IEEE International Conference on Advanced Networks and Telecommunications Systems
14-17 December 2020 // Virtual Conference

The Role of AI/Machine Learning in the Evolution of Connected Vehicles

The field of connected vehicles stands at the confluence of three evolving disciplines – the Internet of Things (IoT), emerging standards for connectivity of vehicles, and AI/machine learning. The number of connected IoT devices is expected to grow from 9.5 billion devices in 2019 to 22.5 billion devices in 2025 [1]. More optimistic estimates project the number of IoT devices in 2025 to be 55 billion connected devices [2]. Consequently, applications of IoT devices have rapidly expanded to integrate intelligent sensing and processing along with smart applications of the technology into various fields such as smart homes, smart appliances, enterprises, smart transportation including connected vehicles, smart cities, agriculture, energy, security, healthcare, shopping, location-based services including tracking and other similar fields. The exponential growth of IoT is transforming the quality of living of human beings around the globe.

Fueling the growth in the evolution of vehicles towards total automation is the development of novel sensors, 3D cameras, lidars and radars and their ability to connect to the Internet, upload the data to a cloud. The sensors of an autonomous vehicle collect anywhere from 1.4 TB to 19 TB of data per hour. Whether or not the vehicles are autonomous, one of the key features of connected vehicles is that they are able to share data between themselves in real-time. For example, the scene of an accident or road work encountered by a vehicle can be immediately shared with vehicles it is connected to. Thus vehicles may learn about accidents or road work well in advance so as to enable them to make smart decisions and establish alternate routes to their destinations. The workshop will help in understanding the role of these sensors with use cases.

The vast amount of raw data collected must by mined for it to become useful in ensuring traffic safety by means such as intelligent rerouting of traffic or distribution of information on roadwork activities or accidents. Machine learning is a mechanism that has become extremely powerful in extracting meaningful data. A number machine learning algorithms exist and can be broadly classified under unsupervised, supervised, and reinforcement learning algorithms. A number of algorithms exist under each category. The workshop will address the impact of machine learning and their applications to connected vehicles with several use cases.


The workshop will address a number of technical issues involving the application of artificial intelligence/machine learning to connected vehicles such as, but not limited to, the following:

  • 3D computer vision in connected vehicles
  • Action and behavior recognition of drivers/vehicles in connected vehicles
  • Adversarial learning, adversarial attack and defense methods in connected vehicles
  • Biometrics, face, gesture, body pose of driver in connected vehicles
  • Computational photography, image and video synthesis in connected vehicles
  • Efficient training and inference methods for networks in connected vehicles
  • Explainable AI, fairness, accountability, privacy, transparency and ethics in connected vehicles
  • Image retrieval in connected vehicles
  • Low-level and physics-based vision analysis in connected vehicles
  • Machine learning architectures and formulations in connected vehicles
  • Motion and tracking in connected vehicles
  • Neural generative models, auto encoders, GANs in connected vehicles
  • Optimization and learning methods in connected vehicles
  • Recognition (object detection, categorization) in connected vehicles
  • Representation learning, deep learning in connected vehicles
  • Scene analysis and understanding in connected vehicles
  • Segmentation, grouping and shape in connected vehicles
  • Transfer, low-shot, semi- and un- supervised learning in connected vehicles
  • Video analysis and understanding in connected vehicles
  • Vision + language, vision + other modalities in connected vehicles
  • Visual reasoning and logical representation in connected vehicles
  • General Machine Learning (active learning, clustering, online learning, ranking, reinforcement learning, semi-supervised learning, time series analysis, unsupervised learning, etc.) in connected vehicles
  • Deep Learning (architectures, generative models, deep reinforcement learning, etc.) in connected vehicles
  • Learning Theory (bandits, game theory, statistical learning theory, etc.) in connected vehicles
  • Optimization (convex and non-convex optimization, matrix/tensor methods, sparsity, etc.) in connected vehicles
  • Probabilistic Inference (Bayesian methods, graphical models, Monte Carlo methods, etc.) in connected vehicles
  • Trustworthy Machine Learning (accountability, causality, fairness, privacy, robustness, etc.) in connected vehicles

Potential authors are invited to submit papers via EDAS. The papers should follow the IEEE conference format.

