With the broader adoption and highly successful development of large language models (LLMs), there has been growing interest and demand for applying LLMs to autonomous driving technology. Driven by their natural language (NL) understanding and reasoning capabilities, LLMs have the potential to enhance various aspects of autonomous driving systems, from perception and scene understanding to interactive decision-making. This article first introduces the novel concept of designing LLMs for autonomous driving (LLM4AD), followed by a review of existing LLM4AD studies. Then, a comprehensive benchmark is proposed for evaluating the instruction-following and reasoning abilities of LLM4AD systems, which includes LaMPilot-Bench, CARLA Leaderboard 1.0 Benchmark in simulation and NuPlanQA for multiview visual question answering (VQA). Furthermore, extensive real-world experiments are conducted on autonomous vehicle platforms, examining both on-cloud and on-edge LLM deployment for personalized decision-making and motion control. Next, the future trends of integrating language diffusion models into autonomous driving are explored, exemplified by the proposed vision-language diffusion (ViLaD) framework. Finally, the main challenges of LLM4AD are discussed, including latency, deployment, security and privacy, safety, trust and transparency, and personalization.

Autonomous vehicles platooning on highways can save energy costs, improving traffic safety and efficiency. Vehicles take corresponding actions in response to various transportation environments with an embedded dynamics model. However, it is unrealistic to expect that we have all accurate dynamics models due to the heterogeneity of vehicles. This work proposes a physics and data co-driven framework for heterogeneous vehicle platoon control by integrating physics-informed machine learning (PIML) with model predictive control (MPC). The proposed method targets scenarios where only limited observations (data) of vehicle dynamics and partially known physics are available for use. The partially known physics serves as the prior knowledge to penalize the training of the neural network resulting in the physics informed neural networks (PINN), with which we can not only reduce the variance of the neural network but also restore the missing physics during the training of the neural network. We demonstrate the proposed method with two scenarios in the case study. The results show that: 1) the neural network penalized by the partially known physics can accurately forecast the vehicle states in certain time ranges, 2) the missing vehicle dynamics parameters are recovered, and 3) the proposed PINN-MPC outperforms conventional data-driven MPC (NN-MPC) without physics constraints. The demonstration manifests that PINN-MPC has great potential to be used for heterogeneous platoon control with reduced data acquisition cost and only partially known physics.

The task of Pedestrian Trajectory Prediction (PTP) aims to forecast the future movement paths of pedestrians based on their past behavioral patterns, which is crucial for autonomous systems (e.g., autonomous vehicles and social robots) in path planning and decision-making processes. In recent years, with the rapid advancement of Artificial Intelligence (AI), especially in the field of deep learning, PTP has achieved remarkable breakthroughs. However, this field still faces numerous challenges and unresolved issues that require further research and exploration. This paper provides a comprehensive review and perspectives of the latest advancements in PTP methods, starting with the problem definition and method classification. Then, guided by the key issues at hand, we compare and analyze physics-based, classic Machine Learning (ML)-based, and AI-based methods, and discuss their applicability in various application scenarios. Finally, the paper provides existing datasets and performance metrics, and outlines potential research directions.

Existing traffic signal control methods primarily rely on data from a single sensor modality, limiting their ability to comprehensively capture the spatiotemporal features of the traffic network. This leads to a mismatch between traffic signal timing plans and dynamic traffic demands, resulting in underutilization of road capacity. To address these limitations, this paper proposes a traffic signal-vehicle cooperative control method (SVCM) based on multimodal heterogeneous subgraph learning. Specifically, we first design a hybrid-strategy action space with dual-state transitions, enabling the agent to dynamically switch between traffic signal control and cooperative traffic signal-vehicle control schemes according to real-time traffic conditions. Then, by analyzing vehicle steering requirements, driving efficiency factors, and vehicle heterogeneity, we construct a multi-factor weighted decision-making model for vehicle lane-changing. It adjusts the lane-changing probability to balance traffic density among lanes. In addition, to enhance the perception and utilization of the spatiotemporal features of the road network, we designed a multimodal heterogeneous subgraph attention network to integrate multi-source traffic data. This approach more accurately captures key regional features and provides a foundation for state information perception in the aforementioned collaborative control strategies. Experimental results demonstrate that the proposed method, SVCM, outperforms state-of-the-art approaches in both simulated and real-world traffic scenarios. Compared with the best baseline method, SVCM reduces the average queue length by 24.38% to 47.14% and decreases average lane occupancy by 21.09% to 39.72%. This work provides new insights into traffic signal-vehicle cooperative control by integrating multimodal feature information.

