Research papers · Posted 2024.04.16 · Publication / acceptance: author-reported
End-To-End Training and Testing Gamification Framework to Learn Human Highway Driving
End-To-End Training and Testing Gamification Framework to Learn Human Highway Driving
Overview
This framework collects labeled highway-driving data in GTA V and learns image-to-steering and throttle commands. In-game closed-loop tests examine lane keeping and collision avoidance as a simulation-based training and testing example.
Publication and version information
Publication, acceptance or venue information is author-reported on arXiv. The exact source wording is preserved below.
Author-supplied source information
Author-supplied information on arXiv.
Accepted by ITSC
Version: arXiv v2 — manuscript revision