Submission Link

Workshop Chairs

  • Dr. Seshadri Mohan, University of Arkansas at Little Rock,
  • Dr. Nigel Jefferies, Wireless World Research Forum Chairman and Huawei Technologies,
  • Dr. Sachin Sharma, Graphic Era University, Dehradun, India,

Important Dates

  • Paper Submission: 8 Nov, 2020
  • Notification of Acceptance: 16 Nov, 2020
  • Final Submission: 25 Nov, 2020

Call for Papers (PDF)


Seshardi Mohan

Title: The Role of AI/Machine Learning in The Evolution of Connected Vehicles

Dr. Seshadri Mohan is currently a professor in Systems Engineering Department at University of Arkansas at Little Rock, where, from August 2004 to June 2013, he served as the Chair of the Department of Systems Engineering. Prior to the current position he served as the Chief Technology Officer (CTO) and Acting CEO of IP SerVoniX, where he consulted for several telecommunication firms and venture firms and served as the CTO of Telsima (formerly known as Kinera). Besides these positions, his industry experience spans a decade at New Jersey-based Telcordia (formerly Bellcore) and Bell Laboratories. Prior to joining Telcordia, he was an associate professor at Clarkson and Wayne State Universities.
Dr. Mohan has authored/coauthored over 125 publications in the form of books, patents, and papers in refereed journals and conference proceedings with citations to his publications in excess of 5880. He has co-authored the textbook Source and Channel Coding: An Algorithmic Approach. He has contributed to several books, including Mobile Communications Handbook and The Communications Handbook (both CRC Press). He holds fourteen patents in the area of wireless location management and authentication strategies as well as in the area of enhanced services for wireless. He is the recipient of the SAIC Publication Prize for Information and Communications Technology. He has served or is serving on the Editorial Boards of IEEE Personal Communications, IEEE Surveys, IEEE Communications Magazine, Journal of Mobility and Cyber Security and International Journal on Wireless Personal Communications (Springer) and has chaired sessions in many international conferences and workshops. He has also served as a Guest Editor for several Special issues of IEEE Network, IEEE Communications Magazine, and ACM MONET. He served as a co-guest editor of the Feature Topic “Human Bond Communications,” that appeared in the February 2019 issue of IEEE Communications Magazine. He served as a guest editor of 2015 October IEEE Communications Feature Topic titled “Social Networks Meet Next Generation Mobile Multimedia Internet,” March 2012 IEEE Communications Feature Topic titled “Convergence of Applications Services in Next Generation Networks” as well as the June 2012 Feature Topic titled “Social Networks Meet Wireless Networks.” In April 2011, he was awarded 2010 IEEE Region 5 Outstanding Engineering Educator Award. He received the best paper award for the paper “A Multi-Path Routing Scheme for GMPLS-Controlled WDM Networks,” presented at the 4th IEEE Advanced Networks and Telecommunications Systems conference.
Dr. Mohan is a co-founder of the startup IntelliNexus, LLC, the objective of which are the development of innovative adhoc vehicular networking to advance the notion of connected cars and the development of IoT and IoV applications to improve traffic safety and reduce accidents and congestion. Dr. Mohan holds a Ph.D. degree in electrical and computer engineering from McMaster University, Canada, the Masters degree in electrical engineering from the Indian Institute of Technology, Kanpur, India, and the Bachelors degree in Electronics and Telecommunications from the University of Madras, India.

Abstract: The talk will provide an overview of the role of AI/Machine learning as applicable to connected vehicles and provide a couple of examples related to spectrum sharing and driver drowsiness detection.



