Self-Supervised Steering Angle Prediction for Vehicle Control Using Visual Odometry

Qadeer Khan, Patrick Wenzel, Daniel Cremers
Proceedings of The 24th International Conference on Artificial Intelligence and Statistics, PMLR 130:3781-3789, 2021.

Abstract

Vision-based learning methods for self-driving cars have primarily used supervised approaches that require a large number of labels for training. However, those labels are usually difficult and expensive to obtain. In this paper, we demonstrate how a model can be trained to control a vehicle’s trajectory using camera poses estimated through visual odometry methods in an entirely self-supervised fashion. We propose a scalable framework that leverages trajectory information from several different runs using a camera setup placed at the front of a car. Experimental results on the CARLA simulator demonstrate that our proposed approach performs at par with the model trained with supervision.

Cite this Paper


BibTeX
@InProceedings{pmlr-v130-khan21a, title = { Self-Supervised Steering Angle Prediction for Vehicle Control Using Visual Odometry }, author = {Khan, Qadeer and Wenzel, Patrick and Cremers, Daniel}, booktitle = {Proceedings of The 24th International Conference on Artificial Intelligence and Statistics}, pages = {3781--3789}, year = {2021}, editor = {Banerjee, Arindam and Fukumizu, Kenji}, volume = {130}, series = {Proceedings of Machine Learning Research}, month = {13--15 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v130/khan21a/khan21a.pdf}, url = {https://proceedings.mlr.press/v130/khan21a.html}, abstract = { Vision-based learning methods for self-driving cars have primarily used supervised approaches that require a large number of labels for training. However, those labels are usually difficult and expensive to obtain. In this paper, we demonstrate how a model can be trained to control a vehicle’s trajectory using camera poses estimated through visual odometry methods in an entirely self-supervised fashion. We propose a scalable framework that leverages trajectory information from several different runs using a camera setup placed at the front of a car. Experimental results on the CARLA simulator demonstrate that our proposed approach performs at par with the model trained with supervision. } }
Endnote
%0 Conference Paper %T Self-Supervised Steering Angle Prediction for Vehicle Control Using Visual Odometry %A Qadeer Khan %A Patrick Wenzel %A Daniel Cremers %B Proceedings of The 24th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2021 %E Arindam Banerjee %E Kenji Fukumizu %F pmlr-v130-khan21a %I PMLR %P 3781--3789 %U https://proceedings.mlr.press/v130/khan21a.html %V 130 %X Vision-based learning methods for self-driving cars have primarily used supervised approaches that require a large number of labels for training. However, those labels are usually difficult and expensive to obtain. In this paper, we demonstrate how a model can be trained to control a vehicle’s trajectory using camera poses estimated through visual odometry methods in an entirely self-supervised fashion. We propose a scalable framework that leverages trajectory information from several different runs using a camera setup placed at the front of a car. Experimental results on the CARLA simulator demonstrate that our proposed approach performs at par with the model trained with supervision.
APA
Khan, Q., Wenzel, P. & Cremers, D.. (2021). Self-Supervised Steering Angle Prediction for Vehicle Control Using Visual Odometry . Proceedings of The 24th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 130:3781-3789 Available from https://proceedings.mlr.press/v130/khan21a.html.

Related Material