Bioengineers from the University of Illinois, Chicago, claim to have developed a “psychic robot” that can predict the actions of humans by relying on a mathematical algorithm. The paper is published in PLOS ONE.
The software designed by the team of researchers can allegedly calculate people’s intentions when taking previous activity into account. It cannot, as such, read minds, but it is described as being so good that it can accomplish its task even if some action is interrupted. Well, it sounds better than Ultron in this manner, doesn’t it?!
What actions can the robot actually “foresee”? An example entails meeting an obstacle when reaching out for something on a table. Just like a human witnessing the occurrence will be able to guess the intended motion and trajectory, so can the robot. Such was proved when the scientists carried out experiments of tracking and analysing the movement of people’s hands in this scenario.
This technology, if fine-tuned and enhanced, might have important applications in the future. For instance, semi-autonomous vehicle controls could incorporate a similar algorithm to help avoid accidents based on previous driving actions.
“If we hit a patch of ice and the car starts swerving, we want the car to know where we meant to go,” said Justin Horowitz, first author of the study.
“It needs to correct the car’s course not to where I am now pointed, but [to] where I meant to go. The computer has extra sensors and processes information so much faster than I can react. If the car can tell where I mean to go, it can drive itself there. But it has to know which movements of the wheel represent my intention, and which are responses to an environment that’s already changed.”
The technology could also be made part of smart prosthetics. For examples, patients suffering from tremors can use it to reduce physical shaking.
“We call it a psychic robot,” said Horowitz. “If you know how someone is moving and what the disturbance is, you can tell the underlying intent — which means we could use this algorithm to design machines that could correct the course of a swerving car or help a stroke patient with spasticity.”
The author also hopes to integrate the software in machines such as robotic exoskeletons, and surgical robots.