List of Panelist:

Bryn Balcombe (Chief Strategy Officer, Roborace & Founder of, London, England, United Kingdom)

Title: The Molly Problem – Unsolved ethical dilemmas for automated driving

Bryn Balcombe is the Chief Strategy Officer for Roborace, a motorsport competition for human and AI drivers, designed to accelerate the research and development of Vehicle Intelligence and human machine interfaces required for transportation of the future. His previous experience comes from Formula One where he architected and patented vehicle to infrastructure communication systems and developed the F1 Group’s first global media network. He has also consulted on technology strategy for organisations including the BBC and McCann Worldgroup and has a BEng in Mechanical Engineering & Vehicle Design.

Abstract: Self-driving ethics have been dominated by adaptions of the classical Trolley Problem dilemmas. Earlier this year The Molly Problem was introduced to shift this debate forward to consider both post-collision behavior and requirements for Explainable AI to build public trust in both collision and near miss events. This session will review the results of The Molly Problem survey in relation to international standards and regulation.

Prof. Dr. Ing. Klaus David (University of Kassel, Germany)

Title: AI for VRU Safety: The wireless seat belt

Dr. Klaus David ( is full professor and head of communication technology at Kassel University, Germany. His research interests include context awareness and AI focusing on applications such as 6G, digital work, and VRU (Vulnerable Road User) safety.
He has 12 years of industrial experience in various management positions in HP, Bell Northern Research, IMEC, T-Mobile and IHP, with five years international experience in UK, Belgium, USA, and Japan. He has published over 230 scientific articles. He is active in IEEE (Editor in Chief IEEE VT Magazine 2015 – 2018), WWRF (Wireless World Research Forum) and at conferences, such as IST Future Network & Mobile Summit 2012 as TPC chair or General Chair IEEE PerCom 2021.

Abstract: Worldwide 351,000 vulnerable road users (VRU), like pedestrians and bicyclists, were killed in 2016 due to collisions with vehicles, according to the World Health Organization
In this presentation an innovative approach – the wireless seat belt – which can significantly reduce this number of killed VRUs is discussed. One of its core facilitators is Artificial Intelligence (AI) for recognizing a VRU`s activities.

Prof. Pradipta Biswas (I3DLab, Indian Institute of Science, Bangalore)

Title: Non-Conventional Traffic Participants for Semi-Autonomous Vehicles

Dr. Pradipta Biswas is an assistant professor at the Centre for Product Design and Manufacturing (CPDM) and associate faculty at the Robert Bosch Centre for Cyber Physical Systems (RBCCPS) of Indian Institute of Science. His research focuses on user modelling and multimodal human-machine interaction for aviation and automotive environments and for assistive technology. He set up and leads the Interaction Design (I3D) Lab at CPDM, IISc and principal investigator of projects funded by Microsoft, British Telecom, Faurecia, Harman and Wipro, . Pradipta is a Co-Chair of the IRG AVA and Focus Group on Smart TV at International Telecommunication Union. He is a member of the UKRI International Development Peer Review College, Society of Flight Test Engineers and was a professional member of the British Computer Society, Associate Fellow at the UK Higher Education Academy and Royal Society of Medicine. Earlier, he was a Senior Research Associate at Engineering Department, Research Fellow at Wolfson College and Research Associate at Trinity Hall of University of Cambridge. He completed PhD in Computer Science at the Rainbow Group of University of Cambridge Computer Laboratory and Trinity College in 2010 and was awarded a Gates-Cambridge Scholarship in 2006.

AbstractIn recent time there is plethora of progress on both research and commercialization aspects of autonomous vehicles, mostly for European and North American highways. However, traffic participants at developing countries and specific use cases like in an airport require a machine learning system to be trained with unusual situations. For example, responding to presence of animals in a sub-urban road, or unusual shaped vehicles at an airport often poses challenge due to lack of enough training data, privacy and security aspects of the environment.
This talk will address the problem from four different perspectives. We shall present results on comparing existing Convolutional Neural Network (CNN) models with respect to latency and accuracy for unusual traffic participants in Indian road data set. We shall propose use of VR digital twins to prepare synthetic datasets and compare and contrast the approach with Generative Adversial Networks. In the context of training CNN models with real and synthetic data sets, we shall investigate how a CNN actually works and compare the working of intermediate layers of CNN using data visualization techniques. Finally, we shall look at the human machine interaction and teaming aspects of semi-autonomous vehicles and present case studies on operating a vehicle using multiple modalities and automatically estimating cognitive load of front seat passengers.

