Liang Sun, Ph.D.
AVIA Lab Director | Associate Professor Baylor University
- Waco TX
Research focuses on autonomous systems, multi-agent robotics, advanced air mobility, and energy-aware operations.
Media
Biography
Dr. Sun is the Director of the Advanced Vehicle Intelligence and Autonomy (AVIA) Laboratory, located in the Baylor Research and Innovation Collaborative (BRIC). He has also served as Site Director of the Center for Aviation and Space Data Analytics (NSF IUCRC Planning Grant). Dr. Sun is an Associate Fellow of the American Institute of Aeronautics and Astronautics (AIAA) and a Senior Member of the Institute of Electrical and Electronics Engineers (IEEE). Since 2015, he has served as an Associate Editor of the International Journal of Advanced Robotic Systems.
Dr. Sun’s research focuses on autonomous systems, multi-agent robotics, advanced air mobility, and energy-aware operations. His work has been supported by the National Science Foundation, NASA, the Department of Energy, Toyota Research Institute of North America, Sandia National Laboratories, and the New Mexico Space Grant Consortium. He is the Principal Investigator of a $6 million NASA University Leadership Initiative (ULI) project that addresses technical challenges in infrastructure planning for Advanced Air Mobility, bringing together multi-institutional, national laboratory, and industry partners.
Areas of Expertise
Accomplishments
Associate Fellow
2026
American Institute of Aeronautics and Astronautics (AIAA)
Education
Beihang University
B.S.
Automation Control and Electrical Engineering
2004
Beihang University
M.S.
Automation Control and Electrical Engineering
2007
Brigham Young University
Ph.D.
Electrical and Computer Engineering
2012
Articles
Multi-sound-source localization using machine learning for small autonomous unmanned vehicles with a self-rotating bi-microphone array
Journal of Intelligent & Robotic Systems2021
While vision-based localization techniques have been widely studied for small autonomous unmanned vehicles (SAUVs), sound-source localization capabilities have not been fully enabled for SAUVs. This paper presents two novel approaches for SAUVs to perform three-dimensional (3D) multi-sound-sources localization (MSSL) using only the inter-channel time difference (ICTD) signal generated by a self-rotating bi-microphone array. The proposed two approaches are based on two machine learning techniques viz., Density-Based Spatial Clustering of Applications with Noise (DBSCAN) and Random Sample Consensus (RANSAC) algorithms, respectively, whose performances were tested and compared in both simulations and experiments.
Self-localization of tethered drones without a cable force sensor in GPS-denied environments
Drones2021
This paper considers the self-localization of a tethered drone without using a cable-tension force sensor in GPS-denied environments. The original problem is converted to a state-estimation problem, where the cable-tension force and the three-dimensional position of the drone with respect to a ground platform are estimated using an extended Kalman filter (EKF). The proposed approach uses the data reported by the onboard electric motors (i.e., the pulse width modulation (PWM) signals), accelerometers, gyroscopes, and altimeter, embedded in the commercial-of-the-shelf (COTS) inertial measurement units (IMU). A system-identification experiment was conducted to determine the model that computes the drone thrust force using the PWM signals. The proposed approach was compared with an existing work that assumes known cable-tension force.
A spatial localization and attitude estimation system for unmanned aerial vehicles using a single dynamic vision sensor
IEEE Sensors Journal2022
This paper presents a three-dimensional (3D) localization and attitude estimation system to track a Unmanned Aerial Vehicle (UAV) using a single camera without prior knowledge of the environment. The hardware system consists of a Dynamic Vision Sensing (DVS) camera, a circle-shaped blinking marker made by Light-Emitting Diodes (LEDs), and a base station computer. The algorithm for spatial localization and attitude estimation includes a temporal video filter, triangulation-based location and attitude estimation, and 3D real-time plotting with a graphical user interface (GUI). The temporal video filter processes the image stream from the DVS camera to identify the frequency of the marker and removes the background image.
Allocating Limited Resources and Learning Flight Energy Consumption for Advanced Air Mobility
AIAA Journal2025
This paper addresses the problem of efficiently managing clean-energy aerial vehicles for advanced air mobility (AAM) in a distributed manner. A concept of operation for AAM vehicles is considered to deliver packages for a number of customers at different locations. The objective of the problem is to minimize the overall energy consumption of all AAM vehicles. A feed-forward neural network (FFNN) is proposed to predict the fight energy consumption of a delivery drone, whose flight data were used to train the neural network. To optimize the allocation of AAM vehicles to service stations (e.g., for charging and maintenance) with limited service bays, a distributed limited resource allocation algorithm (DLRAA) is proposed based on the Hungarian method.
Distributed Model Predictive Control-Based Power Management Scheme for Grid-Integrated Microgrids
Energies2026
MDPI
Description
Transitioning from traditional electrical grids to smart grids is currently an ongoing process that many nations are striving for due to their access to renewable resources. Energy management is one of the key parameters that decides the performance of such complex systems. Distributed Model Predictive Control (DMPC) is a promising technique that can be used to improve the energy management of grid-connected systems. This paper analyzes a grid-connected inverter system with DMPC that exchanges key operating parameters with the grid to optimize coordinated power sharing between its respective loads. The state-space model for the inverter is derived and verified to ensure controllability and observability. A state observer for an inverter system is then developed to estimate the nominal states in the derived state-space model.
