Pub Date : 2024-03-01DOI: 10.1109/TIV.2024.3434129
{"title":"Share Your Preprint Research with the World!","authors":"","doi":"10.1109/TIV.2024.3434129","DOIUrl":"https://doi.org/10.1109/TIV.2024.3434129","url":null,"abstract":"","PeriodicalId":36532,"journal":{"name":"IEEE Transactions on Intelligent Vehicles","volume":"9 5","pages":"5004-5004"},"PeriodicalIF":14.0,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10613473","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141964758","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-01DOI: 10.1109/TIV.2024.3415410
Weishan Zhang;Baoyu Zhang;Xiaofeng Jia;Hongwei Qi;Rui Qin;Juanjuan Li;Yonglin Tian;Xiaolong Liang;Fei-Yue Wang
This letter is a brief summary of a series of IEEE TIV's decentralized and hybrid workshops (DHWs) on Federated Intelligence for Intelligent Vehicles. The discussed results are: 1) Different scales of large models (LMs) can be federated and deployed on IVs, and three types of federated collaboration between large and small models can be adopted for IVs. 2) Federated fine-tuning of LMs is beneficial for IVs data security. 3) The sustainability of IVs can be improved through optimizing existing models and continuous learning using federated intelligence. 4) LM-enhanced knowledge can make IVs smarter.
{"title":"Federated Intelligence for Intelligent Vehicles","authors":"Weishan Zhang;Baoyu Zhang;Xiaofeng Jia;Hongwei Qi;Rui Qin;Juanjuan Li;Yonglin Tian;Xiaolong Liang;Fei-Yue Wang","doi":"10.1109/TIV.2024.3415410","DOIUrl":"https://doi.org/10.1109/TIV.2024.3415410","url":null,"abstract":"This letter is a brief summary of a series of IEEE TIV's decentralized and hybrid workshops (DHWs) on Federated Intelligence for Intelligent Vehicles. The discussed results are: 1) Different scales of large models (LMs) can be federated and deployed on IVs, and three types of federated collaboration between large and small models can be adopted for IVs. 2) Federated fine-tuning of LMs is beneficial for IVs data security. 3) The sustainability of IVs can be improved through optimizing existing models and continuous learning using federated intelligence. 4) LM-enhanced knowledge can make IVs smarter.","PeriodicalId":36532,"journal":{"name":"IEEE Transactions on Intelligent Vehicles","volume":"9 5","pages":"4835-4839"},"PeriodicalIF":14.0,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141965566","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-01DOI: 10.1109/TIV.2024.3415815
Yueyuan Li;Songan Zhang;Mingyang Jiang;Xingyuan Chen;Jing Yang;Yeqiang Qian;Chunxiang Wang;Ming Yang
Simulators generate diverse and realistic traffic scenarios to boost the development of autonomous driving systems. However, existing simulators often fall short in scenario diversity and interactive behavior models for traffic participants. This deficiency underscores the need for a flexible, reliable, user-friendly open-source simulator. Addressing this challenge, Tactics2D provides a highly modular and extensive framework for traffic scenario construction, encompassing road elements, traffic regulations, behavior models, physics simulations for vehicles, and event detection mechanisms. By integrating numerous popular algorithms and models, Tactics2D empowers users to customize driving scenarios and evaluate model performance across various scenarios by leveraging both public datasets and user-collected real-world data. This letter results from discussions at several IEEE T-IV's Decentralized and Hybrid Workshops on Scenarios Engineering for Smart Mobility.
{"title":"Tactics2D: A Highly Modular and Extensible Simulator for Driving Decision-Making","authors":"Yueyuan Li;Songan Zhang;Mingyang Jiang;Xingyuan Chen;Jing Yang;Yeqiang Qian;Chunxiang Wang;Ming Yang","doi":"10.1109/TIV.2024.3415815","DOIUrl":"https://doi.org/10.1109/TIV.2024.3415815","url":null,"abstract":"Simulators generate diverse and realistic traffic scenarios to boost the development of autonomous driving systems. However, existing simulators often fall short in scenario diversity and interactive behavior models for traffic participants. This deficiency underscores the need for a flexible, reliable, user-friendly open-source simulator. Addressing this challenge, Tactics2D provides a highly modular and extensive framework for traffic scenario construction, encompassing road elements, traffic regulations, behavior models, physics simulations for vehicles, and event detection mechanisms. By integrating numerous popular algorithms and models, Tactics2D empowers users to customize driving scenarios and evaluate model performance across various scenarios by leveraging both public datasets and user-collected real-world data. This letter results from discussions at several IEEE T-IV's Decentralized and Hybrid Workshops on Scenarios Engineering for Smart Mobility.","PeriodicalId":36532,"journal":{"name":"IEEE Transactions on Intelligent Vehicles","volume":"9 5","pages":"4840-4844"},"PeriodicalIF":14.0,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141964745","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-01DOI: 10.1109/TIV.2024.3426519
Fei-Yue Wang
The current issue includes 2 perspectives, 2 letters, and 12 regular papers. These perspectives explore critical issues within the field of IVs and pontential research directions based on the evolution of foundation models.
