A gamified simulator and physical platform for self-driving algorithm training and validation
This provides a low-cost solution for improving the safety and resilience of self-driving algorithms through unsupervised crowdsourcing and cross-platform validation, though it is incremental in combining existing simulation and physical testing methods.
The authors tackled the need for high-quality training data for self-driving algorithms by developing a gamified simulator that collects synthetic lane-following data, enabling a CNN to drive in-game, and they successfully transferred this model to a low-cost physical RC vehicle platform without modification.
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.