Passenger-driven framework for evaluating the safety of connected and autonomous vehicles in critical situations

Advances in IoT and IoV technology have made connected autonomous vehicles (CAVs) data sources. Using CAVs as data sources and in incident management algorithms can create faster, more reliable, and more effective algorithms. This paper proposes a modified standard normal deviation (MSND) incident detection algorithm that uses CAVs as data sources and considers multiple traffic parameters. MSND is utilized in conjunction with two other incident detection algorithms, Standard Normal Deviation (SNS) and California (CAL), in a method of incident management known as Variable Speed Limits (VSL). SUMO Traffic Simulation Software is used to evaluate the effectiveness of the proposed method. A 10.4-kilometer road network is developed. Numerous scenarios are simulated on this road network, with variables including traffic demand, autonomous vehicle penetration rate, incident location, incident length, and incident lane. On the effectiveness metrics of detection rate, false alarm rate, and mean time to detect, simulation results demonstrate that the proposed method outperforms the SND and California methods. In terms of detection rate, the MSND algorithm performs the best, with a 12.27% improvement over the SND algorithm and a 21.99% improvement over the California method. After integrating all incident detection algorithms with the VSL traffic management method and simulating each combination, it was determined that the MSND-VSL integration reduced average density in the critical region by 19.73 percent, followed by SND-VSL with a 13.94 percent reduction and CAL-VSL with a 9.9 percent reduction.

Connected autonomous vehicles (CAVs) may offer benefits, such as fewer traffic accidents and a lower environmental impact, but they also raise concerns about issues such as liability in case of an accident. This dissertation explores which psychological factors influence the overall evaluation of CAVs, and intention to use CAVs.<br/><br/>We found that people evaluate CAVs more favourably when they more strongly believe CAVs are safe, can meet their mobility needs, and are environmentally friendly. Additionally, people evaluate CAVs more favourably the more they believe that many close others will use CAVs, and when they feel better able to use CAVs.<br/><br/>The intention to use CAVs is higher when people more strongly believe CAVs are enjoyable to drive, safe, trustworthy, and able to meet their mobility needs. After experiencing a CAV in a driving simulator, people believe CAVs are safer and more trustworthy than before the experience. Complexity of the driving environment does not influence intention to use CAVs, meaning that intention to use CAVs is similar for both urban (complex) and clear motorway (easy) situations.<br/><br/>How a CAV is presented affects people’s perceptions of the vehicle. When a CAV is presented as more humanlike, rather than machine-like, people evaluate CAVs and different characteristics of CAVs, such as safety, more positively. Both the evaluation and intention to use of CAVs may be enhanced or decreased by addressing the characteristics of CAVs that we discussed above.

Connected autonomous vehicle (CAV) systems could bring considerable benefits to our daily lives, and possibly outperform single autonomous vehicle (AV). Nevertheless, the real-time determination of the optimal route for each connected autonomous vehicle (CAV) within a continuous space presents a considerable challenge. This difficulty arises from the exponential growth of potential motion combinations for CAVs, considering the diverse road geometries they encounter. This article proposed a CAV group planning framework to overcome this challenge. The framework works hierarchically. The global and local controllers play a crucial role in generating long-term reference paths for each CAV by employing a versatile road geometry model capable of accommodating diverse road shapes. Initially, waypoints are extracted utilizing this generalized road geometric model. Subsequently, potential combinations of waypoints are generated by considering the CAV group as a fleet. Finally, optimal waypoint combinations are assigned to each CAV by considering the CAVs’ own benefit and road usage. Reference paths for each CAV are generated using the selected waypoints and are passed on to the CAVs and roadside units (RSUs) layer. The CAVs and RSUs generate short-term motion, given the reference paths. This is operated in the Frenet frame, and the optimal motion for each CAV is selected in the aspect of the entire CAV fleet. The proposed framework is tested in simulation and has shown the ability to generate safe and sound paths under various road geometries with obstacles and in mixed traffics in real time.

