Search

Technologies such as Autonomous Guided Vehicles (AGVs) and the Internet of Things (IoT) increasingly disrupt traditional manufacturing and production systems. However, there is a scarcity of empirical studies synthesising and evaluating the impact of disruptive technologies on existing manufacturing systems. This study examines the impact of AGVs applying IoT on Flexible Manufacturing Systems (FMS) through a case study demonstrating the integration of AGVs with IoT in a manufacturing company. As a concept, FMS was conceived decades ago; this study uses socio-technical systems theory to elaborate the concept of FMS into the current context. Key themes uncovered from the literature review include (i) AGVs in warehouse systems, (ii) AGV scheduling and routing, (iii) Human-machine interface, and (iv) integrating and controlling AGVs/IoT. The case study demonstrates how AGVs can create smart, flexible manufacturing systems by taking the following steps: (a) problem identification, (b) performance measurement, (c) designing the proposed solution, (d) evaluate IoT systems, (e) implementation of the new solution, and (f) future improvements. The study concludes with specific recommendations to implement Industry 4.0 in manufacturing companies. [ABSTRACT FROM AUTHOR]

This project convened a series of meetings and workshops to prioritize listening to multi-sector stakeholders from local government, advocacy, and industry in US cities where autonomous vehicles are operating. The objective was to listen and learn from all stakeholders, raise issues surrounding accessibility and equity, and to solicit responses. Key findings from the workshops include a consensus across the three sectors on the need for good channels of multi-stakeholder communication, and voices across all sectors agreed on the importance of disability access and serving diverse populations. Many parties, representing voices from all sectors, recognized that federal regulatory activities appear to be moving too slowly. Preventing any roadway incidents is a priority for many stakeholders, and some suggest a playbook for handling day-to-day roadway issues and common standards for first-responder interactions. Disability access is a high priority across all sectors, and there many see nearer term to accommodations for blind, hearing-impaired riders, but the timeline for providing service to people with non-folding wheelchairs is less clear. There is also ongoing debate surrounding the limits of regulatory purview, the role for cities, and how to actualize equitable expansion into rural areas. There is more work to do to advance a multi-sector dialogue around the role for local governments and community-based organizations in shepherding a safe, equitable and sustainable expansion of autonomous vehicles.

Robotaxi services, or rideshare operated by autonomous vehicles, present an opportunity for independent and convenient transportation for people with disabilities. The proliferation of robotaxis in California has been met with mixed reactions from the disability community. To better understand perceptions of and expectations for robotaxis, this report uses semi-structured interviews with representatives from disability advocacy organizations. For many people with disabilities, especially for people with intellectual, developmental, and/or physical disabilities, robotaxis are inaccessible. Given the intricacies of accommodating a wide audience, not all interviewees were confident that robotaxi design and programming will be inclusive. Some interviewees trusted that autonomous vehicle companies will independently pursue accessibility features in their robotaxis. Other interviewees regarded statewide accessibility standards as essential to ensure accessibility. Overall, interviewees shared that people with disabilities want to be included in the process of designing, testing, and regulating robotaxis. Implications for accessible robotaxi governance in California is presented, with an emphasis on wheelchair access, considering impact on public transportation service, and centering people with disabilities. Interviewees also discussed ideal accommodations that would allow a broad audience to request a ride, board the robotaxi, communicate with the operation system, and exit the vehicle. These findings may be useful to AV companies as they consider how robotaxis can accommodate people with a variety of disabilities.

This report explores opportunities for employing autonomous driving technology to dampen stop-and-go waves on freeways. If successful, it could reduce fuel consumption and emissions. This technology was tested in an on-road experiment with 100 vehicles over one week. Public stakeholders were engaged to assess the planning effort and feasibility of taking the technology to the next level: a pilot involving 1000+ vehicles over several months. Considerations included the possible geographical boundaries, target fleets of vehicles, and suitable facilities such as bridges or managed lanes. Flow smoothing technology may improve the user experience and operations of managed lanes or bridges, however it may require external incentives such as reduced tolls to entice the traveling public to use it. This must be matched with other goals such as verifying vehicle occupancy. It might be possible for some hybrid solution that addresses both challenges to provide a way forward. A concept of operations needs to be developed specifically for a target road geometry and a California partner. This concept should benefit from lessons learned from previous pilot projects and will need to be defined so as to achieve both (1) a penetration rate sufficient to achieve measurable effects; and (2) sufficient quality and quantity of data to confirm benefits.

Autonomous vehicles (AVs) heavily rely on machine learning-based perception models to accurately interpret their surroundings. However, these crucial perception components are vulnerable to a range of malicious attacks. Even though individual attacks can be highly successful, the actual security risks such attacks can pose to our daily life are unclear. Various factors, such as lack of stealthiness, cost-effectiveness, and ease of deployment, can deter potential attackers from employing certain attacks, thereby reducing the actual risk. This research report presents the first quantitative risk assessment for physical adversarial attacks on AVs. The specific focus is on attacks on AV’s perception components due to their highly critical function and representation in existing research. The report defines the daily-life risk as the likelihood that a given type of attack will be employed in real life and the authors develop a problem-specific risk scoring system and accompanying metrics. They perform an initial evaluation of the proposed risk assessment method for all the reported attacks on AVs from 2017 to 2023. They quantitatively rank the daily-life risks posed by each of eight different categories of attacks s and find three attacks with the highest risks: 2D printed images, 2D patches, and coated camouflage stickers, which deserve more focused attention for potential future mitigation strategy development and policy making.

