Bioengineers have developed a so-called "psychic robot" using an algorithm that can predict a person's intention while doing tasks or actions, a capability that can potentially help save lives.
The software is not capable of reading the mind, but it can calculate a person's intention based on a previous activity regardless if this action is interrupted.
Justin Horowitz, from the University of Illinois at Chicago (UIC) who co-developed the algorithm, said that it can predict the way a person wanted to move based on his intentions.
The mathematical algorithm, which was reported in a study published in PLOS ONE on Sept. 1 is capable of analyzing an action and estimate a person's intent regardless if the action was disturbed and disrupted.
The mathematical algorithm has life-saving implications when incorporated in a vehicle's artificial intelligence. The car's course, for instance, can be made to be more in line with the intended action of the driver. Semi-autonomous cars can avoid accidents based on observations of the driver's previous steering actions, a capability that may help reduce the incidences of a car crash.
Data from the non-profit Association for Safe International Road Travel (ASIRT) show that road crashes kill 1.3 million people per year, which is equivalent to about 3,287 deaths per day. In the U.S., 37,000 people die due to car crashes per year and 2.35 million others get injured or disabled.
"If we hit a patch of ice and the car starts swerving, we want the car to know where we meant to go. It needs to correct the car's course not to where I am now pointed, but [to] where I meant to go," Horowitz said. "It has to know which movements of the wheel represent my intention, and which are responses to an environment that's already changed."
The researchers said that since it can "see through" a person's intent, the algorithm has a range of other potential applications such as in improving interactions between humans and machines and in the field of medicine. A smart prosthesis, for instance, can help a stroke patient complete a task smoothly by interpreting what he intends to do even if tremors corrupt his actions.
"Knowing such an intent signal is broadly applicable: enhanced human-machine interaction, the study of impaired intent in neural disorders, the real-time determination (and manipulation) of error in training, and complex systems that embody planning such as brain machine interfaces, team sports, crowds, or swarms," the researchers wrote.