Autonomous Road Vehicles Research Articles

Transport Policy Pathways for Autonomous Road Vehicles to Promote Sustainable Urban Development in the European Union: A Multicriteria Analysis

The European Union’s policy aims for the wide-scale deployment of automated mobility by 2030, i.e., within the next programming period (2028–2034), with the deployment of autonomous road vehicles (AVs) in cities playing a key role. Researchers suggest that AV deployment will have complex impacts on urban development, which are difficult to quantify due to scarce real-life data. The present research aims to evaluate different policy pathways of AV deployment for sustainable urban development in the next EU programming period. A multicriteria analysis is conducted, combining AHP and VIKOR, with the participation of experts across Europe. Initially, the potential impacts on sustainable urban development are weighted as evaluation criteria. Then, different pathways are evaluated against these criteria, i.e., AV deployment as collective and/or private transport in specific areas and periods or in the whole Functional Urban Area (FUA) on a 24 h basis. An interesting finding is that the effect on the city’s spatial development, not thoroughly examined by literature, is highly ranked by experts. Regarding policy pathways, autonomous collective transport with 24 h service of the FUA emerged as the optimum alternative. The proposed methodology provides a tool for planners, researchers, and policy makers and a framework for an open debate with society.

Acoustic and vibrations measurments in an autonomous shuttle bus

In response to the ADEME's call for Autonomous Road Vehicle Experimentation projects, a consortium was created to propose the SAM project about Safety and Acceptability of Autonomous Driving and Mobility. It was composed of industrial and research teams, associated with local partners. SAM is a national project involving large-scale trials of autonomous driving and mobility on open roads. The assessments covered several topics, including environmental impacts, focusing on air pollution, noise and the life cycle of components. Cerema proposed a methodology to characterize acoustic and vibration levels for autonomous driving in the specific site near Paris. The tests consisted in instrumenting the interiors of an automated shuttle and a conventional car to determine the user's feelings. The vehicles were driven in a quiet area and in a high traffic area. The results displayed by Cerema are based on statistical studies on 20 vehicle passages for each experiment. The indicators were characterized for the entire route and by homogeneous sections. In fluid navigation situation, the measurements showed that the acoustic and vibration impacts are minimal. However, the tests have highlighted the effects of the lack of anticipation of an automated shuttle during specific events requiring rapid braking.

The Safety Risks of AI-Driven Solutions in Autonomous Road Vehicles

The Safety Risks of AI-Driven Solutions in Autonomous Road Vehicles

Robust Reinforcement Learning-based Vehicle Control with Object Avoidance

This paper presents a control design framework for robust reinforcement learning (RL) based vehicle control enhanced with object avoidance using a model predictive approach. The proposed integration method is applied for motion control of autonomous road vehicles. In the motion control, longitudinal and lateral dynamics are incorporated, and the high-performance motion of the vehicle, through the RL-based control agent is achieved. ’H.co based robust control is used as a baseline parallel to the RL-agent to ensure stable operation. The object avoidance and limited error path following are achieved using a model-based predictive algorithm. Finally, the control signals of the three controllers are combined using a supervisor layer, which solves a constrained optimization task to ensure high performance and safe motion. The effectiveness of the proposed control method using simulation scenarios is illustrated.

Assessing Public Acceptance of Autonomous Vehicles for Smart and Sustainable Public Transportation in Urban Areas: A Case Study of Jakarta, Indonesia

This study examines the benefits and drawbacks of autonomous public transit vehicles among 210 Indonesians. Some 25% of respondents knew nothing about driverless vehicles, whereas 14% did. The average 5-point Likert scale response was 3.12 (SD = 1.05), indicating intermediate expertise. Some 42% of respondents used autonomous vehicle sources such as public transport, 47% had no experience, and 11% were doubtful. The survey items’ Cronbach’s alpha score is 0.873, indicating strong internal consistency and reliability. Most respondents supported the deployment of autonomous road vehicles for public transportation and said they would improve public transportation quality and accessibility. Technical issues and legal liabilities worried responders. The mean scores for the seven autonomous car benefits were similar, showing that respondents did not strongly prefer any benefit. After assessing the socioeconomic status and concerns, the study indicated that people who saw greater benefits were more tolerant of autonomous vehicles. Most respondents also wanted a clearer explanation of their legal responsibilities in case of an accident, thought human operators should play a major role in the future, and supported government trials of autonomous vehicles before their widespread usage. The study’s findings can help policymakers and stakeholders increase public acceptance of new transportation solutions such as autonomous vehicles, and improve future mobility safety and sustainability.