Autonomous vehicle storage and retrieval systems (AVS/RSs) are widely used in e-commerce warehouses due to their high throughput and flexibility. In such systems, storage and retrieval transactions are performed by lifts and vehicles. This paper focuses on the sequencing retrievals problem in an AVS/RS, which is an important problem for daily operations. We formulate this sequencing problem as a mixed-integer program to determine a retrieval sequence for the lift and the vehicles, one that minimises the makespan. A dynamic programming approach is proposed to solve the sequencing problem to optimality. However, the solution time of the dynamic programming method is exponentially increasing in the number of retrieval requests. To be more practical, we present a beam search heuristic that can solve large-sized instances in reasonable time. Computational experiments verify that near-optimal solutions can be found by the beam search heuristic. Compared to commonly used heuristics and straightforward heuristics, the beam search decreases the makespan by up to 15%. Finally, we analyse how vehicle modes impact the makespan, showing evidence that a small makespan can be achieved when considering a realistic mode of vehicles. [ABSTRACT FROM AUTHOR]

In this article, a compact and high-gain, wide steering range and very low cross-polarization level holographic metasurface for beam steering is presented. The triangular modulated impedance surface is used for radiating the desired wave. The direction of the radiated beam is controlled through the varactor diode by changing the surface impedance of the device. The two prototypes of the designed device have been fabricated with two different varactor diodes. A higher gain of 11.7 dBi with a lower beam steering range of 25° and a radiation efficiency above 70% has been obtained from the device with a varactor diode SMV1405-079LF having lower parasitic resistance and larger capacitance properties. However, another fabricated device with higher parasitic resistance and lower capacitance property varactor diode SMV2201-40LF gives a lower gain of 9.1 dBi, a radiation efficiency below 55%, and a larger beam steering range of 61°. The experimental results are in good agreement with the simulation ones. The proposed device can be used for various applications like autonomous vehicles, toll plazas, and satellite communication. [ABSTRACT FROM AUTHOR]

Due to the cyber-physical nature of robotic vehicles, security is especially crucial, as a compromised system not only. exposes privacy and information leakage risks, but also increases the risk of harm in the physical world. As such, in this paper, we explore the current vulnerability landscape of robotic vehicles exposed to and thus remotely accessible by any party on the public Internet. Focusing particularly on instances of the Robot Operating System (ROS), a commonly used open-source robotic software framework, we performed new Internet-wide scans of the entire IPv4 address space, identifying, categorizing, and analyzing the ROS-based systems we discovered. We further performed the first measurement of ROS scanners in the wild by setting up ROS honeypots, logging traffic, and analyzing the traffic we received. We found over 190 ROS systems on average being regularly exposed to the public Internet and discovered new trends in the exposure of different types of robotic vehicles, suggesting increasing concern regarding the cybersecurity of today’s ROS-based robotic vehicle systems.

This article introduces the challenges presented in establishing governance of autonomous vehicles, dealing with questions of liability, where domestic law needs to cohere with international transport conventions, Islamic jurisprudence, Supreme Court jurisprudence, and technical safety standards. The primary objective of the article is to assess the applicability of established legal norms governing carrier liability in traditional road transport contracts in the United Arab Emirates. These legal tenets, rooted in Islamic jurisprudence and drawn from historical sources such as the 'Al-Ahkam Al-Adliya Journal,' constitute the foundation of civil law in numerous Arab countries, including the Arab Gulf States, Egypt, Jordan, Syria, and others. Melding legal and technical perspectives, this study provides legal insights for judges, arbitrators, and legal practitioners, and offers solutions to the liability challenges that may arise when autonomous vehicles begin operating on UAE streets or any other Arab country. [ABSTRACT FROM AUTHOR]

Autonomous vehicle (AV) companies are rolling out driverless taxi-type services in cities around the world, promising to enhance road safety, promote equity, and foster environmental sustainability while simultaneously threatening the jobs of current taxi and ride-hailing drivers. The potential impacts of these "robotaxi" services hinge upon not only whether AV technology becomes sufficiently performant, but also whether AV services become economically competitive. In this study, we develop ground-up cost models for a traditional taxi and a robotaxi service to compare their relative competitiveness. We draw on direct observations of commercially available robotaxi services, semi-structured interviews with AV operational and regulatory experts (N = 27), and archival documents to include the most detailed accounting of frontline robotaxi labor roles to date. We find that labor remains a significant cost for existing robotaxi services but that robotaxi operating costs are still lower than those of traditional taxi services. Ultimately, utilization rates and annual mileage will serve as the most influential factors for robotaxi competitiveness. Finally, if jobs shift from traditional taxi to robotaxi services, the total number of frontline jobs could decrease by between 57% and 76%, but the distribution of worker wages would shift higher. Transportation planners, researchers, and policymakers should continue accounting for labor costs in an AV future, as these costs will influence where AV deployment and job losses are (and are not) likely to occur, and should proactively investigate alternative career paths for potentially displaced frontline workers. Robotaxi costs are highly sensitive to lower labor ratios (i.e., fewer vehicles per worker), but firms reach economies of scale relatively quickly. Robotaxi firms should weigh marginal labor cost reductions against impacts to passengers and workers. • Fieldwork and semi-structured interviews identify additional labor roles for robotaxis. • Labor remains a significant operational cost for existing robotaxi services. • Robotaxi operating costs are still lower than those of traditional taxi services. • Utilization rates and annual mileage will be limiting factors for robotaxi competitiveness. • Shift from taxi to robotaxi services could decrease the total number of frontline jobs. [ABSTRACT FROM AUTHOR]

