Towards closing the generalization gap in autonomous driving
OA Version
Citation
Abstract
Autonomous driving research faces significant challenges in transitioning from simulation-based evaluations to real-world implementations. While simulation environments offer controlled settings for training driving agents, real-world scenarios introduce unforeseen complexities crucial for assessing the robustness and adaptability of these agents. This study addresses two pivotal questions in autonomous driving research: (1) the translation of simulated experiences to a real-world environment, and (2) the correlation between offline evaluation metrics and closed-loop driving performance To address the first question, we employ a novel method using pre-trained foundation models to abstract vision input. This allows us to train driving policies in simulation and assess their performance with real-world data, investigating the effectiveness of Sim2Real for driving scenarios. For the second question, we analyze the relationship between a selected set of offline metrics and established closed-loop metrics in both simulation and real-world contexts. By comparing their performance, we aim to ascertain the efficacy of offline evaluations in predicting closed-loop driving behavior. Our research aims to bridge the gap between simulation and real-world environments, understanding the efficacy of open-loop evaluation in autonomous driving.
Description
2024