Sensitivity Analysis of the Spatial Parameters in Modelling the Evolutionary Interaction Between Autonomous Vehicles and Other Road Users

The road user network is a dynamic, ever-evolving population in which road users interact to share and compete for road space. The advent of autonomous road vehicles (ARVs) will usher in numerous opportunities and challenges in road user dynamics. One of the challenges is whether an ARV population would be able to successfully enter the existing road user space. Previous work demonstrates that successful introduction of ARVs into the road network must consider the evolutionary dynamics of the existing population. This study examines the effect of different spatial parameters as starting conditions for the introduction of a small population of ARVs into a resident population of human-driven vehicles (HDV). The model utilises the concept of evolutionary game theory and uses a square lattice grid with a novel agent mobility approach. The results show that ARV success exhibits significant sensitivity to variations in initial cluster size, position, and travel range. ARVs seem to perform best in fewer, larger clusters with a shorter travel range. This suggests that the best form of early ARV introduction may take the shape of centralised, highly co-operative fleets of local passenger or freight transport.

Integration of Robust Control with Reinforcement Learning for Safe Autonomous Vehicle Motion

This paper presents a control design framework for the integration of robust control and reinforcement learning-based (RL) control agent. The proposed integration method is applied for motion control of autonomous road vehicles, providing safe motion. In the integrated motion control, longitudinal and lateral dynamics are incorporated. The high-performance motion of the vehicle, e.g., high-velocity motion, path following, and reduction of lateral acceleration, through the RL-based control agent is achieved. The training through Proximal Policy Optimization during episodes is performed. Safe motion with guaranteed performances, i.e., keeping limits on lateral error, through the robust control and the supervisor is achieved. The robust control is designed through the H∞ method, and in the supervisor, a constrained quadratic programming task is performed. As a result, lateral and longitudinal control inputs of the vehicle are calculated by the integrated control system. The effectiveness of the proposed control method using simulation scenarios and test scenarios on a small-scaled test vehicle is illustrated.

High-Resolution Spectral Estimation for Continuous Wave Jamming Mitigation of GNSS Signals in Autonomous Vehicles

Future autonomous vehicles will rely mainly on global navigation satellite system (GNSS) receivers for positioning services. However, GNSS cannot maintain an accurate, continuous and reliable navigation solution in the presence of jamming. The widespread availability of in-car jammers or personal privacy devices (PPDs) made GNSS receivers an attractive target for signal jamming. Jammers not only jeopardize current positioning and timing services; they can indeed endanger the safety of the evolving intelligent transportation, autonomous road vehicles and critical infrastructure. The disruption of GNSS signal in some applications, especially safety-critical ones can lead to crucial consequences and risks such as loss of time synchronization and potential loss of life, to name a few. Thus, it is essential for future autonomous vehicles and transport service providers to deploy reliable GNSS anti-jamming techniques. This paper introduces a novel anti-jamming technique based on a high-resolution spectral estimation that utilizes fast orthogonal search (FOS) algorithm in which the jamming signal is modeled using a set of candidate functions and then eliminated from the received signal. The performance of the proposed method is assessed using experiments obtained from Spirent_TM GSS6700 simulation system. The jamming signal is either obtained from a real jammer or simulated using interference signal generator that is connected to Spirent_TM system. The results showed that the developed anti-jamming algorithm was able to successfully suppress the continuous wave (CW) interference signal, thus, the performance of the acquisition, tracking and navigation modules within a GPS software receiver were all enhanced.

