The development of autonomous vehicles has shown great potential to enhance the efficiency and safety of transportation systems. However, the decision-making issue in complex human-machine mixed traffic scenarios, such as unsignalized intersections, remains a challenge for autonomous vehicles. While reinforcement learning (RL) has been used to solve complex decision-making problems, existing RL methods still have limitations in dealing with cooperative decision-making of multiple connected autonomous vehicles (CAVs), ensuring safety during exploration, and simulating realistic human driver behaviors. In this paper, a novel and efficient algorithm, Multi-Agent Game-prior Attention Deep Deterministic Policy Gradient (MA-GA-DDPG), is proposed to address these limitations. Our proposed algorithm formulates the decision-making problem of CAVs at unsignalized intersections as a decentralized multi-agent reinforcement learning problem and incorporates an attention mechanism to capture interaction dependencies between ego CAV and other agents. The attention weights between the ego vehicle and other agents are then used to screen interaction objects and obtain prior hierarchical game relations, based on which a safety inspector module is designed to improve the traffic safety. Furthermore, both simulation and hardware-in-the-loop experiments were conducted, demonstrating that our method outperforms other baseline approaches in terms of driving safety, efficiency, and comfort.

This paper proposed a timescale graph-parallel (GP) computation method to solve the real-time optimization problem of nonlinear predictive energy-saving control, thus to realize the implementation of MPC on vehicle on-board controllers. The proposed scheme consists of two parts: forward prediction of the objective function and backpropagation of the partial differential function, both of which can be calculated in parallel. Thus, compared with traditional serial solution method for optimization problems, the timescale graph-parallel computation method can utilize the computing resources of the controller fully. In this paper, firstly, based on the characteristics of commercial vehicles, a mixed integral optimal control problem (MIOCP) was constructed. Then, a detailed timescale graph-parallel computation algorithm was derived for the MIOCP. Finally, GP and Pontryagin’s Minimum Principle (PMP) algorithms were applied on the predefined road for the simulation of the prediction of energy-saving control for commercial vehicles. The simulation results showed that compared with PMP, the maximum iteration number, average iteration number, single longest solution time, and single average solution time of the proposed GP decreased by 60%, 64.28%, 89.53%, and 93.56%, respectively. In addition, GP can also improve fuel efficiency by 1.55% without sacrificing much power performance.

Vehicle trajectory prediction is crucial for ensuring the safety and reliability of autonomous driving systems. Due to the highly stochastic nature of road participants’ behaviors, it is vital that prediction models accommodate a wide range of possible scenarios to mitigate safety risks. To address this challenge, we propose a novel trajectory prediction model called DiffusionTrajPred, an innovative trajectory prediction model based on the diffusion model. This model uniquely combines forward and reverse processes, manipulating noise levels in trajectory data to forecast future paths. Through the application of a mask-based reverse process, the model can make full use of historical trajectory information and predict trajectories that combine accuracy and multiple possibilities. The model utilizes a Transformer architecture for learning the noise, which enables the model to extract richer temporal information from trajectory data, resulting in improved semantic comprehension. Furthermore, we have effectively encoded high-definition (HD) semantic map information and vehicle interaction dynamics as crucial input features, improving the model ’s predictive power. Extensive experiments on the widely recognized open-source dataset ’Argoverse’ reveal that our method outperformed the most existing state-of-the-art methods in terms of accuracy and multimodality, demonstrating the diffusion model’s unique advantage in addressing the stochastic nature of road scenarios in autonomous driving.

The urban transportation network is crucial for societal development, but it is prone to failures like congestion caused by accidents or disasters. In particular, often network-wide failure is the result of a series of cascading failures originating from a small set of individual links. To prevent such failures, it is essential to identify these critical links and take early action. However, most existing approaches in the literature for evaluating the importance of each link rely on manually designed metrics (e.g., the Network Robustness Index). These methods are time-consuming and not suitable for large-scale urban networks. Additionally, these metrics fail to accurately capture the dynamic traffic interactions influenced by vehicle movement. In this paper, we present a novel method for identifying critical links by learning effective traffic interaction representation (the spatio-temporal dependencies) among roads. By representing the network as an un-directed graph and abstracting the road links as the nodes, we introduce a temporal graph attention model to capture spatial and temporal dependence between nodes. This model combines a graph attention network and a long short-term memory neural network and produces an attention matrix, which represents traffic interactions among links. Furthermore, we propose a traffic influence propagation model to evaluate the influence of each link for the entire road network based on the traffic interaction representation. We rank the importance of links based on their influence and then identify the critical links. A real-world case study in the city of Hangzhou, China is conducted to test our method and we use the network efficiency ratio to quantify its performance. The results suggest that our method can effectively identify the critical links at different periods.

Automated vehicle steering control systems have great potential to improve road safety. The development of such systems calls for mathematical driver models able to represent human drivers' steering behavior in response to automated steering intervention. This article concerns the experimental evaluation of a game-theoretic driver steering control model. The driver model centers on a steering control strategy developed based on the Nash equilibrium of a theoretic noncooperative game between the driver and automated steering controller. The key parameters of the game-theoretic driver model are identified by fitting the model to real driver steering behavior measured from six driver subjects in an experiment using a driving simulator. The game-theoretic driver model is evaluated by compared to a "conventional" optimal-control-theoretic driver model, and analyzing their model fitting errors. Results from the analysis demonstrate that the game-theoretic driver model is statistically significantly better than the conventional driver model for representing three out of the six subjects' steering behavior. For the other three subjects, both the two models perform statistically equivalently well.

Interactive decision-making between multiple automated vehicles under unsigned intersections is a high-level dynamic decision-making scenario, greatly increasing the complexity of decision-making. In this situation, making the decision-making manner in accordance with the logic of human and guaranteeing driving safety is technically challenging. A multi-factor-enabled interactive decision-making method is proposed in this paper to realize such behavior, which employs multiple complementary factors and switchable modes in a dynamic game. More specifically, these factors are driving performance requirements, e.g., moving safety, smoothness comfort, fast passing, and surrounding space, as well as diversified driving styles suitable for different driver groups. Meanwhile, to improve the reasonability of automated driving and reduce the complexity of multi-vehicle games, switchable game modes are established to realize the dynamic adjustment mechanism. The effectiveness of the proposed method in resolving conflicts in a continuous interactive way is verified through extensive simulations. The results indicate the proposed method can reflect the interaction process between multi-agents, and improve compliance between intelligent decision-making and the logic of human.

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.

A growing interest in autonomous driving (AD) and intelligent vehicles (IVs) is fueled by their promise for enhanced safety, efficiency, and economic benefits. While previous surveys have captured progress in this field, a comprehensive and forward-looking summary is needed. Our work fills this gap through three distinct articles. The first part, a “survey of surveys” (SoS), outlines the history, surveys, ethics, and future directions of AD and IV technologies. The second part, “Milestones in AD and IVs Part I: Control, Computing System Design, Communication, high-definition map (HD map), Testing, and Human Behaviors” delves into the development of control, computing system, communication, HD map, testing, and human behaviors in IVs. This part, the third part, reviews perception and planning in the context of IVs. Aiming to provide a comprehensive overview of the latest advancements in AD and IVs, this work caters to both newcomers and seasoned researchers. By integrating the SoS and Part I, we offer unique insights and strive to serve as a bridge between past achievements and future possibilities in this dynamic field.

This special issue of the IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING (T-ASE) focuses on how the state-of-the-art achievements and applications in the general area of artificial intelligence in automation for autonomous unmanned systems applications. As Guest Editors, we are very pleased to present the selected 16 articles, whose topics are specifically related to artificial intelligence real-time object detection, recognition, localization, control optimization, motion planning, formation control, adaptive control, and autonomous decision-making.

Driver decisions and behaviors regarding the surrounding traffic are critical to traffic safety. It is important for an intelligent vehicle to understand driver behavior and assist in driving tasks according to their status. In this paper, the consumer range camera Kinect is used to monitor drivers and identify driving tasks in a real vehicle. Specifically, seven common tasks performed by multiple drivers during driving are identified in this paper. The tasks include normal driving, left-, right-, and rear-mirror checking, mobile phone answering, texting using a mobile phone with one or both hands, and the setup of in-vehicle video devices. The first four tasks are considered safe driving tasks, while the other three tasks are regarded as dangerous and distracting tasks. The driver behavior signals collected from the Kinect consist of a color and depth image of the driver inside the vehicle cabin. In addition, 3-D head rotation angles and the upper body (hand and arm at both sides) joint positions are recorded. Then, the importance of these features for behavior recognition is evaluated using random forests and maximal information coefficient methods. Next, a feedforward neural network (FFNN) is used to identify the seven tasks. Finally, the model performance for task recognition is evaluated with different features (body only, head only, and combined). The final detection result for the seven driving tasks among five participants achieved an average of greater than 80% accuracy, and the FFNN tasks detector is proved to be an efficient model that can be implemented for real-time driver distraction and dangerous behavior recognition.

