Accurate driving behavior modeling is fundamental to safe and efficient trajectory prediction, yet remains challenging in complex traffic scenarios. This paper presents a novel Inverse Reinforcement Learning (IRL) framework that captures human-like decision-making by inferring diverse reward functions, enabling robust cross-scenario adaptability. The learned reward function is utilized to maximize the likelihood of output by integrating Mamba blocks for efficient long-sequence dependency modeling with graph attention networks to encode spatial interactions among traffic agents. Comprehensive evaluations on urban intersections and roundabouts demonstrate that the proposed method not only outperforms various popular approaches in terms of prediction accuracy but also achieves 2.3 times higher generalization performance to unseen scenarios compared to other baselines, achieving adaptability in Out-of-Distribution settings that is competitive with fine-tuning.

• Modular legal-interpretation layer with hybrid vector–graph RAG for AV guidance. • Two datasets: SFT and RAG for multilingual, cross-jurisdiction evaluation. • Hybrid retrieval improves faithfulness and reduces hallucination vs single modes. • Trust module scores context, groundedness, and answer relevance online. • Validated in smart-cabin, V2X intersection monitoring, and offline auditing. Autonomous vehicles (AVs) face persistent challenges in complying with complex and evolving traffic laws. Existing approaches, including rule-based, learning-based, and large language model (LLM) methods, each face limits in adaptability, generalizability, or trustworthiness. We present DriveLegal , a modular legal-interpretation framework for downstream autonomous driving applications. DriveLegal pairs fine-tuned multilingual large language models (LLMs) with an intelligent hybrid retrieval module that routes between vector search and knowledge graph, then returns concise, cited answers. A trust layer scores context relevance, groundedness, and answer relevance and supports continuous improvement through periodic automatic signals and targeted human review. We introduce the DriveLegal datasets for supervised fine-tuning and for retrieval and graph reasoning. Across benchmarks and case studies in smart cabin and vehicle-to-everything (V2X) settings, the hybrid retrieval strategy improves contextual accuracy and reduces hallucination while producing jurisdiction-aware outputs suitable for compliance checks, incident analysis, and reporting.

This paper develops a fuzzy game-theoretic tube model predictive control (MPC) framework for coordinated vehicle lateral motion control using active front steering (AFS) and direct yaw moment control (DYC). The vehicle dynamics are represented by a discrete-time Takagi-Sugeno fuzzy model to capture operating-condition dependence and parametric uncertainty, while a common-feedback tube MPC structure is employed to guarantee robust constraint satisfaction through an offline-designed invariant tube and terminal set. On this basis, the nominal control problem is formulated as a two-player finite-horizon Nash game, allowing AFS and DYC to optimize individual performance objectives under shared state dynamics and constraints. To enable real-time implementation, two fixedcomplexity online Nash solvers are considered: a best-response (BR) iteration scheme and a variational inequality (VI) formulation solved by an extragradient method. The closed-loop analysis establishes recursive feasibility under bounded disturbances and finite-iteration online equilibrium computation. In addition, a practical input-to-state stability result is derived, in which the effect of inexact online Nash solutions is explicitly captured through a practical-descent framework. Compared with the BR solver, the VI-based solver provides a more direct residual-based interpretation of equilibrium approximation accuracy and its relation to closed-loop stability margins. Hardware-in-the-loop experiments under multiple driving maneuvers verify that the proposed framework is computationally tractable and effective in real time, while achieving robust tracking performance, constraint satisfaction, and coordinated actuator usage.