Enabling Safe and Sustainable Medical Deliveries by Connected Autonomous Freight Vehicles Operating within Dangerous Goods Regulations

Health service providers in developed nations are responsible for 5% of their national carbon emissions, much of which originate from transport and supply chains. Connected autonomous freight vehicles (CAV-Fs) offer the potential to reduce this impact and enable lower cost operations, with trials being explored across the world. Transportation and carriage regulations, particularly in relation to the movement of dangerous goods (DG) such as medicines and diagnostic specimens, have not been developed for and applied to this new transport mode, particularly where loads are unaccompanied. Through an audit of current legislation and practice, this paper evaluates current DGs regulations applied to the transportation of medical products and medicines by autonomous road vehicles. Where existing regulations are not appropriate for CAV-Fs, recommendations and adaptations have been proposed to support safe and practical application. Remote monitoring and tracking of vehicles are critical for ensuring load security, quick and effective incident response, and management of documents and communications between parties. Loading/unloading procedures are significantly more important than in crewed vehicles, with load segregation and recording of all activity being of key importance. Other recommendations relate to training provision, vehicle specifications, and product health monitoring.

Deep and Transfer Learning Approaches for Pedestrian Identification and Classification in Autonomous Vehicles

Pedestrian detection is at the core of autonomous road vehicle navigation systems as they allow a vehicle to understand where potential hazards lie in the surrounding area and enable it to act in such a way that avoids traffic-accidents, which may result in individuals being harmed. In this work, a review of the convolutional neural networks (CNN) to tackle pedestrian detection is presented. We further present models based on CNN and transfer learning. The CNN model with the VGG-16 architecture is further optimised using the transfer learning approach. This paper demonstrates that the use of image augmentation on training data can yield varying results. In addition, a pre-processing system that can be used to prepare 3D spatial data obtained via LiDAR sensors is proposed. This pre-processing system is able to identify candidate regions that can be put forward for classification, whether that be 3D classification or a combination of 2D and 3D classifications via sensor fusion. We proposed a number of models based on transfer learning and convolutional neural networks and achieved over 98% accuracy with the adaptive transfer learning model.

Stability of Interval Type-3 Fuzzy Controllers for Autonomous Vehicles

Economic efficient Autonomous Road Vehicles (ARVs) are invariably subjected to uncertainties and perturbations. Therefore, control of vehicle systems requires stability to withstand the effect of variations in the nominal performance. Lateral path-tracking is a substantial task of ARVs, especially in critical maneuvering and cornering with variable speed. In this study, a new controller on the basis of interval type-3 (T3) fuzzy logic system (FLSs) is designed. The main novelties and advantages are as follows. (1) The uncertainty is a main challenge in the path-following problem of ARVs. However, in the fuzzy-based approaches, the bounds of uncertainty are assumed to be known. However, in the our suggested approach, the bounds of uncertainties are also fuzzy sets and type-3 FLSs with online adaptation rules are suggested to handle the uncertainties. (2) The approximation errors (AEs) and perturbations are investigated and tackled by the compensators. (3) The bounds of estimation errors are also uncertain and are estimated by the suggested adaptation laws. (4) The stability is ensured under unknown dynamics, perturbations and critical maneuvers. (5) Comparison with the benchmarking techniques and conventional fuzzy approaches verifies that the suggested path-following scheme results in better maneuver performance.

On Addressing Heterogeneity in Federated Learning for Autonomous Vehicles Connected to a Drone Orchestrator

In this paper we envision a federated learning (FL) scenario in service of amending the performance of autonomous road vehicles, through a drone traffic monitor (DTM), that also acts as an orchestrator. Expecting non-IID data distribution, we focus on the issue of accelerating the learning of a particular class of critical object (CO), that may harm the nominal operation of an autonomous vehicle. This can be done through proper allocation of the wireless resources for addressing learner and data heterogeneity. Thus, we propose a reactive method for the allocation of wireless resources, that happens dynamically each FL round, and is based on each learner’s contribution to the general model. In addition to this, we explore the use of static methods that remain constant across all rounds. Since we expect partial work from each learner, we use the FedProx FL algorithm, in the task of computer vision. For testing, we construct a non-IID data distribution of the MNIST and FMNIST datasets among four types of learners, in scenarios that represent the quickly changing environment. The results show that proactive measures are effective and versatile at improving system accuracy, and quickly learning the CO class when underrepresented in the network. Furthermore, the experiments show a tradeoff between FedProx intensity and resource allocation efforts. Nonetheless, a well adjusted FedProx local optimizer allows for an even better overall accuracy, particularly when using deeper neural network (NN) implementations.

