Bayesian Optimization and Deep Learning forsteering wheel angle prediction
This work addresses the time and resource-intensive process of hyperparameter tuning in deep learning for automated driving, offering a more efficient solution for developers in this domain, though it is incremental as it applies an existing optimization method to a specific network architecture.
The authors tackled the problem of optimizing hyperparameters for a deep neural network used in automated driving systems, specifically for steering wheel angle prediction, by applying Bayesian Optimization to a Spatiotemporal-LSTM network, resulting in a model (BOST-LSTM) that achieved the highest accuracy on a public dataset compared to classical end-to-end driving models.
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 BOST-LSTM -- which resulted, on a public dataset, the most accurate when compared to classical end-to-end driving models.