Cooperative Data Dissemination in Future Vehicular Networks (D2VNet)

Session D2VNet-Opening

Opening Session

Conference
9:15 AM — 9:30 AM EDT
Local
Oct 11 Sun, 9:15 AM — 9:30 AM EDT

Opening session

Marco Giordani (University of Padova), Michele Zorzi (University of Padova)

0
N.D.

Session Chair

Michele Zorzi, Marco Giordani

Session D2VNet-Technical-1

Technical Session I

Conference
9:30 AM — 11:30 AM EDT
Local
Oct 11 Sun, 9:30 AM — 11:30 AM EDT

How to Deal with Data Hungry V2X Applications?

Alessandro Bazzi (University of Bologna, Italy), Claudia Campolo (University Mediterranea of Reggio Calabria, Italy), Barbara Masini (CNR - IEIIT, Bologna, Italy), Antonella Molinaro (University Mediterranea of Reggio Calabria, Italy)

1
Current vehicular communication technologies were designed for a so-called phase 1, where cars needed to advise of their presence. Several projects, research activities and field tests have proved their effectiveness to this scope. But entering the phase 2, where awareness needs to be improved with non-connected objects and vulnerable road users, and even more with phases 3 and 4, where also coordination is foreseen, the spectrum scarcity becomes a critical issue. In this work, we provide an overview of various 5G and beyond solutions currently under investigation that will be needed to tackle the challenge. We first recall the undergoing activities at the access layer aimed to satisfy capacity and bandwidth demands. We then discuss the role that emerging networking paradigms can play to improve vehicular data dissemination, while preventing congestion and better exploiting resources. Finally, we give a look into edge computing and machine learning techniques that will be determinant to efficiently process and mine the massive amounts of sensor data.

The Role of Machine Learning for Trajectory Prediction in Cooperative Driving

Luis Sequeira (King's College London), Toktam Mahmoodi (King's College London)

1
In this paper, we study the role that machine learning can play in cooperative driving. Given the increasing rate of connectivity in modern vehicles, and road infrastructure, cooperative driving is a promising first step in automated driving. The example scenario we explored in this paper, is coordinated lane merge, with data collection, test and evaluation all conducted in an automotive test track. The assumption is that vehicles are a mix of those equipped with communication units on board, i.e. connected vehicles, and those that are not connected. However, roadside cameras are connected and can capture all vehicles including those without connectivity. We develop a Traffic Orchestrator that suggests trajectories based on these two sources of information, i.e. connected vehicles, and connected roadside cameras. Recommended trajectories are built, which are then communicated back to the connected vehicles. We explore the use of different machine learning techniques in accurately and timely prediction of trajectories.

Distributed Resource Allocation with Multi-Agent Deep Reinforcement Learning for 5G-V2V Communication

Alperen Gündogan (Nomor Research and Technical University of Munich, Chair of Communication Networks), H. Murat G¸rsu (Technical University of Munich, Chair of Communication Networks), Volker Pauli (Nomor Research, Germany), Wolfgang Kellerer (Technical University of Munich, Chair of Communication Networks)

1
We consider the distributed resource selection problem in Vehicle-to-vehicle (V2V) communication in the absence of a base station. Each vehicle autonomously selects transmission resources from a pool of shared resources to disseminate Cooperative Awareness Messages (CAMs). This is a consensus problem where each vehicle has to select a unique resource. The problem becomes more challenging whenódue to mobilityóthe number of vehicles in vicinity of each other is changing dynamically. In a congested scenario, allocation of unique resources for each vehicle becomes infeasible and a congested resource allocation strategy has to be developed. The standardized approach in 5G, namely semi-persistent scheduling(SPS) suffers from effects caused by spatial distribution of the vehicles. In our approach, we turn this into an advantage. We propose a novel DIstributed Resource Allocation mechanism using multi-agent reinforcement Learning (DIRAL) which builds on a unique state representation. One challenging issue is to cope with the non-stationarity introduced by concurrently learning agents which causes convergence problems in multi-agent learning systems. We aimed to tackle non-stationarity with unique state representation. Specifically, we deploy view-based positional distribution as a state representation to tackle non-stationarity and perform complex joint behavior in a distributed fashion. Our results showed that DIRAL improves PRR by %20 compared to SPS in challenging congested scenarios.

