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
- Avant Special Forces Summit: UCaaS Vendors Court Agent Channel, Zoom Founder Blasts Ciscoon October 7, 2020 at 3:35 pm
The master agent Avant Communications hosted the first day of its Special Forces Summit. Zoom Founder and CEO Eric Yuan blasted Cisco WebEx.
- Next Premiere Recap: Fox's New Drama Sets the Stage for the Artificial Intelligence Apocalypseon October 6, 2020 at 7:00 pm
- What is intelligence?on October 5, 2020 at 11:34 am
Neuroeconomist Daeyeol Lee discusses his new book and the development of artificial intelligence, asking 'Will AI ever surpass human intelligence?' ...
- Pediatric Diabetes, COVID-19 and Artificial Intelligence: IBM Watson supports families during pandemic shutdownon October 5, 2020 at 3:12 am
IBM Canada ProBono volunteer program delivers a virtual agent using Watson Assistant for Quebec's Diabetic Children FoundationMONTREAL, Oct. 5, 2020 /PRNewswire/ -- IBM Canada (NYSE: IBM) is working w ...
- An artificial hyper-intelligence may be Fox’s ‘NEXT’ big thingon October 4, 2020 at 2:21 am
If you’re already dazzled or baffled by artificial intelligence, wait until you see what’s next. Technology runs amok — with dangerous implications for virtually everyone — ...
- Up ‘Next’ on TV — an artificial intelligence threatens humanityon October 2, 2020 at 8:53 am
That was the launching point for “Next,” a dark thriller about an artificial intelligence that’s on the precipice of taking over the world. The series centers on billionaire ...
- How Artificial Intelligence Affects Real Estateon September 30, 2020 at 12:44 pm
Artificial intelligence has made inroads into not one or two, but virtually every industry on the face of Earth, including real estate. The technology has found incredibly exciting applications in ...
- MBZUAI talks webinar to explore evolution and major breakthroughs in artificial intelligenceon September 29, 2020 at 9:42 am
Expert Dr. Munawar Hayat to host public webinar called 'Evolution of Artificial Intelligence: Past, Current and Future' ...
- This interactive VR 'film' lets you play god to an evolving artificial intelligenceon September 28, 2020 at 6:00 am
If you could play god to an emerging artificial intelligence, would you? Or better: Should you? That’s the moral dilemma at the heart of Agence, an interactive “dynamic film” that blends virtual ...
- The Promise of Artificial Intelligenceon September 25, 2020 at 7:15 am
Artificial intelligence and machine learning are increasingly being used to automate critical business functions and support clinicians making complex clinical decisions. As the pandemic challenges ...
via Bing News