LiDAR-based 3D scene perception is a fundamental and important task for autonomous driving. Most state-of-the-art methods on LiDAR-based 3D recognition tasks focus on single-frame 3D point cloud data, ignoring temporal information. We argue that the temporal information across the frames provides crucial knowledge for 3D scene perceptions, especially in the driving scenario. In this paper, we focus on spatial and temporal variations to better explore temporal information across 3D frames. We design a temporal variation-aware interpolation module and a temporal voxel-point refinement module to capture the temporal variation in the 4D point cloud. The temporal variation-aware interpolation generates local features from the previous and current frames by capturing spatial coherence and temporal variation information. The temporal voxel-point refinement module builds a temporal graph on the 3D point cloud sequences and captures the temporal variation with a graph convolution module, transforming coarse voxel-level predictions into fine point-level predictions. With our proposed modules, we achieve superior performances on SemanticKITTI, SemantiPOSS and NuScenes. [ABSTRACT FROM AUTHOR]

This research estimated models for long-distance domestic passenger trips before and after the introduction of autonomous vehicles (AVs) and their application to a 10% synthetic US population. The authors synthesized 12.1M households and 28.1M individuals across 73,056 US census tracts. To generate disaggregated passenger trips, travel demand models, including trip frequency, season, purpose, party size, mode choice, and destination choice, and vehicle ownership models were estimated. Different datasets, including a 2021 long-distance AV survey, 2016/17 National Household Travel Survey (NHTS) survey, EPA Smart Location data, and FHWA rJourney dataset were used for model estimation. The model applications indicated AV ownership to be 0.33 per capita after the introduction of AVs within the marketplace with a $3500 AV technology cost premium in the year 2040. Total person-miles traveled per capita in long-distance trips was also estimated to rise 35% (from 280 to 379 miles per month). [ABSTRACT FROM AUTHOR]

Path tracking plays a critical role in autonomous driving for autonomous ground vehicle (AGV). However, AGV faces challenges in accurate tracking and chatter reduction due to external disturbances, making it difficult to meet the tracking performance requirements. Currently, sliding mode control (SMC) and disturbances observer are primarily employed for disturbance estimation. However, ensuring finite‐time robust control remains a significant challenge. To ensure rapid convergence of tracking errors and effective disturbance rejection, this paper proposed a novel non‐singular fast terminal sliding mode (NFTSM) control scheme based on finite‐time disturbance observation (FDO). First, a novel NFTSM controller based on AGV dynamic model is developed to achieve fast convergence of tracking errors. Then, to mitigate disturbances effects and suppress chatter, an innovative FDO method is employed. Finally, based on FDO, the NFTSM‐FDO establishes a control scheme that enhances disturbances suppression and accelerates convergence. The simulation and experimental results demonstrate the innovation of the proposed method. Compared with other SMC methods, the results validate the effectiveness and advantages of the proposed approach, exhibiting fast convergence and superior tracking performance. [ABSTRACT FROM AUTHOR]

High-speed autonomous vehicles can effectively improve the performance of obstacle-avoidance trajectory-planning and tracking control through integration with existing electronic control systems. However, relatively little research has been conducted in this field. This paper proposes a novel methodology of obstacle-avoidance trajectory-planning and tracking control based on active front-wheel steering integrated with tilting technology that can tilt the vehicle body toward the inside of the curve via active suspension when turning. The controller is designed using hierarchical control, in which the upper layer uses the point-mass vehicle model to design the trajectory-planning algorithm based on model predictive control. The lower layer uses the nonlinear vehicle model to design obstacle-avoidance tracking nonlinear model predictive control based on active steering integrated with tilt control. Then, the constrained nonlinear model predictive control problem is transformed into a constrained nonlinear programming problem, which is solved by sequential quadratic programming. Finally, simulations were performed using the CarSim/Simulink co-simulation platform. Two other hierarchical obstacle-avoidance tracking nonlinear model predictive controllers were designed as comparison objects. The simulation results show that the planning trajectory of the proposed integrated controller is closest to the obstacle. This controller effectively improves the vehicle obstacle-avoidance trajectory-tracking performance, handling stability, and maneuverability. [ABSTRACT FROM AUTHOR]

