Saved in:
Bibliographic Details
Main Authors: Zhang, Chuancheng, Wang, Zhenhao, Wang, Jiangcheng, Su, Kun, Lv, Qiang, Jiang, Bin, Hao, Kunkun, Wang, Wenyu
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.12055
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914025035530240
author Zhang, Chuancheng
Wang, Zhenhao
Wang, Jiangcheng
Su, Kun
Lv, Qiang
Jiang, Bin
Hao, Kunkun
Wang, Wenyu
author_facet Zhang, Chuancheng
Wang, Zhenhao
Wang, Jiangcheng
Su, Kun
Lv, Qiang
Jiang, Bin
Hao, Kunkun
Wang, Wenyu
contents Decision-making in long-tail scenarios is pivotal to autonomous-driving development, and realistic and challenging simulations play a crucial role in testing safety-critical situations. However, existing open-source datasets lack systematic coverage of long-tail scenes, and lane-change maneuvers being emblematic, rendering such data exceedingly scarce. To bridge this gap, we introduce a data mining framework that exhaustively analyzes two widely used datasets, NGSIM and INTERACTION, to identify sequences marked by hazardous behavior, thereby replenishing these neglected scenarios. Using Generative Adversarial Imitation Learning (GAIL) enhanced with Proximal Policy Optimization (PPO), and enriched by vehicular-environment interaction analytics, our method iteratively refines and parameterizes newly generated trajectories. Distinguished by a rationally adversarial and sensitivity-aware perspective, the approach optimizes the creation of challenging scenes. Experiments show that, compared to unfiltered data and baseline models, our method produces behaviors that are simultaneously both adversarial and natural, judged by collision frequency, acceleration profiles, and lane-change dynamics, offering constructive insights to amplifying long-tailed lane-change instances in datasets and advancing decision-making training.
format Preprint
id arxiv_https___arxiv_org_abs_2503_12055
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Generative Modeling for Adversarial Lane-Change Scenarios
Zhang, Chuancheng
Wang, Zhenhao
Wang, Jiangcheng
Su, Kun
Lv, Qiang
Jiang, Bin
Hao, Kunkun
Wang, Wenyu
Robotics
Decision-making in long-tail scenarios is pivotal to autonomous-driving development, and realistic and challenging simulations play a crucial role in testing safety-critical situations. However, existing open-source datasets lack systematic coverage of long-tail scenes, and lane-change maneuvers being emblematic, rendering such data exceedingly scarce. To bridge this gap, we introduce a data mining framework that exhaustively analyzes two widely used datasets, NGSIM and INTERACTION, to identify sequences marked by hazardous behavior, thereby replenishing these neglected scenarios. Using Generative Adversarial Imitation Learning (GAIL) enhanced with Proximal Policy Optimization (PPO), and enriched by vehicular-environment interaction analytics, our method iteratively refines and parameterizes newly generated trajectories. Distinguished by a rationally adversarial and sensitivity-aware perspective, the approach optimizes the creation of challenging scenes. Experiments show that, compared to unfiltered data and baseline models, our method produces behaviors that are simultaneously both adversarial and natural, judged by collision frequency, acceleration profiles, and lane-change dynamics, offering constructive insights to amplifying long-tailed lane-change instances in datasets and advancing decision-making training.
title Generative Modeling for Adversarial Lane-Change Scenarios
topic Robotics
url https://arxiv.org/abs/2503.12055