A Dual-Mode Medium Access Control Mechanism for UAV-Enabled Intelligent Transportation System

With the exponential growth in technologies for the vehicular Internet of things applications and high demands for autonomous road vehicles, future transportation systems are projected to be revolutionized on a global scale. This new landscape requires a stable, flexible, and business-friendly base of connectivity, networking, and computing technology, in which Unmanned Aerial Vehicles (UAVs) can play an important role. A UAV-enabled Intelligent Transportation System (ITS) can provide a cost-effective communication solution to improve the safety and efficiency of the transportation system, particularly if the data traffic is nonhomogeneous and nonstationary. Typically, wireless is the communication medium between vehicles and UAVs in an ITS setting, which is based on the IEEE802.11p MAC protocol adopted by car manufactures. However, the IEEE 802.11p MAC protocol is modified solely for omnidirectional antennas, which restricts network coverage, delay, and throughput. In comparison, the directional antenna has greater network coverage, spatial reuse, and bandwidth. In addition, a multiaccess edge computing (MEC) facility at the backhaul link will provide ultralow latency and high bandwidth services to meet the increasingly growing demand for latency-sensitive vehicle applications such as vehicular video data analytics, autonomous driving, and intelligent navigation. Therefore, this article aims to propose a novel dual-mode MAC protocol that can work in two antenna modes, i.e., directional and omnidirectional. For modeling and simulation purposes, we use the Optimized Network Engineering Tool (OPNET) and aim to seek an evaluation with respect to throughput, media access delay, and retransmission attempts. The results obtained demonstrate the effectiveness of the proposed scheme.

A Waypoint Tracking Controller for Autonomous Road Vehicles Using ROS Framework.

Automated Driving Systems (ADSs) require robust and scalable control systems in order to achieve a safe, efficient and comfortable driving experience. Most global planners for autonomous vehicles provide as output a sequence of waypoints to be followed. This paper proposes a modular and scalable waypoint tracking controller for Robot Operating System (ROS)-based autonomous guided vehicles. The proposed controller performs a smooth interpolation of the waypoints and uses optimal control techniques to ensure robust trajectory tracking even at high speeds in urban environments (up to 50 km/h). The delays in the localization system and actuators are compensated in the control loop to stabilize the system. Forward velocity is adapted to path characteristics using a velocity profiler. The controller has been implemented as an ROS package providing scalability and exportability to the system in order to be used with a wide variety of simulators and real vehicles. We show the results of this controller using the novel and hyper realistic CARLA Simulator and carrying out a comparison with other standard and state-of-art trajectory tracking controllers.

Understanding Autonomous Road Public Transport Acceptance: A Study of Singapore

This study examines the perceptions of concerns and benefits surrounding autonomous road vehicles deployed for public transport, their relationships with public acceptance, and what the public prefers during its implementation. Surveying 210 participants in Singapore, we found a general acceptance of the deployment of autonomous road public transport in Singapore with agreement that introducing them would be beneficial, particularly in improving public transport reliability and accessibility. However, they reported concerns in the areas of technical-related issues and legal liability. Participants who perceived greater benefits were also likely to report greater acceptance, even after taking into account their concerns and sociodemographic backgrounds. Participants also reported preferences for human operators to continue playing an active role, the government to test the autonomous vehicles extensively before making them available for public use and greater clarity on the legal liability when accidents involving autonomous vehicles occur when autonomous road public transport is eventually implemented.

