This study examines the impact of conditionally automated driving vehicles (CADVs) handing control over to human drivers on the string stability of mixed traffic. It specifically considers various penetration rates of CADVs and different time-to-collision (TTC) thresholds set at 5, 7, and 9 s. To gather relevant vehicle trajectory data, driving simulator tests were performed, capturing both the normal car-following and the post-takeover processes. Then, the intelligent driver model parameters were calibrated for these two processes, respectively. Additionally, a car-following model was developed to incorporate the dynamic takeover process of CADVs within the heterogeneous traffic. Theoretical analysis was conducted to determine the string stability boundary of heterogeneous traffic, with numerical simulation tests performed to validate the results. The results indicate that the transition of control from CADVs to human drivers significantly contributed to the instability of mixed traffic. Specifically, a higher TTC correlated with more CADVs transferring control to human drivers. The increase in the takeover rate from CADVs to human drivers resulted in pronounced instability within heterogeneous traffic flows. Additionally, the simultaneous control transition of multiple CADVs was associated with reduced minimum platoon speed, exacerbating traffic congestion. Conversely, enhancing the permeability of CADVs led to smoother traffic conditions and suppressed the formation of unstable traffic waves. The findings underscore the significant impact that the transition of control from CADVs to human drivers has on the stability of heterogeneous traffic. This lays a crucial foundation for implementing cooperative safety control measures within such traffic systems. Moreover, implementing a 5-second takeover request lead time in automated driving systems can effectively reduce the takeover rate of CADVs, thereby enhancing overall traffic stability.

This article presents a novel formation tracking scheme for networked marine surface vehicles facing external disturbances, based on a stipulated-time stability that stipulates the actual settling time. By using a class of regulation functions, a distributed observer is firstly developed to accurately estimate the leader's state exactly at a stipulated time, and then a stipulated-time sliding mode control protocol is proposed to achieve the formation tracking. Unlike the existing predefined-time formation control works that only specify the upper bound for the settling time and may cause over-engineering solutions, the proposed scheme exhibits the following features: 1) the actual settling time for the tracking errors is almost prescribed by a single parameter, regardless of the initial conditions and 2) the initial control input magnitude and system overshoot can be effectively reduced by skillfully choosing the regulation function parameters. Simulation examples are ultimately provided to showcase the effectiveness of the proposed control scheme.

Generating synthetic driving scenarios in virtual environments is being actively studied for autonomous driving systems, whose safety is challenging to verify in physical environments. While several works proposed a way to describe such driving scenarios called Operational Design Domain (ODD), their syntax still lacks formal semantics, which makes it difficult to design trustworthy <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">compilers</i>—a software that converts an <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">abstract</i> scenario expressed in ODDs into a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">concrete</i> scenario executable in a virtual environment. We propose a systematic way to formalize the lane-level driving scenarios described using a subset of ASAM OpenSCENARIO syntax. In particular, our formalization exploits the concept of separating concerns in which an abstract scenario is described without exposing the low-level behavioral details of autonomous driving; the details can then be auto-filled during the concrete scenario generation via different objectives. We define the decision variables that need to be determined when generating concrete scenarios; then, we propose a set of constraint categories that restrict the valuation space of the variables according to the syntactic structure of an abstract scenario. We implemented two compiler designs as exemplar based on two solvers: one with SMT (Satisfiability Modulo Theories) and another MILP (Mixed-Integer Linear Programming) solvers, and show the qualitative and quantitative analysis of concrete scenarios auto-generated from an abstract one.

This paper studies the secure formation tracking (SFT) problem of networked marine surface vehicles (NMSVs) in the presence of denial of service (DoS) attacks, model uncertainties, external disturbances and actuator constraints. A cyber-physical framework is developed for designing the data-driven observer-based control (DDOBC) algorithm, which consists of two layers. In the cyber layer, a distributed resilient trajectory estimator is proposed to accurately estimate the information of virtual leader under DoS attacks over digraphs. In the physical layer, a neural network-based (NN-based) data-driven observer is firstly utilized to resolve the model uncertainties. Then, a observer-based local controller is designed to achieve the SFT problem with input saturations and actuator faults. The sufficient conditions for system convergence and stability are derived based on the Lyapunov stability theory. Finally, simulation experiments are conducted to verify the effectiveness of the theoretical results.

This paper proposes a novel Internet of Vehicles architecture, CFEA-IoV, designed to enhance accident notification using the IoV platform. Capitalizing on the advancements in software-defined networks, cloud computing, and fog computing, CFEA-IoV prioritizes reliability and timeliness in emergency response scenarios. It achieves this by leveraging SDN's global knowledge and programmability with cloud-based architecture, coupled with the low-latency services offered by fog computing. A key contribution of CFEA-IoV is a multisession genetic programming-based scheduling method for efficient packet routing. This method considers multiple factors, including multi-topology routing with high connectivity, route selection based on graph partition factors, reliability coefficients, and resource availability for packet forwarding. The effectiveness of CFEA-IoV is evaluated through simulations using the NS-3 tool, Crash Report Sampling System dataset, and Simulation of Urban Mobility to ensure realistic conditions and reliable outcomes. The results demonstrate the efficiency of the proposed solution, potentially leading to faster emergency response times and improved life-saving capabilities.