本期包括 2 篇观点、2 封来信和 12 篇常规论文。这些观点探讨了 IV 领域的关键问题以及基于基础模型演变的潜在研究方向。
{"title":"From RAG/RAT to SAGE: Parallel Driving for Smart Mobility","authors":"Fei-Yue Wang","doi":"10.1109/TIV.2024.3426519","DOIUrl":"https://doi.org/10.1109/TIV.2024.3426519","url":null,"abstract":"The current issue includes 2 perspectives, 2 letters, and 12 regular papers. These perspectives explore critical issues within the field of IVs and pontential research directions based on the evolution of foundation models.","PeriodicalId":36532,"journal":{"name":"IEEE Transactions on Intelligent Vehicles","volume":"9 5","pages":"4821-4825"},"PeriodicalIF":14.0,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141964753","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With advancements in computer technology, the benefits of embodied intelligence are increasingly evident. This interactive learning model allows AI to be more flexibly deployed across diverse fields. Recent developments in multi-modal large language models (LLMs) have accelerated AI progress, especially in autonomous driving. This perspective highlights how embodied intelligence can enhance LLM applications in the mining industry, presenting new opportunities and potential to revolutionize the field. It also examines the challenges of deploying embodied agents in mining and offers insights into future research and development.
{"title":"Embodied Intelligence in Mining: Leveraging Multi-Modal Large Language Models for Autonomous Driving in Mines","authors":"Luxi Li;Yuchen Li;Xiaotong Zhang;Yuhang He;Jianjian Yang;Bin Tian;Yunfeng Ai;Lingxi Li;Andreas Nüchter;Zhe Xuanyuan","doi":"10.1109/TIV.2024.3417938","DOIUrl":"https://doi.org/10.1109/TIV.2024.3417938","url":null,"abstract":"With advancements in computer technology, the benefits of embodied intelligence are increasingly evident. This interactive learning model allows AI to be more flexibly deployed across diverse fields. Recent developments in multi-modal large language models (LLMs) have accelerated AI progress, especially in autonomous driving. This perspective highlights how embodied intelligence can enhance LLM applications in the mining industry, presenting new opportunities and potential to revolutionize the field. It also examines the challenges of deploying embodied agents in mining and offers insights into future research and development.","PeriodicalId":36532,"journal":{"name":"IEEE Transactions on Intelligent Vehicles","volume":"9 5","pages":"4831-4834"},"PeriodicalIF":14.0,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141965565","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-01DOI: 10.1109/TIV.2024.3384835
Hui Yu;Wei Liang;Lili Fan;Yutong Wang;Fei-Yue Wang
Artificial technologies have made rapid progress and achieved various superior tasks in the past few years, including but not limited to classification, detection, image generation and data processing. Particularly, the very recent emerging Sora has demonstrated the exceptional ability of text-to-video generation lasting for 1 minute long with impressive quality. It provides a huge potential for many new applications across industries, especially social interaction in intelligent vehicles. The emergence of innovative intelligence vehicle applications has given rise to novel requirements for social and human-vehicle interaction within the associated contexts, where Sora and social vision could play an important role. In this perspective, we present a new Social Interaction framework based on Sora and parallel intelligence in intelligent vehicles and provide a novel perspective for conducting new social and human-vehicle interaction in the context of intelligent vehicles.