EKF-Neural Network Observer Based Type-2 Fuzzy Control of Autonomous Vehicles

This paper proposes a novel robust path-following strategy for autonomous road vehicles based on type-2 fuzzy PID neural network (PIDT2FNN) method coupled to an Extended Kalman Filter-based Fuzzy Neural Network (EKFNN) observer. Uncertain Gaussian membership functions (MFs) are employed to self-adjust the universe of discourse for MFs using the adaptation mechanism derived from Lyapunov stability theory and Barbalat's lemma. External disturbances are significant in autonomous vehicles by changing the driving condition. Furthermore, parametric uncertainties related to the physical limits of tires and the change of the vehicle mass may significantly affect the desired performance of autonomous vehicles. The robustness of the proposed controller against the parametric uncertainties and external disturbances is compared with one active disturbance rejection control (ADRC) algorithm, and a linear-quadratic tracking (LQT) method. The obtained results in terms of the maximum error and root mean square error (RMSE), demonstrate the effectiveness of the proposed control algorithm to reach the minimized path-tracking error.

Scenario-based definition of technical safety requirements for autonomous road vehicles

The article provides a brief overview of the standards ISO 26262 and ISO 21448 and the safety life cycle defined therein. A method for technical requirements development based on road situation statistics is proposed. Possibilities for improvement of safety life cycle for autonomous vehicles using traffic data are considered. An outlook towards the implementation of traffic scenarios into the safety lifecycle is briefly described.

Autonomous road vehicles: recent issues and expectations

The automotive industry is currently facing an automated driving revolution. This technology is tightly linked to societal and economic challenges: minimisation of traffic accidents, fuel consumption, traffic congestion, parking demand, and providing mobility for an ageing population, as well as to customer needs toward more personalised services. This study aims at the analysis and presentation of the current state of the art and prospects of automated vehicles (AVs) from various perspectives. This study concentrates on revision of the critical technologies, estimation of the impact on social aspects, identification of legal issues, consideration of factors in commercial success through user acceptance, and foresight carried out by other researchers. The primary material was prepared by review and analysis of research papers, standards, regulations, roadmaps, and projects in the field of AVs technology and its implementation worldwide. A SWOT analysis was performed, and it was found that for rapid AV spread, technological solutions need to be made taking into account law and regulation; user acceptance and human-robot interaction need to be solved together as part of one system.

Maneuver Classification for Road Vehicles with Constrained Filtering Techniques

Abstract Environment perception and situation awareness are keystones for autonomous road vehicles. The problem of maneuver classification for road vehicles in the context of multi-model state estimation under model uncertainty is addressed in this paper. The conventional approach is to define different motion models that match the desired type of movements. In this work we used a single motion model as a starting point and applied constraints to construct such filters that are fine tuned for the predefined maneuvers. The estimation is carried out in the interacting multiple model framework, where the elemental filters are constrained Kalman filters. To capture the characteristics of the considered maneuvers linear equality and non-equality state constraints were used. The performance of the proposed method is demonstrated in a simulation environment participating an observer and a maneuvering vehicle.

Deep reinforcement‐learning‐based driving policy for autonomous road vehicles

In this work the problem of path planning for an autonomous vehicle that moves on a freeway is considered. The most common approaches that are used to address this problem are based on optimal control methods, which make assumptions about the model of the environment and the system dynamics. On the contrary, this work proposes the development of a driving policy based on reinforcement learning. In this way, the proposed driving policy makes minimal or no assumptions about the environment, since a priori knowledge about the system dynamics is not required. Driving scenarios where the road is occupied both by autonomous and manual driving vehicles are considered. To the best of our knowledge, this is one of the first approaches that propose a reinforcement learning driving policy for mixed driving environments. The derived reinforcement learning policy, firstly, is compared against an optimal policy derived via dynamic programming, and, secondly, its efficiency is evaluated under realistic scenarios generated by the established SUMO microscopic traffic flow simulator. Finally, some initial results regarding the effect of autonomous vehicles' behavior on the overall traffic flow are presented.