Knowledge Commons of Institute of Automation,CAS
Parallel Data and Foundation Model Driven Closed-Loop of Autonomous Driving | |
Bin Tian1![]() ![]() ![]() ![]() | |
2024 | |
会议名称 | IEEE International Conference on Intelligent Transportation Systems |
会议日期 | SEP 24-27, 2024 |
会议地点 | Edmonton, Canada |
摘要 | Data closed loop plays a crucial role in autonomous
driving for application in real world. The research for data closed
loop on autonomous driving in urban scene have been conducted
in the past few decades. But there is not unified framework for
data closed loop related to autonomous driving in surface mine.
The scenes in surface mine, which are unstructured, complex,
changeable, and the objects in surface mine like rockfalls, which
are differ in thousands of ways, not only put forward high
generalization requirements for our perception system, but also
bring many unpredictable risk for autonomous driving. In this
work, we proposed a uniform framework of data closed loop
driven by large-scale foundation model for autonomous driving
in surface mine. Corner cases are predicted through hard scenes
in simulation system, which is a parallel system with real scene.
In addition, high quality data selection and deployment model
distillation are conducted by method base on foundation model.
This framework can not only improve the generalization ability
of the perception but also promote the efficiency for corner
case mining and has achieved good application for autonomous
driving in surface mine. |
收录类别 | EI |
七大方向——子方向分类 | 人工智能+交通 |
国重实验室规划方向分类 | 虚实融合与迁移学习 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/58530 |
专题 | 多模态人工智能系统全国重点实验室_平行智能技术与系统团队 |
通讯作者 | Tingting Yao; Ruiqi Song |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences 2.Hebei University of Engineering |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Bin Tian,Tingting Yao,Yisheng Lv,et al. Parallel Data and Foundation Model Driven Closed-Loop of Autonomous Driving[C],2024. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Parallel Data and Fo(5420KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论