N. Klein, C. Hoffmann
End-to-end learners for autonomous driving are deep neural networks
that predict the instantaneous steering angle directly from images of the street
ahead. These learners must provide reliable uncertainty estimates for their
predictions in order to meet safety requirements and to initiate a switch to
manual control in areas of high uncertainty. However, end-to-end learners
typically only deliver point predictions, since distributional predictions are
associated with large increases in training time or additional computational
resources during prediction. To address this shortcoming, we investigate efficient
and scalable approximate inference for deep distributional regression.
It produces densities for the steering angle
that are marginally calibrated. To ensure the scalability to large n regimes, we develop efficient estimation based on variational
inference. We demonstrate the accuracy and speed on two end-to-end learners trained for highway driving.
Keywords: Calibration, deep neural network, implicit copula, neural linear models, probabilistic forecasting, uncertainty quantification, variational inference
Scheduled
GT11.BAYES2 Invited Session
November 7, 2023 6:40 PM
CC1: Audience