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
- A motion retargeting and style transfer deep learning framework for 3D characters [SIGGRAPH 2020]on May 12, 2020 at 5:42 pm
A motion retargeting and style transfer deep learning framework for 3D characters [SIGGRAPH 2020] - DeepMotionEditing/deep-motion-editing ...
- DeepCube Launches Industry-First Deep Learning Software Accelerator to Enable Real-World AI Deploymentson May 12, 2020 at 6:17 am
DeepCube today launched the only software-based inference accelerator that drastically improves deep learning performance on intelligent edge devices ...
- The usefulness of the Deep Learning method of variational autoencoder to reduce measurement noise in glaucomatous visual fieldson May 12, 2020 at 2:27 am
The aim of the study was to investigate the usefulness of processing visual field (VF) using a variational autoencoder (VAE). The training data consisted of 82,433 VFs from 16,836 ...
- NEUCHIPS Announces World's First Deep Learning Recommendation Model (DLRM) Accelerator: RecAccelon May 12, 2020 at 1:59 am
NEUCHIPS Corp., an AI compute company specializing in domain-specific accelerator solutions, announced the world's first recommendation engine - RecAccelTM - that can perform 500,000 inferences per ...
- Deep Learning System Market Insights by Size, Status and Forecast 2025 | NVIDIA, Intel, Xilinxon May 11, 2020 at 5:57 am
Advance Market Analyticsreleased the research report of Global Deep Learning System Market, offers a detailed overview of the factors influencing the global business scope. Global Deep Learning System ...
- Deep learning enables accurate clustering with batch effect removal in single-cell RNA-seq analysison May 11, 2020 at 2:06 am
We present DESC, an unsupervised deep embedding algorithm that clusters scRNA-seq data by iteratively optimizing a clustering objective function. Through iterative self-learning, DESC gradually ...
- Global Deep Learning System Market Price and Sales Revenue Analysis (2020-2029)on May 10, 2020 at 7:20 am
MarketResearch.Bizhas carefully uploaded a smart research report titled Global Deep Learning System Market 2020 Development Status and Future Statistics by 2029 to its immense online database. The ...
- Deep Learning Chip Market is Determined to cross a value of $ 21.31 Bn by 2027on May 6, 2020 at 2:10 pm
The Deep Learning Chip Market report, recently added by Market Study Report, LLC, examines the industry in terms of the ...
- The future of deep-reinforcement learning, our contemporary AI superheroon May 5, 2020 at 3:53 pm
AI algorithms for deep-reinforcement learning have demonstrated the ability to learn at very high levels in constrained domains.
- Deep Learning Algorithm Outperforms Experts in Making Alzheimer’s Diagnosison May 5, 2020 at 11:42 am
New technology developed at BU School of Medicine could reduce misdiagnosis, improve early Alzheimer’s detection in low-resource areas ...
via Bing News