From senses to sensors: autonomous cars and probing what machine learning does to mobilities studies

Cars are nowadays being programmed to learn how to drive themselves. While autonomous cars are often portrayed as the next step in the auto-motive industry, they have already begun roaming the streets in some US cities. Building on a growing body of critical scholarship on the development of autonomous cars, we explore what machine learning is in open environments like cities by juxtaposing this to the field of mobilities studies. We do so by revisiting core concepts in mobilities studies: movement, representation and embodied experience. Our analysis of machine learning is centred around the transition from human senses to sensors mounted on cars, and what this implies in terms of autonomy. While much of the discussions related to this transition are already foregrounded in mobilities studies, due to this field's emphasis on complexities and the understanding of automobility as a socio-technological system, questions about autonomy still emerge in a slightly new light with the advent of machine learning. We conclude by suggesting that in mobilities studies, autonomy has always been seen as intertwined with technology, yet we argue that machine learning unfolds autonomy as intrinsic to technology, as the space between the car, the driver and the context is collapsing with autonomous cars.