在过去几年里，人工技术取得了突飞猛进的发展，完成了各种卓越的任务，包括但不限于分类、检测、图像生成和数据处理。特别是最近新出现的 Sora，它已经展示了从文字到视频的超强生成能力，可持续 1 分钟之久，质量令人印象深刻。它为各行各业的许多新应用提供了巨大的潜力，尤其是智能汽车中的社交互动。创新型智能汽车应用的出现对相关环境中的社交和人车互动提出了新的要求，而 Sora 和社交视觉可以在其中发挥重要作用。从这个角度出发，我们提出了一个基于智能汽车中的 Sora 和并行智能的新型社交互动框架，并为在智能汽车背景下开展新型社交和人车互动提供了一个新的视角。
{"title":"Sora for Social Vision With Parallel Intelligence: Social Interaction in Intelligent Vehicles","authors":"Hui Yu;Wei Liang;Lili Fan;Yutong Wang;Fei-Yue Wang","doi":"10.1109/TIV.2024.3384835","DOIUrl":"https://doi.org/10.1109/TIV.2024.3384835","url":null,"abstract":"Artificial technologies have made rapid progress and achieved various superior tasks in the past few years, including but not limited to classification, detection, image generation and data processing. Particularly, the very recent emerging Sora has demonstrated the exceptional ability of text-to-video generation lasting for 1 minute long with impressive quality. It provides a huge potential for many new applications across industries, especially social interaction in intelligent vehicles. The emergence of innovative intelligence vehicle applications has given rise to novel requirements for social and human-vehicle interaction within the associated contexts, where Sora and social vision could play an important role. In this perspective, we present a new Social Interaction framework based on Sora and parallel intelligence in intelligent vehicles and provide a novel perspective for conducting new social and human-vehicle interaction in the context of intelligent vehicles.","PeriodicalId":36532,"journal":{"name":"IEEE Transactions on Intelligent Vehicles","volume":"9 3","pages":"4240-4243"},"PeriodicalIF":8.2,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140820323","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-01DOI: 10.1109/TIV.2024.3388848
Lili Fan;Xingxia Wang;Jing Yang;Yuhang Liu;Chen Lv;Hui Yu;Jiaqi Ma;Fei-Yue Wang
The low-altitude economy is playing a crucial role in promoting economic development, strengthening social security, and serving international security, thus becoming an increasingly vital engine for global development. As an essential technological backbone and application carrier of the low-altitude economy, intelligent vehicles are not only active on land but also increasingly needed to actively participate in the air and water. The integration of social radars and social vision will enable intelligent vehicles to perceive complex scenarios and task demands from a human perspective, providing more efficient and safer services for the low-altitude economy. This presents an exciting prospect for the application of social radars and social vision, as well as their integration with intelligent vehicles for envisaged service scenarios in the low-altitude economy.
{"title":"Social Radars for Social Vision of Intelligent Vehicles: A New Direction for Vehicle Research and Development","authors":"Lili Fan;Xingxia Wang;Jing Yang;Yuhang Liu;Chen Lv;Hui Yu;Jiaqi Ma;Fei-Yue Wang","doi":"10.1109/TIV.2024.3388848","DOIUrl":"https://doi.org/10.1109/TIV.2024.3388848","url":null,"abstract":"The low-altitude economy is playing a crucial role in promoting economic development, strengthening social security, and serving international security, thus becoming an increasingly vital engine for global development. As an essential technological backbone and application carrier of the low-altitude economy, intelligent vehicles are not only active on land but also increasingly needed to actively participate in the air and water. The integration of social radars and social vision will enable intelligent vehicles to perceive complex scenarios and task demands from a human perspective, providing more efficient and safer services for the low-altitude economy. This presents an exciting prospect for the application of social radars and social vision, as well as their integration with intelligent vehicles for envisaged service scenarios in the low-altitude economy.","PeriodicalId":36532,"journal":{"name":"IEEE Transactions on Intelligent Vehicles","volume":"9 3","pages":"4244-4248"},"PeriodicalIF":8.2,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140820421","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-01DOI: 10.1109/TIV.2024.3422002
Jingqiu Guo;Long Chen;Lingxi Li;Xiaoxiang Na;Ljubo Vlacic;Fei-Yue Wang
Advanced Air Mobility (AAM) envisages a sustainable, safe, convenient, and affordable air transport system. In socio-technical transition of AAM, there are a number of trade-offs in ecosystem that need to be studied. Three perspectives on economic feasibility are explored: first, based on history of VTOL services and value of time estimates, we discuss whether AAM can provide customers with competitive mobility services; second, what are the stakeholders’ insights on the deployment of AAM; last, the experience in the development of autonomous driving technology, such as parallel intelligence, can inform future AAM research.
{"title":"Exploring the Economic Feasibility of Advanced Air Mobility in the Early Stages","authors":"Jingqiu Guo;Long Chen;Lingxi Li;Xiaoxiang Na;Ljubo Vlacic;Fei-Yue Wang","doi":"10.1109/TIV.2024.3422002","DOIUrl":"https://doi.org/10.1109/TIV.2024.3422002","url":null,"abstract":"Advanced Air Mobility (AAM) envisages a sustainable, safe, convenient, and affordable air transport system. In socio-technical transition of AAM, there are a number of trade-offs in ecosystem that need to be studied. Three perspectives on economic feasibility are explored: first, based on history of VTOL services and value of time estimates, we discuss whether AAM can provide customers with competitive mobility services; second, what are the stakeholders’ insights on the deployment of AAM; last, the experience in the development of autonomous driving technology, such as parallel intelligence, can inform future AAM research.","PeriodicalId":36532,"journal":{"name":"IEEE Transactions on Intelligent Vehicles","volume":"9 5","pages":"4826-4830"},"PeriodicalIF":14.0,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141966050","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：