Sora for Hierarchical Parallel Motion Planner: A Safe End-to-End Method Against OOD Events

IF 14 1区工程技术 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

IEEE Transactions on Intelligent Vehicles Pub Date : 2024-04-01 DOI:10.1109/TIV.2024.3392647

Siyu Teng;Ran Yan;Xiaotong Zhang;Yuchen Li;Xingxia Wang;Yutong Wang;Yonglin Tian;Hui Yu;Lingxi Li;Long Chen;Fei-Yue Wang

{"title":"Sora for Hierarchical Parallel Motion Planner: A Safe End-to-End Method Against OOD Events","authors":"Siyu Teng;Ran Yan;Xiaotong Zhang;Yuchen Li;Xingxia Wang;Yutong Wang;Yonglin Tian;Hui Yu;Lingxi Li;Long Chen;Fei-Yue Wang","doi":"10.1109/TIV.2024.3392647","DOIUrl":null,"url":null,"abstract":"End-to-end motion planners have shown great potential for enabling fully autonomous driving. However, when facing out-of-distribution (OOD) events, these planners might not guarantee the optimal prediction of control commands. To better enhance safety, an end-to-end method that benefits robust and general policy learning from potential OOD events is urgently desirable. In this perspective, Sore4PMP, a hierarchical parallel motion planner, is presented as a suitable solution. Based on raw perception data and descriptive prompts, Sore4PMP can first leverage the advanced generative capabilities of Sora to generate virtual OOD events, and then integrate these events into the decision-making process, thereby enhancing the robustness and generalization of autonomous vehicles (AVs) in emergency scenarios. With a comprehensive outlook, this perspective aims to provide a potential direction for the development of foundation models coupled with autonomous driving and finally promote the safety, efficiency, reliability, and sustainability of AVs.","PeriodicalId":36532,"journal":{"name":"IEEE Transactions on Intelligent Vehicles","volume":"9 4","pages":"4573-4576"},"PeriodicalIF":14.0000,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Intelligent Vehicles","FirstCategoryId":"5","ListUrlMain":"https://ieeexplore.ieee.org/document/10517427/","RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}

引用次数: 0

Abstract

End-to-end motion planners have shown great potential for enabling fully autonomous driving. However, when facing out-of-distribution (OOD) events, these planners might not guarantee the optimal prediction of control commands. To better enhance safety, an end-to-end method that benefits robust and general policy learning from potential OOD events is urgently desirable. In this perspective, Sore4PMP, a hierarchical parallel motion planner, is presented as a suitable solution. Based on raw perception data and descriptive prompts, Sore4PMP can first leverage the advanced generative capabilities of Sora to generate virtual OOD events, and then integrate these events into the decision-making process, thereby enhancing the robustness and generalization of autonomous vehicles (AVs) in emergency scenarios. With a comprehensive outlook, this perspective aims to provide a potential direction for the development of foundation models coupled with autonomous driving and finally promote the safety, efficiency, reliability, and sustainability of AVs.

查看原文本刊更多论文

分层平行运动规划器 Sora：针对 OOD 事件的安全端到端方法

端到端运动规划器在实现完全自主驾驶方面展现出巨大潜力。然而，当面临失控（OOD）事件时，这些规划器可能无法保证控制指令的最优预测。为了更好地提高安全性，迫切需要一种能从潜在的 OOD 事件中获得稳健而通用的策略学习的端到端方法。从这个角度出发，分层并行运动规划器 Sore4PMP 就是一个合适的解决方案。基于原始感知数据和描述性提示，Sore4PMP 可首先利用 Sora 的高级生成功能生成虚拟 OOD 事件，然后将这些事件整合到决策过程中，从而增强自动驾驶汽车（AV）在紧急情况下的鲁棒性和通用性。本视角以全面的视角，旨在为与自动驾驶相结合的基础模型的发展提供一个潜在的方向，并最终促进自动驾驶汽车的安全性、效率、可靠性和可持续性。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

IEEE Transactions on Intelligent Vehicles Mathematics-Control and Optimization

CiteScore

12.10

自引率

13.40%

发文量

177

期刊介绍： The IEEE Transactions on Intelligent Vehicles (T-IV) is a premier platform for publishing peer-reviewed articles that present innovative research concepts, application results, significant theoretical findings, and application case studies in the field of intelligent vehicles. With a particular emphasis on automated vehicles within roadway environments, T-IV aims to raise awareness of pressing research and application challenges. Our focus is on providing critical information to the intelligent vehicle community, serving as a dissemination vehicle for IEEE ITS Society members and others interested in learning about the state-of-the-art developments and progress in research and applications related to intelligent vehicles. Join us in advancing knowledge and innovation in this dynamic field.