Enhance Sample Efficiency and Robustness of End-to-End Urban Autonomous Driving via Semantic Masked World Model
IEEE Transactions on Intelligent Transportation Systems · 2024-10 · 25 (10) · 13067-13079
DOI: 10.1109/tits.2024.3400227 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Intelligent Transportation Systems, 2024-10. Verfasst von Zeyu Gao und 6 weiteren Autor:innen. Die Arbeit wurde bisher 36-mal zitiert (Crossref) und nennt 40 Literaturangaben. Gefördert von: National Key Research and Development Plan of China, Tsinghua University Initiative Scientific Research Program, NSF China, Beijing NSF.
Abstract (Originalsprache)
End-to-end autonomous driving provides a feasible way to automatically maximize overall driving system performance by directly mapping the raw pixels from a front-facing camera to control signals. Recent advanced methods construct a latent world model to map the high dimensional observations into compact latent space. However, the latent states embedded by the world model proposed in previous works may contain a large amount of task-irrelevant information, resulting in low sampling efficiency and poor robustness to input perturbations. Meanwhile, the training data distribution is usually unbalanced, and the learned policy is challenging to cope with the corner cases during the driving process. To solve the above challenges, we present a SEMantic Masked recurrent world model (SEM2), which introduces a semantic filter to extract key driving-relevant features and make decisions via the filtered features, and is trained with a multi-source data sampler, which aggregates common data and multiple corner case data in a single batch, to balance the data distribution. Extensive experiments on CARLA show our method outperforms the state-of-the-art approaches in terms of sample efficiency and robustness to input permutations.
Förderung
- National Key Research and Development Plan of China
- Tsinghua University Initiative Scientific Research Program, NSF China
- Beijing NSF
- Strategic Priority Research Program of the Chinese Academy of Sciences
Zitieren
APA
Gao, Z., Mu, Y., Chen, C., Duan, J., Luo, P., Lu, Y., & Li, S. E. (2024). Enhance Sample Efficiency and Robustness of End-to-End Urban Autonomous Driving via Semantic Masked World Model. IEEE Transactions on Intelligent Transportation Systems, 25(10), 13067-13079. https://doi.org/10.1109/tits.2024.3400227
Vancouver
Gao Z, Mu Y, Chen C, Duan J, Luo P, Lu Y, et al. Enhance Sample Efficiency and Robustness of End-to-End Urban Autonomous Driving via Semantic Masked World Model. IEEE Transactions on Intelligent Transportation Systems. 2024;25(10):13067-13079. doi:10.1109/tits.2024.3400227
BibTeX
@article{Gao2024,
author = {Gao, Zeyu and Mu, Yao and Chen, Chen and Duan, Jingliang and Luo, Ping and Lu, Yanfeng and Li, Shengbo Eben},
title = {Enhance Sample Efficiency and Robustness of End-to-End Urban Autonomous Driving via Semantic Masked World Model},
journal = {IEEE Transactions on Intelligent Transportation Systems},
year = {2024},
volume = {25},
number = {10},
pages = {13067--13079},
doi = {10.1109/tits.2024.3400227}
}
EUVIMED