Vision Transformers (ViTs) have shown exceptional performance in vehicle re-identification (ReID) tasks. However, non-square aspect ratios of image or video inputs can negatively impact re-identification accuracy. To address this challenge, we propose a novel, human perception driven, and general ViT-based ReID framework that fuses models trained on various aspect ratios. Our key contributions are threefold: (i) We analyze the impact of aspect ratios on performance using the VeRi-776 and VehicleID datasets, providing guidance for input settings based on the distribution of original image aspect ratios. (ii) We introduce patch-wise mixup strategy during ViT patchification (guided by spatial attention scores) and implement uneven stride for better alignment with object aspect ratios. (iii) We propose a dynamic feature fusion ReID network to enhance model robustness. Our method outperforms state-of-the-art transformer-based approaches on both datasets, with only a minimal increase in inference time per image.The code is released here: Adaptive_AR_PM_TransReID.

Personalized driving refers to an autonomous vehicle’s ability to adapt its driving behavior or control strategies to match individual users’ preferences and driving styles while maintaining safety and comfort standards. However, existing works either fail to capture every individual’s preference precisely or become computationally inefficient as the user base expands. Vision-Language Models (VLMs) offer promising solutions to this front through their natural language understanding and scene reasoning capabilities. In this work, we propose a lightweight yet effective on-board VLM framework that provides low-latency personalized driving performance while maintaining strong reasoning capabilities. Our solution incorporates a Retrieval-Augmented Generation (RAG)-based memory module that enables continuous learning of individual driving preferences through human feedback. Through comprehensive real-world vehicle experiments, our system has demonstrated the ability to provide safe, comfortable, and personalized driving experiences across various scenarios and significantly reduce takeover rates by up to 76.9%. To the best of our knowledge, this work represents the first personalized VLM motion control system in real-world autonomous vehicles. The demo video can be watched at https://tinyurl.com/4xsnz79n.

Aiming to boost production efficiency and reduce human workload, human-centricity has emerged as the core concept of Industry 5.0 (I5.0). However, current works have not established a unified automation and autonomous framework for human-centric smart manufacturing across various real world applications. Addressing this gap, this research introduces an innovative automated framework, ParallelWorkforce, which integrates blockchain intelligence and decentralized autonomous organizations and operations (DAOs) to drive the evolution from digital twins to parallel intelligence. First, this research conducts a comprehensive investigation into smart manufacturing in I5.0, summarizing the ongoing evolution. Next, a detailed exploration of ParallelWorkforce is provided to offer customized strategies for managing different levels of out-of-distribution events, significantly alleviating the workload on biological workers and maximizing the potential of both digital and robotic workers. Finally, the development of ParallelWorkforce across various key applications of smart manufacturing is demonstrated, including autonomous transportation, task assignment, and worker management. This research provides a viable solution for the further development of human-centered smart manufacturing and paves the way for the realization of “6S” goals in I5.0.

The proliferation of shared micro-mobility services, including electric scooters (e-scooters), plays an important role in modern urban travel. Despite the growing popularity of e-scooters, their interactions with motor vehicles or pedestrians can lead to potential traffic accidents. In particular, the vehicle and e-scooter interaction (VEI) at intersections is of utmost importance to study, where the actions and intentions of e-scooter riders can vary greatly depending on the dynamic traffic situations. Moreover, due to the unique moving characteristics of e-scooters, drivers must maintain adequate awareness of the environment to mitigate unforeseen collision risks. In this paper, we aim to provide a novel risk analysis methodology to identify potential risky factors in the VEI process. Qualitative and quantitative analyses of various traffic situations are introduced to validate the functionality of the proposed system. The backtracking process algorithm (BPA) is also applied to demonstrate the effectiveness of the proposed framework.

Electric scooters (e-scooters) have become increasingly popular for intermodal transportation across major US cities, raising safety concerns for both motorists and non-motorists. To develop E-scooter AEB (Autonomous Emergency Braking) systems for intelligent vehicles, it is important to understand the association between e-scooter crash characteristics including facility type, crash severity, and motorist/non-motorist maneuvers. This paper investigates e-scooter crashes to map variable associations. The findings reveal that less severe crashes may be highly underreported. The most critical facilities for e-scooter safety are intersection crosswalks and travel lanes, with the former resulting in more severe injuries. Observing crash trajectories, right-turn crashes are found to be most common at intersections, while only a few intersection crashes result from left-turning vehicles. The findings highlight the need for dedicated safety design and policies for e-scooters, especially for vehicles at intersection crosswalks. Since data on e-scooter crashes is limited, future studies should focus on gathering larger samples from a wider geographic area to investigate and quantify predictor-crash relationships and develop diagnostic and predictive models using statistics and data-driven approaches.