The development and testing of automotive perception systems require a large amount of labeled data. The ground truth of the measurement scene is usually generated by manual video annotation. However, besides requiring a lot of manual effort, it can be time-consuming. Moreover, since the annotation boxes must be transformed into the vehicle's BEV space, the result is often not precise enough due to the camera's poor depth estimation. The existing ground truth generation systems rely on extremely expensive sensor clusters, including LiDARs and GNSS RTK. In this paper, we present a novel semi-automatic ground truth generation tool that exclusively depends on a mono-vision camera and an automotive radar, eliminating the need for these costly sensors. The proposed system comprises an automatic pre-generation algorithm and an interactive GUI annotation tool. We present a novel pre-generation algorithm relying on offline tracking algorithms and fusing radar and camera data that exploits the offline nature of the problem and enhances the preciseness of depth estimation. The proposed system is evaluated on a highway section by comparing the automatically generated objects to the manually created ground truth. According to the results, the automatic pre-generation can significantly decrease the effort of manual annotation, which is also supported by a user-friendly GUI. Along with the theoretical background, the tool and the dataset used for this paper are provided on GitHub.

In vehicular ad-hoc networks (VANETs), ensuring passenger safety requires fast and reliable emergency message broadcasts. The current communication standard for messaging in VANETs is IEEE 802.11p. As IEEE 802.11p allows carrier-sense multiple access with collision avoidance (CSMA/CA) in the media access control (MAC) layer. A large contention window (<inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$CW$</tex-math></inline-formula>) value will increase delay, whereas a small <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$CW$</tex-math></inline-formula> value will increase the probability of collision. Therefore, adaptive regulation of the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$CW$</tex-math></inline-formula> value is needed to achieve high reliability and low delay in VANETs, in accordance with variations in the environment. However, the traditional MAC protocol cannot achieve the aforementioned requirements. Reinforcement learning (RL) emphasizes the selection of optimal action according to observations of the environment to achieve optimal system performance. In this study, a Q-learning (QL) RL algorithm based on IEEE 802.11p was used to achieve the requirements of adaptive broadcasting. Adaptive broadcasting was achieved based on a reward definition of high reliability and low delay for the QL algorithm. In this approach, the learning state is the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$CW$</tex-math></inline-formula> size, the system sets up a Q-table using RL, and the optimal action is based on the maximum Q-value. The <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$CW$</tex-math></inline-formula> size can be provided with adaptive self-regulation by RL, providing high reliability and low delay for the broadcast of emergency messages. We also compared our proposed scheme to other QL-based MAC protocols in VANETs by performing simulations and demonstrated that it can achieve high reliability and low delay for the broadcast of emergency messages.

Globally referenced and accurate positioning is of great significance for the application of intelligent vehicular systems. The visual and inertial measurement unit (IMU) integrated navigation system (VINS) is widely used in many intelligent positioning-based services. However, VINS are prone to drift over time and their performance is significantly compromised in urban canyons since the numerous outlier visual features caused by moving objects and unstable illuminations. Similarly, the global navigation satellite system (GNSS) is reliable in open areas but struggles with signal obstructions and reflections in urban canyons. To exploit the complementariness of the VINS and GNSS, this paper proposed a sliding window factor graph optimization (FGO)-based GNSS/Visual/IMU/Map (GVIM) integration, which exploits the full suit raw measurements from GNSS, IMU, and visual, together with the prior lightweight map. Unlike the existing tightly-coupled GNSS/Visual/IMU integration schemes, the potential of the carrier-phase measurement is fully explored using the recently developed window carrier phase (WCP) model. To further mitigate the impacts of the GNSS outliers, a novel sliding window (SW)-based map matching model is proposed to correct the states using the lightweight OpenStreetMap (OSM). Different from conventional filtering-based map matching, the states within the sliding window are associated with the lane information from the OSM which effectively exploits the measurement redundancy provided by the factor graph model. The experiments are conducted in the urban canyons of Hong Kong, utilizing a challenging dataset characterized by poor satellite visibility and numerous visual feature outliers, to verify the performance of the proposed method.

With the recent advances in battery technology enabling fast charging, public Charging Stations (CSs) are becoming a viable choice for Electric Vehicles (EVs). However, the distribution of EVs relies on strategic assignment of EVs to CSs. EVs drivers' Quality of Experience (QoE) is an significant impact factor that should be considered to find the optimal assignment of EVs to CSs. In this context, a novel framework to find the optimal assignment of EVs to CSs has been proposed based on optimization of QoE. Our proposed approach considers the travel time of EVs towards CSs taking into account the distance between EVs and CSs, the impact of congestion level on the roads resulted from the Internal Combustion Engine Vehicles (ICEVs) and EVs, queuing time at the CSs, and the time required to fully charge the EVs battery when connected to any charging slot at a CSs. The adjacency between the different zones in a city environment is also considered in order to minimize the potential number of CSs for each EVs. Specifically, the assignment problem is formulated as Mixed Integer Nonlinear Programming (MINLP), and a heuristic solution is developed using the Genetic Algorithm (GA) technique. The performance evaluation in realistic metropolitan environment attests the benefits of the proposed CSs assignment framework considering range of charging metrics.