Towards End-to-End Deep Learning for Autonomous Racing: On Data Collection and a Unified Architecture for Steering and Throttle Prediction
It addresses the complex problem of autonomous racing for researchers and developers, but the approach appears incremental as it builds on existing end-to-end learning methods.
This paper tackles autonomous racing by analyzing how training data affects the maximum speed for steering prediction and proposing a unified neural network architecture for predicting steering and throttle without feedback or recurrent connections, achieving successful application of DNNs at high speeds.
Deep Neural Networks (DNNs) which are trained end-to-end have been successfully applied to solve complex problems that we have not been able to solve in past decades. Autonomous driving is one of the most complex problems which is yet to be completely solved and autonomous racing adds more complexity and exciting challenges to this problem. Towards the challenge of applying end-to-end learning to autonomous racing, this paper shows results on two aspects: (1) Analyzing the relationship between the driving data used for training and the maximum speed at which the DNN can be successfully applied for predicting steering angle, (2) Neural network architecture and training methodology for learning steering and throttle without any feedback or recurrent connections.