Computer scientists at The University of Texas at Austin have taught an artificial intelligence agent how to do something that usually only humans can do—take a few quick glimpses around and infer its whole environment, a skill necessary for the development of effective search-and-rescue robots that one day can improve the effectiveness of dangerous missions.
The team, led by professor Kristen Grauman, Ph.D. candidate Santhosh Ramakrishnan and former Ph.D. candidate Dinesh Jayaraman (now at the University of California, Berkeley) published their results today in the journal Science Robotics.
Most AI agents—computer systems that could endow robots or other machines with intelligence—are trained for very specific tasks—such as to recognize an object or estimate its volume—in an environment they have experienced before, like a factory. But the agent developed by Grauman and Ramakrishnan is general purpose, gathering visual information that can then be used for a wide range of tasks.
“We want an agent that’s generally equipped to enter environments and be ready for new perception tasks as they arise,” Grauman said. “It behaves in a way that’s versatile and able to succeed at different tasks because it has learned useful patterns about the visual world.”
The scientists used deep learning, a type of machine learning inspired by the brain’s neural networks, to train their agent on thousands of 360-degree images of different environments.
Now, when presented with a scene it has never seen before, the agent uses its experience to choose a few glimpses—like a tourist standing in the middle of a cathedral taking a few snapshots in different directions—that together add up to less than 20 percent of the full scene. What makes this system so effective is that it’s not just taking pictures in random directions but, after each glimpse, choosing the next shot that it predicts will add the most new information about the whole scene. This is much like if you were in a grocery store you had never visited before, and you saw apples, you would expect to find oranges nearby, but to locate the milk, you might glance the other way. Based on glimpses, the agent infers what it would have seen if it had looked in all the other directions, reconstructing a full 360-degree image of its surroundings.
“Just as you bring in prior information about the regularities that exist in previously experienced environments—like all the grocery stores you have ever been to—this agent searches in a nonexhaustive way,” Grauman said. “It learns to make intelligent guesses about where to gather visual information to succeed in perception tasks.”
One of the main challenges the scientists set for themselves was to design an agent that can work under tight time constraints. This would be critical in a search-and-rescue application. For example, in a burning building a robot would be called upon to quickly locate people, flames and hazardous materials and relay that information to firefighters.
For now, the new agent operates like a person standing in one spot, with the ability to point a camera in any direction but not able to move to a new position. Or, equivalently, the agent could gaze upon an object it is holding and decide how to turn the object to inspect another side of it. Next, the researchers are developing the system further to work in a fully mobile robot.
Using the supercomputers at UT Austin’s Texas Advanced Computing Center and Department of Computer Science, it took about a day to train their agent using an artificial intelligence approach called reinforcement learning. The team, with Ramakrishnan’s leadership, developed a method for speeding up the training: building a second agent, called a sidekick, to assist the primary agent.
“Using extra information that’s present purely during training helps the [primary] agent learn faster,” Ramakrishnan said.
Learn more: New AI Sees Like a Human, Filling in the Blanks
The Latest on: Artificial intelligence agent
[google_news title=”” keyword=”artificial intelligence agent” num_posts=”10″ blurb_length=”0″ show_thumb=”left”]
via Google News
The Latest on: Artificial intelligence agent
- Are AI agents the next step in the AI revolution?on May 10, 2024 at 3:37 pm
In the future, we will see AI transcend current limitations, morphing into what can be best described as ‘Fully human-capable AI Agents.
- Is This Beaten-Down Artificial Intelligence Stock a No-Brainer Buy Right Now?on May 10, 2024 at 6:00 am
Founded in 1993, The Motley Fool is a financial services company dedicated to making the world smarter, happier, and richer. The Motley Fool reaches millions of people every month through our premium ...
- After Strong Q1 Results Powered by Artificial Intelligence, Is Now the Time to Buy Amazon Stock?on May 10, 2024 at 1:00 am
Amazon noted that while it will need to spend money upfront, this leads to better operating margins and free cash flow down the line. It also said 85% of global IT spend is still on-premises, so the ...
- How to stop the artificial intelligence apocalypse: David Brin, Uplift authoron May 9, 2024 at 6:58 pm
Uplift and The Postman author David Brin has devised a clever plan to keep AIs from going rogue. But can we pull it off?
- Starknet to bring on AI agents that can carry out on-chain activityon May 9, 2024 at 3:30 am
Starknet is allowing Giza to put AI agents on its blockchain, which are slated to take over some on-chain tasks like optimizing yield.
- Boomi upgrades its integration platform as a service with new AI agents, acquisitionson May 8, 2024 at 2:04 pm
Boomi LP has acquired software assets from two companies, APIIDA GmbH and Cloud Software Group Inc., to enhance its flagship integration-platform-as-a-service product.
- Altera Closes $9M Seed Round to Build Digital Human Beings and Redefine AI Agentson May 8, 2024 at 7:18 am
After shutting their MIT lab, founders raise $11.1 million in first five months of company's inception ...
- Artificial Intelligence Could Help Officers Screen Applicants for Asylum at Borderon May 8, 2024 at 6:27 am
The Department of Homeland Security is piloting artificial intelligence to train officers who review applicants for refugee status in the United States, Secretary Alejandro Mayorkas told reporters on ...
- 12 Best Artificial Intelligence Stocks to Buy Now According to Wall Street Analystson May 7, 2024 at 4:40 pm
In this piece, we will take a look at the 12 best artificial intelligence stocks to buy now according to Wall Street analysts. If you want to skip our coverage of the latest developments in the ...
- SIMA: Scaling Up AI Agents Across Virtual Worlds for Diverse Applicationson May 7, 2024 at 7:19 am
Discover how Google DeepMind's Scalable Instructable Multiworld Agent (SIMA) revolutionizes AI technology, with human-like adaptability ...
via Bing News