Multimodal End-to-End Learning for Autonomous Steering in Adverse Road and Weather Conditions
This addresses the problem of reliable autonomous driving in challenging real-world conditions for the automotive industry, but it is incremental as it builds on prior end-to-end learning methods.
The paper tackles autonomous steering in adverse road and weather conditions by extending end-to-end learning with multimodal data, showing that lidar improves performance in sensor-fusion models based on 28 hours of collected data.
Autonomous driving is challenging in adverse road and weather conditions in which there might not be lane lines, the road might be covered in snow and the visibility might be poor. We extend the previous work on end-to-end learning for autonomous steering to operate in these adverse real-life conditions with multimodal data. We collected 28 hours of driving data in several road and weather conditions and trained convolutional neural networks to predict the car steering wheel angle from front-facing color camera images and lidar range and reflectance data. We compared the CNN model performances based on the different modalities and our results show that the lidar modality improves the performances of different multimodal sensor-fusion models. We also performed on-road tests with different models and they support this observation.