Bayesian optimization and deep learning for steering wheel angle prediction

Abstract

Automated driving systems (ADS) have undergone a significant improvement in the last years. ADS and more precisely self-driving cars technologies will change the way we perceive and know the world of transportation systems in terms of user experience, mode choices and business models. The emerging field of Deep Learning (DL) has been successfully applied for the development of innovative ADS solutions. However, the attempt to single out the best deep neural network architecture and tuning its hyperparameters are all expensive processes, both in terms of time and computational resources. In this work, Bayesian optimization (BO) is used to optimize the hyperparameters of a Spatiotemporal-Long Short Term Memory (ST-LSTM) network with the aim to obtain an accurate model for the prediction of the steering angle in a ADS. BO was able to identify, within a limited number of trials, a model—namely BO_ST-LSTM—which resulted, on a public dataset, the most accurate when compared to classical end-to-end driving models.

Memory based neural networks for end-to-end autonomous driving

“…Vision based end-to-end autonomous driving have gained significant attraction in recent literature. Vision is an integral segment of accumulating exteroceptive information about the surrounding environment of the vehicle [4], [10], [13], [14], [16], [18], [19], [21], [23]. Using vision for end-to-end control of autonomous vehicles was proposed by NVIDIA's PilotNet [4] framework where the goal was to deliver steering and control commands based on raw frontal images with the help of a CNN.…”