In this paper, we consider the path planning problem of the Unmanned Air‐Ground Vehicle (UAV‐UGV) system for large‐scale environmental persistent surveillance. The goal is to acquire a set of periodically visited surveillance nodes while minimizing the traveling distance. Some expected key problems are the limitations of UAV speed, UGV speed, UAV endurance, and UAV field of view. To address this issue, the path planning of UAV‐UGV surveillance system is modeled as a TSP optimization problem based on multiple constraints, aiming to minimize the total path length of the system to perform the task. UAV is responsible for visiting the surveillance node and UGV serves as a mobile charging station. And a two‐layer chaotic aptenodytes forsteri optimization algorithm (Two‐CAFO) is proposed to solve this problem. Our solution has been tested in several simulated and real‐world environments. The results demonstrate that the proposed Two‐CAFO has superior performance compared to other state‐of‐the‐art algorithms in solving the path planning problem for large‐scale environmental persistent surveillance tasks of UAV and UGV. © 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC. [ABSTRACT FROM AUTHOR]

Effective driving decision-making significantly enhances the safety of automated commercial vehicles. Different from small passenger vehicles mainly focusing on anti-collision, the inducements of collision and rollover for commercial vehicles are coupled with each other. However, these factors are not considered together which results in a limitation in the safety performance. This paper proposes a novel comprehensive driving decision-making methodology based on deep reinforcement learning (CDDM-DRL) for automated commercial vehicles in expressway scenarios. The CDDM-DRL consists of two parts. First, a feature encoding network is designed to encode hierarchical features from traffic situations and driving conditions, which can provide more useful feature information. Then an actor–critic network incorporating ensemble methods is developed to learn and provide effective driving actions, such as whether to turn and when to turn. Finally, extensive simulations in common and challenging scenarios with different traffic densities were performed. Experimental results show that our proposed method is better than some classical DRL methods in terms of time headway, backward clearance, lateral acceleration, etc. Moreover, it can prevent collision and rollover simultaneously, and realize safe driving decision-making for automated commercial vehicles. [ABSTRACT FROM AUTHOR]

Although full automation has not yet been achieved, automated vehicles are a valid research area. Not only would automated vehicles provide ultimate driver convenience, but they would maximize energy efficiency by eliminating undesired human driving behaviors and optimally controlling the powertrain. From the perspective of control related to energy saving, speed profile optimization is important for improving system efficiency and satisfying passenger demands. This study employs Dynamic Programming (DP) to solve the constrained optimal problem for travel time, distance, and speed limit by exploring all possible control options. The solutions obtained by DP demonstrate consistent control patterns combining four control modes—acceleration, cruising, coasting, and braking, with cruising or coasting being selective depending on the boundary conditions. This study introduces DP-based simulation results and attempts to provide comprehensive interpretations of the optimal policy by analyzing the essential factors that affect the control problem, including boundary conditions, road load, and powertrain characteristics. Based on these interpretations, the control concepts can be explained as the optimal policy selecting the best control option based on system efficiency and boundary conditions. The results of DP are compared with a human-like driver model to show that the optimal speed profiles can effectively reduce energy consumption. [ABSTRACT FROM AUTHOR]

With the rapid promotion of autonomous driving technology, it is extremely important to scientifically anticipate the related technologies and analyze their possible impact on urban road systems. The accuracy of detection and localization of traffic elements of autonomous driving is closely related to the ability of autonomous driving devices to make control decisions and the safety of autonomous driving. The study designs a new high-speed road driving scheme based on autonomous driving by analyzing the challenges related to urban traffic that may be brought about by unmanned driving. On the basis of the faster R-CNN algorithm, the context information around the target is introduced to locate and detect small-scale traffic signs. A new pedestrian detection model is designed, which is based on the feature pyramid network and introduces the SE module to highlight the features of the visible part of the pedestrian and reduce the missed detection rate caused by inter-class occlusion. The improved traffic sign detection framework improves the detection accuracy by 18.91% compared to the original faster R-CNN, while the enhanced pedestrian inspection method improves the detection accuracy by 14.00%. For both traffic sign detection and pedestrian detection accuracy and speed are improved compared to the original method. [ABSTRACT FROM AUTHOR]

Any moral algorithm for autonomous vehicles must provide a practical solution to moral problems of the trolley type, in which all possible courses of action will result in damage, injury, or death. This article discusses a hitherto neglected variety of this type of problem, based on a recent psychological study whose results are reported here. It argues that the most adequate solution to this problem will be achieved by a moral algorithm that is based on Confucian ethics. In addition to this philosophical and psychological discussion, the article outlines the mathematics, engineering, and legal implementation of a possible Confucian algorithm. The proposed Confucian algorithm is based on the idea of making it possible to set an autonomous vehicle to allow an increased level of protection for selected people. It is shown that the proposed algorithm can be implemented alongside other moral algorithms, using either the framework of personal ethics settings or that of mandatory ethics settings. [ABSTRACT FROM AUTHOR]

