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
- Conversing with chatbots—Artificial Intelligence research keeps it more ‘human’on December 12, 2019 at 10:40 am
The rapid advance of artificial intelligence (AI) begs a daunting question – will we ever achieve ‘human ... To achieve this, the researchers have combined their research in empathy-based modeling for ...
- Are The Robots Coming For Us? Misconceptions About AI And Machine Learningon December 12, 2019 at 10:37 am
in which software ‘agents’ are set loose in the world (or a virtual world, such as a videogame) and learn by being rewarded for desirable behavior.” The Christian Science Monitor: “Fears about robot ...
- The Artificial Intelligence Takeoveron December 12, 2019 at 9:33 am
Artificial intelligence has played a significant role in music this year ... Revive, his latest project, "explores the affordances of live interaction between the artificial musical agent MASOM, human ...
- Aivo’s Conversational AI Bot Now Available on Genesys AppFoundryon December 12, 2019 at 6:08 am
SAN FRANCISCO--(BUSINESS WIRE)--The use of artificial intelligence (AI) is rapidly advancing in the corporate sector ... Together with PureCloud, Aivo's conversational AI bot complements contact ...
- AI R&D is booming, but general intelligence is still out of reachon December 11, 2019 at 9:01 pm
Trying to get a handle on the progress of artificial intelligence is a daunting task ... Such training usually relies on AI agents sinking many lifetimes’ worth of work into a single game, training ...
- Is Artificial Intelligence and Machine Learning really a strong market to invest in?on December 11, 2019 at 9:22 am
Prominent players profiled in the study: ?AIBrain, Amazon, Anki, CloudMinds, Deepmind, Google, Facebook, IBM, Iris AI, Apple, Luminoso, Qualcomm Artificial intelligence (AI) is the study of ...
- XOKind Emerges From Stealth Mode Raising Over 1.6MM Led by Section 32, Announces Plans for Building AI Agents for Travelon December 11, 2019 at 4:37 am
"We support XOKind's long term vision of building general artificial intelligence through a sustainable and positive stream of new products incorporating AI assistance to better the human experience," ...
- Observe.AI Raises $26M; Leverages Artificial Intelligence To Optimize Voice Customer Serviceon December 11, 2019 at 3:52 am
“Today’s customer service agents have a unique ability to emotionally connect with customers and are often a brand’s only frontline representatives. This investment will fuel our mission to elevate ...
- Observe.AI Raises $26 Million to Digitally Transform the $300 Billion Voice Customer Service Market with Artificial Intelligenceon December 10, 2019 at 4:30 am
SAN FRANCISCO, Dec. 10, 2019 /PRNewswire/ -- Observe.AI, the leader in AI-powered agent enablement for voice customer service, today announced a $26 million Series A financing led by Scale Venture ...
- FlightHub and JustFly on Why Artificial Intelligence (AI) May Be the Future of Travelon December 9, 2019 at 5:11 am
The bots are pre-programmed with hundreds of likely responses, therefore removing the need to speak with live agents. This also allows companies the resources and flexibility to provide clients with ...
via Bing News