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
via Google News
The Latest on: Artificial intelligence agent
- The path to real-world artificial intelligenceon July 10, 2020 at 1:30 pm
Experts from MIT and IBM held a webinar this week to discuss where AI technologies are today and advances that will help make their usage more practical and widespread.
- Providers need strong campaigns to boost patient trust in coronavirus screening chatbots: studyon July 10, 2020 at 11:43 am
While artificial intelligence-powered chatbots have the potential to relieve pressure on hospital contact centers – especially during the pandemic – the No. 1 factor driving patient response is ...
- AI for self-driving cars doesn’t account for crimeon July 10, 2020 at 10:09 am
Because today’s simplistic ethical considerations in AI and autonomous vehicles don’t account for malicious intent, vigorous driving simulation testing is required.
- Polycraft Team Wins DARPA Grant To Lay Groundwork for Smarter AIon July 10, 2020 at 8:58 am
Researchers will use their video game modification to simulate events that can train artificial intelligence systems to adapt to the unpredictable as part of a project funded by the Defense Advanced ...
- Five Of The Leading British AI Companies Revealedon July 10, 2020 at 3:45 am
Britain's leading artificial intelligence start-ups continue to raise capital despite the uncertainties of Covid-19 ...
- Video Surveillance Market is projected to reach $74.6 billion by 2025 | CAGR of 10.4%on July 10, 2020 at 1:07 am
The report "Video Surveillance Market by System, Offering (Hardware (Camera, Storage Device, Monitor), Software (Video Analytics, Video Management System) & Service (VSaaS)), Vertical (Commercial, ...
- Company offers agents course on artificial intelligenceon July 9, 2020 at 1:14 pm
SecondsToFly has partnered with ASTA, to make the course available to members free as part of its educational resources.
- Artificial Intelligence in Contrast Media Injectors Market a Gamechanger: Future Market Insightson July 9, 2020 at 12:00 pm
The contrast media injectors market shall expand at a CAGR of 4.9% through 2030, but gains in 2020 will be impacted by the sluggishness ...
- Lemonade IPO Shows The Power Of AI (Artificial Intelligence)on July 3, 2020 at 9:29 am
Lemonade is a next-generation AI company. The technology is all-pervasive across its operations. Keep in mind that the insurance industry was actually the first industry that was data driven. The ...
- Eye in the sky tower: AI will monitor US-Mexico border, tip off patrol agents about 'infiltrators'on July 3, 2020 at 8:54 am
Of the 2,000 mile border with Mexico, Trump’s steel wall covers just 200 miles, and border patrol agents can’t be everywhere.
via Bing News