SWShao-Hua Wang

Shao-Hua Wang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Shao-Hua Wang has a total of 19 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Alleviating Congestion Attacks on Traffic Signal Systems

    by Tsung-Lin Tsai, Shao-Hua Wang, Chun-Ting Wu, Ting-Yu Lin, Chia-Heng Tu, Meng-Hsun Tsai, Wei-Hsun Lee, Da-Wei Chang

    This work addresses congestion attacks on prioritization and preemption signal applications (PPSA), an important variant of cooperative intelligent transport systems (C-ITS). In PPSA, priority vehicles, such as buses and ambulances, can request traffic signal adjustments in their favor to reduce travel time. These systems rely on vehicle-to-everything (V2X) communications, which makes them vulnerable to congestion attacks. When under attack, these systems experience disruptions in information exchange between vehicles and infrastructure, leading to traffic congestion and safety hazards. Nevertheless, existing solutions do not address the attacks at a system level and within the PPSA context. Our proposal presents a software framework designed to enhance both sustainability and safety during congestion attacks. Specifically, it introduces a whitelist-based traffic-filtering mechanism that preserves system sustainability by ensuring only legitimate priority requests are processed. Additionally, a monitoring mechanism evaluates the PPSA service rate at runtime to identify and address potential safety risks arising from insufficient service rates. Moreover, we analyze the limitations of a machine learning-based defense method and highlight risks of potential service unavailability due to false positives. We believe that this research contributes to the development of a secure and safe traffic management system for smart cities.

  • Open Access

    A Multi-Agent LLM Framework for Design Space Exploration in Autonomous Driving Systems

    by Po-An Shih, Shao-Hua Wang, Yung-Che Li, Chia-Heng Tu, Chih-Han Chang

    Designing autonomous driving systems requires efficient exploration of large hardware/software configuration spaces under diverse environmental conditions, e.g., with varying traffic, weather, and road layouts. Traditional design space exploration (DSE) approaches struggle with multi-modal execution outputs and complex performance trade-offs, and often require human involvement to assess correctness based on execution outputs. This paper presents a multi-agent, large language model (LLM)-based DSE framework, which integrates multi-modal reasoning with 3D simulation and profiling tools to automate the interpretation of execution outputs and guide the exploration of system designs. Specialized LLM agents are leveraged to handle user input interpretation, design point generation, execution orchestration, and analysis of both visual and textual execution outputs, which enables identification of potential bottlenecks without human intervention. A prototype implementation is developed and evaluated on a robotaxi case study (an SAE Level 4 autonomous driving application). Compared with a genetic algorithm baseline, the proposed framework identifies more Pareto-optimal, cost-efficient solutions with reduced navigation time under the same exploration budget. Experimental results also demonstrate the efficiency of the adoption of the LLM-based approach for DSE. We believe that this framework paves the way to the design automation of autonomous driving systems.

  • Open Access

    PARD: A Dataflow Aware Profiler for ROS-Based Autonomous Driving Software

    by Shao-Hua Wang, Chen-Xuan Lin, Yu-Tsung Wu, Chia-Heng Tu

    Robot Operating System (ROS) is an open source software platform that is well-suited for building complex robotic systems. Autonomous driving systems are one of the emerging robotic systems that are built on top of ROS. However, complicated communications among ROS processes pose a great challenge for system designers to design efficient computing hardware in autonomous vehicles. This complexity stems from the implicit data dependencies among these processes. When a process is bound by computation or communication, it can lead to increased data generation time for subsequent processes in the dependency chain. Unfortunately, existing tools for ROS are either built for tracking the communication latencies or revealing the communication performance with abstracted performance graphs. For analyzing computational resource utilization, general-purpose profiling tools like perf should be further adopted. Substantial human effort is required to consolidate and analyze all the performance data generated by the above tools so as to pinpoint potential performance issues. To address this challenge, a ROS-based dataflow aware profiler PARD is proposed. PARD employs dataflow aware analysis methods to automatically analyze collected ROS performance data, and highlights potential computation and communication performance issues on our profile graph, helping users promptly identify system bottlenecks. Thanks to the proposed data analysis methods, the system designers are able to identify and solve the performance issues rapidly through the graphical data representation that accentuates the potential performance issues. The experimental results on the commercial-grade ROS-based autonomous driving software Autoware demonstrate PARD is useful for quickly identifying the potential performance issues for autonomous valet parking. Moreover, its overall impact on the system is around 2%, indicating that PARD is indeed useful for accelerating hardware design exploration in autonomous driving vehicles.


  • Open Access

    A Simulation Framework for Prototyping Intelligent Vehicle-to-Infrastructure Applications: A Case Study on RSU-Based Intersection Movement Assist for Connected Autonomous Vehicles

    by Chun-Ting Wu, Shao-Hua Wang, Chia-Heng Tu

    A cooperative intelligent transport system (C-ITS) enables information sharing among ITS subsystems, such as vehicle and roadside infrastructure, with vehicle-to-everything (V2X) communications. Novel C-ITS applications aim to reduce traffic congestion and improve road safety. For example, a roadside unit (RSU) can sense the traffic status of an intersection and share the information to nearby vehicles to prevent potential collision, i.e., the intersection movement assist (IMA) scenario. Typically, C-ITS applications are developed in a simulated world to mitigate the high costs and safety hazards associated with the real-world counterpart. Unfortunately, existing simulation tools focus primarily on modeling vehicle-to-vehicle (V2V) communications, rather than the vehicle-to-infrastructure (V2I) communications involved in the above example. This poses a great challenge for developing V2I-based applications, especially for the application-level performance assessment on such systems. This work proposes a software framework that enables the simulation of full software stacks for the ITS subsystems, i.e., vehicle and RSU. This full-stack simulation capability enables hardware-in-the-loop simulations, evaluating the application-level performance and relative cost in the early stage of system development. This can shorten the time to market for C-ITS applications. We believe that this framework paves the way toward the development of novel V2I applications.