Objectives: This study aimed to investigate drivers' disengagement from nondriving related tasks (NDRT) during scheduled takeovers and to evaluate its impact on takeover performance. Background: During scheduled takeovers, drivers typically have sufficient time to prepare. However, inadequate disengagement from NDRTs can introduce safety risks. Method: Participants experienced scheduled takeovers using a driving simulator, undergoing two conditions, with and without an NDRT. We assessed their takeover performance and monitored their NDRT disengagement from visual, cognitive, and physical perspectives. Results: The study examined three NDRT disengagement timings (DTs): DT1 (disengaged before the takeover request), DT2 (disengaged after the request but before taking over), and DT3 (not disengaged). The impact of NDRT on takeover performance varied depending on DTs. Specifically, DT1 demonstrated no adverse effects; DT2 impaired takeover time, while DT3 impaired both takeover time and quality. Additionally, participants who displayed DT1 exhibited longer eye-off-NDRT duration and a higher eye-off-NDRT count during the prewarning stage compared to those with DT2 and DT3. Conclusion: Drivers can benefit from earlier disengagement from NDRTs, demonstrating resilience to the adverse effects of NDRTs on takeover performance. The disengagement of cognition is often delayed compared to that of eyes and hands, potentially leading to DT3. Moreover, visual disengagement from NDRTs during the prewarning stage could distinguish DT1 from the other two. Application: Our study emphasizes considering NDRT disengagement in designing systems for scheduled takeovers. Measures should be taken to promote early disengagement, facilitate cognitive disengagement, and employ visual disengagement during the prewarning period as predictive indicators of DTs. [ABSTRACT FROM AUTHOR]

Objective: This study investigated the effects of nondriving-related task (NDRT) touchscreen location and NDRT difficulty level on the driver task performance, eye gaze behavior, and workload during SAE Level 3 conditionally automated driving. Two driver tasks were considered: a visuomanual NDRT and a take-over task. Background: Touchscreens are expected to play important roles inside automated vehicles. However, few studies have investigated the driver-touchscreen interaction during automated driving. Method: A driving simulator experiment was conducted. The experimental task consisted of two successive subtasks: an NDRT followed by a take-over task. NDRT touchscreen location (Upper Left, Upper Right, and Lower Right) and NDRT difficulty level (Easy and Hard) were the independent variables. A set of driver task performance, eye gaze behavior, and perceived workload measures were employed for each subtask as the dependent variables. Results: NDRT touchscreen location significantly affected both the NDRT and the take-over task performance. Lower Right was superior to Upper Right in the NDRT performance but was inferior in the take-over task performance. NDRT touchscreen location affected the perceived physical workload of the NDRT. NDRT difficulty level affected the perceived workload of the take-over task. Conclusion: The research findings enhance our understanding of how NDRT touchscreen location and NDRT difficulty level impact the driver task performance during conditionally automated driving, and, further provide useful design implications and knowledge. Application: The study results would inform the NDRT touchscreen interface design and the NDRT design for conditionally automated vehicles. [ABSTRACT FROM AUTHOR]

Trajectory prediction plays a crucial and indispensable role in autonomous driving, enhancing safety and reliability, particularly in complex intersections with variable vehicle trajectories. This study aims to investigate the application of vehicle trajectory prediction in intersections and to improve the prediction accuracy of the model by utilizing multicolumn neural networks and self-attention mechanisms. Trajectory data were extracted using DataFromSky software from unmanned aerial vehicle (UAV)-captured aerial footage at specific intersections in Xi'an, Shaanxi Province, China. The deep learning model developed for trajectory prediction included a multicolumn (MC) neural network and a self-attention (SA) mechanism based on the gated recurrent unit (GRU). The model was abbreviated as MC-SA-GRU in this study. The multicolumn structure captures richer feature representations, whereas SA captures temporal correlations in time-series data. Experimental comparisons on corresponding data sets demonstrate the exceptional performance of these models in accurately predicting vehicle trajectories at intersections. This study contributes valuable insights for improving autonomous driving systems, advancing safety and reliability in real-world scenarios. Practical Applications: The results of this case study showed that combining deep learning time series models with plug-in modules effectively improved the accuracy of vehicle trajectory prediction. Vehicle trajectory prediction was a highly significant research problem in the field of autonomous driving, particularly in complex intersection scenarios. Accurate vehicle trajectory prediction had the potential to significantly enhance the safety and reliability of self-driving vehicles. The data utilized in this study were collected by an unmanned aerial vehicle at several specific intersections in Xi'an, Shaanxi Province, China. The proposed method was based on gated recurrent units, incorporating multicolumn neural networks to fully explore the potential features of the data, and included a self-attention (SA) mechanism to consider the temporal correlation of the data. It was compared with various benchmark methods, demonstrating excellent performance across various evaluation metrics. Experimental results validated the effectiveness of this approach. Thus, this research provided valuable insights for improving the safety and reliability of real-world autonomous driving systems. [ABSTRACT FROM AUTHOR]