Vehicle re-identification (ReID) matches the same vehicle across different cameras in a surveillance system, crucial for Intelligent Transportation Systems (ITS). This study investigates if optimal detection regions, guided by confidence scores, enhance feature matching and ReID tasks. Using YOLOv8 for detection and DeepSORT for tracking across twelve Indiana Highway videos, vehicle images were cropped from inside and outside Regions of Interest (ROIs). Features were extracted using ResNet50, ResNeXt50, Vision Transformer, and Swin-Transformer. Results showed higher cosine similarity for in-ROI images, and the most significant difference was observed during night conditions (0.7842 inside vs. 0.5 outside the ROI with Swin-Transformer) and in cross-camera scenarios (0.75 inside-inside vs. 0.52 inside-outside the ROI with Vision Transformer). Information entropy and clustering variance supported greater feature consistency in ROIs. These findings suggest strategically selected ROIs can improve tracking and ReID accuracy in ITS.

With the development of automated driving systems and V2I (vehicle-to-infrastructure) communications, soft-safety driver alerts can be implemented to supplement imminent driver alerts. This type of alert improves drivers’ situational awareness of emerging risks over a more extended period with more detailed incident information and longer response time. However, compared to the large number of studies focusing on imminent risks, there are insufficient studies on the evaluation and effectiveness of soft-safety alerts. This study proposed an innovative metric to assess the comfort and safety of soft-safety driver alerts by constructing an ideal speed profile and calculating the deviation between the actual and ideal profile. We select the highway end-of-queue event as the experiment scenario, which is a leading cause of fatal highway crashes. Human subjects’ experiments are conducted in the driving simulator to validate the proposed metrics. The results have proved that the proposed metrics have good potential to assess driving comfort objectively. We also found that soft-safety alerts tend to improve driving comfort. However, there is insufficient evidence to conclude statistically about the prototype soft-safety alerts implemented in the experiments.

Vehicle platooning for connected and automated vehicles (CAVs) has many potential benefits, such as lowering fuel consumption, improving traffic safety, and reducing traffic congestion. However, challenges remain toward safe and efficient vehicle platooning since its performance could be degraded due to uncertainty from vehicle dynamics, environmental disturbances, and communication delays, among others. In this talk, I will introduce one recent work on a new control method that combines distributed stochastic model predictive control (DSMPC) with Taguchi’s robustness (TR-DSMPC) for vehicle platooning. The proposed method inherits the advantages of both Taguchi’s robustness (maximizing the mean performance and minimizing the performance variation due to uncertainty) and stochastic model predictive control (ensuring a specific reliability level). The proposed method was compared with two other MPC-based methods in terms of safety (spacing error) and efficiency (relative velocity). The results indicate that the proposed method can effectively reduce the performance variation and maintain the mean performance compared to other methods.

This paper aims to propose a pedestrian trajectory prediction model based on pedestrian–vehicle game theory to study pedestrian trajectories during pedestrian–vehicle interaction at unsignalized right-turn intersections. First, pedestrian–vehicle interaction scene data at unsignalized right-turn intersections were collected. Then, a novel pedestrian–vehicle game theory model was established, where its parameters were calibrated using the Nash equilibrium of a complete information static game and the probabilities of pedestrians and vehicles crossing the street. A new pedestrian–vehicle game utility matrix is embedded into the social-generative adversarial network pedestrian trajectory prediction model, which considers information between pedestrians and vehicles and analyzes the state of pedestrian–vehicle-interactions under various decisions through microscopic motion factors and macroscopic game decisions. The experimental results show that the proposed model is more accurate and explanatory than traditional pedestrian trajectory prediction models, such as long short-term memory (LSTM), Social LSTM, Social generative adversarial network(S-GAN), and Sophie.

