Researchers are exploring possible impacts of developing robots that are driven by Artificial Intelligence. Developing robots that have a mind of their own can automate a number of real-world situations.
A team of researchers from the University of Texas, Austin is incorporating AI into machines. These systems can learn themselves and operate in the home, workplace and even the sports field. If these robots can deal with real-world situations, we can soon have intelligent robots that you must have seen in science fiction movies.
The fictional representations of intelligence robots are in the minds of global users for over 50 years now. The manufacturing sector has been the biggest beneficiary of robotic technologies. The robots that can carry out preordained and repetitive tasks can solve a number of problems. But these robots are not capable of dealing with real-world situations.
Even the simplest tasks that can be unpredictable need human interaction to solve. Researchers from the University of Texas, Austin is solving the challenge of bringing out robots from their comfort zone into the chaotic real-world situations. The idea is to train robots to carry out simple instructions like finding a colleague or locating a piece of equipment.
The researchers' team led by Dr Jesse Thomason is using AI techniques to help robots in understanding the real-world situations. Thomason’s colleague, Dr Andrea Thomaz is trying to teach human etiquette to a robot called Daleks. Thomaz has developed a code that enables robust to give out social cues like waving at someone and then analyzing the expressions of human counterparts.
Dr Thomaz said, “The problem really is that robots have to be able to deal with the dynamics and noise and unpredictability that people bring into the environment, and so we have to think about perception, control and learning to build robots that can deal with that sort of thing.” The same team is also working on an International RoboCup initiative.
RoboCup is a football by teams of humanoid robots. These robots play on a mini indoor football pitch. Enabling the robots to play football is much more complex for AI and machine learning models than training the robots to play chess. Prof Peter Stone is leading the project of robot’s football game project called ‘Tiki-Take’.
Prof Stone said, “Rather than turn-taking, you have everyone moving at the same time. And if you take too long to decide what to do when you pass the ball, your opponents come and take the ball from you. It's also continuous. There are no discrete places where people need to be. They are always moving, through the air and through space. So there are many challenges in contrast to some of the board games.”
Source: TechGIG
Source: TechGIG
Comments
Post a Comment