By studying humans’ gait, body symmetry, and foot placement, researchers at the University of Michigan are teaching self-driving cars to recognise and predict pedestrians’ motion with greater precision than current technologies. Data collected by vehicles through cameras, lidar and GPS allows the UM researchers to capture video snippets of humans in motion and then recreate them in 3D computer simulation. With that, they have created a ‘biomechanically inspired recurrent neural network’ (Bio-LSTM) that catalogs human movements. With it, they can predict poses and future locations for one or several pedestrians up to about 46 metres from the vehicle, which is about the scale of a city street junction.
Equipping vehicles with the necessary predictive power requires the network to dive into the minutiæ of human movement: the pace of a human’s gait, the mirror symmetry of limbs, and the way foot placement affects stability during walking.