Shared control provides a human-centered development direction for intelligent driving. However, existing shared control methodologies address the risk factors related to both the driver and the traffic environment inadequately. To this end, a shared steering control strategy is proposed based on the driver-vehicle-road (DVR) system risk assessment result. Firstly, the driver’s steering behavior is described through a two-point preview driver model. The key parameters are identified using real driving data. Meanwhile, the deep deterministic policy gradient (DDPG) algorithm is applied to train a reinforcement learning (RL) agent considering tracking accuracy, steering smoothness and vehicle stability as the autonomous driving controller. Afterwards, three time-varying risk factors are designed to evaluate the DVR system risk level, which represent driver risk, road risk and lane departure risk, respectively. Based on the system risk level, the control authority is initially calculated by a fuzzy inference method. Then, considering the smoothness of authority transition, a model prediction control (MPC) method is applied to optimize the initial authority level in real-time. Finally, simulation and the driver-in-the-loop (DIL) experiments are performed to validate the proposed strategy. The results demonstrate that the proposed shared control strategy could reduce driving burden and demonstrates distinct superiority in terms of human-machine collaboration, driving comfort and personalized support.

Vehicle re-identification (Re-ID) is a crucial task in intelligent transportation systems (ITS), aimed at retrieving and matching the same vehicle across different surveillance cameras. Numerous studies have explored methods to enhance vehicle Re-ID by focusing on semantic enhancement. However, these methods often rely on additional annotated information to enable models to extract effective semantic features, which brings many limitations. In this work, we propose a CLIP-based Semantic Enhancement Network (CLIP-SENet), an end-to-end framework designed to autonomously extract and refine vehicle semantic attributes, facilitating the generation of more robust semantic feature representations. Inspired by zero-shot solutions for downstream tasks presented by large-scale vision-language models, we leverage the powerful cross-modal descriptive capabilities of the CLIP image encoder to initially extract general semantic information. Instead of using a text encoder for semantic alignment, we design an adaptive fine-grained enhancement module (AFEM) to adaptively enhance this general semantic information at a fine-grained level to obtain robust semantic feature representations. These features are then fused with common Re-ID appearance features to further refine the distinctions between vehicles. Our comprehensive evaluation on three benchmark datasets demonstrates the effectiveness of CLIP-SENet. Our approach achieves new state-of-the-art performance, with 92.9% mAP and 98.7% Rank-1 on VeRi-776 dataset, 90.4% Rank-1 and 98.7% Rank-5 on VehicleID dataset, and 89.1% mAP and 97.9% Rank-1 on the more challenging VeRi-Wild dataset.

This paper proposes a novel method for multi-lane convoy formation control that uses large language models (LLMs) to tackle coordination challenges in dynamic highway environments. Each connected and autonomous vehicle in the convoy uses a knowledge-driven approach to make real-time adaptive decisions based on various scenarios. Our method enables vehicles to dynamically perform tasks, including obstacle avoidance, convoy joining/leaving, and escort formation switching, all while maintaining the overall convoy structure. We design a Interlaced formation control strategy based on locally dynamic distributed graphs, ensuring the convoy remains stable and flexible. We conduct extensive experiments in the SUMO simulation platform across multiple traffic scenarios, and the results demonstrate that the proposed method is effective, robust, and adaptable to dynamic environments. The code is available at: https://github.com/chuduanfeng/ConvoyLLM.

With the rapid advancement of end-to-end autonomous driving, the integration of prediction and planning has increasingly become a research focus in the field of autonomous driving. However, most existing methods do not adequately consider the robustness of driving trajectories during the trajectory generation, making them less effective in handling complex driving scenarios. To address this issue, this paper introduces Planning with Path-Informed Prediction for Autonomous Driving (PPP), which constructs a prediction-decision module that fuses multi-dimensional information by integrating the ego vehicle's potential multimodal future paths with environmental features. Moreover, we introduce a multi-stage trajectory evaluation mechanism during the trajectory generation process, which significantly enhances the system's performance in dynamic environments, thereby achieving improvements in both accuracy and robustness in complex driving scenarios. Through experiments on the nuPlan dataset, our method demonstrates exceptional competitiveness in closed-loop tests. Notably, in complex scenario tests, PPP outperforms learning-based and hybrid methods. Code will be available under https://github.com/Keria0812/PPP.

