This paper presents a structured framework for real-time reliability assessment across different estimation paths (topologies) to ensure reliable estimation under fault conditions. Our multi-stage approach first analyzes multiple redundant estimation pathways to effectively isolate fault sources and then reconfigures to the most reliable path based on a analytically defined reliability index. Considering all sensor configurations and independent pathways for estimating vehicle states, the resulting structure forms a directed acyclic graph, termed an estimation graph. A reconfigurable estimation scheme is proposed to enhance reliability across diverse fault conditions. The framework leverages a detailed structural analysis of the estimation graph to enhance fault detectability, as shown by isolating the fault in vertical acceleration. By analytically quantifying fault propagation along each estimation path, the framework enables real-time selection of the optimal path. The proposed analytical formulation offers a unified and computationally efficient approach to quantifying the effects of common soft faults, such as bias and excessive noise. Validation using both high-fidelity CarSim simulations and real-vehicle experiments confirms the accuracy of the analytical derivations and demonstrates the framework's effectiveness in localizing fault sources, ensuring reliable estimation, and enabling real-time reconfiguration under various fault conditions.

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.

This paper proposes a hybrid model/data fault detection and diagnosis system applicable to any vehicle sensor and actuator. This system works based on comparing the measurements of a target sensor or the desired control actions of a target actuator with their estimations. These estimations are obtained by a hybrid estimator developed based on the integration of model-based and data-driven estimators leveraging the strength of each estimator. Considering the weakness of pure data-driven estimators in confronting unknown conditions, a self-updating dataset is proposed to learn new cases. After fault detection, the estimations of the hybrid estimator are used to reconstruct sensor data or find the level of actuator failure. To evaluate the performance of the proposed hybrid fault detection and diagnosis system, it is applied to a vehicle’s lateral acceleration sensor and traction motor. The results of experimental tests conducted on an all-wheel-drive vehicle show the effectiveness of the algorithm in detecting and quantifying faults in the target component.

Agent-based model predictive control (AMPC) has recently been proposed as a distributed scheme that collaborates with all agents to achieve optimal holistic performance. However, its optimality highly depends on the prediction accuracy that requires all agents or their contributions to be known, which is too idealistic for actual implementation. This research proposes a novel practical hybrid control scheme - learning agent-based MPC (LAMPC), combining the model-based AMPC approach and data-based learning methods to improve the holistic vehicle performance for multi-agent systems. The Gaussian process regression (GPR) enhanced by an online data management strategy serves as the learning core to predict unknown contributions. A novel multi-step prediction mechanism leverages the GPR learning potential along the horizon. The predicted mean, representing the learned unknown contributions, completes the system model in the MPC for more accurate control. Meanwhile, a stochastic framework is formulated to guarantee control safety and feasibility using soft chance constraints based on the prediction variance. Both simulations and experiments show that, with the learning capability, LAMPC outperforms the traditional AMPC. LAMPC can achieve higher tracking performance in well-learned scenarios and always guarantee constraint satisfaction even in less-learned scenarios. Moreover, the proposed hybrid control scheme is efficient for real-time implementation and is flexible to any control agent topology.

Left turning for autonomous vehicles at intersections is challenging due to the various driving behaviors from different human drivers and the strong interaction between the autonomous vehicle and human traffic participants. This paper proposes a planning and decision making framework for intersection left-turning which considers the interaction between autonomous vehicles and human drivers as well as pedestrians to address this issue. The proposed framework considers interactions mathematically by formulating the problem as a linear quadratic differential game. Through solving the Nash equilibrium of the game, the autonomous vehicle is able to properly interact with surrounding traffic participants. Under the differential game framework, the accuracy of the interaction formulation is closely related to the behavior model of human drivers. Therefore, real-world human behavior is extracted and evaluated from naturalistic driving dataset to help establish more realistic modeling and estimation of various kinds of traffic participants, including aggressive, neutral and conservative traffic participants. The simulation results show that the autonomous vehicle is able to properly estimate the types of traffic participants by observing their behavior using the proposed technique. Then the autonomous vehicle behave according to the types of those traffic participants to enable interactive and human-like planning and decision making at intersections.