In 2014, IEEE Intelligent Transportation Systems Society established a Technical Committee on Transportation 5.0 with the mission of promoting and transforming the deployment of advanced and innovative technologies, especially Artificial Intelligence in transportation. This paper briefly summarizes our main research and findings over the last decade. Transportation Foundation Models, Transportation Scenarios Engineering, and Transportation Operating Systems have been identified as the main directions for the research and development of next-generation intelligent transportation systems.

Mines are one of the important energy sources in the world. Due to mining areas are often affected by adverse weather and environmental conditions (sand, dust, extreme cold, heavy snow, etc.), the efficiency and security of mining are low. As a new, efficient, prospective mode, Metaverse has been studied and successfully applied in various industries. However, there is still no research about its usage in mines. In this article, we apply Metaverse to mining and propose MetaMining. We present its definition and analyze the functions it could perform. Furthermore, we propose its development phases and architecture. Specifically, MetaMining is a mode, which aims to achieve high-efficiency, high-security mining in the physical world through the interaction between the physical world and the virtual world. Its development phases involve three steps: 1) digital twins; 2) digital natives; and 3) surreality. Its architecture consists of three components: 1) human world; 2) virtual mining system; and 3) physical mining system. In addition, we analyze key technologies and possible challenges in the construction of MetaMining.

Vehicle platooning for highway driving has many benefits, such as lowering fuel consumption, improving traffic safety, and reducing traffic congestion. However, its performance could be undermined due to uncertainty. This work proposes a new control method that combines distributed stochastic model predictive control with Taguchi’s robustness (TR-DSMPC) for vehicle platooning. The proposed method inherits the advantages of both Taguchi’s robustness (maximizing the mean performance and minimizing the performance variation due to uncertainty) and stochastic model predictive control (ensuring a specific reliability level). Taguchi’s robustness is achieved by introducing a variation term in the control objective to bring a trade-off between mean performance and its variation. TR-DSMPC propagates uncertainty via an approximation method: First-Order Second Moment, which is far more efficient than Monte Carlo-based methods. The uncertainty is considered from two perspectives, time-independent uncertainty by random variables and time-dependent uncertainty by stochastic processes. We compare the proposed method with two other MPC-based methods in terms of safety (spacing error) and efficiency (relative velocity). The results indicate that our proposed method can effectively reduce the performance variation and maintain the mean performance.

Detecting loop closures in 3D Light Detection and Ranging (LiDAR) data is a challenging task since point-level methods always suffer from instability. This paper presents a semantic-level approach named GOSMatch to perform reliable place recognition. Our method leverages novel descriptors, which are generated from the spatial relationship between semantics, to perform frame description and data association. We also propose a coarse-to-fine strategy to efficiently search for loop closures. Besides, GOSMatch can give an accurate 6-DOF initial pose estimation once a loop closure is confirmed. Extensive experiments have been conducted on the KITTI odometry dataset and the results show that GOSMatch can achieve robust loop closure detection performance and outperform existing methods.

The high-definition (HD) map is critical for the localization and motion planning of connected and automated vehicles (CAVs). With all the road and lane information pre-scanned in a certain area, the vehicles can know its position with respect to the lane marks and roadside, and hence make better decisions on planning future trajectories. A common issue, however, is the accuracy of the scanned outputs from different data sources. Because of the limitations of online maps (e.g., zooming and stretching in their image layers), visualizing the data in the bird's eye view on maps cannot satisfy the accuracy requirement of being the ground-truth system. To this end, a feasible method that can combine sensing data from different sources and obtain reliable ground-truth information is necessary. In this paper, we develop a novel method to transform the data points from the bird's eye view to the view angle of a web camera installed on the windshield of the ego vehicle. In such a case, the position of landmarks from the captured frames of the camera can be used as the ground-truth. In particular, we take the lane marking detection outputs from the Mobileye system as the reference for a better accuracy. We evaluate the proposed method using the field data on highway I-75 in Michigan, USA. The results show that this method has achieved a very good accuracy of over 90% for location determination of lane information. The main contribution of this paper is that the proposed method can be more intuitive and reliable than using the traditional maps in bird's eye view.

