Accurate prediction of pedestrian trajectories is crucial for safe motion planning of autonomous vehicles in urban environments. Many existing temporal and generative models are constrained by the long-tailed distribution of the data, which limits their ability to handle random or irregular pedestrian movements. Moreover, few studies have addressed the problem of scoring and probabilistic evaluation of predicted trajectories, despite their importance for downstream decision-making tasks. To address these issues, we propose a regularization-randomization network (R-RNet). The core regularization-randomization (R-R) module enables flexible trajectory prediction across diverse scenarios, while the probability predictor provides trajectory scoring and probability estimation to enhance reliability and utility in subsequent tasks. Besides, a self-attention mechanism is utilized to enhance prediction performance by capturing features from the distribution of the goals. The experimental results on the ETH and the UCY datasets show that R-RNet is capable of making reliable evaluations on output trajectories and achieves competitive results in terms of average displacement error and miss rate, while maintaining a lightweight architecture. Extensive experiments and analyses underscore the critical importance of both regularization and randomization operations. The source code is released athttps://github.com/RoboSafe-Lab/R-RNet

Intelligent driving aims to handle dynamic driving tasks in complex environments, while driver behavior onboard is less focused. In contrast, an intelligent cockpit mainly focuses on interacting with a driver, with limited connection to the driving scenarios. Since the driver onboard could affect the driving strategy significantly and thus have nonnegligible safety implications on an autonomous vehicle, a cockpit-driving integration (CDI) is generally essential to take the driver’s behavior and intention into account when shaping the driving strategy. However, no comprehensive review of current existing CDI technologies is conducted despite the significant role of CDI in safe driving. Therefore, we are motivated to summarize the state-of-the-art of CDI methods and investigate the development trends of CDI. To this end, we identify thoroughly current applications of CDI for the perception and decision-making of autonomous vehicles and highlight critical issues that urgently need to be addressed. Additionally, we propose a lifelong learning framework based on evolvable neural networks as solutions for future CDI. Finally, challenges and future work are discussed. The work provides useful insights for developers regarding designing safe and human-centric autonomous vehicles.

Autonomous driving datasets (ADDs) have long served as a critical foundation for the development of autonomous driving technologies. Among them, drone-based ADD (DADD) refers to traffic flow trajectory datasets captured by drones. This paper reviews 17 currently available open-source DADDs and introduces evaluation metrics to assess their quality. By comparing and analyzing these datasets and related papers, we found that the elaboration of the dataset generation chain is incomplete, and we propose a generic generation framework for DADD, including four parts: data collection, trajectory acquisition, map construction, and traffic signal data acquisition. Specific optional methods are specified for each part, and optimization directions are proposed. In addition, we summarize the applications of DADD in the field of autonomous driving and intelligent transportation and deeply analyze the future application trends of DADD. Our work provides researchers not only with a guide for selecting open-source DADDs and generating DADDs but also with a guideline for the future construction and application of DADDs.

Ensuring the safety of autonomous vehicles (AVs) is paramount before they can be introduced to the market. More specifically, securing the Safety of the Intended Functionality (SOTIF) poses a notable challenge; while ISO 21448 outlines numerous activities to refine the performance of AVs, it offers minimal quantitative guidance. This paper endeavors to decompose the acceptance criterion into quantitative perception requirements, aiming to furnish developers with requirements that are not only understandable but also actionable. This paper introduces a risk decomposition methodology to derive SOTIF requirements for perception. More explicitly, for subsystem-level safety requirements, we define a collision severity model to establish requirements for state uncertainty and present a Bayesian model to discern requirements for existence uncertainty. For component-level safety requirements, we proposed a decomposition method based on the Shapley value. Our findings indicate that these methods can effectively decompose the system-level safety requirements into quantitative perception requirements, potentially facilitating the safety verification of various AV components.