Dr. Marcus Wong (Wireless Standard Department, Futurewei Technologies)

Title: Security Landscape in Connected Vehicles

Dr. Marcus Wong has over 20 years of experience in the wireless network security field with AT&T Bell Laboratories, AT&T Laboratories, Lucent Technologies, and Samsung’s Advanced Institute of Technology. He is CISSP certified.
Marcus has concentrated his research and work in many aspects of security in wireless communication systems. Marcus joined Futurewei Technologies (a subsidiary of Huawei Technologies) in 2007 and continued his focus on research and standardization. Marcus has held elected official positions in both WWRF and 3GPP. He also served as guest editor in the IEEE Vehicular Technology magazine. As an active contributor, author, and publisher, he has shared his security research on a variety of whitepapers, book chapters, and speaking engagements.

Abstract: This talk looks at the different standards as they relate to security aspect of connected vehicles, from ITS to IEEE 802.11P to IEEE 1609.2 and finally to 3GPP. As commercialization nears, the security standards converge to form an end-to-end security that can be applied to connected vehicles.

Sayon Karmakar (ENSS Doctoral Scholar, UA Little Rock, Little Rock, Arkansas)

Title: Intelligent ADAS and Adaptive Vehicular Networks: Machine Learning Perspective

Sayon Karmakar is pursuing Doctoral studies at UALR under Dr. Seshadri Mohan and also a masters student at NIT, Sikkim. He was a research intern in the University of Arkansas at Little Rock, USA under Dr. Seshadri Mohan and developed a Driver Drowsiness Detection System using multiple ML algorithms which was presented in 41st Meeting of WWRF in Aarhus University, Herning, Denmark. The paper has been accepted for publication in the Journal of Mobile Multimedia, River Publishers. His current interest is concerned with “Monitoring biomarkers of drivers with medical wireless sensor networks deployed in Connected Vehicles” and “Intelligent ADAS and Adaptive Vehicular Networks: Machine Learning Perspective”.

Abstract: Drivers are at a constant threat even after precautions and safety measures taken by their vigilance with additional safety features present in the automobile. Driving is a complex psychomotor task. This when added with the non deterministic nature of human behavior outlined by the high degree of inter and intra driver variability, makes this research dauntingly complex. ADAS and Network Framework are prioritized working fields of UNECE. The penultimate objective is distinguishing the high level driving strategies from low level control strategies and integrate in a way to assist driver by reducing cognitive load at a minimum to completely replace human at a maximum. The fundamental difference from current ADAS to a fully automated vehicle’s ADAS is the complex combination of longitudinal and lateral control of the vehicle provided by the latter. Current ADAS is capable of processing one dimensional control based on condition and case by case basis, hence called Intelligent ADAS. The adaptive vehicular networks would serve as the foundation of inter vehicular communication which would reduce the road accidents. Issues in communications can be addressed by the adaptive algorithms which optimize the utility of resources. The combined infrastructure of intelligent ADAS and adaptive vehicular networks would provide the foundation of Connected Vehicles that promise to provide a safer road travel.Therefore, the role of ML in intelligence of ADAS and optimizing heterogenous challenges of Vehicular Network show promising results leading to a design of reliable system as well as optimal utilization of spectrum. Secondly, current ADAS is automobile centric, which acquires information around the vehicle that is relayed to driver. The shift in vehicle centric approach to driver centric ADAS development since 90% accidents are caused by human error is a proposed methodology. State (cognitive, health, mental) of driver must be considered as a universal metric around which the safety systems development be carried out with the enormous computational power provided by the machine learning algorithms, which made non-quantifiable parameters to be quantified objectively to an acceptable extent.

Vishnu Ram OV, TSDSI