In the field of autonomous driving, safe and efficient decision-making through deep reinforcement learning remains a significant challenge. Existing methods often struggle to adapt to the dynamic and complex conditions of urban environments, while the lack of interpretability in reinforcement learning algorithms raises safety concerns. To address these issues, this paper proposes a reinforcement learning method guided by reward machine. Firstly, a reward machine tailored for autonomous driving scenarios is constructed to better guide the agent's behavior selection. Then, a time sensitivity factor is proposed to adjust the generation of counterfactual experiences, optimizing the effectiveness of policy learning. Furthermore, to improve the safety of autonomous driving decisions, formal verification of the decision-making process is conducted via the UPPAAL model checker, enabling the identification and handling of potential hazardous states. Finally, the effectiveness and safety of this method are validated through a case study of an autonomous driving system, demonstrating that the proposed reward machine-guided reinforcement learning algorithm performs well in complex road scenarios.

Abstract Given the complexity of software development and testing environments, the establishment of software reliability growth models (SRGMs) is diverse. To date, no SRGM can be applied and implemented in all software development and testing environments. Therefore, how to choose an appropriate SRGM for software reliability evaluation in the current software development and testing environment is an important practical issue. In this study, we proposed a weighted Grey relational analysis method to select the optimal SRGMs, including closed- and open-source SRGMs, as well as perfect and imperfect debugging SRGMs. To effectively validate the effectiveness of the proposed method, we used 12 SRGMs, 11 model evaluation criteria, and 2 successive versions of open-source software fault datasets. Results of this study indicated that the proposed method can select the optimal SRGM in the current software development and testing environment. To conclude, this study has important practical significance for actual software development and testing and makes important contributions to assisting developers or testers in selecting the optimal SRGM for software reliability assessment.

ABSTRACT Context Ensuring safety in autonomous driving systems is a major challenge, particularly in highly dynamic and complex environments. Traditional verification techniques struggle to capture intertwined spatial and temporal safety requirements in real‐time autonomous behaviors. Objective This study aims to provide a formal specification and verification framework that ensures safety‐critical spatio‐temporal interactions in autonomous driving, supporting rigorous analysis and preventing unsafe behaviors. Method We propose a spatio‐clock synchronous constraint framework, which includes: (1) a formal definition of spatio‐clock constraint trajectories; (2) the development of a specification language (SCSL) integrating RCC and CCSL; (3) the design of Spatio‐Clock Synchronous Automata (SCSA) for modeling driving behaviors; (4) formalization of safety guards and safe transitions; and (5) a verification process based on model checking. Result The framework is validated through a highway autonomous overtaking scenario. The case study demonstrates our approach's effectiveness to formally verify collision‐free guarantees under complex spatial‐temporal interactions and controller decision‐making logic. Conclusion The proposed framework enables precise and modular safety specification and verification for autonomous systems. It has practical value in supporting safety assurance during system design, especially in safety‐critical driving tasks under dynamic conditions.

Automatic land cover classification from high-resolution remote sensing (RS) images remains challenging due to the complex composition of classes. Given the potential of a graph to simulate latent class composition, the latest development of graph convolutional network (GCN) has received increasing attention. However, most existing methods only use a single perspective graph structure, which largely limits their ability to capture the complementary features that would better represent the underlying data structure of images. Therefore, this paper proposes a novel multi-view GCN-based representation learning network(MvRLNet) for RS image classification. First, a superpixel-based spectral component decomposes module(SSCDM) is designed to enhance the uniqueness and homogeneity of graph nodes because the mixed superpixels may lead to miscellaneous information on graph aggregations. Second, a multi-view graph learning module(MGLM) is proposed to integrate topology and spectral graph information into a unified network with an effective feature learning strategy. Finally, the effectiveness of the proposed MvRLNet is validated on a variety datasets with different resolutions. The experimental results show that the proposed MvRLNet performs better than state-of-the-art techniques.

Summary Collaborative and autonomous driving vehicles combine hardware and software complex processes, also are heavily dependent on and influenced by the world of physical and cyber interactions. They have enabled many new features and advanced functionalities, such as stochastic and hybrid natures, mobile spatial topologies, and time‐critical dependability. However, the existing modeling and verification techniques have not established faith in proving correctness and safety. Spatial and time collision avoidance remains crucial obstacles on the path to becoming ubiquitous and dependable. In order to ensure safety, we first design an accident prediction architecture in system design‐time and run‐time stages. We apply it on collaborative and autonomous overtaking systems involving spatial‐ and time‐critical accident predictions. Then, we develop a novel and dedicated spatio‐clock stochastic specification language (SCSSL) to describe safety invariants and guards in domain‐specific autonomous driving systems. Next, we create the spatio‐clock stochastic and hybrid automata models based on SCSSL in order to model inherently stochastic and hybrid behaviors. To illustrate the effectiveness of spatio‐clock consistency stochastic specification and verification, we adopt statistical model checking natively to provide reliable predictions for the incoming collision instants and positions. Finally, we present an illustrative overtaking case study to verify spatio‐clock stochastic and hybrid related properties and ensure correct modeling, and demonstrate the significance of our proposed approach.