To facilitate cooperation among connected automated vehicles (CAVs), such as cooperative platooning or cooperative lane changes in mixed traffic comprising CAVs, connected human-driven vehicles (CHVs), and conventional (unconnected) human-driven vehicles (HDVs), an ego CAV needs to discern which surrounding vehicles are connected (CAVs or CHVs) and which are unconnected (HDVs). Therefore, this paper introduces a surrounding vehicles identification system (SVIS) designed to enable CAVs to identify the connectivity status of surrounding vehicles. Unlike a previously developed preceding vehicle identification system that only identifies the connectivity of its immediately preceding vehicle, the proposed SVIS generalizes this identification to nearby surrounding vehicles. Furthermore, the proposed SVIS significantly reduces the error in the connected vehicle identification by integrating distance and the magnitude of velocity for matching instead of distance-only matching used by the previous system. The SVIS is a must to enable CAVs to form platoons via lane changes after a connected vehicle is detected in an adjacent lane. We compared a newly proposed distance-plus-speed-matching approach with a previously developed distance-only-matching approach using Next Generation Simulation (NGSIM) data. Through comparison, the efficacy of the proposed distance-plus-speed-matching SVIS is demonstrated to be considerably superior to that of the distance-only-matching SVIS. Given that a reliable and robust method for identifying surrounding connected vehicles is key to the successful formation of cooperative adaptive cruise control (CACC) platoons and cooperative lane changes, the proposed distance-plus-speed-matching SVIS would help quickly and efficiently form platoons in a mixed traffic environment. [ABSTRACT FROM AUTHOR]

Pedestrian intent prediction is an essential task for ensuring the safety of pedestrians and vehicles on the road. This task involves predicting whether a pedestrian intends to cross a road or not based on their behavior and surrounding environment. Previous studies have explored feature-based machine learning and vision-based deep learning models for this task but these methods have limitations in capturing the global spatio-temporal context and fusing different features of data effectively. To address these issues, we propose a novel hybrid framework HSTGCN for pedestrian intent prediction that combines spatio-temporal graph convolutional neural networks (STGCN) and long short-term memory (LSTM) networks. The proposed framework utilizes the strengths of both models by fusing multiple features, including skeleton pose, trajectory, height, orientation, and ego-vehicle speed, to predict their intentions accurately. The framework's performance have been evaluated on the JAAD benchmark dataset and the results show that it outperforms the state-of-the-art methods. The proposed framework has potential applications in developing intelligent transportation systems, autonomous vehicles, and pedestrian safety technologies. The utilization of multiple features can significantly improve the performance of the pedestrian intent prediction task. [ABSTRACT FROM AUTHOR]

Trajectory prediction is highly essential for accurate navigation. Existing deep learning-based approaches always encounter serious performance degradation when facing shifted data or unseen scenarios. For learning transferable representations across different scenarios, the promising pretraining technique is applied to trajectory prediction tasks. However, relevant studies employ point-level masking mechanisms, which cannot capture local motion information across multiple time steps. Additionally, for trajectory data that couples multiple motion states, extracting the temporal dependencies within each state sequence remains highly challenging. To tackle this issue, we propose a channel-independent pretrained network via tokenized patching for efficient vehicle trajectory prediction, and it is composed of tokenized patch masking, channel-independent extractor (CiE), and state decoupling-mixing (SDM). Specifically, first of all, based on the designed tokenized patching scheme, TPM is established to represent local information and long-term relations in masked sequences. Then, through a series of weight-shared dense layers, CiE is designed to capture the individual dependencies among state sequences in an unsupervised pretraining manner. Moreover, by decoupling the complicated trajectory into pseudo-state representations, SDM is proposed to independently reconstruct the state sequences and further carry out representation mixing operations, to realize available trajectory predictions. Finally, extensive experiments show that our framework is effective and achieves the state-of-the-art performance on the INTERACTION and Argoverse2 datasets. [ABSTRACT FROM AUTHOR]

As a prominent and appealing technology, neural networks have been widely applied in numerous fields, with one of the most notable applications being autonomous driving. However, the intrinsic structure of neural networks presents a black box problem, leading to emergent security issues in driving and networking that remain unresolved. To this end, we introduce a novel method for robust validation of neural networks, named as Dual Boundary Robust (DBR). Specifically, we creatively integrate adversarial attack design, including perturbations like outliers, with outer boundary defenses, in which the inner and outer boundaries are combined with methods such as floating-point polyhedra and boundary intervals. Demonstrate the robustness of the DBR's anti-interference ability and security performance, and to reduce the black box-induced emergent security problems of neural networks. Compared with the traditional method, the outer boundary of DBR combined with the theory of convex relaxation can appropriately tighten the boundary interval of DBR used in neural networks, which significantly reduces the over-tightening of the potential for severe security issues and has better robustness. Furthermore, extensive experimentation on individually trained neural networks validates the flexibility and scalability of DBR in safeguarding larger regions. [ABSTRACT FROM AUTHOR]

Copyright of Automatisierungstechnik is the property of De Gruyter and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Many companies and institutions focus on autonomous vehicles. Accordingly, the commercialization of fully autonomous vehicles is expected to proceed rapidly. Autonomous vehicle companies are already demonstrating or commercializing vehicles on real roads. However, autonomous vehicle data is not disclosed to the public, and related academic research is very rare. In this study, changes in the functional levels of autonomous driving sensors in various environments were analyzed using actual collected autonomous driving data. A hypothesis was established by reviewing previous studies related to the functional levels of sensors, and the hypothesis was verified by comparing actual autonomous driving data using two different statistical analysis methods. The hypothesis was tested using the 2-sample K-S test and the DTW algorithm, with different sensor elements used in each verification stage. As a result of the analysis, we found that sensor performance changed on rainy and cloudy days compared to sunny days. This study confirms that the functional levels of autonomous vehicle sensors change depending on the environment. The results of this study are expected to serve as foundational data for establishing standards and criteria for safety evaluations of autonomous vehicles in the future. [ABSTRACT FROM AUTHOR]