Vehicle collision avoidance system (CAS) is a control system that can guide the vehicle into a collision-free safe region in the presence of other objects on road. Common CAS functions, such as forward-collision warning and automatic emergency braking, have recently been developed and equipped on production vehicles. However, these CASs focus on mitigating or avoiding potential crashes with the preceding cars and objects. They are not effective for crash scenarios with vehicles from the rear-end or lateral directions. This paper proposes a novel collision avoidance system that will provide the vehicle with all-around (360-degree) collision avoidance capability. A risk evaluation model is developed to calculate potential risk levels by considering surrounding vehicles (according to their relative positions, velocities, and accelerations) and using a predictive occupancy map (POM). By using the POM, the safest path with the minimum risk values is chosen from 12 acceleration-based trajectory directions. The global optimal trajectory is then planned using the optimal rapidly exploring random tree (RRT*) algorithm. The planned vehicle motion profile is generated as the reference for future control. Simulation results show that the developed POM-based CAS demonstrates effective operations to mitigate the potential crashes in both lateral and rear-end crash scenarios.

Vehicles in Internet of Vehicles (IoV) exchange information about location, environment, infotainment, as well as social information with other units via vehicular communication networks. This makes IoV with key social entities in the human-vehicle-infrastructure-roadside units (RSUs) as integrated intelligent transportation systems. Therefore, by identifying the cyber-physical-social features of IoV and presenting its complexity issues of both engineering and social dimensions, this article proposes and introduces the concept, architecture, and applications of parallel IoV (PIoV). Three main components of PIoV are demonstrated, which are artificial IoV to learn and describe the physical IoV, computation experiments to evaluate and predict the consequences and values of driving strategies, and parallel execution to prescribe the operation of the physical IoV. PIoV makes it possible to achieve safe, smart, effective, and efficient transportation management and control. The final objective of PIoV is to equip IoV with descriptive, predictive, and prescriptive intelligence based on the parallel intelligence approach.

The measurement of influence on online platforms has been an important issue for various applications, including viral marketing, recommender systems, and the Internet celebrity economy. Generally, the citation frequency, mention frequency, and in-degree of users are the three major criteria for evaluating online influence in existed studies. However, some online media platforms neither provide social networking functions nor support social relationship labeling, making it infeasible to measure the user influence via the above three criteria. Such platforms can be named nonexplicit-relationship platforms. In this article, we propose three new criteria, explicit conversion rate (ER), frequency of promotion (FP), and average participation density (APD), and design a novel algorithm to effectively calculate and evaluate users' influence on these platforms. The stability and sustainability of user influence are evaluated to distinguish the real influentials from the disguised ones, while the latter usually appears for temporary commercial advertisement purposes. The experiments proved the effectiveness of the proposed criteria and the algorithm in determining influentials' influence, as well as the corresponding stability and sustainability.

Since data are collected from a range of sources via different techniques, multiview clustering has become an emerging technique for unsupervised data classification. However, most existing soft multiview clustering methods only consider the pairwise correlations and ignore high-order correlations among multiple views. To integrate more comprehensive information from different views, this article innovates a fuzzy clustering model using the low-rank tensor to address the multiview data clustering problem. Our method first conducts a standard fuzzy clustering on different views of the data separately. Then, the obtained soft partition results are aggregated as the new data to be handled by a Kullback-Leibler (KL) divergence-based fuzzy model with low-rank tensor constraints. The KL divergence function, which replaces the traditional minimized Euclidean distance, can enhance the robustness of the model. More importantly, we formulate fuzzy partition matrices of different views as a third-order tensor. So, a low-rank tensor is introduced as a norm constraint in the KL divergence-based fuzzy clustering to obtain dexterously high-order correlations of different views. The minimization of the final model is convex and we present an efficient augmented Lagrangian alternating direction method to handle this problem. Specially, the global membership is derived by using tensor factorization. The efficiency and superiority of the proposed approach are demonstrated by the comparison with state-of-the-art multiview clustering algorithms on many multiple-view data sets.

Vehicle detection from short-range aerial image faces challenges including vehicle blocking, irrelevant object interference, motion blurring, color variation etc., leading to the difficulty to achieve high detection accuracy and real-time detection speed. In this paper, benefiting from the recent development in MobileNet family network engineering, we propose a compressed MobileNet which is not only internally resistant to the above listed challenges but also gains the best detection accuracy/speed tradeoff when comparing with the original MobileNet. In a nutshell, we reduce the bottleneck architecture number during the feature map downsampling stage but add more bottlenecks during the feature map plateau stage, neither extra FLOPs nor parameters are thus involved but reduced inference time and better accuracy are expected. We conduct experiment on our collected 5-k short-range aerial images, containing six vehicle categories: truck, car, bus, bicycle, motorcycle, crowded bicycles and crowded motorcycles. Our proposed compressed MobileNet achieves 110 FPS (GPU), 31 FPS (CPU) and 15 FPS (mobile phone), 1.2 times faster and 2% more accurate (mAP) than the original MobileNet.

