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.

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 vehicle trajectory prediction (VTP) is important for autonomous vehicles to make decisions. However, it is challenging because of the inherent uncertainty, dynamic nature, and interactions within driver-vehicle-traffic systems. Moreover, existing methods inadequately balance interpretability and accuracy. Furthermore, few works have been dedicated to analyzing VTP on the drivers cognitive level, while drivers have powerful reasoning abilities due to extensive driving experience and knowledge. To alleviate these, a spatial-temporal graph convolutional network based on domain-knowledge guided learning is proposed by analyzing the drivers cognitive mechanism for VTP on highway. Specifically, a topological graph is constructed to represent the interactions of driving scenarios. A spatial-temporal graph convolutional network, incorporating spatial-temporal attention and domain knowledge, is developed to model the interactions and improve the interpretability. The experimental results suggest that our proposed method outperforms previous methods in both accuracy and interpretability of VTP for the next 5 seconds.

Autonomous parking trajectory planning in unstructured environments with irregular obstacles must address the challenges posed by non-convex obstacle constraints. Due to the coupling between problem complexity and the number of surrounding obstacles, existing methods often suffer from increased computation time and failure rates in dense environments. To tackle this issue, this paper proposes an efficient parking trajectory planner with fast obstacle retrieval capability. The proposed planner follows a classical two-stage architecture consisting of front-end trajectory generation and back-end trajectory optimization. In the first stage, a multi-resolution sampling-based trajectory generation method is introduced. By using multi-resolution sampling strategy and a KD-Tree-based collision detection algorithm, the method achieves high-quality initial trajectory while maintaining computational efficiency. In the second stage, we present a novel iterative trajectory optimization method based on neighbor obstacle indexing, which restricts the scale of obstacle constraints during each optimization iteration, which improves computational efficiency of trajectory optimization. Extensive comparative studies and real-car experiments are conducted to validate the advantages of the proposed method, particularly in terms of computation time and robustness in complex, cluttered environments.

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.

The human-vehicle collaboration in automated vehicles is an effective transitional means to overcome the difficulty of rapidly transitioning to a highly automated level of intelligence. Furthermore, it can fully leverage the strengths of both drivers and autonomous driving systems, embodying a design philosophy of human-centered. Therefore, this paper provides a review and perspectives of the human-vehicle collaboration for automated vehicles. First, the concept, forms and methods of human-vehicle collaboration are reviewed. Then, a human-vehicle mutual trust collaboration framework based on complementary advantages of humans and vehicles and brain-like intelligence is proposed. Specifically, the framework focuses on driver behavior understanding and brain-like cognitive decision planning. After that, the methods of driver behavior understanding and brain-like cognitive decision planning are summarized. Finally, challenges and future works are analyzed to contribute the develop of understandable, trustable, and acceptable human-vehicle collaboration systems.

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.

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.

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.