When humans and autonomous systems operate together as what we refer to as a hybrid team, we of course wish to ensure the team operates successfully and effectively. We refer to team members as agents. In our proposed framework, we address the case of hybrid teams in which, at any time, only one team member (the control agent) is authorized to act as control for the team. To determine the best selection of a control agent, we propose the addition of an AI manager (via Reinforcement Learning) which learns as an outside observer of the team. The manager learns a model of behavior linking observations of agent performance and the environment/world the team is operating in, and from these observations makes the most desirable selection of a control agent. From our review of current state of the art, we present a novel manager model for oversight of hybrid teams by our support for diverse agents and decision-maker operations across multiple time steps and decisions. In our model, we restrict the manager's task by introducing a set of constraints. The manager constraints indicate acceptable team operation, so a violation occurs if the team enters a condition which is unacceptable and requires manager intervention. To ensure minimal added complexity or potential inefficiency for the team, the manager should attempt to minimize the number of times the team reaches a constraint violation and requires subsequent manager intervention. Therefore, our manager is optimizing its selection of authorized agents to boost overall team performance while minimizing the frequency of manager intervention. We demonstrate our manager's performance in a simulated driving scenario representing the case of a hybrid team of agents composed of a human driver and autonomous driving system. We perform experiments for our driving scenario with interfering vehicles, indicating the need for collision avoidance and proper speed control. Our results indicate a positive impact on our manager, with some cases resulting in increased team performance up to \(\approx 187\%\) that of the best solo agent performance. [ABSTRACT FROM AUTHOR]

We explore the use of radiance fields (RFs) to reconstruct photorealistic 3D urban scenes, creating digital twins (DTs) for autonomous driving (AD) by leveraging Nerfacto and Splatfacto models integrated with the CARLA simulator. Our research demonstrates that publicly available RFs can be utilized through Nerfstudio library to create photorealistic urban scenes and extract arbitrary images based on the camera pose. These scenes can serve as simulations for AD or as DT repositories for static environments within the vehicular metaverse. Additionally, we quantitatively evaluate RF models and use masking to remove dynamic objects, successfully simulating real-world scenarios. Quantitative evaluation shows that the Splatfacto model achieves a peak signal-to-noise ratio (PSNR) of up to 26.40, a structural similarity index measure (SSIM) of 0.84, and a learned perceptual image patch similarity (LPIPS) score of 0.21, consistently outperforming the Nerfacto model. [ABSTRACT FROM AUTHOR]

In this paper, we present an adaptive optimal control algorithm for solving the tracking control problem of multiple autonomous surface vehicles under uncertain dynamics and unknown external disturbances. The proposed control algorithm uses an adaptive dynamic programming technique with optimal compensation terms. A disturbance observer is designed to handle the problem of unknown time-varying external disturbances. It is proven that all the signals in the closed-loop system are bounded. Simulation results are provided to illustrate the effectiveness of the proposed control algorithm. [ABSTRACT FROM AUTHOR]

Traffic-related fatalities, often caused by human error, present a global challenge. Autonomous vehicles (AVs), designed to reduce these fatalities by eliminating human error, still experience crashes. Prior research, limited by the scope of the data set and analytical depth, has not fully explored these factors, resulting in a lingering lack of clarity about the cause of the crashes. The study utilized a comprehensive dataset spanning from 2014 to May 2024 and implemented a stratified sampling alongside class weighting techniques to rectify imbalances within the crash data. A variety of machine learning algorithms such as logistic regression, decision trees, random forests, gradient boosting, bagging classifiers, and easy ensemble methods were utilized to perform the data analysis. The random forest model stood out for its balance in sensitivity and specificity, reducing false negatives. The study revealed that factors such as the extent of vehicle damage, the AV manufacturer, and type of collision were critical predictors of crash injuries. The research provides valuable insights for various stakeholders, including transportation professionals, AV manufacturers, and policymakers. The findings can guide the development of enhanced safety protocols, improved vehicle designs, and more informed policy frameworks aimed at reducing AV-related injuries. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Shanghai Jiaotong University (Science) is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

This study examines the multifaceted mechanisms driving the adoption of autonomous vehicle (AV) policy in the United States. Drawing from diffusion and network governance theories, it explores the intricate interplay between state governments, private industry, and shared mobility services in shaping AV policies. Several states like California, Nevada, and Texas have emerged as frontrunners in AV testing and innovation. However, policymakers grapple with unique challenges related to AV technology, including safety, liability, and infrastructure enhancement, necessitating innovative policy solutions. As AVs signify a transformative shift in transportation, state governments assume a pivotal role in policy innovation and experimentation. Using a blend of dyadic quantitative analysis and qualitative interviews, this study examines to what extent policy learning predominantly drives AV policy adoption. In doing so, we explore specific diffusion mechanisms, including policy learning and competitive dynamics, to understand how they shape the early adoption of AV policies across states. We find substantial evidence for interstate learning facilitated by intergovernmental organizations and the private sector. [ABSTRACT FROM AUTHOR]