Mining traffic-relevant information from social media data has become an emerging topic due to the real-time and ubiquitous features of social media. In this paper, we focus on a specific problem in social media mining which is to extract traffic relevant microblogs from Sina Weibo, a Chinese microblogging platform. It is transformed into a machine learning problem of short text classification. First, we apply the continuous bag-of-word model to learn word embedding representations based on a data set of three billion microblogs. Compared to the traditional one-hot vector representation of words, word embedding can capture semantic similarity between words and has been proved effective in natural language processing tasks. Next, we propose using convolutional neural networks (CNNs), long short-term memory (LSTM) models and their combination LSTM-CNN to extract traffic relevant microblogs with the learned word embeddings as inputs. We compare the proposed methods with competitive approaches, including the support vector machine (SVM) model based on a bag of n-gram features, the SVM model based on word vector features, and the multi-layer perceptron model based on word vector features. Experiments show the effectiveness of the proposed deep learning approaches.

Road departure detection systems (RDDSs) for avoiding/mitigating road departure crashes have been developed and included on some production vehicles in recent years. In order to support and provide a standardized and objective performance evaluation of RDDSs, this paper describes the development of the data acquisition and data post-processing systems for testing RDDSs. Seven parameters are used to describe road departure test scenarios. The overall structure and specific components of data collection system and data post-processing system for evaluating vehicle RDDSs is devised and presented. Experimental results showed sensing system and data post-processing system could capture all needed signals and display vehicle motion profile from the testing vehicle accurately. Test track testing under different scenarios demonstrates the effective operations of the proposed data collection system.

Welcome to the third issue of the IEEE Transactions on Computational Social Systems (TCSS) for 2018.

Bicyclist Pre-Collision Systems (BPCS) for helping avoid and/or mitigate bicyclist crashes have been equipped on some production vehicles. To support the standardized performance evaluation of BPCS, a surrogate bicyclist has been developed by the Transportation Active Safety Institute (TASI) at Indiana University-Purdue University Indianapolis (IUPUI). The surrogate bicyclist was designed to have representative visual and radar characteristics of real bicyclists in the United States. One question to be answered in surrogate bicyclist development is what the representative clothing color should be. This paper presents an approach to determine the clothing color of surrogate bicyclist for the standard evaluation of BPCS. The clothing color of bicyclists was gathered from the TASI-110 car naturalistic driving data collected in the Greater Indianapolis area. A clustering algorithm was used to determine the representative clothing colors of bicyclists.

Extensive research interest has been focused on protecting vulnerable road users in recent years, particularly pedestrians and cyclists, due to their attributes of vulnerability. However, comparatively little effort has been spent on detecting pedestrian and cyclist together, particularly when it concerns quantitative performance analysis on large datasets. In this paper, we present a unified framework for concurrent pedestrian and cyclist detection, which includes a novel detection proposal method (termed UB-MPR) to output a set of object candidates, a discriminative deep model based on Fast R-CNN for classification and localization, and a specific postprocessing step to further improve detection performance. Experiments are performed on a new pedestrian and cyclist dataset containing 30 490 annotated pedestrian and 26 771 cyclist instances in over 50 000 images, recorded from a moving vehicle in the urban traffic of Beijing. Experimental results indicate that the proposed method outperforms other state-of-the-art methods significantly.

This paper starts with depicting the test series carried out by the Transportation Active Safety Institute, with two cars equipped with pedestrian automatic emergency braking (AEB) systems. Then, an AEB analytical model that allows the prediction of the crash speed, stopping distance, and stopping time with a high degree of accuracy is presented. The model has been validated with the test results and can be used for real-time application due to its simplicity. The concept of the active safety margin is introduced and expressed in terms of deceleration, time, and distance in the model. This margin is a criterion that can be used either in the design phase of pedestrian AEB for real-time decision making or as a characteristic indicator in test procedures. Finally, the decision making is completed with the analysis of the behavior of the pedestrian lateral movement and the calculation of the certainty of finding the pedestrian into the crash zone. This model of certainty completes the analysis of decision making and leads to the introduction of the new concept of “critical speed for decision making.” All major variables influencing the performance of pedestrian AEB have been modeled. A proposal of certainty scale in this kind of tests and a set of recommendations are given to improve the efficiency and accuracy of evaluation of pedestrian AEB systems.