  • Open Access

    Traffic Signal Preemption and Prioritization for High-Density Road Networks

    by Chun Ting Wu, Yung-Jen Hsu, Chia-Heng Tu, Shaohua Wang

    Traffic signal priority and preemption modify the traffic signals, offering priority to specific vehicle types, such as buses, streetcars, or emergency vehicles. Specialized hardware and software systems are developed to facilitate the preemption and prioritization signal application (PPSA). Nevertheless, the international standards and the existing research works focus on providing a solid foundation for the application, rather than deploying them in high-density road networks, where the distances between two consecutive intersections are shorter than typical roads and are commonly seen in Southeast Asia cities. The shorter distances between intersections result in less time for the vehicle drivers to react when the PPSA does not grant their request, raising safety concerns. This work proposes a software framework for the PPSA, including a detailed analysis of the international standards related to PPSA, a timely response mechanism (to provide a longer reaction time after thoroughly analyzing the standards for exchanging messages), and a time estimation model (to evaluate if the system configurations have safety concerns). Experiments are conducted on our prototype system with actual hardware platforms. The experimental results show the proposed framework works well for high-density road networks. The time estimation model can be used to assess the traffic safety of PPSA systems under different system configurations. The proposed framework, standard protocol analysis, and time estimation model can be used by system designers to improve the safety and efficiency of PPSA systems, especially in areas with small street blocks.


  • Multi-mode signal fusion and improved residual dense network fault diagnosis of nuclear power plant

    by Jianhong Zhang, Jie Ma, Jinxiao Yuan, Shaohua Wang

    The primary cooling system is one of the important components of a nuclear power plant, and once the main cooling system fails that, it can lead to serious consequences. In this paper, a method of multimodal signal fusion and improved residual dense network for nuclear power plant fault diagnosis is proposed. In order to obtain the multifaceted information of the fault, firstly, the original signal is changed in the frequency domain, the time-frequency domain is changed, and then the fused information is fed into the residual dense network improved by convolutional attention for learning. The convolutional attention mechanism can improve the convergence speed and accuracy of the network. Finally, the simulation experiment is verified by the simulation data center of Hualong-1 nuclear power plant. The experimental results as well as comparative analysis show that the algorithm has a better recognition effect than the traditional algorithm on the faults of the main cooling system.

  • Open Access

    CAT: Context Aware Tracing for Rust Asynchronous Programs

    by Tsung-Yen Wang, Shao-Hua Wang, Chia-Heng Tu, Wen-Yew Liang

    Modern programming languages, such as Rust, have adopted the coroutine concept to better utilize computation resources and to improve program execution efficiency by allowing the overlap of the execution for asynchronous tasks. These programming languages often use the concept of userland thread library to dispatch the asynchronous tasks defined by the programmers. Nevertheless, it is often the case that the task scheduling on a user-space library is non-preemptive and would lead to unbounded execution time of a task. In this work, we aim to develop a tracing methodology to capture unbounded execution time of asynchronous tasks in Rust programs. Based on the analyses of the Rust standard library, we identify several execution contexts of asynchronous computation in Rust, and develop a portable context aware tracing methodology that is able to trace the execution time of nested asynchronous computation work across different Rust runtimes. We develop a framework, called CAT, to collect and visualize the asynchronous runtime activities. The results show that CAT can help pinpoint the asynchronous computation exhibiting prolonged execution time. We believe that CAT is a complement of existing tools to improve the execution efficiency of asynchronous operations in Rust.

  • Open Access

    Automatic traffic modelling for creating digital twins to facilitate autonomous vehicle development

    by Shao-Hua Wang, Chia-Heng Tu, Jyh-Ching Juang

    A digital twin is often adopted in computer simulations to expedite autonomous vehicle developments by using the simulated 3D environment that reflects a physical environment. In particular, traffic simulations are a crucial part of training the driving logic before the field test of an autonomous vehicle is performed on specific regions to adapt to the region-specific, dynamic traffic conditions. Currently, the traffic conditions are either synthesised by tools (e.g. using mathematical models) or created manually (using domain knowledge), which cannot reflect the realistic, region-specific conditions or will require extensive labour works. In this article, we propose an automatic methodology to model the real-world traffic conditions captured by the sensor data and to reproduce the modeled traffic in the digital twin. We have built the tools based on the methodology and use the KITTI dataset to validate the effectiveness of the tools. To recreate the region-specific traffic, we present the results of capturing, modelling, and recreating the two-wheeler traffic condition on the Southeast Asia road. Our experimental results show that the proposed method facilitates the simulation of real-world, Southeast Asia-specific traffic conditions by removing the needs of the synthesised traffic and the labour hours.