Andreas Festag

Technische Hochschule Ingolstadt · Department of Electrical Engineering and Information Technology

Vehicles and road infrastructure are starting to be equipped with vehicle-to-everything (V2X) communication solutions to increase road safety and provide new services to drivers and passengers. In Europe, the deployment is based on a set of Release 1 standards developed by ETSI to support basic use cases for cooperative intelligent transport system...

Machine learning (ML) has revolutionized transportation systems, enabling autonomous driving and smart traffic services. Federated learning (FL) overcomes privacy constraints by training ML models in distributed systems, exchanging model parameters instead of raw data. However, the dynamic states of connected vehicles affect the network connection...

Sensor data sharing in V2X communication enables vehicles to exchange locally perceived sensor data with each other to increase their environmental awareness. It relies on the periodic exchange of selected, safety-relevant objects. Object selection is used to reduce channel resource usage. Additionally, vehicles use congestion control mechanisms to...

Bird's eye view (BEV) perception is becoming increasingly important in the field of autonomous driving. It uses multi-view camera data to learn a transformer model that directly projects the perception of the road environment onto the BEV perspective. However, training a transformer model often requires a large amount of data, and as camera data fo...

The efficiency of radio resource allocation and scheduling procedures in Cellular Vehicle-to-X (Cellular V2X) communication networks directly affects link quality in terms of latency and reliability. However, owing to the continuous movement of vehicles, it is impossible to have a centralized coordinating unit at all times to manage the allocation...

Bird's eye view (BEV) perception is becoming increasingly important in the field of autonomous driving. It uses multi-view camera data to learn a transformer model that directly projects the perception of the road environment onto the BEV perspective. However, training a transformer model often requires a large amount of data, and as camera data fo...

Federated learning allows for cooperative training among distributed clients by sharing their locally learned model parameters, such as weights or gradients. However, as model size increases, the communication bandwidth required for deployment in wireless networks becomes a bottleneck. To address this, we propose a residual-based federated learning...

Federated learning enables cooperative training among massively distributed clients by sharing their learned local model parameters. However, with increasing model size, deploying federated learning requires a large communication bandwidth, which limits its deployment in wireless networks. To address this bottleneck, we introduce a residual-based f...

The protection of vulnerable road users (VRUs) by means of V2X communication is increasingly considered for the next generation of cooperative safety systems. Two messaging protocols are being standardized: (i) With collective perception for sensor data sharing: VRUs can be passively perceived by the local sensors in vehicles and roadside units, wh...

Maneuver coordination for Connected and Automated Vehicles (CAVs) can be enhanced by vehicle-to-everything (V2X) communication. In order to disseminate planned maneuver intentions or requests, Maneuver Coordination Messages (MCMs) are exchanged between the CAVs that enable them to negotiate and perform cooperative maneuvers. In this way, V2X commun...

We introduce a novel federated learning framework, FedD3, which reduces the overall communication volume and with that opens up the concept of federated learning to more application scenarios in network-constrained environments. It achieves this by leveraging local dataset distillation instead of traditional learning approaches (i) to significantly...

Communication networks are becoming an increasingly important part of the mobility system. They allow traffic participants to be connected and to exchange information related to traffic and roads. The information exchange impacts the behavior of traffic participants, such as the selection of travel routes or their mobility dynamics. Considering inf...

Sensor data sharing in vehicular networks can significantly improve the range and accuracy of environmental perception for connected automated vehicles. Different concepts and schemes for dissemination and fusion of sensor data have been developed. It is common to these schemes that measurement errors of the sensors impair the perception quality an...

In this paper, we introduce a federated learning framework coping with Hierarchical Heterogeneity (H2-Fed), which can notably enhance the conventional pre-trained deep learning model. The framework exploits data from connected public traffic agents in vehicular networks without affecting user data privacy. By coordinating existing traffic infrastru...

Sensor data sharing enables vehicles to exchange locally perceived sensor data among each other and with the roadside infrastructure to increase their environmental awareness. It is commonly regarded as a next-generation vehicular communication service beyond the exchange of highly aggregated messages in the first generation. The approach is being...

Information sharing is essential for connected and automated driving and smart traffic driven by big data. It enables the acquisition of knowledge in cooperative intelligent transport systems (C-ITS), which ultimately increases the integrity and accuracy of road environmental data and thereby improves the efficiency and safety of the traffic system...

In smart cities, infrastructure-side sensors are already used to increase safety, to mitigate traffic congestion and to reduce pollution caused by vehicles. In the future, infrastructural safeguarding is expected to get a large potential due to availability of advanced infrastructure sensors(camera,radar,lidar) and vehicle-to-infrastructure(V2I) co...

Cellular Vehicle-to-X (Cellular V2X) is a communication technology that aims to facilitate the communication among vehicles and with the roadside infrastructure. Introduced with LTE Release 14, Cellular V2X enables device-to-device communication to support road safety and traffic efficiency applications. We present Artery-C, a simulation framework...

