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
- Artificial Intelligence Provokes Shift in Asset-Allocation Strategieson February 26, 2021 at 9:31 pm
Artificial intelligence affords investment specialists the ability to make autonomous assessment of market conditions, removed from the frailties of human decision making, argues a new white paper by ...
- 2021 Study: Focus on How AI is Making Inroads into the Customer Experience (CX) Space – ResearchAndMarkets.comon February 26, 2021 at 1:28 am
The “Enhancing European Customer Experience with Artificial Intelligence” report has been added to ResearchAndMarkets.com’s offering. This study focuses on how AI is making inroads into the customer ...
- AI conquers challenge of 1980s platform gameson February 25, 2021 at 11:40 am
Scientists have come up with a computer program that can master a variety of 1980s exploration games, paving the way for more self-sufficient robots. They created a family of algorithms ...
- Artificial intelligence is killing choice and chance – changing what it means to be humanon February 25, 2021 at 4:47 am
The history of humans’ use of technology has always been a history of co-evolution. Philosophers from Rousseau to Heidegger to Carl Schmitt have argued that technology is never a neutral tool for ...
- The Combination of AI and Blockchain through Artificial Neural Networkson February 24, 2021 at 10:30 pm
AI and blockchain include technical complexity and will have intense business implications. Using Artificial neural networks can help in forecasting the future cost of bitcoins, decreasing the issues ...
- Superficial Radiation Therapy System Market | Artificial Intelligence to Drive More Opportunitieson February 24, 2021 at 4:16 am
Major superficial radiation therapy system market players are leveraging patient and healthcare professional bias towards minimally invasive therapies for skin cancer, to boost revenues in the ...
- Access Softek adds AI-enabled agent advisor to live chat solutionon February 23, 2021 at 7:27 am
Access Softek, Inc., an omnichannel digital banking platform provider, announced the launch of Agent Advisor the latest feature of its Live Chat solution. Agent Advisor utilizes artificial ...
- AI Is Changing CX, but Human Intelligence Still Matterson February 18, 2021 at 8:44 pm
AI Is Changing CX, but Human Intelligence Still Matters By Mike de la Cruz, CEO, Directly - Artificial intelligence is radically reshaping the modern customer experience, powering sophisticated ...
- What is Artificial Intelligence? How Does AI Work?on February 18, 2021 at 5:41 am
Depending on who you ask, AI is either man’s greatest invention since the discovery of fire”, as Google’s CEO said at Google’s I/O 2017 keynote, or it is a technology that might one day make man ...
- SupportLogic Introduces Agent SX to Improve Customer Service and Team Collaborationon February 15, 2021 at 3:59 pm
With SupportLogic Agent SX, professionals that interact directly with customers can now see customer sentiments on their own cases and set up alerts when interesting events such as negative sentiments ...
via Bing News