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
- You can still Pay What You Want for this AI and Deep Learning Bundle on April 17, 2019 at 10:46 am
This is a time-limited offer, ending soon. In some cases, such as with Online Courses, a store credit refund within 15 days of purchase is possible if you are unhappy with it; this does not apply to ... […]
- Deep Learning Market 2019: Company Profiles, Emerging Technologies, Global Segments, Landscape and Demand by Forecast to 2023 on April 17, 2019 at 9:49 am
Apr 17, 2019 (AB Digital via COMTEX) -- Deep Learning Market Highlights: As per the latest report published by Market Research Future (MRFR), the global deep learning market is expected to post a ... […]
- Adaptive Deep Reuse Technique cuts AI Training Time by more than 60 Percent on April 17, 2019 at 9:36 am
North Carolina State University researchers have developed a technique that reduces training time for deep learning networks by more than 60 percent without sacrificing accuracy, accelerating the ... […]
- New deep-learning approach predicts protein structure from amino acid sequence on April 17, 2019 at 8:05 am
Nearly every fundamental biological process necessary for life is carried out by proteins. They create and maintain the shapes of cells and tissues; constitute the enzymes that catalyze life ... […]
- Bringing Deep Learning for Geospatial Applications to Life on April 17, 2019 at 12:38 am
Whenever we start to talk about artificial intelligence, machine learning, or deep learning, the cautionary tales from science fiction cinema arise: HAL 9000 from 2001: A Space Odyssey, the T-series ... […]
- Researchers Attempt To Predict & Prevent Suicide Using Deep Learning And Math on April 16, 2019 at 5:05 pm
For years scientists have focused on the causes behind veteran suicide. Now the U.S. Department of Energy (DOE) and several national labs are teaming up to use deep learning and mathematics to ... […]
- Leveraging deep learning to understand health beliefs about the Human Papillomavirus Vaccine from social media on April 15, 2019 at 2:35 am
Our aim was to characterize health beliefs about the human papillomavirus (HPV) vaccine in a large set of Twitter posts (tweets). We collected a Twitter data set related to the HPV vaccine from 1 ... […]
- Supercharge Your Sales Efforts With Deep Learning on April 11, 2019 at 7:05 am
Deep learning, one of the most effective approaches to artificial intelligence, continues to gain traction in the business world. And AI is booming: Salesforce’s “2018 State of Sales ... […]
- 'Deep learning' casts wide net for novel 2-D materials on April 10, 2019 at 9:51 am
Scientists are discovering new two-dimensional materials at a rapid pace, but they don't always immediately know what those materials can do. Researchers at Rice University's Brown School of ... […]
- A Deep Dive into Deep Learning on April 10, 2019 at 9:02 am
On Wednesday, March 27, the 2018 Turing Award in computing was given to Yoshua Bengio, Geoffrey Hinton and Yann LeCun for their work on deep learning. Deep learning by complex neural networks lies ... […]
via Bing News