arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.00866cs.AIcs.CL
收藏

基础CAN语言模型:一种用于汽车CAN数据的预训练语言模型

Foundation CAN LM: A Pretrained Language Model For Automotive CAN Data

Akiharu Esashi, Pawissanutt Lertpongrujikorn, Justin Makino, Yuibi Fujimoto, Mohsen Amini Salehi

AI总结:

本文提出基础CAN语言模型,通过预训练实现对汽车CAN数据的多目标下游泛化,推动汽车AI中的可泛化表征学习。

摘要:

控制器局域网络(CAN)总线提供了一种丰富的车辆信号源,越来越多地被用于汽车和汽车保险领域,包括碰撞检测、预测性维护和驾驶员风险建模。尽管有这种潜力,现有的流程大多在原始CAN数据上训练孤立的任务特定模型,仅有有限的努力探索了解码信号。这种碎片化阻止了共享表征学习并限制了跨任务泛化。相比之下,自然语言处理(NLP)和计算机视觉(CV)已通过基础模型范式得到转变:大规模预训练后进行任务特定适应。在本工作中,我们引入了基础CAN模型,通过单一预训练骨干展示多目标下游泛化。我们的方法将CAN数据视为一种语言:我们在大规模、无标签的解码CAN信号上进行预训练,并在异构汽车保险任务上进行微调。为了实现这一点,我们提出了一种统一的分词方案,用于混合离散-连续信号,并解决时间复杂性和行程特定变化的挑战。我们的结果表明,一个预训练的CAN模型可以有效地适应多样化的预测任务,验证了基础模型范式在NLP和CV中已被证明有效,也适用于CAN数据。这为汽车AI中的可泛化表征学习指明了新方向。

英文摘要:

The Controller Area Network (CAN) bus provides a rich source of vehicular signals increasingly leveraged for applications in automotive and auto insurance domains, including collision detection, predictive maintenance, and driver risk modeling. Despite this potential, existing pipelines largely train isolated task-specific models on raw CAN data, with only limited efforts exploring decoded signals. Such fragmentation prevents shared representation learning and limits cross-task generalization. By contrast, natural language processing (NLP) and computer vision (CV) have been transformed by the foundation model paradigm: large-scale pretraining followed by task-specific adaptation. In this work, we introduce the foundation CAN model that demonstrates multi-objective downstream generalization using a single pretrained backbone. Our approach treats CAN data as a language: we pretrain on large-scale, unlabeled decoded CAN signals and fine-tune across heterogeneous auto insurance tasks. To enable this, we propose a unified tokenization scheme for mixed discrete-continuous signals and address challenges of temporal complexity and trip-specific variability. Our results show that one pretrained CAN model can adapt effectively to diverse predictive tasks, validating that the foundation modeling paradigm, proven in NLP and CV, also holds for CAN data. This establishes a new direction for generalizable representation learning in automotive AI.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