ACM MobiHoc Workshop on “Cooperative data dissemination in future vehicular networks” (D2VNet)
Held online on October 11, 2020
Call For Papers
Recent developments in software, hardware and communication technologies have opened the way towards Cooperative and Intelligent Transportation Systems (C-ITSs) as a means to deliver improved road safety, traffic efficiency and infotainment services. This potential will be unleashed through cooperative dissemination of context information, including observations that intelligent vehicles acquire through sophisticated sensors (e.g., radars, cameras and LiDARs).
Sending information about all of on-board sensor observations may saturate the capacity of traditional technologies for vehicular communications, especially in a dense urban environment with a large number of vehicles, thus motivating efforts towards the design of techniques that set a bound on the amount of information that is distributed over bandwidth-constrained communication channels.
A traditional approach is to monitor the age of information (AoI), so that vehicles broadcast sensory messages that are not too old. Another approach is to rank the utility of sensor data by relying on feedback messages which describe how helpful the received information was in relation with the requirements of target applications. Machine learning has also emerged as a promising option to measure the mutual information of different combinations of the sensory readings and dynamically assign them value scores which depend on the degree of correlation. Autoencoders can also be trained in an unsupervised manner to extract features from input vectors and prioritize the transmission that have greatest value for target applications.
This workshop aims at collecting original contributions that can advance the state of the art on the design challenges for data dissemination in vehicular networks, with a focus on three main areas of interest. First, it is of particular interest the analysis and design of compression techniques for sensory acquisitions, in order to facilitate storage and dissemination in vehicular applications. Second, we look forward to submissions that study how to optimize the concept of data dissemination while avoiding network congestion, enhancing average network throughput and prioritizing specific vehicles messages. Third, we encourage submissions focusing on the trade-off between on-board and edge-assisted approaches for the processing of sensors’ observations, where signal latency, power consumption, and system overhead performance is compared. We particularly welcome papers on the application of machine learning techniques in vehicular scenarios, with a focus on multi-frame perception, prediction, feature extraction, and evaluation of data correlation for autonomous driving.
Topics of interest for the workshop include, but are not limited to:
- Cooperative services in vehicular networks.
- V2X technologies for data dissemination.
- Value of information in vehicular networks.
- Data-driven techniques in anticipatory vehicular communication systems.
- Machine learning for sensor-based object detection and/or tracking.
- Machine learning for resource-efficient data dissemination.
- Machine learning for cross-modal feature extraction in automotive sensors.
- Machine learning for compression of automotive sensors’ observations.
- Machine learning for mutual information maximization among automotive sensors.
- Challenges of sensors’ data dissemination in a commercial vehicular system.
- On-board vs. edge-assisted sensor processing in vehicular networks.
- New automotive sensor technologies.
Prospective authors should submit a paper with a maximum length of six (6) pages, including all figures and references. Papers must be formatted with the ACM style sheet. If you are using LaTeX, you can make use of a simplified ACM conference template. The papers of this workshop will go through the same single-blind peer-review process of the main conference. Submitted manuscripts must be original and not be published or under review elsewhere. Papers must not infringe any copyright or third party right. The submission website is https://d2vnet20.hotcrp.com.
|June 14, 2020 [Extended]
||Workshop paper submission
|June 28, 2020
||Notification of papers acceptance
|July 28, 2020 [Extended]
Marco Giordani, University of Padova
Michele Zorzi, University of Padova
Onur Altintas, TOYOTA North America, Infotech Labs
Takamasa Higuchi, TOYOTA North America, Infotech Labs
Antonella Molinaro, Università Mediterranea di Reggio Calabria
Toktam Mahmoodi, King's College London
Robert Piechocki, University of Bristol
Marco Centenaro, Fondazione Bruno Kessler (FBK)
Falko Dressler, Paderborn University
Christian Wietfeld, TU Dortmund University
Robert W. Heath Jr., University of Texas at Austin
Carla Fabiani Chiasserini, Politecnico di Torino
Tommy Svensson, Chalmers University of Technology