The papers in this special section present some recent advances in ongoing research of unmanned intelligent vehicles in China.

In this paper, we consider the problem of developing a microscopic model for a signalized traffic intersection using Petri nets (PNs). We propose a two-module timed PN representation, where the first module is to model the traffic intersection and the second module is to model its traffic signal system. We use both deterministic and stochastic transitions in our model, and we describe in detail how they operate by considering both the event and time constraints associated with the physical traffic intersection. We also compare our model with some existing models in literature, and we explicitly state the potential advantages of our model.

In this paper, we propose a hierarchical model predictive control (MPC) approach for signal split optimization in large-scale urban road networks. To reduce the computational complexity, a large-scale urban road network is first divided into several subnetworks using a network decomposition method. Second, the MPC optimization problem of the large-scale urban road network is presented, in which the interactions between neighboring subnetworks are described with interconnecting constraints. To coordinate the subnetworks, Lagrange multipliers are introduced to deal with interconnecting constraints among subnetworks, and an augmented Lagrange function is constructed. Then, based on dual optimization theory and a decomposition strategy, the dual optimization problem of the original MPC problem is divided into several new subproblems. In addition, we develop a coordination algorithm based on an interaction prediction approach to coordinate the resulted subproblems with a two-level hierarchical structure. Finally, experimental results by means of simulation on a benchmark road network are presented, which illustrate the performance of the proposed approach.

Modeling vehicle-pedestrian interactions in the road environment is essential to develop pedestrian detection and pedestrian crash avoidance systems. In this paper, one novel approach is proposed to estimate the vehicle-pedestrian encountering risk in the road environment based on a large scale naturalistic driving data collection. Considering the difficulty to record actual pedestrian crashes in the naturalistic data collection, the encountering risk is estimated by the chances for driver to meet with pedestrian in the roadway as well as the chances for the driver and pedestrian to get into a potential conflict. Effects of different scenarios consisting of road conditions, pedestrian behaviors, and pedestrian numbers on the risk levels are also evaluated, and significant results are provided.

In this paper, we are trying to find the developmental tendencies and study hotspots of intelligent transportation systems technologies by theme classification and analysis of core articles from all papers published in IEEE Transactions on Intelligent Transportation Systems during 2010-2013. First, we classify theme categories by co-word analysis with different research domains and obtain 12 themes that include vehicle control technology, modeling and simulation, image processing, etc. Second, we find research focuses and directions of these themes by analyzing the trends of the article numbers published in each year of the TOP 5 themes. Finally, we identify TOP 5 core articles of these 12 themes and obtain their specific study hotspots by sorting the citations without self-citations of the articles in the Web of Science.

Integrated multimodal systems is one promising direction to improve human-vehicle interaction. In order to create intelligent human-vehicle interfaces and reduce visual load during secondary tasks, combining a haptic rotary device and a graphic display will provide one practical solution. However, in literature, the proper display position for the haptic rotary device is not fully investigated. In this paper, one experimental infotainment system is studied (including a haptic rotary control device and a graphic display) to evaluate the proper display position. Measurements used include task completion time, reaction to road events, lane/velocity keeping during secondary tasks, and user preference. Three display positions are considered: high mounted position, cluster position, and center stack position. The results show that, with increased on-road and off-road visual loads, the cluster display position can reduce lane position deviation significantly compared to high mounted and center stack positions. In addition, the high mounted and cluster display positions are better toward two different road events, including strong wind gust and extreme deceleration of the lead car.

Current research in automatic train operation concentrates on optimizing an energy-efficient speed profile and designing control algorithms to track the speed profile, which may reduce the comfort of passengers and impair the intelligence of train operation. Different from previous studies, this paper presents two intelligent train operation (ITO) algorithms without using precise train model information and offline optimized speed profiles. The first algorithm, i.e., ITOe, is based on an expert system that contains expert rules and a heuristic expert inference method. Then, in order to minimize the energy consumption of train operation online, an ITOr algorithm based on reinforcement learning (RL) is developed via designing an RL policy, reward, and value function. In addition, from the field data in the Yizhuang Line of the Beijing Subway, we choose the manual driving data with the best performance as ITOm. Finally, we present some numerical examples to test the ITO algorithms on the simulation platform established with actual data. The results indicate that, compared with ITOm, both ITOe and ITOr can improve punctuality and reduce energy consumption on the basis of ensuring passenger comfort. Moreover, ITOr can save about 10% energy consumption more than ITOe. In addition, ITOr is capable of adjusting the trip time dynamically, even in the case of accidents.