The paper investigates the impacts and barriers posed by connected autonomous vehicles (CAVs) for pedestrians with visual impairment. This study uses a customized web-based survey of visually impaired people from Canada and abroad. Collected data are used to estimate econometric models to identify the critical factors that affect the level of trust in CAVs and the preference for using CAVs from the visually impaired individuals’ perspective. Separate models are estimated for Canadian and non-Canadian samples, as Canadian and non-Canadian participants show some differences in perception and positive attitude towards CAVs. The models reveal that the majority of the respondents prefer to get feedback and alerts from CAVs. Congenitally blind Canadians are less likely to trust CAVs, but non-Canadian congenital blinds tend to trust CAVs. The models also indicate that the respondents who experienced being near an accident with an electric vehicle (EV) are less likely to choose CAVs. Respondents who rely on mobile applications and technology-based devices for navigating purposes tend to trust CAVs. Blind people who rely on conventional navigation tools (e.g., white cane, guide dog, etc.) are less likely to be the users of CAVs. Gender effect is visible, as the female participants tend not to trust CAVs. In relation to policy recommendations, subsidies should be provided to various advocacy groups to offer orientation and mobility (O&amp;M) training services, which are pivotal to educate how to use technology-based navigational services. Also, automobile manufacturers should be enforced to add acoustic vehicle alert systems (AVAS) to both EVs and CAVs.

Space-weighted information fusion using deep reinforcement learning: The context of tactical control of lane-changing autonomous vehicles and connectivity range assessment

Increasing traffic capacity of mixed traffic at signalized traffic intersections using delayed self reinforcement

Road intersections represent the primary bottleneck in transportation systems and connected autonomous vehicles (CAVs) have the potential to aleviate the problem through communication and coordination. As such, this work proposes a novel framework where, accounting for CAVs' location uncertainty, an intersection manager (IM) controls CAVs approaching a road crossing so as to maximize the number of admitted vehicles, while ensuring a guaranteed (tunable) level of safety. To fully exploit the communication links among the IM and the CAVs, several features are included in the proposed framework: (i) periodic re-optimizations of the CAVs' applied controls; (ii) periodic re-ordering of the intersection crossing sequence; and (iii) event-based control and ordering optimizations to achieve the best possible trade-off between complexity and performance. The proposed framework is able to improve both the number of admitted CAVs to the intersection and the CAVs' average speeds as compared to relevant state-of-the-art solutions. Importantly, when event-triggering is applied, most of the benefits introduced by periodic optimizations are retained, while at the same time the number of re-optimizations required are reduced by 47.6% (34.18%) during average (heavy) traffic conditions.

Human-driven vehicles (HDVs) will share the road with connected autonomous vehicles (CAVs) in the near future. Accordingly, the investigation of the interactive behavior of HDV drivers toward CAVs is becoming critical. In this study, a questionnaire survey was first conducted. The heterogenous clusters of HDV drivers were revealed through the latent profile analysis based on the collected dataset, with the focus on their trust and familiarity with CAVs, their attitudes towards sharing the road with CAVs, and their risk perception and perceived behavior control when they faced the CAVs. Subsequently, the correlation between the respective latent cluster and several socio-demographic factors was understood based on the multinomial logistic regression model, and the choice behavior of each cluster in different interactive driving scenarios was revealed. Three vital findings were reported. (1) Three profile clusters of HDV drivers (i.e., negative individuals, neutral individuals, and positive individuals) were revealed. (2) The drivers of a low/middle income and with a long driving experience were more likely to be negative individuals, whereas the CAV experience can make drivers feel positive towards CAVs. (3) Negative individuals might give up on changing lanes when a CAV platoon driving was noticed in the target lanes; in addition, they might raise more rigorous requirements for vehicle spacing in the lane-changing process when finding CAVs driving in the target lanes. To be specific, negative and neutral individuals preferred driving in front of the CAV platoons. The findings can provide references for developing effective management measures or CAV control strategies for transportation systems.