Decision-making and control are the core functionalities of high-level autonomous driving systems. Existing mainstream research, including modular and end-to-end paradigms, typically employ conservative strategies that compromise driving efficiency. However, driving efficiency constitutes a critical constraint on the transition of autonomous vehicles from mere operability to practical utility. Autonomous overtaking systems serve as a typical means to improve driving efficiency. Nevertheless, in stochastic and uncertain traffic scenarios, achieving safe and efficient continuous autonomous overtaking remains a significant challenge. In this context, this paper proposes a decision-making and control framework based on MeUAL to achieve the optimal trade-off between overtaking risk and efficiency. First, at the decision-making layer, a safe reinforcement learning method based on Uncertainty-aware Augmented Lagrangian (UAL) is developed to provide global overtaking guidance. Subsequently, the motion planning and control layer based on Model Predictive Control (MPC) closely tracks the UAL-generated guidance, while preserving the safety and constraint guarantees inherent to traditional MPC. Finally, a Policy Switching Mechanism (PSM) triggered by the safety epistemic uncertainty threshold is designed for the MeUAL-driven autonomous overtaking system. Experimental results demonstrate that MeUAL outperforms baseline algorithms with respect to reward-cost balance, sample efficiency, and learning stability. Moreover, in various test scenarios that are distinct from the training distribution, MeUAL-PSM exhibits strong robustness and interpretable overtaking maneuvers through flexible policy switching.

An adaptive tracking control policy is investigated for uncertain nonlinear systems under the finite-time asymmetric output constraints (FTAOCs). Unlike common output constraints, FTAOCs are characterized as constraints that are initially imposed during system operation and are then removed after a certain time. To tackle this challenge, we have designed novel shift and barrier functions that transform FTAOCs into guarantees of boundedness for an auxiliary variable. Additionally, we have developed an adaptive estimation algorithm to estimate unknown parameters and proposed an adaptive control strategy. Simulation studies on the Resistance-inductance-capacitance (RLC) circuits have been conducted to demonstrate the feasibility of our proposal. In comparison with state-of-the-art methods, our algorithm offers the flexibility to simultaneously address both unconstrained and constrained requirements of nonlinear systems, without requiring revisions to the controller structure.

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.

Learning-based algorithms play a pivotal role in various functional modules of an autonomous driving system. Recognizing and accounting for the impact of learning-based algorithm uncertainties on other functional modules can be crucial for making more dependable driving behavior decisions and for selecting more appropriate driving precaution measures, as opposed to directly executing safety fallback strategies like emergency braking. With the motivation of optimizing the safety without unnecessary disruption to the driving experience, this paper proposes an uncertainty-aware, dual-tiered decision making method named DBNID, which is based on dynamic Bayesian network (DBN) and influence diagram (ID). To begin, the paper formulates the effects of uncertainty propagation stemming from perception and prediction modules using a DBN model. The effects are then solved by an expectation maximum (EM) algorithm. Furthermore, how the uncertainty propagation effects are considered in the decision making process is then presented in an ID model with the introduction of the utility function formulation. Finally, the proposed DBNID method is evaluated on a simulation platform tailored for real-world autonomous driving testing. By considering uncertainty propagation, the results demonstrate that the proposed method can significantly reduce the likelihood of violating critical safe stop requirements, while simultaneously enhancing the minimum time-to-collision (TTC) performance. DBNID method offers valuable insights of integrating learning-based algorithm uncertainties into autonomous vehicle decision making process.

Perception systems play a crucial role in autonomous driving by reading the sensory data and providing meaningful interpretation of the operating environment for decision-making and planning. Guaranteeing a safe perception performance is the foundation for high-level autonomy, so that we can hand over the driving and monitoring tasks to the machine with ease. With the motivation of improving the perception systems’ safety, this survey analyzes and reviews the current achievements of safety-related standards and definitions, sensory modeling, and metrics for perception tasks in autonomous driving applications. Furthermore, it covers the generic categorization of potential failures and causal analysis in perception tasks, correlates the effect with the scenario modelling choices, and highlights major triumphs and noted limitations encountered by current research efforts. The new safety challenges laid out by the information exchange stage of the connected autonomous vehicle application have also been summarized. The open research questions and future directions are outlined to welcome researchers and practitioners to this exciting domain.