The task of making lane change decisions for autonomous vehicles in mixed traffic is intricate and challenging due to the uncertainty of surrounding vehicles. The uncertainty exists in terms of the diverse social driving preferences and unpredictable driving behavior of human drivers. To address these challenges, the decision-making process for changing lanes is represented as an incomplete information game, where the driver characteristics of surrounding vehicles are unknown during the interaction. To eliminate the uncertainty of the driving environment, the concept of driver aggressiveness is proposed to quantify the social driving preferences based on the Risk-Response (R-R) diagram in an explainable manner. Then the predicted trajectory is utilized to calculate the driving risks using Gaussian Mixture Model (GMM) that is trained by the naturalistic driving data in the interactive lane change scenarios extracted from the highD dataset. To make the simulation environment more diverse and realistic, the data-driven motion model social Intelligent Driver Model (SIDM) is constructed based on car-following data obtained from cut-in scenarios in the highD dataset. The simulations are conducted by setting up the environment vehicles equipped with SIDM model with diverse social driving preferences. The findings indicate that the proposed decision-making model can recognize the category of surrounding vehicles, and in realistic interactive driving scenarios, it can produce adaptive and human-like driving decisions.

In this paper, a safety-oriented hierarchical personalized driving system is proposed, which aims to mitigate the preference conflict between the passengers and the intelligent vehicle control system. Firstly, experiments on driving simulator are designed to analyze both the general and individual characteristics of different drivers, and a driving risk field (DRF) model for various driving events, such as free-driving, car-following, and lane-changing, is constructed. Secondly, the HighD natural dataset is clustered to explore the real preferences of different driving styles, and the DRF is calibrated to describe the driver’s subjective risk feeling more realistically. Thirdly, a driving decision-making mechanism with consideration of safety, efficiency, and personalized tolerance on the current lane is designed to select optimal driving events. Then, multi-point visual preview longitudinal speed adjustment and lateral lane-changing trajectory planning methods based on the spatial-temporal DRF under different driving events are proposed. Finally, human-in-the-loop experiments show that the proposed real-time system can generate personalized trajectories for different passengers in changing environments.

Image dehazing is a typical task in the low-level vision field. Previous studies verified the effectiveness of vanilla convolution kernel, transformer, and attention mechanism in dehazing. However, there are two main drawbacks in those methods: vanilla convolution and transformer have the short-comings of the insufficient receptive field and a large number of parameters respectively, and the previous design of the attention mechanism does not sufficiently consider an uneven hazy distribution. In this paper, a novel framework named Mix Structure Image Dehazing Network (MixDehazeNet) is proposed to solve the two issues mentioned above. Specifically, it mainly consists of two parts: the multi-scale parallel large convolution kernel module and the enhanced parallel attention module. Compared with a single vanilla kernel or transformer, parallel large kernels with multi-scale have a large receptive field and a relatively smaller amount of parameters, and the multi-scale characteristics of the image. It can restore a single pixel based on a large range of surrounding pixels and simultaneously recover texture details while capturing large hazed areas. In addition, an enhanced parallel attention module is designed according to atmospheric scattering models, which can extract shared global information and location-dependent local information of the original feature in parallel. It performs better at uneven hazy distribution. Extensive experiments on five benchmarks demonstrate the amazing effectiveness of our proposed methods. We achieved or approached state-of-the-art performance in five standard datasets. The code is released in https://github.com/AmeryXiong/MixDehazeNet.

Multi-agent-based cooperation of autonomous vehicles(AVs) holds the potential to improve road safety, reduce emissions, and increase transport efficiency. However, the presence of uncertainties stemming from various sources poses a risk to the communication network and can alter the network topology, potentially causing instability in the multi-vehicle system. These uncertainties originate from two main sources: internal multi-vehicle system and external traffic environment. Time delays and packet losses contribute to uncertainties within the internal multi-vehicle system due to the uncontrollability of communication quality. Additionally, the dynamic nature of traffic environments introduces uncertainties related to the number of vehicles, interaction relationships, tasks, and destinations, thereby affecting communication resources and network topologies. Consequently, it is imperative to study the uncertainties faced by the multi-agent system and explore consensus methods for addressing these uncertainties. Notably, this study represents the first comprehensive review of consensus methods for both platooning and broader multi-agent cooperation in the presence of uncertain networks. Furthermore, a systematic summary of multi-agent consensus methods is presented, explicitly addressing two aspects of network uncertainty: imperfect communication transmission and the intricacies of traffic dynamics. The conclusion provides insights into open research issues, paving the way for future studies aimed at enhancing overall multi-vehicle system performance, including aspects such as convergence rate, robustness, and resilience.

