C-V2X Resource Deployment Architecture Based on Moving Network Convoys

Lakshminarasimhan, Venkatnarayanan; Knoll, Alois

doi:10.1109/vtc2020-spring48590.2020.9128410

Cited by 8 publications

(5 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on the real world Intelligent Transportation System (ITS) Providentia [14], [15], [16], [17], we have extended the test bed into urban areas in the follow-up project Prov-identia++. On a total length of 3.5 km, the ITS is located at the autobahn A9 as well as the highway B471 near Munich.…”

Section: A Test Bedmentioning

confidence: 99%

A9-Dataset: Multi-Sensor Infrastructure-Based Dataset for Mobility Research

Christian¹,

Zimmer²,

Strand³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Data-intensive machine learning based techniques increasingly play a prominent role in the development of future mobility solutions -from driver assistance and automation functions in vehicles, to real-time traffic management systems realized through dedicated infrastructure. The availability of high quality real-world data is often an important prerequisite for the development and reliable deployment of such systems in large scale. Towards this endeavour, we present the A9-Dataset based on roadside sensor infrastructure from the 3 km long Providentia++ test field near Munich in Germany. The dataset includes anonymized and precision-timestamped multi-modal sensor and object data in high resolution, covering a variety of traffic situations. As part of the first set of data, which we describe in this paper, we provide camera and LiDAR frames from two overhead gantry bridges on the A9 autobahn with the corresponding objects labeled with 3D bounding boxes. The first set includes in total more than 1000 sensor frames and 14000 traffic objects. The dataset is available for download at https://a9-dataset.com.

show abstract

Section: A Test Bedmentioning

confidence: 99%

A9-Dataset: Multi-Sensor Infrastructure-Based Dataset for Mobility Research

Christian¹,

Zimmer²,

Strand³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…To achieve joint learning in a federated fashion, especially wireless communication networks for sharing the locally training results across infrastructure are required. Specifically, deployment of C-V2X networks [4] according to corresponding standards [5] facilities federated learning in C-ITS, where many traffic services and applications need to be developed based on DNN models, e.g., ResNet [6], V2X-ViT [7], etc., for traffic object recognition and detection functions. In this context, [8]- [10] indicate the great potential benefits of federated learning in C-ITS.…”

Section: Related Workmentioning

confidence: 99%

Federated Learning Framework Coping with Hierarchical Heterogeneity in Cooperative ITS

Song¹,

Zhou²,

Lakshminarasimhan³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Deep learning is a key approach for the environment perception function of Cooperative Intelligent Transportation Systems (C-ITS) with autonomous vehicles and smart traffic infrastructure. The performance of the object recognition and detection strongly depends on the data volume in the model training, which is usually not sufficient due to the limited data collected by a typically small fleet of test vehicles. In today's C-ITS, smart traffic participants are capable of timely generating and transmitting a large amount of data. However, these data can not be used for model training directly due to privacy constraints. In this paper, we introduce a federated learning framework coping with Hierarchical Heterogeneity (H 2 -Fed), which can notably enhance the conventional pretrained deep learning model. The framework exploits data from connected public traffic agents in vehicular networks without affecting user data privacy. By coordinating existing traffic infrastructure, including roadside units and road traffic clouds, the model parameters are efficiently disseminated by vehicular communications and hierarchically aggregated. Considering the individual heterogeneity of data distribution, computational and communication capabilities across traffic agents and roadside units, we employ a novel method that addresses the heterogeneity in different aggregation layers of the framework architecture, i.e., aggregation in layers of roadside units and cloud. The experimental results indicate that our method can well balance the learning accuracy and stability according to the knowledge of heterogeneity in current communication networks. Compared to other baseline approaches, the evaluation on a Non-IID MNIST dataset shows that our framework is more general and capable especially in application scenarios with low communication quality. Even when 90% of the agents are timely disconnected, the pre-trained deep learning model can still be forced to converge stably, and its accuracy can be enhanced from 68% to over 90% after convergence.

show abstract

“…In the end, the backend receives the local twins of the RSU and has combined it again to a global digital twin across all measuring points. With this, the ITS of Providentia has created digital twins which combine the advantages of radar and camera from different perspectives [78]- [80]. In 2020, the follow-up project Providentia++ has extended the ITS into urban areas.…”

Section: Creation Digital Twinsmentioning

confidence: 99%

Intelligent Transportation Systems Using External Infrastructure: A Literature Survey

Christian¹,

Bing²,

Knoll³

2021

Preprint

View full text Add to dashboard Cite

Increasing problems in the transportation segment are accidents, bad traffic flow and pollution. The Intelligent Transportation System with the use of external infrastructure (ITS) can tackle these problems. To the best of our knowledge, there exists no current systematic review of the existing solutions. To fill this knowledge gap, this paper provides an overview about existing ITS which use external infrastructure. Furthermore, this paper discovers the currently not adequately answered research questions. For this reason, we performed a literature review to documents, which describes existing ITS solutions since 2009 until today. We categorized the results according to his technology level and analyzed their properties. Thereby, we made the several ITS comparable and highlighted the past development as well as the current trends. According to the mentioned method, we analyzed more than 346 papers, which includes 40 test bed projects. In summary, the current ITS can deliver high accurate information about individuals in traffic situations in real-time. However, further research in ITS should focus on more reliable perception of the traffic with the use of modern sensors, plug and play mechanism as well as secure realtime distribution in decentralized manner for a high amount of data. With addressing these topics, the development of Intelligent Transportation Systems is in a correction direction for the comprehensive roll-out.

show abstract

C-V2X Resource Deployment Architecture Based on Moving Network Convoys

Cited by 8 publications

References 9 publications

A9-Dataset: Multi-Sensor Infrastructure-Based Dataset for Mobility Research

A9-Dataset: Multi-Sensor Infrastructure-Based Dataset for Mobility Research

Federated Learning Framework Coping with Hierarchical Heterogeneity in Cooperative ITS

Intelligent Transportation Systems Using External Infrastructure: A Literature Survey

Contact Info

Product

Resources

About