Driver distraction detection and intervention are important for designing modern driver-assistance systems and for improving safety. The main research question of this paper is to investigate how the cumulative driver off-road glance duration can be controlled to reduce the probability of occurrences of crash and near-crash events. Based on the available data sets from the Virginia Tech Transportation Institute (VTTI) 100-car study, the conditional probability is calculated to study the chance of crash and near-crash events when the given cumulative off-road glance duration in 6 s has been reached. Different off-road eye-glance locations and traffic density levels are also evaluated. The results show that one linear relationship can be obtained between the cumulative off-road eye-glance duration in 6 s and the risk of occurrences of crash and near-crash events, which varies for different off-road eye-glance locations. In addition, the traffic density level is found to be one significant moderator to this linear relationship. Detailed comparisons are made for different traffic density levels, and one nonlinear equation is obtained to predict the probability of occurrences of crash and near-crash events by considering both cumulative off-road glance duration and traffic density levels.

This paper proposes an approach for the optimal design of fault-tolerant Petri net controllers using arc weights minimization. Given a system controller that is modeled as a Petri net, a fault-tolerant Petri net controller is obtained by embedding the given Petri net controller into a larger (redundant) Petri net controller that retains the properties of the original controller and allows the detection and identification of faults that may occur in the controller places. An algorithm is developed to systematically design this fault-tolerant Petri net controller in an optimal sense. The optimality is in terms of minimizing the sum of the entries in the input and output incident matrices of the fault-tolerant controller. Examples of the optimal design of fault-tolerant Petri net controllers for a manufacturing system are also provided to illustrate our approach.

This paper proposes an approach for estimating the least-cost transition firing sequence(s) that matches (match) the observation of a sequence of labels produced by transition activity in a given labeled Petri net. Each transition in the labeled net is associated with a (possibly empty) label and also with a nonnegative cost which captures its likelihood (e.g., in terms of the amount of workload or power required to execute the transition). Given full knowledge of the structure of the labeled Petri net and the observation of a sequence of labels, we aim at finding the transition firing sequence(s) that is (are) consistent with both the observed label sequence and the Petri net, and also has (have) the least total cost (i.e., the least sum of individual transition costs). The existence of unobservable transitions makes this task extremely challenging since the number of firing sequences that might be consistent can potentially be infinite. Under the assumption that the unobservable transitions in the net form an acyclic subnet and have strictly positive costs, we develop a recursive algorithm that is able to find the least-cost firing sequence(s) by reconstructing only a finite number of firing sequences. In particular, if the unobservable transitions in the net are contact-free, the proposed recursive algorithm finds the least-cost transition firing sequences with complexity that is polynomial in the length of the observed sequence of labels.

This paper proposes an approach for providing tolerance against faults that may compromise the functionality of a given controller modeled by a Petri net. The method is based on embedding the given Petri net controller into a larger (redundant) Petri net controller that retains the original functionality and properties, and uses additional places, connections, and tokens to impose invariant conditions that allow the systematic detection and identification of faults via linear parity checks. In particular, this paper considers two types of redundant Petri net controllers: 1) nonseparate redundant Petri net controllers have the same functionality as the given Petri net controller and allow for fault detection and identification, but do not necessarily retain the given controller intact; and 2) separate redundant Petri net controllers are a special case of the nonseparate redundant controllers that retain the given Petri net controller intact but enhance it with additional places to enable fault detection and identification. The work in this paper obtains complete characterizations of both types of redundant controllers along with necessary and sufficient conditions for them to be bisimulation equivalent to the given original Petri net controller. In addition, this paper discusses how each type of redundant controllers can be designed to have desirable fault detection and identification capabilities. When the bisimulation equivalence requirement is not directly enforced, nonseparate redundant controllers can potentially have advantages over separate ones (e.g., they can use fewer connections to detect and identify the same number of faults). An example of a Petri net controller for a production cell and its fault tolerance capabilities using separate and nonseparate embeddings is used to illustrate the approach.

Traditional control algorithms mainly concerned with studies of an isolated intersection. This paper proposes the control signal coordination algorithms of two adjacent traffic intersections based on the relationship of two adjacent traffic intersections, fuzzy rules and high-order generalized neural networks. The traffic signal controller based on our design could control two adjacent intersections efficiently and improve the traffic conditions for both intersections.