From Simulation to Real World Maneuver Execution using Deep Reinforcement Learning
This addresses a critical issue for autonomous driving systems by improving maneuver planning, though it appears incremental as it builds on existing deep reinforcement learning methods.
The paper tackled the problem of domain adaptation between simulation and real-world data in autonomous driving, specifically for roundabout insertion maneuvers, and showed that their multi-environment training system increased generalization capabilities on unseen and real-world scenarios.
Deep Reinforcement Learning has proved to be able to solve many control tasks in different fields, but the behavior of these systems is not always as expected when deployed in real-world scenarios. This is mainly due to the lack of domain adaptation between simulated and real-world data together with the absence of distinction between train and test datasets. In this work, we investigate these problems in the autonomous driving field, especially for a maneuver planning module for roundabout insertions. In particular, we present a system based on multiple environments in which agents are trained simultaneously, evaluating the behavior of the model in different scenarios. Finally, we analyze techniques aimed at reducing the gap between simulated and real-world data showing that this increased the generalization capabilities of the system both on unseen and real-world scenarios.