Browsing by Author "Xu, Hao"

Now showing 1 - 3 of 3
  • Thumbnail Image
    MEng Plan of Study Assistance System
    Malhotra, Shorya; Natnael, Shedon P.; Chang, Ian Y.; Xu, Hao (Virginia Tech, 2022-05-04)
    The MEng Plan of Study Assistance System is a tool that simplifies the research and planning required for a MEng student at Virginia Tech to plan and complete their plan of study. The web application aids students that are part of the Master of Engineering program in choosing courses that will fulfil the Master of Engineering requirements as part of their plan of study. Along with that, the user is able to get information and the syllabus of a course, to assist them in finding the right courses that align with their interests.
  • Thumbnail Image
    Safety of Self-driving Cars: A Case Study on Lane Keeping Systems
    Xu, Hao (Virginia Tech, 2020-07-07)
    Machine learning is a powerful method to handle the self-driving problem. Researchers use machine learning to construct a neural network and train it to drive the car. A self-driving car is a safety-critical system. However, the neural network is not necessarily reliable. The output of a neural network can be easily influenced by many factors, such as the quality of training data and the runtime environment. Also, it takes time for the neural network to generate the output. That is, the self-driving car may not respond in time. Such weaknesses will increase the risk of accidents. In this thesis, considering the safety of self-driving cars, we apply a delay-aware shielding mechanism to the neural network to protect the self-driving car. Our approach is an improvement based on previous research on runtime safety enforcement for general cyber-physical systems that did not consider the delay to generate the output. Our approach contains two steps. The first is to use formal language to specify the safety properties of the system. The second step is to synthesize the specifications into a delay-aware enforcer called the shield, which enforces the violated output to satisfy the specifications during the whole delay. We use a lane keeping system as a small but representative case study to evaluate our approach. We utilize an end-to-end neural network as a typical implementation of such a lane keeping system. Our shield supervises those outputs of the neural network and verifies the safety properties during the whole delay period with a prediction. The shield can correct it if a violation exists. We use a 1/16 scale truck and construct a curvy lane to test our approach. We conduct the experiments both on a simulator and a real road to evaluate the performance of our proposed safety mechanism. The result shows the effectiveness of our approach. We improve the safety of a self-driving car and we will consider more comprehensive driving scenarios and safety features in the future.
  • Thumbnail Image
    Terrestrial radio wave propagation at millimeter-wave frequencies
    Xu, Hao (Virginia Tech, 2000-04-26)
    This research focuses on radio wave propagation at millimeter-wave frequencies. A measurement based channel characterization approach is taken in the investigation. First, measurement techniques are analyzed. Three types of measurement systems are designed, and implemented in measurement campaigns: a narrowband measurement system, a wideband measurement system based on Vector Network Analyzer, and sliding correlator systems at 5.8+AH4AXA-mbox{GHz}, 38+AH4AXA-mbox{GHz} and 60+AH4AXA-mbox{GHz}. The performances of these measurement systems are carefully compared both analytically and experimentally. Next, radio wave propagation research is performed at 38+AH4AXA-mbox{GHz} for Local Multipoint Distribution Services (LMDS). Wideband measurements are taken on three cross-campus links at Virginia Tech. The goal is to determine weather effects on the wideband channel properties. The measurement results include multipath dispersion, short-term variation and signal attenuation under different weather conditions. A design technique is developed to estimate multipath characteristics based on antenna patterns and site-specific information. Finally, indoor propagation channels at 60+AH4AXA-mbox{GHz} are studied for Next Generation Internet (NGI) applications. The research mainly focuses on the characterization of space-time channel structure. Multipath components are resolved both in time of arrival (TOA) and angle of arrival (AOA). Results show an excellent correlation between the propagation environments and the channel multipath structure. The measurement results and models provide not only guidelines for wireless system design and installation, but also great insights in millimeter-wave propagation.