Cheng Wang

Autonomous vehicles (AVs) are poised to revolutionize global transportation systems. However, its widespread acceptance and market penetration remain significantly below expectations. This gap is primarily driven by persistent challenges in safety, comfort, commuting efficiency and energy economy when compared to the performance of experienced human drivers. We hypothesize that these challenges can be addressed through the development of a driver foundation model (DFM). Accordingly, we propose a framework for establishing DFMs to comprehensively benchmark AVs. Specifically, we describe a large-scale dataset collection strategy for training a DFM, discuss the core functionalities such a model should possess, and explore potential technical solutions to realize these functionalities. We further present the utility of the DFM across the operational spectrum, from defining human-centric safety envelopes to establishing benchmarks for energy economy. Overall, We aim to formalize the DFM concept and introduce a new paradigm for the systematic specification, verification and validation of AVs.

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 at https://github.com/RoboSafe-Lab/R-RNet

Corner modules decouple chassis functions and enable independent wheel steering, but their control is highly sensitive to external disturbances and feedback delays. Disturbance observers (DObs) are often introduced to mitigate such disturbances, yet their additional dynamics can also compromise closed-loop stability when delays are present. This paper establishes the closed-loop control system of a corner module steering system based on its dynamics, designs the corresponding control law, and incorporates a DOb. Classical stability analysis is carried out using D-curve mapping and eigenvalue validation. The results reveal that feedback delay progressively shrinks the stable domain. When a DOb is introduced, disturbance rejection is improved; however, the admissible control gain region becomes narrower, and larger observer gains further constrain the derivative action, generating additional unstable regions. This paper mechanistically elucidates the impact of disturbance observation on the stability of a time-delayed control system for a corner module with steering.

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.

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.