Heterogeneous vehicle platoons, consisting of a human-driven vehicle (HDV) as the leader and connected automated vehicles (CAVs) as followers, present a promising solution to address various challenges arising from fully autonomous driving. In this paper, we propose a novel LSTM-based distributed model predictive control (DMPC) platooning method. Initially, we develop and train a vehicle acceleration prediction model based on a long short-term memory (LSTM) network using real-world driving data. Subsequently, the predicted acceleration sequence of the leading HDV is integrated into the DMPC-based platoon control model for the following CAVs. To validate the effectiveness of our method, we conduct simulation experiments using real-world driving data. The results demonstrate that, with a time headway of 1 s, the maximum speed error and maximum spacing error of the heterogeneous vehicle platoon using the proposed LSTM-based DMPC are reduced by at least 5.8% and 5.9%, respectively, compared to the traditional DMPC method. Furthermore, the LSTM-based DMPC outperforms the Transformer-based DMPC method, resulting in a 1.0% reduction in maximum speed error and a 0.7% reduction in maximum spacing error. The proposed method effectively dampens oscillation caused by the leading HDV and enhances tracking accuracy.

There may exist long-term mixed traffic that consists of human-driven vehicles (HDV) and autonomous driving vehicles (ADV). Hence, a formidable challenge arises: the effective decision-making process among these heterogeneous vehicle types. The disparity in the level of decision-making among heterogeneous vehicles is significant. Human driving behaviors and volition, performed in HDV, are speculative and uncertain, while ADV’s behavior is unitary and conservative. To address this issue, a human-like decision-making framework for ADV considering social skills is designed, by introducing social value orientation (SVO) which is used to measure the degree of altruism of human drivers, and a sociality-aware Stackelberg game model and a social potential field model are proposed. Firstly, an inverse reinforcement learning (IRL) algorithm is applied to construct a structural cost function about human-driven interactive trajectories in order to estimate the SVO of HDV and endow ADV with the ability to respond to SVO. Secondly, the sociality-aware Stackelberg game approach is designed to capture the social interaction between heterogeneous vehicles, considering personal and public interests. Furthermore, a social potential field model is proposed, and then combined with receding horizon optimization (RHO) to plan socially-skilled trajectories. Finally, three traffic scenarios are used to verify that the developed decision-making algorithm can make safe and socially-skilled decisions in mixed traffic scenarios, in which several cases in terms of HDV with various SVO values are tested to prove the validity of human-like decision making process of an ADV.

The simplified vehicle model often results in inaccuracy with respect to the conventional model predictive control (MPC) as it causes steady error in tracking control, which has negative implications for vehicle cornering. This study presents a trajectory planning and tracking framework, which applies artificial potential to obtain target trajectory and MPC with PID feedback to effectively track planned trajectory. The experimental and simulation results are then presented to demonstrate the improved performance in tracking accuracy and steering smoothness compared to that of the conventional MPC control. Especially during negotiating a curve, its steady state error is close to 0.

Predicting the future trajectory of a vehicle in a dynamic scene is not a simple problem because the future trajectory of a vehicle is not only influenced by its historical trajectory but also by other vehicles. To solve this problem, we propose a vehicle trajectory prediction model based on attention mechanism and inverse reinforcement learning. The model uses the LSTM encoder-decoder framework as an infrastructure to efficiently extract the temporal features of vehicle trajectories. A social attention module is proposed to model the degree of inter-vehicle influence based on the distance between vehicles. The module generates feature vectors and serves as the weight values of the attention mechanism, enabling the prediction network to focus more on the surrounding vehicles with a greater degree of influence. An inverse reinforcement learning framework is introduced to regularize the encoder network using a reward function. The reward function effectively evaluates the gap between the predicted and true positions of the encoder output and enables the predicted positions to be closer to the true positions by training the network parameters. Based on the experimental results of public datasets SDD and NGSIM, our model can predict the future trajectory of vehicles more accurately than other models.

This article presents a framework to determine driving style and design a driver steering model considering driver characteristics. First, principal component analysis (PCA) and$K$-means clustering are utilized to classify 30 participants into cautious, moderate, and aggressive drivers. Subsequently, a generic steering model is established based on the model predictive control method. Thereafter, the maximum lateral acceleration is extracted as a crucial indicator to represent driver characteristics, and it is calibrated through probabilistic models using the dataset, which consists of the classified drivers. Besides, point estimation model and interval estimation model are leveraged to determine driving style and adjust constraints in the stochastic programming-based steering model. Finally, simulation experiments present the variations of actual output trajectories between the aggressive drivers and the cautious drivers.