Graph-based Model for Beam Management in Mmwave Vehicular Networks

Zana Limani Fazliu (Faculty of Electrical and Computer Engineering, University of Prishtina), Carla Fabiana Chiasserini (Politecnico di Torino), Francesco Malandrino (CNR-IEIIT), Alessandro Nordio (CNR-IEIIT)

1
Mmwave bands are being widely touted as a very promising option for future 5G networks, especially in enabling such networks to meet highly demanding rate requirements. Accordingly, the usage of these bands is also receiving an increasing interest in the context of 5G vehicular networks, where it is expected that connected cars will soon need to transmit and receive large amounts of data. Mmwave communications, however, require the link to be established using narrow directed beams, to overcome harsh propagation conditions. The advanced antenna systems enabling this also allow for a complex beam design at the base station, where multiple beams of different widths can be set up. In this work, we focus on beam management in an urban vehicular network, using a graph-based approach to model the system characteristics and the existing constraints. In particular, unlike previous work, we formulate the beam design problem as a maximum-weight matching problem on a bipartite graph with conflicts, and then we solve it using an efficient heuristic algorithm. Our results show that our approach easily outperforms advanced methods based on clustering algorithms.

Session Chair

Carla Fabiana Chiasserini

Session D2VNet-Break-1

Virtual coffee break

Conference
11:30 AM — 11:45 AM EDT
Local
Oct 11 Sun, 11:30 AM — 11:45 AM EDT

N.D.

N.D.

0
N.D

Session Chair

N.D.

Session D2VNet-Keynote-1

Keynote

Conference
11:45 AM — 12:45 PM EDT
Local
Oct 11 Sun, 11:45 AM — 12:45 PM EDT

Millimeter Wave Vehicular Link Configuration Using Machine Learning

Robert W. Heath Jr.

0
Millimeter-wave (MmWave) vehicular communication enables massive sensor data sharing in vehicular systems, leading to enhances in automation, safety, transportation efficiency and infotainment. Estimating and tracking beams in mmWave vehicular communication, however, is challenging due to the use of large antenna arrays and high mobility in the vehicular context. Fortunately, wireless cellular communication systems have access to many kinds of data, which can make beam training more efficient. In this talk, I introduce beam alignment solutions that work with different types of information related to link performance. Data-driven approaches are able to leverage side information and underlying channel statistics to optimize link configuration in mmWave vehicular communication with negligible overhead.

Session Chair

Michele Zorzi

Session D2VNet-Break-2

Virtual lunch break

Conference
12:45 PM — 1:45 PM EDT
Local
Oct 11 Sun, 12:45 PM — 1:45 PM EDT

N.D.

N.D.

0
N.D.

Session Chair

N.D.

Session D2VNet-Technical-2

Technical Session II

Conference
1:45 PM — 3:15 PM EDT
Local
Oct 11 Sun, 1:45 PM — 3:15 PM EDT

Tensor Completion-Based 5G Positioning with Partial Channel Measurements

Fuxi Wen (Chalmers University of Technology, Sweden),Tommy Svensson (Chalmers University of Technology, Sweden)

0
5G mmWave communication systems have promising properties for high precision user localization and environment mapping. Such information is of high value for emerging applications such as connected automated driving (CAD), and it has also potential to be explored to substantially improve efficiency and reliability of mmWave communications itself. However, the acquisition of such information can not come with too large overhead in the system. Existing studies have so far relied on complete channel measurements, implying a prohibitive channel training overhead. In this paper, we exploit the possibility of 5G positioning using partial channel measurements. We utilize a tensor completion technique to recover the complete channel information from low-rank channel measurements. Simulation results demonstrate the trade-off between user positioning accuracy and channel training overhead and show that sub-meter precision with negligible performance loss is feasible at sample ratio reductions of at least 30%, and meter level precision is achievable with sample ratio reduction of 50%.

