Event-based Vision meets Deep Learning on Steering Prediction for Self-driving Cars
This work addresses the challenge of reliable motion estimation for self-driving cars in adverse conditions, representing an incremental improvement by adapting existing deep learning methods to a new sensor type.
The paper tackles the problem of predicting steering angles for self-driving cars using event cameras, a bio-inspired vision sensor, by adapting deep neural networks to event sensor outputs, and demonstrates robust performance in challenging conditions like poor illumination and fast motion, outperforming state-of-the-art standard camera-based algorithms on a large-scale dataset of ~1000 km.
Event cameras are bio-inspired vision sensors that naturally capture the dynamics of a scene, filtering out redundant information. This paper presents a deep neural network approach that unlocks the potential of event cameras on a challenging motion-estimation task: prediction of a vehicle's steering angle. To make the best out of this sensor-algorithm combination, we adapt state-of-the-art convolutional architectures to the output of event sensors and extensively evaluate the performance of our approach on a publicly available large scale event-camera dataset (~1000 km). We present qualitative and quantitative explanations of why event cameras allow robust steering prediction even in cases where traditional cameras fail, e.g. challenging illumination conditions and fast motion. Finally, we demonstrate the advantages of leveraging transfer learning from traditional to event-based vision, and show that our approach outperforms state-of-the-art algorithms based on standard cameras.