IEEE International Conference on Advanced Networks and Telecommunications Systems
13-16 December 2021 // Hyderabad, India

AI/Machine Learning Enabled Connected Vehicles

Description

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.

Scope

The workshop will address a number of technical issues involving the application of artificial intelligence/machine learning to connected vehicles. The areas in which machine learning can be effective include, but not limited to:

  • Channel estimation, especially with high-mobility vehicles with rapidly changing environment and channel conditions; machine learning can adapt to the environmental dynamics and estimate and even predict the channel characteristics;
  • Prediction of traffic flow by applying machine learning to the vast amount of past traffic flow information, history of accidents, congestion, roadworks, detours, and other traffic incidents possibly due to weather;
  • Resource allocation in wireless networks of connected vehicles by exploiting machine learning, utilizing information gathered from the previously mentioned aspects of channel estimation and traffic flow prediction, to efficiently allocate the scarce radio and network resources to connected vehicles; and
  • Predicting the driving behaviors of drivers, the physical and emotional status, alert the drivers of possible corrective actions to take to avoid accidents.
  • Application of machine learning to determine and even predict security threats to connected vehicles and ensuring privacy and security.
  • Machine learning to protect VRUs and enhance their safety.

The above are only a few of the example topics in which some or most of the following subtopics apply.

  • 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  for connected vehicles
  • Efficient training and inference methods for connected vehicles
  • Explainable AI, fairness, accountability, privacy, transparency and ethics for connected vehicles
  • Image retrieval  in connected vehicles
  • Low-level and physics-based vision analysis for connected vehicles
  • Machine learning architectures and formulations for 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

Timeliness and intended audience

The topic is extremely relevant since the auto makers are engaged with the development of connected autonomous vehicles. 5G Automotive Association (5GAA) was established to facilitate a tighter collaboration between the telecom industry and auto manufactures and to create end-to-end solutions for future mobility and transportation services. As stated already, the standards organizations are rapidly developing standards for connected vehicles and instituting focus groups such as ‘Focus Group on AI for Autonomous and Assisted Driving (AI4AAD). The audience will include researchers from both academia and industry personnel with interests in the field.

Potential authors are invited to submit papers via The EDAS submission link: https://edas.info/N29033. The papers should follow the IEEE conference format.

Workshop Chairs

  • Dr. Seshadri Mohan, University of Arkansas at Little Rock (sxmohan@ualr.edu)
  • Dr. Sachin Sharma, Graphic Era University, Dehradun, India (sachin.cse@geu.ac.in)
  • Prof. Dr.-Ing. Klaus David, University of Kassel, Germany

Key Deadlines

  • Paper submission deadline: 17 October 2021
  • Decision notification to authors: 21 October 2021
  • Final paper & copyright submission deadline: 01 November 2021

2021 Patrons


  • Platinum Sponsor


  • Gold Sponsor


  • Silver Sponsor

     


  • Bronze Sponsor


  • Best Papers Award Sponsor