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


Other papers in the same session

Feedback protocols and a Shiny App for species distribution modelling

M. Figueira Pereira, D. Conesa, A. López-Quílez

Bayesian approaches for fairness in regression models

R. Jiménez Llamas, E. Carrizosa Priego, P. Ramirez Cobo


Cookie policy

We use cookies in order to be able to identify and authenticate you on the website. They are necessary for the correct functioning of it, and therefore they can not be disabled. If you continue browsing the website, you are agreeing with their acceptance, as well as our Privacy Policy.

Additionally, we use Google Analytics in order to analyze the website traffic. They also use cookies and you can accept or refuse them with the buttons below.

You can read more details about our Cookie Policy and our Privacy Policy.