Yifan Zhang

With the increasing adoption of autonomous vehicles, ensuring the reliability of autonomous driving systems (ADSs) deployed on autonomous vehicles has become a significant concern. Driving simulators have emerged as crucial platforms for testing ADSs, offering realistic, dynamic, and configurable environments. However, existing simulation-based ADS testers have largely overlooked the reliability of the simulators, potentially leading to overlooked violation scenarios and subsequent safety security risks during real-world deployment. In our investigations, we identified that collision detectors in simulators could fail to detect and report collisions in certain collision scenarios, referred to as ignored collision scenarios. This paper aims to systematically discover ignored collision scenarios to improve the reliability of autonomous driving (AD) simulators. To this end, we present ICSFuzz, a black-box fuzzing approach to discover ignored collision scenarios efficiently. Drawing upon the fact that the ignored collision scenarios are a sub-type of collision scenarios, our approach starts with the determined collision scenarios. Following the guidance provided by empirically studied factors contributing to collisions, we selectively mutate arbitrary collision scenarios in a step-wise manner toward the ignored collision scenarios and effectively discover them. We compare ICSFuzz with multiple state-of-the-art simulation-based ADS testing methods, by replacing their oracle with our ignored-collision-aware oracle. The evaluation demonstrates that ICSFuzz outperforms ADS testers by finding 7~40x more ignored collision scenarios with a 10~105x speedup. Within the discovered ignored collision scenarios, there are two more types of ignored collision scenarios that ADS testers did not find. All the discovered ignored collisions have been confirmed by developers with one CVE ID assigned.

Graph neural networks (GNNs) have achieved remarkable success in various domains, yet they often struggle with domain adaptation due to significant structural distribution shifts and insufficient exploration of transferable patterns. One of the main reasons behind this is that traditional approaches do not treat global and local patterns discriminatingly so that some local details in the graph may be violated after multi-layer GNN. Our key insight is that domain shifts can be better understood through spectral analysis, where low-frequency components often encode domain-invariant global patterns, and high-frequency components capture domain-specific local details. As such, we propose FracNet (\underline{\textbf{Fr}}equency \underline{\textbf{A}}ware \underline{\textbf{C}}ontrastive Graph \underline{\textbf{Net}}work) with two synergic modules to decompose the original graph into high-frequency and low-frequency components and perform frequency-aware domain adaption. Moreover, the blurring boundary problem of domain adaptation is improved by integrating with a contrastive learning framework. Besides the practical implication, we also provide rigorous theoretical proof to demonstrate the superiority of FracNet. Extensive experiments further demonstrate significant improvements over state-of-the-art approaches.

Network-wide Traffic State Estimation (TSE), which aims to infer a complete image of network traffic states with sparsely deployed sensors, plays a vital role in intelligent transportation systems. With the development of data-driven methods, traffic dynamics modeling has advanced significantly. However, TSE poses fundamental challenges for data-driven approaches, since historical patterns cannot be learned locally at sensor-free segments. Although graph representation learning shows promise in estimating states at locations without sensors, existing methods typically handle unobserved locations by filling them with zeros, introducing bias to the sensitive graph message propagation. The recently proposed Dirichlet Energy-based Feature Propagation (DEFP) method achieves State-Of-The-Art (SOTA) performance in unobserved node classification by eliminating the need for zero-filling. However, applying it to TSE faces three key challenges: inability to handle directed traffic networks, strong assumptions in traffic spatial correlation modeling, and overlooking distinct propagation rules of different patterns (e.g., congestion and free flow). We propose DGAE, a novel inductive graph representation model that addresses these challenges through theoretically derived DEFP for Directed graph (DEFP4D), enhanced spatial representation learning via DEFP4D-guided latent space encoding, and physics-guided propagation mechanisms that separately handle congested and free-flow patterns. Experiments on three traffic datasets demonstrate that DGAE outperforms existing SOTA methods and exhibits strong cross-city transferability. Furthermore, DEFP4D can serve as a standalone lightweight solution, showing superior performance under extremely sparse sensor conditions. The code of this work is publicly available at: https://github.com/ZJU-TSELab/DGAE

In autonomous driving, an accurate understanding of the environment, e.g., the vehicle-to-vehicle and vehicle-to-lane interactions, plays a critical role in many driving tasks, such as trajectory prediction and motion planning. Environment information comes from high-definition maps and historical trajectories of vehicles. To interpret and utilize such information for the two aforementioned driving tasks, both learning-based models and mathematical methods have been proposed, while these existing approaches suffer from the following issues. Specifically, due to the heterogeneity of the map data and trajectory data, many learning-based models extract vehicle-to-vehicle and vehicle-to-lane interactions in a separate and sequential manner, which may capture biased interpretations of interactions, causing lower prediction and planning accuracy. As for the mathematical models, the environment information is mainly used to characterize the collision-free space, while the interactions are largely ignored. To address the above issues, we propose an environment representation, called Temporal Occupancy Flow Graph (TOFG). Specifically, TOFG unifies the map information and vehicle trajectories into a homogeneous data format and enables a consistent prediction. We incorporate TOFG with a graph attention (GAT) based neural network and propose TOFG-GAT to demonstrate the benefit of TOFG to learning-based trajectory prediction and motion planning. Moreover, we design and implement an interaction-aware sampling strategy based on TOFG to improve the mathematical sampling-based motion planning algorithms. Extensive experiment results show that our proposed TOFG can contribute to the trajectory prediction and motion planning tasks by improving the quality of the generated trajectory and computation efficiency for both the learning-based and mathematical models. Extensive experiment results show that our proposed TOFG can contribute to the trajectory prediction and motion planning tasks by improving the quality of the generated trajectory and computation efficiency for both the learning-based and mathematical models.