Safe and reliable operation of future autonomous vehicles requires ultra-low latency vehicle-to-vehicle (V2V) networking. However, due to scalability issues of purely ad hoc network, vehicle-to-infrastructure (V2I) communication is still in demand. To avoid interference between V2V and V2I communications, conventional network association such as ha...

ITS-G5 is a communication system for vehicle-to-everything communication for road safety and traffic efficiency applications. On the lower layers, it is based on IEEE 802.11 standard and uses a simple ad hoc mode with a random medium access control scheme. Ad hoc networking is realized by a geographical routing scheme that provides single- and mult...

Cellular-V2X facilitates a direct communication among vehicles and with the roadside traffic infrastructure. It addresses use cases for safety and traffic efficiency, where data are disseminated in a vehicle’s vicinity with short-latency constraints. Cellular-V2X provides two modes: when the vehicle is located in the coverage of the cellular networ...

Vehicular communications enable information exchange among vehicles including the roadside infrastructure. This has led to applications to primarily increase road safety and traffic efficiency. Standardization efforts on vehicular communications are underway. The physical layer (PHY) is defined based on the IEEE 802.11 family of WiFi standards oper...

Linear precoding provides the potential to boost the data throughput in a cellular multiple-input-multiple-output downlink system. It exploits spatial diversity and enables multiple users to be served on the same time-frequency resources. In a previous study we presented the maximization of the weighted sum data rate in multi-cell networks consider...

Two emerging technologies in the automotive domain are autonomous vehicles and V2X communication. Even though these technologies are usually considered separately, their combination enables two key cooperative features: sensing and maneuvering. Cooperative sensing allows vehicles to exchange information gathered from local sensors. Cooperative mane...

The 5G mobile standard will very likely include a new waveform that addresses scenarios like sporadic lowlatency traffic and dynamic spectrum access (DSA). In both cases the current 4G waveforms have some deficiencies, like the need for strict synchronicity and the high adjacent channel leakage ratio (ACLR) respectively. Several candidate waveforms...

Standardization for wireless vehicular communication ensures, as in other domains, interoperability, supports regulations and legislation, and creates larger markets. For the initial deployment of vehicular communication, consistent sets of standards have been created, commonly named C-ITS in Europe and DSRC in the U.S., both relying on the WiFi st...

This paper explores using the first subsymbol in the structure of a GFDM symbol as a pseudo circular preamble. As data and training sequence overlap in the GFDM structure, an initial estimation approach for isolating the preamble information from the data is presented. The concept allows for adaptation of state-of-the-art techniques developed for O...

The GeoNetworking protocol provides single-hop and multi-hop communication in vehicular ad hoc networks based on IEEE 802.11p/ITS-G5. It has been standardized by the ETSI Technical Committee ITS as part of its Release 1 set of specifications and is expected to be deployed in the next years. This paper presents a performance evaluation of the GeoNet...

Cooperation and information exchange will allow autonomous vehicles to increase their sensing range and maneuver coordinately, thereby greatly enhancing their safety and efficiency. The combination of autonomous driving and vehicular communications will enable Cooperative Autonomous Driving Systems (C-ADS) with stringent requirements. We present tw...

5G mobile networks will very likely include features that allow for a dynamic spectrum access (DSA) in order to exploit spectrum holes of a primary system. The efficient utilization of spectrum holes with minimum impairment of the primary system requires a waveform with a very low adjacent channel leakage ratio as well as robustness to time and fre...

This abstract gives an overview of the German research and development initiative FAST, a project cluster aiming at a technological and economic breakthrough by means of real-time capabilities. The FAST project cluster consists of around 80 partners from industry and academia, with a strong participation of small innovative companies. FAST comprise...

This paper reports intermediate transceiver and frame structure concepts and corresponding results from the European FP7 research project 5GNOW. The core is the unified frame structure concept which supports an integrated 5G air interface, capable of dealing both with broadband data services and small packet services within the same band. It is ess...

Information exchange among vehicles, and between vehicles and the roadside infrastructure is commonly regarded as a base technology to sustainably reduce road accidents and improve traffic efficiency. After more than a decade of research and development efforts, a technological basis has been established that applies WiFibased, wireless communicati...

This paper presents the combination of generalized frequency division multiplexing (GFDM) with the Walsh- Hadamard transform (WHT) to achieve a scheme that is robust against frequency-selective channels (FSC). The proposed scheme is suitable for low-latency scenarios foreseen for 5G networks, specially for Tactile Internet. The paper also presents...

AutoNet2030 – Co-operative Systems in Support of Networked Automated Driving by 2030 – is a European project connecting two domains of intensive research: cooperative systems for Intelligent Transportation Systems and Automated Driving. Given the latest developments in the standardization of vehicular communications, vehicles will soon be wirelessl...