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
- ‘Agents swayed by AI must remember to keep a firm hand on the wheel’on November 21, 2023 at 11:37 pm
Generative AI opens vistas of opportunity for travel marketers and agents, but caution must be taken before rushing into adopting technology just because others are, writes We Are Llama’s Mags Sikora ...
- Artificial Intelligenceon November 21, 2023 at 10:08 pm
By Tripp Mickle and Cade Metz Shield AI, a tech start-up, already has a drone run by artificial intelligence being used by the Israeli military. But persuading the Pentagon to embrace the ...
- US agency streamlines probes related to artificial intelligenceon November 21, 2023 at 1:32 pm
Investigations of cases where artificial intelligence (AI) is used to break the law will be streamlined under a new process approved by the U.S. Federal Trade Commission, the agency said on Tuesday.
- Artificial Intelligence, Other Technologies Already Increasing Fraud In Nigeria – Minister Of Justice, Fagbemion November 21, 2023 at 3:36 am
Nigeria's Attorney-General and Minister of Justice, Lateef Fagbemi (SAN), has identified Artificial Intelligence and generative technologies as new means of fraud in the country, adding that such ...
- Researchers seek consensus on what constitutes Artificial General Intelligenceon November 20, 2023 at 1:25 pm
A team of researchers at DeepMind focusing on the next frontier of artificial intelligence—Artificial General Intelligence (AGI)—realized they needed to resolve one key issue first. What exactly, they ...
- The Top 2 Artificial Intelligence (AI) Companies Revolutionizing the Industry Right Nowon November 20, 2023 at 2:27 am
Detailed price information for International Business Machines (IBM-N) from The Globe and Mail including charting and trades.
- OpenAI Battle IS Over Artificial Super Intelligenceon November 19, 2023 at 11:16 am
A superintelligence is a hypothetical agent that possesses intelligence far surpassing ... suggest that the OpenAI company control chaos is over the emergence of Artificial Super Intelligence. Elon is ...
- How artificial intelligence is being used for sextortionon November 16, 2023 at 5:10 pm
The FBI is warning about a frightening twist on an already disturbing crime targeting children that’s increasing across the country.
- Child Psychiatrist Sexually Exploited Patients, Used Artificial Intelligence to Create Pornographyon November 13, 2023 at 10:32 am
David Tatum of Charlotte, North Carolina recorded under a minor's skirt during a therapy session with him, made secret videos of patients in the shower and "used AI to digitally alter clothed images ...
- Is Artificial Intelligence capable of taking over the world?on November 13, 2023 at 8:01 am
It’s all down to Artificial Intelligence – or AI as it is abbreviated to. Essentially, AI is about computer technology being able to 'think' for itself, and make decisions based on the data it's being ...
via Bing News