International Journal of Vehicle Autonomous Systems (5 papers in press)

Regular Issues

• Energy-efficient cluster-based routing in VANET assisted by hybrid jelly fish and beluga optimisation and fault tolerance  
  by R.K. Mahesh, Shivkumar S. Jawalgi 
  Abstract: VANET clustering solves scalability issues while fortifying the network and extending its lifespan. The following phases are included in the developed work on Energy Efficient Cluster based Routing (EECR) and FT (Fuzzy-Topsis) in VANET: Cluster head selection, routing, and fault tolerance are the first three. Initially, the Hybrid Shuffled Shepherd Namib Beetle Optimization Algorithm (HSS-NBO) method, which is centred on the prior work, is used to pick the cluster heads. Then, using the created Combined Jelly Beluga Whale Optimization (CJ-BWO) model, routing is done as efficiently as possible while taking into account limitations such as security, trust, delay, quality of service, energy, and connection quality (RSSI). Then, as a prerequisite for energy-efficient processing, the intermediate node forwarding mechanism is applied for void handling. In case of occurring faults, it is tolerated by initially detecting the faults and then proposing a recovery phase with a proxy agent Road Side Unit (RSU)deployed.
  Keywords: VANET; quality of service; fault tolerance; recovery phase; CJ-BWO algorithm.
  DOI: 10.1504/IJVAS.2024.10065454
   
  
• A decentralised asynchronous federated learning framework for autonomous driving  
  by Xiaoli Li, Ting Cai, Wei Xiong, Degang Xu 
  Abstract: Traditional autonomous driving usually requires a large number of vehicles to upload data to a central server for training. However, collecting data from vehicles may violate personal privacy as road environmental information contains geographic location. Federated learning can achieve multi-vehicle collaborative sensing of the road environment while protecting data privacy. However, the existing centralised federated learning architecture faces some challenges, such as credibility, fairness, and real-time. To address the above issues, we propose a decentralised asynchronous federated learning framework based on blockchain. Firstly, using blockchain to replace the central server of traditional federated learning architecture avoids the untrustworthy issues caused by the central architecture. Secondly, the blockchain module includes scoring contract units and incentive contract units to prevent malicious vehicle attacks and designs fair incentive mechanisms to ensure the ecological health and sustainable development of federated learning. Thirdly, using the asynchronous federated learning algorithm, blockchain can immediately aggregate model updates from vehicles, greatly improving the overall training flexibility and real-time performance. Experimental results demonstrate the effectiveness of the proposed framework.
  Keywords: autonomous driving; blockchain; federated learning; asynchronous; decentralised.
  DOI: 10.1504/IJVAS.2024.10064091
   
  
• Analysis of recent trends and developments in assisted and automated driving systems: a systematic review  
  by Shivaji Thorat, Ramesh Pawase 
  Abstract: Surface road transportation is an essential part of our daily life, enabling us to commute ubiquitously to work, school, hospitals, and many other places. This leads to an increased need for private transportation. However, road safety is potentially impacted by driving under the influence and distracted driving. Thus, there seems to be a need for advanced driver assistance systems (ADAS) and automated driving (AD) systems in vehicles to ensure human safety in risky road environments. This approach has several benefits such as increased road safety, reduced traffic jams, low fuel consumption, and minimal human interventions. Given this, the race toward automated vehicles (AVs) is on, and several research institutions and automotive companies have ventured to accelerate AVs development. This review paper overviews recent technological trends and advancements in ADAS/AD systems, including future limitations (or challenges) and opportunities. This review-work can enable design improvements in forthcoming ADAS and AD applications.
  Keywords: advanced driver assistance systems; automated driving; autonomous vehicles; electrical and electronics architectures; road safety; sensor fusion; radars.
  DOI: 10.1504/IJVAS.2024.10063840
   
  
• Classification on unmanned underwater vehicles: a review  
  by Arpan Ghatak, Koena Mukherjee, Yogesh Singh 
  Abstract: This paper represents a concise survey of different unmanned underwater vehicles, commonly known as UUV. These unmanned vehicles are classified into two categories, one is a Remotely Operated Underwater Vehicle (ROV) and another is an Autonomous Underwater Vehicle (AUV). In this survey paper, the survey is concentrated into different types of ROVs and AUVs and the functionality of these vehicles. The material classification and components used to construct any underwater vehicle and different fundamental aspects of AUV design are also briefly described. A brief progress work over the years on different types of unmanned underwater vehicles is done to understand the progression of these underwater robots.
  Keywords: unmanned underwater vehicles; DOF; biomimetic AUV; underwater glider; autonomous underwater vehicle.
  DOI: 10.1504/IJVAS.2024.10064856
   
  
• A review on hardware in loop testing for various SAE levels of autonomous vehicle subsystems  
  by M. Siddharth, A. Rammohan 
  Abstract: The complexity of automobiles has increased tremendously in this decade to address environmental issues, customers' sophisticated demands and safety. Electric Vehicles (EV) and Autonomous Vehicles (AV) have a lot of new cutting-edge technologies that have been incorporated into them. EVs and AVs rely on a combination of cameras, sensors and artificial intelligence algorithms for navigation and decision-making on the road. This development in EV and AV subsystems requires a platform to test and validate the developed systems effectively and safely. Hardware in the Loop (HIL) is one of the solutions used to validate the models or prototypes developed in the latest automotive systems. HIL can closely mimic the actual plant model and is used to evaluate the automotive control system before building it into a real-time system. HIL testing adaptation for the autonomous platforms from SAE level 0 vehicles to SAE level 4 vehicles, such as Drivability development and Regenerative Brake by Wire, Longitudinal and Lateral automation, are elaborated in this review. This paper concludes that the HIL testing platform helps the researchers validate the developed subsystems before the prototype or manufacturing of a vehicle, increases safety and reduces development time and cost.
  Keywords: vehicle safety; hardware-in-the-loop; automotive control systems testing and validation.
  DOI: 10.1504/IJVAS.2024.10064857