Acting Selfish for the Good of All: Contextual Bandits for Resource-Efficient Transmission of Vehicular Sensor Data

Benjamin Sliwa (TU Dortmund University, Germany), Rick Adam (TU Dortmund University, Germany), Christian Wietfeld (TU Dortmund University, Germany)

0
In this work, we present Black Spot-aware Contextual Bandit (BS-CB) as a novel client-based method for resource-efficient opportunistic transmission of delay-tolerant vehicular sensor data. BS-CB applies a hybrid approach which brings together all major machine learning disciplines – supervised, unsupervised, and reinforcement learning – in order to autonomously schedule vehicular sensor data transmissions with respect to the expected resource efficiency. Within a comprehensive real world performance evaluation in the public cellular networks of three Mobile Network Operators (MNOs), it is found that 1) The average uplink data rate is improved by 125%-195% 2) The apparently selfish goal of data rate optimization reduces the amount of occupied cell resources by 84%-89% 3) The average transmission-related power consumption can be reduced by 53%-75% 4) The price to pay is an additional buffering delay due to the opportunistic medium access strategy.

Vehicular Knowledge Networking and Application to Risk Reasoning

Seyhan Ucar (InfoTech Labs, Toyota Motor North America R&D), Takamasa Higuchi (InfoTech Labs, Toyota Motor North America R&D), Chang-Heng Wang (InfoTech Labs, Toyota Motor North America R&D), Duncan Deveaux (EURECOM - Communication Systems Department, Sophia-Antipolis, France), Jérôme Härri (EURECOM - Communication Systems Department, Sophia-Antipolis, France), Onur Altintas (InfoTech Labs, Toyota Motor North America R&D)

0
Vehicles are expected to generate and consume an increasing amount of data, but how to perform risk reasoning over relevant data is still not yet solved. Location, time of day and driver behavior change the risk dynamically and make risk assessment challenging. This paper introduces a new paradigm, transferring information from raw sensed data to knowledge and explores the knowledge of risk reasoning through vehicular maneuver conflicts. In particular, we conduct a simulation study to analyze the driving data and extract the knowledge of risky road users and risky locations. We use knowledge to facilitate reduced volume and share it through a Vehicular Knowledge Network (VKN) for better traffic planning and safer driving.

Session Chair

Marco Giordani

Session D2VNet-Panel-1

Industrial Panel

Conference
3:15 PM — 4:45 PM EDT
Local
Oct 11 Sun, 3:15 PM — 4:45 PM EDT

The role of machine learning for autonomous driving

Dr. Mate Boban (Moderator), Tim Leinmüller (Panelist), Tahir Sari​ (Panelist), Andreas Festag (Panelist)

0
The panel will (i) identify the most relevant areas where machine learning can be applied to cooperative autonomous driving, (ii) discuss challenges of integrating communications with the "non-cooperative" self-driving technologies enabled by computer vision, sensor data fusion, etc., (iii) discuss the interaction between in-car and the in-network processing, and (iv) identify requirements on communications network (radio access and architecture) components needed to support save cooperative driving.

Session Chair

Mate Boban

Session D2VNet-Closing

Closing remarks

Conference
4:45 PM — 5:00 PM EDT
Local
Oct 11 Sun, 4:45 PM — 5:00 PM EDT

Closing remarks

Marco Giordani (University of Padova), Michele Zorzi (University of Padova)

0
N.D.

Session Chair

Michele Zorzi, Marco Giordani

Made with in Toronto · Privacy Policy · © 2022 Duetone Corp.