"If you could see me through my eyes": Predicting Pedestrian Perception
This work addresses pedestrian safety for autonomous vehicles, but it is incremental as it relies on synthetic data and preliminary simulations.
The authors tackled the problem of predicting pedestrian visual perception in autonomous driving scenarios by training neural networks on synthetic data, achieving accurate predictions within relevant time horizons.
Pedestrians are particularly vulnerable road users in urban traffic. With the arrival of autonomous driving, novel technologies can be developed specifically to protect pedestrians. We propose a machine learning toolchain to train artificial neural networks as models of pedestrian behavior. In a preliminary study, we use synthetic data from simulations of a specific pedestrian crossing scenario to train a variational autoencoder and a long short-term memory network to predict a pedestrian's future visual perception. We can accurately predict a pedestrian's future perceptions within relevant time horizons. By iteratively feeding these predicted frames into these networks, they can be used as simulations of pedestrians as indicated by our results. Such trained networks can later be used to predict pedestrian behaviors even from the perspective of the autonomous car. Another future extension will be to re-train these networks with real-world video data.