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
- Why organizations might want to design and train less-than-perfect AIon August 5, 2020 at 6:00 am
Companies “need to change the way they motivate people in environments where parts of their jobs are done by AI,” argues a Stanford economics professor.
- Customer Experience Outsourcers Launch Intelligent and Self-service Options to Improve Business Outcomes in Europeon August 5, 2020 at 6:00 am
Outsourcers integrate advanced analytics, artificial intelligence, and machine learning to improve the customer journey and agent experience, finds Frost & SullivanSANTA CLARA, Calif., Aug.
- How AI is Becoming Essential to Cyber-Strategyon August 5, 2020 at 5:03 am
In a recent Infosecurity webinar, the topic of the impact of artificial intelligence on cyber-resilience was discussed ... These AI security programs instead use small local programs (agents) to act ...
- USGIC Launches India's 1st AI-powered Conversational Agent for Motor Insuranceon August 3, 2020 at 10:27 am
PRNewswire/ -- The Covid-19 pandemic has caused ambiguity and disruption in customer services across the world and has changed the life of people ...
- Artificial General Intelligence will not resemble human intelligenceon July 30, 2020 at 3:45 am
Airplanes don't flap their wings like birds, and artificial general intelligence (AGI) will never think like the human brain, which is more complex than we imagine ...
- Can Artificial Intelligence Lead to Personalized Macular Edema Treatment?on July 29, 2020 at 10:22 am
Using automated spectral-domain optical coherence tomography, researchers found the presence of subretinal fluid (SRF) in individuals with diabetic macular edema (DME) is associated with lower ...
- Using artificial intelligence, this SaaS startup is helping travel agencies scale up their businesson July 27, 2020 at 5:57 pm
Vervotech is a SaaS startup which helps travel agencies on ecommerce platforms by providing them intelligence comprising the lowest prices and best margins.
- Iridium 'Quant Lens' brings artificial intelligence to valuation and sentiment analysis in listed companieson July 27, 2020 at 4:19 am
Iridium Advisors, the investor relations consultancy, today unveils two self-funded technologies that decode valuation drivers of listed companies and automate sentiment analysis in earnings calls.
- Artificial Intelligence + Machine Learning = Great Customer experienceon July 24, 2020 at 4:51 pm
In today’s digital era, digital transformation is atop, gone are the days of offering courteous and superficial customer interaction. To satisfy the customer using the right tone of voice has no more ...
- Artificial intelligence can help predict the bacteria responsible for pneumonia in emergency roomson July 24, 2020 at 7:40 am
A team of researchers showed that artificial intelligence (AI) could help predict the type of bacteria that caused the infection in patients with pneumonia. The research is presented at ASM Microbe ...
via Bing News