, 2019 at 8:57 am
Artificial intelligence software company Sightcorp has developed improved biometric facial detection capabilities for facial analysis and recognition software based on deep learning, rather than ...
- What Is Deep Learning?on August 8, 2019 at 7:25 am
Deep learning, an advanced artificial intelligence technique, has become increasingly popular in the past few years, thanks to abundant data and increased computing power. It's the main technology ...
via Bing News