In the transition era towards connected autonomous vehicles (CAVs), the sharing of the roadway by CAVs and human-driven vehicles (HDVs) in a mixed-traffic stream is expected to pose safety and flow efficiency concerns even though CAVs may tend to adopt rather conservative maneuvering policies. Unfortunately, this will likely cause HDV drivers to unduly exploit such conservativeness by driving in ways that imperil safety. A context of this situation is lane-changing by the CAV, a potential major source of traffic disturbance at multi-lane highways that could impair their traffic flow efficiency. In dense, high-speed traffic conditions, it will be extremely unsafe for the CAV to change lanes without cooperation from neighboring vehicles in the traffic stream. To help address this issue, this paper developed a framework through which connected HDVs (CHDVs) could cooperate to facilitate safe and efficient lane-changing by the CAV. A numerical experiment was carried out to demonstrate the efficacy of the framework. The results indicated the CAVs’ lane-changing feasibility and the overall duration of the lane-changing if the CAV carries out that maneuver. It was observed that throughout the lane-changing process, the safety of not only the CAV but also of all neighboring vehicles, was promoted through the framework’s collision avoidance mechanism. The overall traffic flow efficiency was analyzed in terms of the ambient level of CHDV–CAV cooperation. Overall, the results of the study present evidence of how CHDV–CAV cooperation can help enhance the overall system efficiency.

Connected Autonomous Vehicles (CAVs) are expected to enable reliable, efficient, and intelligent transportation systems. Most motion-planning algorithms for multi-agent systems implicitly assume that all vehicles/agents will execute the expected plan with a small error and evaluate their safety constraints based on this fact. This assumption, however, is hard to keep for CAVs since they may have to change their plan (e.g., to yield to another vehicle) or are forced to stop (e.g., a CAV may break down). While it is desired that a CAV never gets involved in an accident, it may be hit by other vehicles and, sometimes, preventing the accident is impossible (e.g., getting hit from behind while waiting at a red light). Responsibility-Sensitive Safety (RSS) is a set of safety rules that defines the objective of CAVs to blame, instead of safety. Thus, instead of developing a CAV algorithm that will avoid any accident, it ensures that the ego vehicle will not be blamed for any accident it is a part of. Original RSS rules, however, are hard to evaluate for merge, intersection, and unstructured road scenarios, plus RSS rules do not prevent deadlock situations among vehicles. In this article, we propose a new formulation for RSS rules that can be applied to any driving scenario. We integrate the proposed RSS rules with the CAV’s motion planning algorithm to enable cooperative driving of CAVs. We use Control Barrier Functions to enforce safety constraints and compute the energy optimal trajectory for the ego CAV. Finally, to ensure liveness, our approach detects and resolves deadlocks in a decentralized manner. We have conducted different experiments to verify that the ego CAV does not cause an accident no matter when other CAVs slow down or stop. We also showcase our deadlock detection and resolution mechanism using our simulator. Finally, we compare the average velocity and fuel consumption of vehicles when they drive autonomously with the case that they are autonomous and connected.

Utilizing intelligent transportation infrastructures can significantly improve the throughput of intersections of Connected Autonomous Vehicles (CAV), where an Intersection Manager (IM) assigns a target velocity to incoming CAVs in order to achieve a high throughput. Since the IM calculates the assigned velocity for a CAV based on the model of the CAV, it's vulnerable to model mismatches and possible external disturbances. As a result, IM must consider a large safety buffer around all CAVs to ensure a safe scheduling, which greatly degrades the throughput. In addition, IM has to assign a relatively lower speed to CAVs that intend to make a turn at the intersection to avoid rollover. This issue reduces the throughput of the intersection even more. In this paper, we propose a space and time-aware technique to manage intersections of CAVs that is robust against external disturbances and model mismatches. In our method, RIM, IM is responsible for assigning a safe Time of Arrival (TOA) and Velocity of Arrival (VOA) to an approaching CAV such that trajectories of CAVs before and inside the intersection does not conflict. Accordingly, CAVs are responsible for determining and tracking an optimal trajectory to reach the intersection at the assigned TOA while driving at VOA. Since CAVs track a position trajectory, the effect of bounded model mismatch and external disturbances can be compensated. In addition, CAVs that intend to make a turn at the intersection do not need to drive at a slow velocity before entering the intersection. Results from conducting experiments on a 1/10 scale intersection of CAVs show that RIM can reduce the position error at the expected TOA by 18X on average in presence of up to 10% model mismatch and an external disturbance with an amplitude of 5% of max range. In total, our technique can achieve 2.7X better throughput on average compared to velocity assignment techniques.

