A5002773357- GNSS positioning and interference
- Target Tracking and Data Fusion in Sensor Networks
- Traffic control and management
- Autonomous Vehicle Technology and Safety
- Traffic Prediction and Management Techniques
- Robotic Path Planning Algorithms
- Robotics and Sensor-Based Localization
- Fault Detection and Control Systems
- Transportation Planning and Optimization
- Time Series Analysis and Forecasting
- Indoor and Outdoor Localization Technologies
- Statistical Methods and Inference
- Remote Sensing and LiDAR Applications
- Advanced Optical Sensing Technologies
- Vehicle Dynamics and Control Systems
- Probabilistic and Robust Engineering Design
- Urban Green Space and Health
- Astronomical Observations and Instrumentation
- Inertial Sensor and Navigation
- Precipitation Measurement and Analysis
- Seismology and Earthquake Studies
- Control Systems and Identification
- Soil Geostatistics and Mapping
- Robot Manipulation and Learning
- Control and Dynamics of Mobile Robots
Hong Kong Polytechnic University
2023-2024
Wuhan University
2020-2021
Traffic flow forecasting has been a long-standing topic in intelligent transportation systems, and renewed interest seen recent years due to the development of artificial intelligence techniques. New deep neural networks have developed model traffic flow, but it is very challenging predict citywide at road level fine temporal scale owing influence spatiotemporal dependencies spatial sparsity. In this study, based on an in-depth analysis patterns, we propose learning network for each segment...
Accurate and reliable localization is of great importance for autonomous vehicles (AV). Mainstream approaches in (AV) are limited by the reliability onboard sensors, which could be vulnerable to sensor failure, such as signal outages camera spoofing global navigation satellite systems (GNSS). Different from these active or passive vehicle dynamic model (VDM), application physical laws a motion, environmentally independent capable providing motion estimation continuously. However, performance...
Fault detection for localization systems with non-Gaussian measurement noises is a challenging task. This paper investigates the impacts of noise modeling on fault performance in inertial units (IMU) and light ranging (LiDAR) integrated system based extended Kalman filter (EKF). Specifically, we model distribution LiDAR range measurements as Gaussian mixture (GMM) establish clear relationship between residual EKF through error propagation. After proving that also GMM distributed, test...
vehicle dynamic models are the basis of various navigation algorithms in autonomous mobile robots (AMRs), describing motion purely by physical law. However, its simplifications on system complexity and assumptions environments prevent it from providing accurate positioning results. Instead introducing sensors to correct pose estimation error, this study aims utilize endogenous information AMRs improve performance. A identification process is conducted identify dynamics plants AMRs, where...
In integrity monitoring applications, a sharp yet conservative overbound for heavy-tailed error distribution is essential to meet the strict availability and continuity requirements. This paper proposes Principal Gaussian distributions by leveraging membership weights analysis of Mixture model. We prove that overbounding property preserved through convolution, enabling derivation pseudorange-level requirements from position domain On both worldwide simulated dataset real-world urban dataset,...
Fault detection is crucial to ensure the reliability of navigation systems. However, mainstream fault methods are developed based on Gaussian noise assumptions, while other targeting non-Gaussian noises lack rigorous statistical properties. The performance and these challenged in real-world applications. This paper proposes a method for linearized pseudorange-based positioning systems under noises. Specifically, this test statistic jackknife technique, which proved be linear combination...
Localization plays a vital role in various autonomous systems, providing essential information for perception and planning tasks. However, mainstream localization methods are based on the sensors approach, which is vulnerable some extreme conditions where probably fail short period, such as camera-based visual positioning. This study proposes sensor-free method by integrating vehicle dynamic models an online system identification module. First, process conducted to identify dynamics of...
In <xref ref-type="bibr" rid="ref1">[1]</xref>, the first page footnote needs to indicate that authors Tao Jia and Penggao Yan contributed equally this work. It should read as: