Motor imagery (MI) based brain–computer interfaces (BCIs) enable active device control through electroencephalography (EEG), offering contactless human–machine interaction. However, realistic MI-EEG decoding is challenged by non-uniform electrode coupling, long-range rhythmic dynamics, unstable second-order statistics, and blurred boundaries among fine-grained motor intentions. These challenges require topology-aware, statistically stable, and boundary-discriminative EEG representations, which remain insufficiently addressed in realistic decoding scenarios. To address these challenges, we propose ASDL-EEG, a coordinated representation learning framework for robust MI-EEG decoding. First, ASDL-EEG introduces a topology-aware first-order encoder that performs asymmetric electrode-axis spatial aggregation with multi-scale receptive fields and dilated temporal modeling to capture non-uniform spatial dependencies and long-range MI rhythms. Second, the Log-Diagonal Riemannian (LDR) extractor constructs aligned log-diagonal covariance descriptors as a compact, stability-oriented alternative to high-dimensional full covariance representations. To further enhance boundary discrimination, we propose RPA-v2, a sample-specific hard-negative prototype alignment method for fused first- and second-order EEG embeddings enlarging the margin between the target prototype and the most confusing non-target prototype. We further construct CW-MI-5, to the best of our knowledge, the first five-class MI-EEG dataset for intelligent-cockpit car-window control, serving as a naturalistic benchmark with synchronized EEG sensing and cockpit interaction cues. Experiments on CW-MI-5 and BCI Competition IV-2a show superior accuracy and Cohen’s kappa, validating ASDL-EEG in both cockpit interaction and standard MI benchmark settings.

Urban traffic congestion is becoming increasingly complex, necessitating innovative solutions for adaptive traffic signal control (ATSC). The multi-agent reinforcement learning (MARL) framework offers a promising approach by enabling coordinated decision-making across multiple intersections. However, in large-scale scenarios, more intersections worsen issues like poor credit assignment and low data efficiency, degrading performance. In this paper, we introduce the Traffic Sequence Transformer (TrafSeqFormer), a novel MARL-based framework that leverages sequence modeling for cooperative traffic signal control. TrafSeqFormer incorporates an encoder-decoder architecture for actor and critic networks and applies the Multi-Agent Advantage Decomposition Theorem to transform the joint policy search in multi-intersection traffic control into a sequential decision-making process. Using auto-regressive action generation and self-attention, TrafSeqFormer improves credit assignment, data efficiency, and agent collaboration, enhancing scalability for real-world traffic systems. We compare TrafSeqFormer to both MARL and domain-specific baselines. In synthetic traffic networks, it reduces queue length by up to 83%, increases throughput by 15%, and cuts delay by 65%. In real-world datasets from Beijing, Hangzhou, and Jinan, TrafSeqFormer further reduces queue length by 27% and delay by 73.7%, consistently outperforming competitive baselines across diverse urban scenarios.

A game-based cooperative steering control (GCSC) approach is introduced to facilitate effective collaboration between human drivers and automation, incorporating the neuromuscular delay inherent in human responses. In this framework, a dynamic coordination between driver and automation goals is achieved through the establishment of a game equilibrium in instances of driver and automation conflict. In response to the challenges posed by frequent modifications in driving weights and their subsequent burden on human drivers, this article proposes a strategy that integrates fixed initial weights with dynamic adjustments to driver–automation driving weights. Moreover, a comprehensive evaluation method including subjective and objective evaluation indexes is proposed. Different drivers are invited to perform virtual driving experiments, and the experimental results are analyzed by the proposed evaluation method. It is concluded that the driver’s driving weight should be kept at a high level during cooperative steering control when the driver’s intention cannot be perfectly obtained, and the determination of the driving weight should also consider the driver’s driving skills.

End-to-end learning has emerged as a transformative paradigm for autonomous driving. However, the inherently multimodal nature of driving behaviors remains a fundamental challenge to robust deployment. We propose DiffE2E, a diffusion-based end-to-end autonomous driving framework. The architecture first performs multi-scale alignment of perception features from multiple sensors via a hierarchical bidirectional cross-attention mechanism. Subsequently, we design a hybrid diffusion-regression-classification decoder based on the Transformer architecture, adopting a collaborative training paradigm to seamlessly fuse the strengths of diffusion and explicit strategies. DiffE2E conducts structured modeling in the latent space: diffusion captures the multimodal distribution of future trajectories, while regression and classification act as explicit strategies to precisely model key control variables such as velocity, enhancing both the precision and controllability of the model. A global condition integration module further enables deep fusion of perception features with high-level goals, significantly improving the quality of trajectory generation. The subsequent cross-attention mechanism facilitates efficient interaction between integrated features and hybrid latent variables, promoting joint optimization of diffusion and explicit strategies for structured output generation and thereby yielding more robust control. Experimental results demonstrate that DiffE2E achieves state-of-the-art performance on both CARLA closed-loop benchmarks and NAVSIM evaluations. The proposed unified framework that integrates diffusion and explicit strategies provides a generalizable paradigm for hybrid action representation and shows substantial potential for extension to broader domains, including embodied intelligence.

Trajectory prediction is a crucial technology to ensure the safe driving of intelligent vehicles on complex urban roads. Early works mainly focused on designing complicated architectures in deep learning-based prediction models. However, existing trajectory prediction methods still have three main shortcomings: 1) insufficient heterogeneous interactions between vehicles and environmental factors, such as maps; 2) inadequate consideration of the coupling relationship between prediction and planning modules; and 3) insubstantial purposive cognition leads to the limitation of future driving behaviors. To address these challenges, this article proposes a multimodal trajectory prediction model driven by target anchors using a graph attention network coupled with the motion trend of the ego vehicle (EV). The model first constructs a multilevel dynamic scene graph and a multigranularity static scene graph to describe the heterogeneous interactions between vehicles and the map accurately. Second, the model can consider the interaction between the EV’s future trajectory and the predicted information of the target vehicle (TV). Additionally, the model represents driving intent as target anchors, which can convey rich details on future distributions, reducing the complexity of the intent space. Experiments were conducted to evaluate the prediction accuracy on the Argoverse 1 dataset and its generalization capabilities on the CARLA+ROS2 simulator. The experimental results demonstrated that the proposed method can predict the trajectory of traffic participants much more accurately than the state-of-the-art methods and exhibit excellent generalization performance under different environmental conditions.

Traffic control at signal-free intersections is extensively studied to facilitate cooperative traffic for connected and autonomous vehicles (CAVs). Reinforcement learning (RL) techniques have proven effective for cooperative intersection management (CIM) challenges, but often involves unsafe states due to the arbitrary exploration of trial-and-error mechanism. To tackle the safety challenges associated with current RL-based CIM methods, this article proposes a safety-augmented CIM (SACIM) method. Initially, we introduce a constrained RL framework that integrates the augmented Lagrangian method with proximal policy optimization to address a constrained Markov decision process (CMDP). A policy network is designed to optimize performance, while multiple value networks are employed to evaluate policy performance and safety. By incorporating Lagrange multipliers and quadratic penalties, the method effectively transforms constraints optimization problems into unconstrained primal-dual problems, achieving an optimal solution without requiring strong convexity. Simultaneously, we incorporate communication delays and long- and short-term costs into the CMDP formulation to enhance safe and efficient policy exploration, closely mirroring real-world scenarios. Long-term cost reflects traffic safety related to collisions, while short-term cost accounts for the driving risks associated with safety violations during vehicle interactions. Furthermore, our method integrates a motion prediction-based, in-the-loop safety layer, facilitating rapid and robust policy learning. Through this safety enhancement design, SACIM effectively resolves the CIM issue within the CMDP framework, training a safe and reliable CIM method. Simulation results demonstrate that our method significantly improves traffic safety, efficiency, comfort, and inference time, outperforming various methods based on rules, optimal control, and RL.

Appropriate interaction with human-driven vehicles is crucial for advancing autonomous vehicles from demonstrations in controlled environments to applications in open-road scenarios. Accurately recognizing and quantifying driver interaction behaviors is essential for understanding their interaction intentions and subsequently formulating suitable responses. Previous studies have primarily focused on the generation of interaction behaviors. However, insufficient attention has been paid to the recognition and quantification of driver interaction behaviors. We establish a higher-order traffic flow network and present mathematical definitions for driver interaction behaviors and their strengths based on this framework. Furthermore, we find that humans identify interaction behaviors during driving by perceiving conflicts between different drivers’ intentions. Therefore, we propose a driver resistance field model (DRFM) to characterize driving intentions and describe these conflicts through operations within the resistance fields, enabling the recognition of interactions. Through computational social experiments and real-world experiments, the DRFM is demonstrated to accurately quantify the strength of driver-driver interactions. The analysis of extensive cases indicates that the quantification from the DRFM effectively capture the dynamics of interaction behaviors, aligning with human cognition of driver interactions, with remarkably higher correlation coefficients compared to baseline methods.

Quantifying uncertainty will significantly improve perceptual performance and provide more comprehensive environmental information for decision-making and planning modules of autonomous vehicles. Unfortunately, most perception methods exhibit excellent performance in accuracy but fall short in estimating associated uncertainty. To fill this gap, the variance inference ensemble network is proposed to enhance environmental perception and quantify uncertainty for 3-D object detection in point cloud. Specifically, the method is divided into three parts. Several variance inference neural networks that adopt multivariate Gaussian distribution for direct modeling are first constructed through a two-stage training strategy, extracting both the object details and variances from point cloud data in parallel. Following this, an uncertainty-aware fusion strategy is designed to integrate and filter the multiple results above based on the associated uncertainty and yield reliable and comprehensive results. Furthermore, a novel metric, uncertainty index, is coined to estimate the uncertainty of detected objects for the single deterministic network and ensemble network in a unified and quantitative manner. Finally, we validate our method on the KITTI dataset. The experiment demonstrates that our method outperforms the original baseline and recent uncertainty quantification methods across different scenarios.

Autonomous Intersection Management (AIM) systems present a novel paradigm for the cooperative control of Connected and Automated Vehicles (CAVs) at unsignalized intersections in future cities. Although Reinforcement Learning (RL) offers potential for increased computational efficiency and optimized solutions, challenges remain. These include limited inference capabilities and poor generalization due to simplified neural networks, along with insufficient safety-focused policy optimization. This study presents a novel offline-to-online framework, Prior-Enhanced Multi-Agent Constrained Decision Transformer (PE-MACDT), designed to tackle these challenges. The process begins with sequential decision-making using offline safe RL, which determines optimal actions through autoregressive modeling based on past states, actions, and both reward and cost returns. Leveraging the superior reasoning abilities and strong generalization of large language models like GPT-x and BERT, the sequence modeling challenges are addressed using the Transformer architecture, enhanced by sequence-level entropy regularizers to foster policy exploration. Subsequently, the safety policy learned from the offline dataset is deployed in the online environment and fine-tuned using the Multi-Agent Constrained Policy Optimization (MACPO) method combined with prior knowledge. This approach employs trust and constraint domains for policy updates, ensuring adherence to high standards of safety, comfort, and efficiency in dynamic traffic environments. Simulation results show our methodology outperforms state-of-the-art AIM methods in training convergence speed and asymptotic performance, as well as post-deployment outcomes in traffic efficiency, driving safety, and passenger comfort. The integration of offline pre-training with MACDT and online fine-tuning using MACPO offers a groundbreaking approach with significant potential for advancements in intelligent transportation systems.

As Connected and Autonomous Vehicles (vehicle) evolve, Autonomous Intersection Management (AIM) systems are emerging to enable safe, efficient traffic flow at urban intersections without traffic signals. However, existing AIM systems, whether based on traditional optimization control methods or machine learning, suffer from low computational efficiency and a lack of robustness in ensuring safety, respectively. To overcome these limitations, we propose an innovative AIM scheme rooted in Safe Multi-Agent Deep Reinforcement Learning (MADRL). We initially model the safe MADRL problem as a constrained Markov game (CMG) and tackle it with our multiagent projective constrained policy optimization (MAPCPO). This method first optimizes policy updates within the Kullback Leibler divergence trust region to maximize performance, and then projects these optimized policies onto the bounds of risk constraints, thus ensuring safety. Building on this, we introduce a Risk-Bounded RL for Autonomous Intersection Management (RbRL-AIM) algorithm. This algorithm adopts an architecture that consists of an LSTM based policy neural network, a reward value network, and a risk neural network. These components, through the MAPCPO policy, enable continuous learning from complex and random intersection traffic environments, thereby facilitating the safe, efficient, and smooth control of vehicles at intersections. Our method is validated in a CARLA simulation, showing significant gains in computational and traffic efficiency over baseline optimization control methods. Compared to non-safety-aware MADRL methods, our approach achieves zero collisions and improved ride comfort.

This paper introduces an innovative hybrid approach for estimating vehicle lateral velocity, merging mechanism-based methods with a Long Short-Term Memory (LSTM) neural network. Traditional estimation techniques, which are often susceptible to drift and inaccuracies due to parameter mismatches, fail to effectively adapt to varying driving conditions. Our proposed approach leverages the accuracy of mechanism-based estimates in specific scenarios to feed the LSTM network, creating a data-mechanism-driven solution. To overcome the inherent challenges of data-driven models, particularly concerning data quality and volume, our lateral velocity estimation model incorporates a feature extraction layer alongside a regression output layer. This architecture not only facilitates efficient parameter optimization within the feature extraction phase but also enables targeted retraining of the regression layer, significantly boosting transfer learning capabilities. We validate the robustness and the practicality of transfer learning across different vehicle classes in a simulation environment, showcasing its broad applicability and effectiveness.

This paper introduces a novel nonlinear game-based driver-automation cooperative steering control method to mitigate collision caused by the driver’s limited experience on low adhesion road conditions. First, we utilize a model predictive control (MPC) driver model to capture the characteristics of driver experience deficit in low adhesion road conditions, considering the driver’s neuromuscular delay as the system time lag. Then, a dynamic driving weighting strategy is proposed to adjust the driving weights, taking into account both driver-automation handling conflicts and road risks. Next, in order to account for the nonlinear tire dynamics encountered on low adhesion road surfaces, the problem of driver-automation cooperative steering control is mathematically framed as a nonlinear game. The utilization of the piecewise affine(PWA) theory enables the linearization of the nonlinear game optimization problem, facilitating the derivation of an optimal control strategy for ensuring vehicle stability on low adhesion road conditions. Finally, the proposed method is rigorously validated through simulations and driver-in-the-loop tests, comparing its performance against an existing driver-automation cooperative steering control approach. The experimental results substantiate the effectiveness of the proposed method in mitigating the driver’s steering workload and leveraging tire forces optimally to enhance vehicle stability.

Autonomous driving (AD) endows vehicles with the capability to drive partly or entirely without human intervention. AD agents generate driving policies based on online perception results, which are crucial to the realization of safe, efficient, and comfortable driving behaviors, particularly in high-dimensional and stochastic traffic scenarios. Currently, deep reinforcement learning (DRL) techniques to derive and validate AD policies have witnessed vast research efforts and have shown rapid development in recent years. However, a comprehensive interpretation and evaluation of their strengths and limitations concerning the full-stack AD tasks remain uncharted. This paper presents a survey of this body of work, which is conducted at three levels. First, it analyzes the multi-level AD task characteristics and delves deeply into the current DRL methodologies primarily employed in AD. Second, a taxonomy of the literature studies is constructed from the system perspective, identifying six modes of DRL model integration into an AD architecture that span the entire spectrum of AD policy processes, from perception understanding and decision-making to motion control, as well as verification and validation. Each literature review comprehensively encompasses the main elements of designing such a system, including modeling partially observable environments, state and action spaces, reward structuring, and the design and training methodologies of neural network models. Finally, an in-depth foresight is conducted on how the eight critical issues of AD application development are addressed by the DRL models tailored for real-world AD challenges.

Autonomous Intersection Management (AIM) systems present a new paradigm for conflict-free cooperation of connected autonomous vehicles (CAVs) at road intersections, the aim of which is to eliminate collisions and improve the traffic efficiency and ride comfort. Given the challenges of current centralized coordination methods in balancing high computational efficiency and robust safety assurance, this paper proposes an innovative conflict-free management scheme for CAVs at unsignalized intersections, leveraging safe multi-agent deep reinforcement learning (MADRL). Firstly, we formulate the safe MADRL problem as a constrained Markov game (CMG) and then transform the AIM problem into a CMG by carefully designing state, action, reward, and cost functions. Subsequently, we propose the Multi-Agent Constrained Policy Optimization (MACPO), specifically tailored to solve the CMG problem. MACPO incorporates safety constraints that further restrict the trust region formed by the Kullback-Leibler (KL) divergence, facilitating reinforcement learning policy updates that maximize performance while keeping constraint costs within their limit bounds. This leads us to introduce the MACPO-based AIM Algorithm. Finally, we train an AIM policy and compare its computation time, ride comfort, traffic efficiency, and safety with management schemes based on Model Predictive Control (MPC), Mixed Integer Programming (MIP), and non-safety-aware reinforcement learning. According to the results, compared with the MPC and MIP methods, our method has increased computational efficiency by 65.22 times and 731.52 times respectively, and has improved traffic efficiency by 2.41 times and 1.80 times respectively. In contrast to the non-safety awareness RL methods, our method achieves a zero collision rate for the first time, while also enhancing ride comfort, highlighting the advantages of using MACPO.

Connected and automated vehicles (CAVs) have the potential to transform traffic management, especially at intersections. Traditional traffic signals might become obsolete with the implementation of autonomous intersection management (AIM) systems, which aim for efficient and safe vehicle flow. Current AIM methods often rely on optimization control algorithms, which are not computationally efficient. Some methods use reinforcement learning (RL) but compromise safety for rewards and simplify traffic scenarios by designating specific turn lanes. This paper introduces a novel approach, the risk situation-aware constrained policy optimization (RSCPO), to enhance RL training with safety assurance. It uses Kullback-Leibler (KL) divergence to form a trust region, identifying risk levels in policy updates that could lead to dangerous situations, and suggests safe policy update mechanisms. Furthermore, the paper presents a safety reinforced all-directional autonomous intersection management (SafeR-ADAIM) algorithm. This algorithm accounts for the complexity of unpredictable all-direction turn lanes and collaboratively ensures the safety, efficiency, and smooth operation of CAVs at intersections. In simulations, our method surpasses the model predictive control (MPC)-based method in computational and traffic efficiency by 67.81 and 1.46 times, respectively. Additionally, it significantly reduces the mean collision rate from at most 35.01% to 0% compared to non-safety aware RL methods.

The scarcity of driving data constrains the accuracy of deep learning (DL)-based driver identification methods in practical application scenarios. To address this issue, this study proposes a novel unsupervised deep generative model called the convolution condition variant autoencoder (CCVAE) for driving data augmentation. In CCVAE, aided by driver identification information, the condition variant autoencoder can learn the real driving data distribution of each driver through an unsupervised learning paradigm; and aiming for better feature representation ability, convolutional neural network and deconvolution are leveraged, respectively. Therefore, a large number of synthetic samples can be generated by the generative part of the CCVAE. We demonstrate the effectiveness of the CCVAE through extensive experimental analysis using a real dataset collected from a vehicular CAN bus; the improvement of the DL-based driver identification results is demonstrated using synthetic samples. For instance, when only using 2% of the original data, approximately 20% improvement is achieved in terms of four evaluation indicators for two commonly used DL-based driver identification methods, namely, 1-D CNN and LSTM. Furthermore, several comparable experiments with state-of-the-art deep generative methods reveal the superior performance of the proposed CCVAE with respect to identification results, synthetic data quality, and model computation time. Therefore, the proposed model accomplishes a breakthrough in driver identification with limited data and shows great potential in data-driven applications of intelligent vehicles.

High-precision vehicle trajectory prediction can enable autonomous vehicles to provide a safer and more comfortable trajectory planning and control. Unfortunately, current trajectory prediction methods have difficulty extracting hidden driving features across multiple time steps, which is important for long-term prediction. In order to solve this shortcoming, a temporal pattern attention-based trajectory prediction network, named TP2Net, was proposed, and vehicle of interest inception was established to construct an interaction model among vehicles. Experimental results show a 15% improvement in predictive performance over the previous best method under a 5-s prediction horizon. Moreover, in order to explain why temporal pattern attention was adopted and demonstrate its ability to extract hidden features that are intuitive to human beings, a layer interpretation module was included in TP2Net to quantify the mutual information contained between the input and the intermediate layer output tensor. The results of experiments using naturalistic trajectory datasets indicated that temporal pattern attention can extract three important stages in lane changing, showing that temporal pattern attention can effectively extract hidden features and improve prediction accuracy.

Lane changing assistance in autonomous vehicles is a popular research topic. Scene modeling of the driving area is a prerequisite for lane changing decision problems. A road environment representation method based on a dynamic occupancy grid is proposed in this study. The model encapsulates the data such as vehicle speed, obstacles, lane lines, and traffic rules into a form of spatial drivability probability. This information is compiled into a hash table, and the grid map is mapped into a hash map by means of hash function. A vehicle behavior decision cost equation is established with the model to help drivers make accurate vehicle lane changing decisions based on the principle of least cost, while considering influencing factors such as vehicle drivability, safety, and power. The feasibility of the lane changing assistance strategy is verified through vehicle tests, and the results show that the lane changing assistance system based on a probabilistic model of dynamic occupancy grids can provide lane changing assistance to drivers taking into consideration the dynamics and safety.

This study presents a biosignal based driving experience analysis of an actual-vehicle experiment. A total of 10 subjects were enrolled during the experimental study. Based on their driving mileages per year, subjects were divided into novice and skilled ones at first, and then electromyography (EMG) signals of upper trapezius and sternocleidomastoid muscles were acquired continuously to evaluate a subject response to dynamic motions of the vehicle during the curve, with a driving speed of 30, 40 and 50 km/h respectively. Meanwhile, an EMG evaluation index of a normalized root mean square (RMS) was proposed to reflect the variance of EMG signals. From the experimental results, the RMS based evaluation of right upper trapezius muscle were significantly different between novice and skilled drivers, while driving with a higher speed on curve road. In addition, the RMS based evaluation of right sternocleidomastoid muscle were significantly different between novice and skilled drivers, while driving with a higher or a lower speed on curved road. It indicate that the skilled driver may have a better driving experience than that of novice ones for most curve driving conditions.

This paper focused on biosignal characteristics to analyze road rage of young drivers in a driving simulator experiment. A total of 12 subjects were enrolled during the experimental study. At first, an unfair incident video is utilized to induce the anger emotion of drivers, and then the anger state is recorded based on the Likert anger scale; meanwhile, a physiological recorder is used to acquire electroencephalogram (EEG) and electrocardiogram (ECG) signals of the subjects. In biosignal processing stage, four typical rhythm bands of α,β,δ, and θ are extracted from the original EEG using a digital filter and wavelet packet decomposition, and power spectrums of the four typical rhythm bands are obtained with a fast Fourier transform analysis. In addition, the average heart rate and R-R standard deviation are calculated through a temporal domain analysis from the original ECG signals. Furthermore, the relationships are analyzed between the sex calculated indicators and four angry levels. It indicates that there is a mainly statistical effect of the angry state for typical rhythm bands of α,β,δ, average heart rate and R-R standard deviation, indicating that these features were significantly different for the normal state, light anger, moderate anger, and heavy anger. The research results provide a theoretical basis and data support for driving emotion detection and aggressive driving behavior analyzing.