A reference to the following paper was omitted: McDonald AD, Lee JD, Aksan NS, Dawson JD, Tippin J, Rizzo M. The language of driving: Advantages and applications of symbolic data reduction for analysis of naturalistic driving data. Transp Res Rec. 2013;2392(1):22-30.

Cooperative driving systems may increase the utilization of road infrastructure resources through coordinated control and platooning of individual vehicles with the potential of enhancing both traffic safety and efficiency. Vehicle cooperative driving is essentially a hybrid system that is a combination of discrete events, i.e., the transition of discrete cooperative maneuvering modes, such as vehicle merging and platoon splitting, as well as continuous vehicle dynamics. In this paper, a novel hybrid system consisting of the discrete cooperative maneuver switch and the continuous vehicle motion control is introduced into a multi-vehicle cooperative control system with a distributed control structure, leading each automated vehicle to conduct path planning and motion control separately. The primary novelty of this paper lies in that it presents a control algorithm combining artificial potential field (APF) approach with model predictive control (MPC), and using the optimizer of the MPC controller to replace the gradient-descending method in the traditional APF approach. Such a method can accomplish both path planning and motion control synchronously. Second, based on hybrid automata, a cooperative maneuver switching model consisting of a system state set and a discrete maneuver transition rule is established for two discrete maneuvers in the cooperative driving system, i.e., single-vehicle cruising and multiple-vehicle platooning. Simulations in several typical traffic scenarios demonstrate the effectiveness of the proposed method.

Summary Vehicle field test can be conducted smoothly because of the automobile‐mounted monitoring system and abundant diving data have been collected. Driving data mining is in an urgent need of new thoughts introduced to break through the original technical bottleneck. This paper presented a novel method of symbolic representation in diving data mining and applied the idea of time series symbolization to traffic engineering. The sample data is processed by normalization, dimensionality reduction, discretization, and symbolization based on the three steps of symbolic aggregate approximation (SAX) with driving data characteristics taken into adequate consideration. The results showed that the high‐dimensionality miscellaneous driving time series data was rationally converted into highly readable, easy to search and locate symbolic series after semantic encoding, and the main characteristics of time series data was preserved after a substantial reduction of data dimensionality. Finally, the paper demonstrated the positive effects of this method on the analysis of actual vehicle driving safety based on case study, and it explored the application of SAX to speed and acceleration data from driving data set.

This paper aims to recognize driving risks in individual vehicles online based on a data-driven methodology. Existing advanced driver assistance systems (ADAS) have difficulties in effectively processing multi-source heterogeneous driving data. Furthermore, parameters adopted for evaluating the driving risk are limited in these systems. The approach of data-driven modeling is investigated in this study for utilizing the accumulation of on-road driving data. A recognition model of driving risk based on belief rule-base (BRB) methodology is built, predicting driving safety as a function of driver characteristics, vehicle state and road environment conditions. The BRB model was calibrated and validated using on-road data from 30 drivers. The test results show that the recognition accuracy of our proposed model can reach about 90% in all situations with three levels (none, medium, large) of driving risks. Furthermore, the proposed simplified model, which provides real-time operation, is implemented in a vehicle driving simulator as a reference for future ADAS and belongs to research on artificial intelligence (AI) in the automotive field.

Accidents such as those caused by rollovers and sideslips in complex driving environments involving heavy-duty vehicles (HDVs) often have serious consequences. Such accidents can be due to many factors. In this paper, a probabilistic method for predicting and preventing these accidents is presented. First, a specific vehicle dynamics model based on various random parameters that consider the wind velocity and road curvature is developed. Second, a safety margin function is defined to divide the safe and dangerous domains in the parameter space. Then, the first-order reliability method and second-order reliability method approximations are developed to evaluate the probability of such an accident by using the vehicle dynamics model. Finally, the probability model is applied to explore the interrelations and sensitivities of those parameters with regard to their effects on the accident probability in different scenarios. The study suggests that the presented probabilistic methodology can effectively estimate rollovers and sideslips of HDVs in complex environments, which represent a challenge for the prediction of accidents based on sensors alone.