As a specific articulated vehicle, lateral stability of car-trailer combination deserves special attention because this vehicle shows catastrophic dynamic instability occasionally at high speeds. This is known as sway or flutter and might poses a serious threat to traffic safety on the highway. The problem can be attribute to complex dynamics coupling between the towing car and the trailer. This paper proposes a phase portrait-based sliding mode control method via differential braking at the towing car and the trailer simultaneously to realize the direct yaw moment control and improve dynamic stability. In this process, a nonlinear single-track model with 3 degrees of freedom is established and integrated into the controller design. The stability region of the towing car and the trailer is analyzed based on the sideslip angle – yaw rate phase portraits under different speeds. And the sliding mode surface of controller is designed based on the stability region. The Matlab/Simulink and TruckSim co-simulation is established to verify the performance of controller. The steering wheel input of simulation is designed in accordance with ISO9815 and the dynamic critical speed is determined based on the yaw damping ratio of car-trailer combination. Compared with the model predictive control-based method, the simulation results demonstrate that the phase portrait-based sliding mode control method has realized yaw damping ratio of 0.81 both in the towing car and the trailer at dynamic critical speed. The proposed method has superior performance in enhancing the dynamic stability of car-trailer combination.

Artificial Intelligence (AI) shows promising applications for the perception and planning tasks in autonomous driving (AD) due to its superior performance compared to conventional methods. However, highly complex AI systems exacerbate the existing challenge of safety assurance of AD. One way to mitigate this challenge is to utilize explainable AI (XAI) techniques. To this end, we present the first comprehensive systematic literature review of explainable methods for safe and trustworthy AD. We begin by analyzing the requirements for AI in the context of AD, focusing on three key aspects: data, model, and agency. We find that XAI is fundamental to meeting these requirements. Based on this, we explain the sources of explanations in AI and describe a taxonomy of XAI. We then identify five key contributions of XAI for safe and trustworthy AI in AD, which are interpretable design, interpretable surrogate models, interpretable monitoring, auxiliary explanations, and interpretable validation. Finally, we propose a conceptual modular framework called SafeX to integrate the reviewed methods, enabling explanation delivery to users while simultaneously ensuring the safety of AI models.

Goal recognition (GR) involves inferring the goals of other vehicles, such as a certain junction exit, which can enable more accurate prediction of their future behaviour. In autonomous driving, vehicles can encounter many different scenarios and the environment may be partially observable due to occlusions. We present a novel GR method named Goal Recognition with Interpretable Trees under Occlusion (OGRIT). OGRIT uses decision trees learned from vehicle trajectory data to infer the probabilities of a set of generated goals. We demonstrate that OGRIT can handle missing data due to occlusions and make inferences across multiple scenarios using the same learned decision trees, while being computationally fast, accurate, interpretable and verifiable. We also release the inDO, rounDO and OpenDDO datasets of occluded regions used to evaluate OGRIT.

Safety validation is a challenge for releasing automated driving, even though substantial effort has been made in this field. This paper proposes an online safety validation method within the frame of virtual assessment of automation in field operation (VAAFO). The basic idea of VAAFO is that a virtual automated vehicle runs in the background, while the physical vehicle is driven in an automated or manual mode. The virtual automated vehicle receives input from real sensors, but has no access to the actuators. Thus, the risk-free nature of simulation-based testing and the validity of field operational testing are combined. The testing of automated vehicles is accelerated by applying the approach in customer vehicles. In this paper, we elaborate on and implement this approach. Essential parameters are studied and specified, while the necessary coordinate transformation is performed. Triggers are defined and concretized by a newly developed criticality index. Two derived simulated cases and a real-world case are utilized to illustrate the VAAFO approach. The study cases show that the safety of automated vehicles can be assessed online and critical scenarios can be discovered by the defined triggers under the framework of VAAFO. The results demonstrate that the proposed approach is able to safely and efficiently test automated vehicles online under real driving conditions and discover unknown unsafe scenarios.