Dynamically Conservative Self-Driving Planner for Long-Tail Cases
IEEE Transactions on Intelligent Transportation Systems · 2023-03 · 24 (3) · 3476-3488
DOI: 10.1109/tits.2022.3225538 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Intelligent Transportation Systems, 2023-03. Verfasst von Weitao Zhou und 5 weiteren Autor:innen. Die Arbeit wurde bisher 38-mal zitiert (Crossref) und nennt 39 Literaturangaben. Gefördert von: National Natural Science Foundation of China, China Postdoctoral Science Foundation, Tsinghua University-Toyota Joint Center.
Abstract (Originalsprache)
Self-driving vehicles (SDVs) are becoming reality but still suffer from “long-tail” challenges during natural driving: the SDVs will continually encounter rare, safety-critical cases that may not be included in the dataset they were trained. Some safety-assurance planners solve this problem by being conservative in all possible cases, which may significantly affect driving mobility. To this end, this work proposes a method to automatically adjust the conservative level according to each case’s “long-tail” rate, named dynamically conservative planner (DCP). We first define the “long-tail” rate as an SDV’s confidence to pass a driving case. The rate indicates the probability of safe-critical events and is estimated using the statistics bootstrapped method with historical data. Then, a reinforcement learning-based planner is designed to contain candidate policies with different conservative levels. The final policy is optimized based on the estimated “long-tail” rate. In this way, the DCP is designed to automatically adjust to be more conservative in low-confidence “long-tail” cases while keeping efficient otherwise. The DCP is evaluated in the CARLA simulator using driving cases with “long-tail” distributed training data. The results show that the DCP can accurately estimate the “long-tail” rate to identify potential risks. Based on the rate, the DCP automatically avoids potential collisions in “long-tail” cases using conservative decisions while not affecting the average velocity in other typical cases. Thus, the DCP is safer and more efficient than the baselines with fixed conservative levels, e.g., an always conservative planner. This work provides a technique to guarantee SDV’s performance in unexpected driving cases without resorting to a global conservative setting, which contributes to solving the “long-tail” problem practically.
Förderung
- National Natural Science Foundation of China
- China Postdoctoral Science Foundation
- Tsinghua University-Toyota Joint Center
Zitieren
APA
Zhou, W., Cao, Z., Deng, N., Liu, X., Jiang, K., & Yang, D. (2023). Dynamically Conservative Self-Driving Planner for Long-Tail Cases. IEEE Transactions on Intelligent Transportation Systems, 24(3), 3476-3488. https://doi.org/10.1109/tits.2022.3225538
Vancouver
Zhou W, Cao Z, Deng N, Liu X, Jiang K, Yang D. Dynamically Conservative Self-Driving Planner for Long-Tail Cases. IEEE Transactions on Intelligent Transportation Systems. 2023;24(3):3476-3488. doi:10.1109/tits.2022.3225538
BibTeX
@article{Zhou2023,
author = {Zhou, Weitao and Cao, Zhong and Deng, Nanshan and Liu, Xiaoyu and Jiang, Kun and Yang, Diange},
title = {Dynamically Conservative Self-Driving Planner for Long-Tail Cases},
journal = {IEEE Transactions on Intelligent Transportation Systems},
year = {2023},
volume = {24},
number = {3},
pages = {3476--3488},
doi = {10.1109/tits.2022.3225538}
}
EUVIMED