As an important safety-critical cyber-physical system (CPS), the braking system is essential to the safe operation of the electric vehicle. Accurate estimation of the brake pressure is of great importance for automotive CPS design and control. In this paper, a novel probabilistic estimation method of brake pressure is developed for electrified vehicles based on multilayer artificial neural networks (ANNs) with Levenberg-Marquardt backpropagation (LMBP) training algorithm. First, the high-level architecture of the proposed multilayer ANN for brake pressure estimation is illustrated. Then, the standard backpropagation (BP) algorithm used for training of the feed-forward neural network (FFNN) is introduced. Based on the basic concept of BP, a more efficient training algorithm of LMBP method is proposed. Next, real vehicle testing is carried out on a chassis dynamometer under standard driving cycles. Experimental data of the vehicle and the powertrain systems are collected, and feature vectors for FFNN training collection are selected. Finally, the developed multilayer ANN is trained using the measured vehicle data, and the performance of the brake pressure estimation is evaluated and compared with other available learning methods. Experimental results validate the feasibility and accuracy of the proposed ANN-based method for braking pressure estimation under real deceleration scenarios.

Driver-in-the-loop and different human-machine goal consistency should be considered when designing driver-AFS interactive steering control system. In this paper, a novel design approach, namely dynamic game theory is used for the modelling of shared steering control between driver and AFS. Linear Quadratic dynamic optimization approach is used to derive the non-cooperative Nash, non-cooperative Stackelberg, cooperative Pareto equilibrium steering control strategies of the driver and the AFS controller. Two different driving scenarios, where driver's target path has high or low consistency with AFS's are simulated and corresponding simulation results are presented respectively. It was found that different control strategies result in distinct steering behaviors under different driving scenarios. Furthermore, the most interesting simulation result is that using the principle of Stackelberg equilibrium can effectively decrease the steering wheel angle applied by driver in the driving scenario where driver's target path has high consistency with AFS's compared with two other control strategies.

The increasing use of active front steering (AFS) technology for obstacle avoidance raises the question of drivers' interaction with vehicle automation. Mathematical models capable of representing such interaction are in demand for driver behavior study. This paper presents the application of open-loop Stackelberg equilibrium to modeling a driver's interaction with vehicle AFS control in an obstacle avoidance scenario, where both the driver and the AFS controller are exerting steering control to the vehicle. In this paper, such driver-AFS interactive steering control is modeled as a leader-follower game. Mathematical expressions of the driver's and the AFS controller's steering control strategies are derived using the linear quadratic dynamic optimization approach and the distributed model predictive control (DMPC) approach. These two approaches are found to give identical control gains, which suggest their equivalence in representing driver-AFS interaction. The DMPC approach is found to consume far less computation time due to its numerical nature. Mathematical modifications to the steering control strategies are then introduced to allow practical implementation for a future experimental study. Simulation results including time histories of steering angles and vehicle responses are illustrated and discussed.

Development of vehicle active steering collision avoidance systems calls for mathematical models capable of predicting a human driver's response so as to reduce the cost involved in field tests while accelerating product development. This paper provides a discussion on the paradigms that may be used for modeling a driver's steering interaction with vehicle collision avoidance control in path-following scenarios. Four paradigms, namely decentralized, noncooperative Nash, noncooperative Stackelberg, and cooperative Pareto are established. The decentralized paradigm, which is developed on the basis of optimal control theory, represents a driver's interaction with the collision avoidance controllers that disregard driver steering control. The noncooperative Nash and Stackelberg paradigms are used for predicting a driver's steering behavior in response to the collision avoidance control that actively compensates for driver steering action. These two are devised based on the principles of equilibria in noncooperative game theory. The cooperative Pareto paradigm is derived from cooperative game theory to model a driver's interaction with the collision avoidance systems that take into account the driver's target path. The driver and the collision avoidance controllers' optimization problems and their resulting steering strategies arise in each paradigm are delineated. Two mathematical approaches applicable to these optimization problems namely the distributed model predictive control and the linear quadratic dynamic optimization approaches are described in detail. A case study illustrating a conflict in steering control between driver and vehicle collision avoidance system is performed via simulation. It was found that the variation of driver path-error cost function weights results in a variety of steering behaviors, which are distinct between paradigms.