A team of bioengineers are currently working on developing what they are calling a ‘psychic robot’ that analyses the driver to determine where they are intending to go in the eventuality of an accident.
Of course, these so-called ‘psychic robots’ will not be reading the driver’s mind so-to-speak, but will be able to analyse where they had planned on going and attempt to bring the car back on to that particular path.
According to researchers from the University of Illinois, the technology uses a mathematical algorithm that effectively uses machine learning to predict the driver’s behaviour over time.
In their development, however, they have looked at the concept on a smaller scale with testing to see how the algorithm would be able to map a person’s movement when they reach for a piece of paper and are blocked mid-reach.
While the person affected by the block would not be able to register what exactly had happened, a second pair of eyes watching would have been able to predict where they had intended to reach out to.
Using this algorithm in the example of a semi-autonomous car, the researchers said, could realign the car on its expected path in the event of an accident.
“If we hit a patch of ice and the car starts swerving, we want the car to know where we meant to go,” said the lead researcher on the project, Justin Horowitz. “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.”
Their study has now been published in the online journal, PLOS ONE.
Crashed toy car image via Shutterstock