>>“Even though your light might be green, it may recommend you not go because there are people behaving badly that you may not be aware of,” said Jonathan How, an aeronautics and astronautics professor who co-created the algorithm."
There is the possibility that this could result in more red-light running instances, if runners begin to presume there is this collision warning system. Whereas before they were "taking chances", now it'd become less "chancy".
I wish it would explain how the accuracy numbers work. I could say 'no' to every car and get pretty good naive accuracy, so that's clearly not the method they're using to give the old models scores of only 15-20%.
>>“Even though your light might be green, it may recommend you not go because there are people behaving badly that you may not be aware of,” said Jonathan How, an aeronautics and astronautics professor who co-created the algorithm."
There is the possibility that this could result in more red-light running instances, if runners begin to presume there is this collision warning system. Whereas before they were "taking chances", now it'd become less "chancy".