Forecasting the motion of surrounding vehicles is necessary for a self-driving vehicle to plan a safe and efficient trajectory for the future. Like experienced human drivers, the self-driving vehicle needs to perceive the interaction of surrounding vehicles and decide the best trajectory from many choices. However, previous methods either lack modeling of interactions or ignore the multi-modal nature of this problem. In this paper, we focus on two important cues of trajectory prediction: interaction and maneuver, and propose Maneuver conditioned Attentional Network named MAN. MAN learns the interactions of all vehicles in a scenario in parallel by self-attention social pooling and the attentional decoder generates the future trajectory conditioned on the predicted maneuver among 3 classes: Lane Changing Left (LCL), Lane Changing Right (LCR) and Lane Keeping (LK). Experiments demonstrate the improvement of our model in prediction on the publicly available NGSIM and HighD datasets. We also present quantitative analysis to study the relationship between maneuver prediction accuracy and trajectory error.

GNSS tomography is acknowledged as one of the most attractive techniques to accurately retrieve three-dimensional distribution of atmospheric water vapor with high-resolution. Here the development of a wide-area tomography technique for the retrieval of water vapor fields by jointly using GNSS observations and numerical weather prediction forecasts is described. We present an improved node parameterization tomography to retrieve the high-resolution wet refractivity fields over the continent of USA. This method does not depend on numerical integration by Newton-Cotes quadrature and considerably reduces computational burden in linearization. To refine the tomographic modeling, vertical variation parameter of water vapor for each voxel is estimated dynamically from the updated wet refractivity profiles after each iteration, towards achieving a self-adaptive design matrix. Global Forecast System products from NCEP are applied to initialize the tomographic solution for a simulation of real time mode. Tomography experiment is demonstrated with GPS data collected from 1440 stations over a one-month period of June 2020. Compared with the traditional node parameterization method, the improved method can enhance the performance by 6% and reduce the computational burden by 30%, respectively.

Autonomous driving vehicles are a kind of typical cyber-physical systems integrating complex interactions between hardware and software components such as collaborative computation, distributed communication, and spatio-clock synchronous control with surrounding traffic environment. They can percept the environment, communicate with surroundings, and react fast enough to control independently. The purpose of autonomous driving emergence is to improve driving safety, reduce environmental pollution, and ease the traffic congestion. However, new features with surrounding open and dynamic environment make systems design and verification becoming more and more complex than ever, such as stochastic communication delay, hardware spontaneous failure distribution, and natively hybrid behaviors described by ordinary differential equations. Spatial and time collision avoidance remains crucial obstacles on the path to becoming ubiquitous and dependable. In this paper, we adopt statistical model checking (SMC) to enlighten possible hazards affected by stochastic and hybrid features in the design phase of autonomous driving systems. In order to provide safety and accountability, we first propose a dedicated multi-lane spatio-clock stochastic specification language (MLSCL) to describe safety invariants and guards in domain-specific autonomous driving systems. Then, we present the semantic mapping rules between MLSCL and UPPAAL SMC models, and design the spatio-clock stochastic and hybrid automata based on MLSCL in order to model inherently stochastic and hybrid behaviors. Finally, we present an illustrative lane-change case study to verify spatio-clock stochastic and hybrid-related properties adopting SMC, and demonstrate the effectiveness of our proposed approach.

Abstract In recent years, open source software (OSS) has been widely used and developed. The reliability of OSS has also become a hot research topic. Due to the complexity, dynamics, and uncertainty of the development and testing process of OSS, it is also a difficult task to accurately evaluate the reliability of OSS. In this paper, we consider the nonlinear changes of fault detection and fault introduction in the development and testing of OSS and propose a reliability model of OSS based on the nonlinear changes of fault detection and fault introduction. Experimental results show that the proposed model is more in line with the actual changes of fault detection and fault introduction in the processes of OSS development and testing. Compared with other models, the proposed model has better fitting and predictive performance. We also give a simple OSS optimal release method considering the testing‐effort and reliability changes in the processes of OSS development and testing. The proposed model and optimized release method can effectively assist OSS developers to evaluate software reliability and determine the optimal release time.

Abstract Software reliability assessment methods have been changed from closed to open source software (OSS). Although numerous new approaches for improving OSS reliability are formulated, they are not used in practice due to their inaccuracy. A new proposed model considering the decreasing trend of fault detection rate is developed in this study to effectively improve OSS reliability. We analyse the changes of the instantaneous fault detection rate over time by using real-world software fault count data from two actual OSS projects, namely, Apache and GNOME, to validate the proposed model performance. Results show that the proposed model with the decreasing trend of fault detection rate has better fitting and predictive performance than the traditional closed source software and other OSS reliability models. The proposed model for OSS can further accurately fit and predict the failure process and thus can assist in improving the quality of OSS systems in real-world OSS projects.

With the development of aerospace technology, the method which uses linear model to represent the nonlinear component is not able to match the fault detection perfectly in hydraulic actuator control system. This paper proposes a polynomial fit based simulation method to build nonlinear model in hydraulic actuator control system. This method is used to simulate two kinds of typical hydraulic actuator control system. Contrastively, a simulation with traditional linear model is also executed. Through comparison among the result of two kinds of simulation and the test data, it is proved that this polynomial fit based method is more accurate than the traditional method and it can perform more effectively for fault detection in hydraulic actuator control system.