In the wave of research on autonomous driving, 3D object detection from the Bird's Eye View (BEV) perspective has emerged as a pivotal area of focus. The essence of this challenge is the effective fusion of camera and LiDAR data into the BEV. Current approaches predominantly train and predict within the front view and Cartesian coordinate system, often overlooking the inherent structural and operational differences between cameras and LiDAR sensors. This paper introduces CL-FusionBEV, an innovative 3D object detection methodology tailored for sensor data fusion in the BEV perspective. Our approach initiates with a view transformation, facilitated by an implicit learning module that transitions the camera's perspective to the BEV space, thereby aligning the prediction module. Subsequently, to achieve modal fusion within the BEV framework, we employ voxelization to convert the LiDAR point cloud into BEV space, thereby generating LiDAR BEV spatial features. Moreover, to integrate the BEV spatial features from both camera and LiDAR, we have developed a multi-modal cross-attention mechanism and an implicit multi-modal fusion network, designed to enhance the synergy and application of dual-modal data. To counteract potential deficiencies in global reasoning and feature interaction arising from multi-modal cross-attention, we propose a BEV self-attention mechanism that facilitates comprehensive global feature operations. Our methodology has undergone rigorous evaluation on a substantial dataset within the autonomous driving domain, the nuScenes dataset. The outcomes demonstrate that our method achieves a mean Average Precision (mAP) of 73.3% and a nuScenes Detection Score (NDS) of 75.5%, particularly excelling in the detection of cars and pedestrians with high accuracies of 89% and 90.7%, respectively. Additionally, CL-FusionBEV exhibits superior performance in identifying occluded and distant objects, surpassing existing comparative methods. [ABSTRACT FROM AUTHOR]

The integration of Autonomous Vehicles (AVs) into our modern society hinges on gaining widespread acceptance from potential road users. To indicate the preparedness of these road users and elucidate their perspectives regarding the use of AVs in future, it is imperative to conduct surveys gauging public acceptance and satisfaction with this emerging mode of transportation. This paper reports the results of a comprehensive questionnaire study involving 1,000 individuals in Gyor City. The survey's primary objective was to assess participants' attitudes and willingness to embrace autonomous vehicles within the city's road networks. The study delved into various socio-demographic factors, such as age, gender, and employment status, while also exploring participants' prior knowledge and opinions regarding the advantages and limitations of AVs. The findings reveal a generally favorable disposition among the public toward the inclusion of AVs in urban traffic, paving the way for the acceptance of mixed traffic patterns. Notably, respondents in younger age groups exhibit greater enthusiasm for incorporating AVs into their daily transportation, whereas individuals aged 65 and above express more reservations, displaying a conservative outlook. Furthermore, participants with prior knowledge and a deeper understanding of AVs exhibit a markedly more positive inclination toward this emerging technology compared to those lacking such familiarity. [ABSTRACT FROM AUTHOR]

Streaming perception is a crucial task in the field of autonomous driving, which aims to eliminate the inconsistency between the perception results and the real environment due to the delay. In high-speed driving scenarios, the inconsistency becomes larger. Previous research has ignored the study of streaming perception in high-speed driving scenarios and the robustness of the model to object's speed. To fill this gap, we first define the full-speed domain streaming perception problem and construct a real-time meta-detector, StreamTrack. Second, to perform motion trend extraction, Swift Multi-Cost Tracker (SMCT) is proposed for fast and accurate data association. Meanwhile, the Direct-Decoupled Prediction Head (DDPH) is introduced for predicting future locations. Furthermore, we introduce the Uniform Motion Prior Loss (UMPL), which ensures stable learning of the model for rapidly moving objects. Compared with the strong baseline, our model improves the SAsAP (Speed-Adaptive steaming Average Precision) by 15.46 %. Extensive experiments show that our approach achieves state-of-the-art performance in the full-speed domain streaming perception task. [ABSTRACT FROM AUTHOR]

Identifying objects in real-time is a technology that is developing rapidly and has a huge potential for expansion in many technical fields. Currently, systems that use image processing to detect objects are based on the information from a single frame. A video camera positioned in the analyzed area captures the image, monitoring in detail the changes that occur between frames. The You Only Look Once (YOLO) algorithm is a model for detecting objects in images, that is currently known for the accuracy of the data obtained and the fast-working speed. This study proposes a comprehensive literature review of YOLO research, as well as a bibliometric analysis to map the trends in the automotive field from 2020 to 2024. Object detection applications using YOLO were categorized into three primary domains: road traffic, autonomous vehicle development, and industrial settings. A detailed analysis was conducted for each domain, providing quantitative insights into existing implementations. Among the various YOLO architectures evaluated (v2–v8, H, X, R, C), YOLO v8 demonstrated superior performance with a mean Average Precision (mAP) of 0.99. [ABSTRACT FROM AUTHOR]