Detecting driver inattentive behaviors is crucial for driving safety in a driver monitoring system (DMS). Recent works treat driver distraction detection as a multiclass action recognition problem or a binary anomaly detection problem. The former approach aims to classify a fixed set of action classes. Although specific distraction classes can be predicted, this approach is inflexible to detect unknown driver anomalies. The latter approach mixes all distraction actions into one class: anomalous driving. Because the objective focuses on finding the difference between safe and distracted driving, this approach has better generalization in detecting unknown driver distractions. However, a detailed classification of the distraction is missing from the predictions, meaning that the downstream DMS can only treat all distractions with the same severity. In this work, we propose a two-phase anomaly proposal and classification framework [driver anomaly detection and classification network (DADCNet)] robust for open-set anomalies while maintaining high-level distraction understanding. DADCNet makes efficient allocation of multimodal and multiview inputs. The anomaly proposal network first utilizes a subset of the available modalities and views to suggest suspicious anomalous driving behavior. Then, the classification network employs more features to verify the anomaly proposal and classify the proposed distraction action. Through extensive experiments in two driver distraction datasets, our approach significantly reduces the total amount of computation during inference time while maintaining high anomaly detection sensitivity and robust performance in classifying common driver distractions.

Accurate forecasting of future traffic is a critical contemporary problem for transportation research. However, it is difficult to understand the feature patterns of traffic events due to the complexity of the traffic environment, heterogeneous factors, and lack of abnormal samples. This article proposes a framework to integrate the social traffic data and use the TabNet model to facilitate the representation learning task in traffic event prediction. With the tabular learning and model interpretability analysis, the importance of common traffic external factors toward traffic events is studied. The study has practical significance for regulating traffic planning and the development of the operational boundary for autonomous driving systems.

Multi-vehicle motion planning (MVMP) has become an emerging paradigm in connected and automated vehicles (CAVs). The cooperative lane-change movements with the coexistence of platoons and CAVs are typical scenarios on the muti-lane roads. This paper proposes an optimal control framework with the advantages of completeness and universality for platoons and CAVs’ cooperative lane-change motion planning in different task scenarios. Two typical cooperative scenarios are designed for the subsequent study of optimal modeling. The platoons’ reconfiguration and original shape maintenance are considered to reflect the universality of moving objects and the diversity of cooperative tasks. Approximately geometric contour models, dynamic externally tangent rectangle and inflated rectangle, are utilized to describe the platoon’s profile. Analytical complete collision avoidance constraints among different motion objects are constructed effectively. Other necessary constraints and the weighted cost function that minimizes lane-change time and motion energy are comprehensively considered. The optimal control models are established for the desired scenarios. Moreover, a numerical solution method combined with the simultaneous direct collocation method based on the trapezoidal rule and the barrier function method is proposed to obtain the optimal schemes. Simulation and contrast experiments are conducted for two scenarios. The results indicate that the cost function’s weight coefficients and specific lane-change tasks influence the cooperative motion planning effects and verify that the proposed optimal control framework is of reasonability, effectiveness, and unification.

In this article, we investigate the exponential stabilization issue of a wave equation with the external input disturbance, which is described by a nonlinear exogenous system. A novel disturbance observer is constructed to estimate the unknown input disturbance. Then, based on the proposed disturbance observer, a boundary control strategy is developed to cancel the effect of disturbance and stabilize the system. The exponential stability is proven by employing the Lyapunov’s direct method. This method can be extended to a class of flexible systems described by the hyperbolic partial differential equation met in the practical engineer area. The example of a nonuniform flexible string system is given, where the effectiveness of the proposed strategy is evaluated based on simulations.

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.

Autonomous urban driving navigation is still an open problem and has ample room for improvement in unknown complex environments and terrible weather conditions. In this paper, we propose a two-stage framework, called IPP-RL, to handle these problems. IPP means an Imitation learning method fusing visual information with the additional steering angle calculated by Pure-Pursuit (PP) method, and RL means using Reinforcement Learning for further training. In our IPP model, the visual information captured by camera can be compensated by the calculated steering angle, thus it could perform well under bad weather conditions. However, imitation learning performance is limited by the driving data severely. Thus we use a reinforcement learning method-Deep Deterministic Policy Gradient (DDPG)-in the second stage training, which shares the learned weights from pretrained IPP model. In this way, our IPP-RL can lower the dependency of imitation learning on demonstration data and solve the problem of low exploration efficiency caused by randomly initialized weights in reinforcement learning. Moreover, we design a more reasonable reward function and use the n-step return to update the critic-network in DDPG. Our experiments on CARLA driving benchmark demonstrate that our IPP-RL is robust to lousy weather conditions and shows remarkable generalization capability in unknown environments on navigation task.