We identify the need for a gamified self-driving simulator where game mechanics encourage high-quality data capture, and design and apply such a simulator to collecting lane-following training data. The resulting synthetic data enables a Convolutional Neural Network (CNN) to drive an in-game vehicle. We simultaneously develop a physical test platform based on a radio-controlled vehicle and the Robotic Operating System (ROS) and successfully transfer the simulation-trained model to the physical domain without modification. The cross-platform simulator facilitates unsupervised crowdsourcing, helping to collect diverse data emulating complex, dynamic environment data, infrequent events, and edge cases. The physical platform provides a low-cost solution for validating simulation-trained models or enabling rapid transfer learning, thereby improving the safety and resilience of self-driving algorithms.
@article{arxiv.1911.07759,
title = {A gamified simulator and physical platform for self-driving algorithm training and validation},
author = {Joshua E. Siegel and Georgios Pappas and Konstantinos Politopoulos and Yongbin Sun},
journal= {arXiv preprint arXiv:1911.07759},
year = {2019}
}