Differential impacts of autonomous and connected-autonomous vehicles on household residential location

Статья посвящена архитектуре автономных (беспилотных) автомобилей, а также инфраструктуре для их эксплуатации. Автоматизированные транспортные средства обладают большим потенциалом для преобразования нашей жизни, создания умных городов и обеспечения эффективности в транспортировке людей и товаров. Однако, и потенциальный вред может быть намного больше, чем у исторических ошибок данных, связанных с мобильными устройствами, ноутбуками, рабочими местами или облачными технологиями. В работе используется термин CAV (Connected Autonomous Vehicles). В работе рассматривается основная физическая экосистема типичного автономного транспортного средства, которая включает в себя глобальную систему позиционирования (GPS), лидары, камеры, ультразвуковые и радиолокационные датчики, выделенные приемники связи. Конечно, отдельными физическими устройствами и необработанной информацией невозможно управлять во время движения, поэтому на CAV нужна компьютерная система, которая должна уметь взаимодействовать с внешним миром с очень малой задержкой. В работе рассматриваются уровни развития CAV, показано, что из органов человеческого восприятия мира в процессе вождения заменяет CAV. Также приведен сравнительный анализ сильных и слабых сторон по различным аспектам функции распределения между людьми и аппаратно-программными системами, а также оценка производительности датчиков во время движения по отношению к человеческому глазу. Обсуждается процесс поиска оптимальности этого взаимодействия. При этом CAV будут зависеть не только от физической, но и от цифровой инфраструктуры. Крайне важно, чтобы мы начали понимать необходимые изменения в планировании и проектировании инфраструктуры. Например, транспортные средства будут взаимодействовать и обмениваться данными друг с другом, а также обмениваться данными с инфраструктурой, такими как светофоры и указатели для пешеходов. Чтобы этот обмен был надежным, мы должны полностью учитывать как необходимые данные, так и их передачу. The article is devoted to the architecture of autonomous (unmanned) vehicles, as well as the infrastructure for their operation. Automated vehicles have great potential to transform our lives, create smart cities and ensure efficiency in transporting people and goods. However, potential harm may be much greater than historical data errors associated with mobile devices, laptops, workstations, or cloud technologies. The term CAV (Connected Autonomous Vehicles) is used in this work. The paper considers the main physical ecosystem of a typical autonomous vehicle, which includes the global positioning system (GPS), LIDARs, cameras, ultrasonic and radar sensors, and dedicated communication receivers. Of course, individual physical devices and raw information cannot be controlled while in motion, therefore, CAV needs a computer system that should be capable to interact with the outside world with a very low latency. The paper examines the levels of CAV development and shows that it replaces CAV from the organs of human perception of the world in the process of driving. It also provides a comparative analysis of strengths and weaknesses in various aspects of the distribution function between people and hardware-software systems, as well as an assessment of the performance of sensors during movement with respect to the human eye. The process of finding the optimality of this interaction is discussed. In this case, CAV will depend not only on the physical but also on the digital infrastructure. It is imperative that we begin to understand the necessary changes in infrastructure planning and design. For example, vehicles will interact and exchange data with each other, as well as exchange data with infrastructure, such as traffic lights and pedestrian signs. For this exchange to be reliable, we must fully take into account both the necessary data and their transfer.

We can find in the literature many research papers and technical reports tackling various problems related to the Autonomous Vehicles (AV) and Vehicle to everything (V2X) paradigms. However, safety guarantee of these technologies is the most critical problem to deal with because of its direct relation with human life. On one hand, we can find fewer works than the former, regarding the jointly study of the situations related to both AV and V2X. On the other hand, at our best of knowledge, there is no work investigating reliability in the transition phase when just a few of the Connected Autonomous Vehicle (CAV) are part of the traffic road. In this paper we explore this research gap, by analyzing and evaluating reliability of various CAV densities in the special case of four road intersection and for low traffic density. The results show that the convergence speed of reliability functions series to the reliability function of the system when only CAV populate the roads are not constant. This leads to the need of establishing solutions for the transitional phase to accompany the penetration process of the CAV in the automotive market.

Capacity of a freeway lane with platoons of autonomous vehicles mixed with regular traffic