PhD candidate at Southeast University, China
Fengyu Liu is a dedicated researcher specializing in deep learning, integrated navigation, intelligent unmanned systems, multi-sensor fusion, and SLAM (Simultaneous Localization and Mapping). He has authored 10 academic papers, including 5 SCI-indexed Q1 journal articles, and has contributed significantly to the fields of robotics and sensor technology. With 5 domestic invention patents and 1 PCT patent, his work demonstrates a strong focus on innovation. He has received numerous awards, including the National Scholarship and the Southeast University ‘Zhishan’ Scholarship, and has won four national and provincial-level first prizes in student competitions. He actively participates in academic conferences and serves as a reviewer for IEEE TIM, IEEE Sensor Journal, and MST journals. His research contributions and leadership in the academic community make him a promising figure in the field of intelligent navigation and robotics.
Professional Profile
Education
Fengyu Liu earned his B.S. degree in Electronic Science and Technology from the School of Instrument and Electronics, North University of China, in 2020. Currently, he is pursuing a Ph.D. in Instrument Science and Technology at the School of Instrument Science and Engineering, Southeast University, Nanjing, China. His doctoral research focuses on deep learning-driven navigation, SLAM, and multi-sensor fusion for intelligent unmanned systems. Throughout his academic journey, he has been recognized for his outstanding performance, receiving prestigious scholarships and awards for academic excellence and research contributions.
Professional Experience
During his undergraduate studies, Fengyu Liu served as the Chair of the Embedded Laboratory at the Innovation Elite Research Institute, where he led multiple student research projects. He has been actively involved in presenting at international conferences, including the 2023 International Conference on Robotics, Control, and Vision Engineering (Tokyo) and the China-Russia “Navigation and Motion Control” Youth Forum (2024, Nanjing). His research findings have been published in top-tier journals, and he has contributed as a reviewer for leading IEEE journals. His expertise in SLAM, sensor fusion, and AI-driven navigation technologies has led to patents and real-world applications, making him a key contributor to the advancement of autonomous systems and intelligent robotics.
Research Interests
Fengyu Liu’s research focuses on deep learning, integrated navigation, intelligent unmanned systems, multi-sensor fusion, and simultaneous localization and mapping (SLAM). His work explores advanced sensor fusion techniques, including the integration of LiDAR, cameras, inertial measurement units (IMUs), and deep learning models to enhance navigation accuracy and autonomy in complex environments. He is particularly interested in developing robust localization algorithms for dynamic and unstructured environments, with applications in robotics, autonomous vehicles, and aerospace navigation. His contributions to AI-driven SLAM and vision-based perception systems aim to improve real-time mapping, object recognition, and motion estimation for next-generation autonomous systems.
Awards and Honors
Fengyu Liu has received multiple prestigious awards, including the National Scholarship and the Southeast University ‘Zhishan’ Scholarship, recognizing his academic excellence. He has won four first prizes at national and provincial-level university student competitions, demonstrating his problem-solving skills and technical expertise. His research has also been recognized at academic conferences, earning him the Outstanding Paper Award at the 2022 Science and Technology Workers Seminar of the Chinese Society of Inertial Technology. His participation in international research forums, such as the China-Russia “Navigation and Motion Control” Youth Forum (2024, Nanjing), further highlights his growing impact in the field.
Research Skills
Fengyu Liu possesses a diverse skill set in deep learning, computer vision, and multi-sensor data fusion, particularly for robotics and autonomous navigation. He is proficient in developing AI-based SLAM algorithms, sensor calibration techniques, and real-time embedded system implementations. His expertise extends to software tools and programming languages, including Python, MATLAB, C++, TensorFlow, and PyTorch, which he utilizes for machine learning and signal processing applications. He has hands-on experience with robotic perception systems, LiDAR-based mapping, and inertial navigation technologies, contributing to multiple high-impact research projects. Additionally, his role as a peer reviewer for IEEE TIM, IEEE Sensor Journal, and MST journals reflects his strong analytical and critical evaluation skills in cutting-edge research.
Conclusion
Fengyu Liu is a highly promising young researcher with strong academic contributions, patents, and international recognition. His research in SLAM, deep learning, and multi-sensor fusion aligns with cutting-edge advancements in robotics and AI. His leadership roles, awards, and editorial responsibilities further strengthen his profile.
For the Best Researcher Award, he is a strong candidate, but additional international collaborations, funded research projects, and industry partnerships could further enhance his competitiveness for top-tier global research awards.
Publications Top Noted
-
Confidence Factor Based Robust Localization Algorithm with Visual-Inertial-LiDAR Fusion in Underground Space
-
LiDAR-Aided Visual-Inertial Odometry Using Line and Plane Features for Ground Vehicles
-
Spatial Feature Recognition and Layout Method Based on Improved CenterNet and LSTM Frameworks
-
Transformer-Based Local-to-Global LiDAR-Camera Targetless Calibration With Multiple Constraints
-
Spacecraft-DS: A Spacecraft Dataset for Key Components Detection and Segmentation via Hardware-in-the-Loop Capture
-
A Visual SLAM Method Assisted by IMU and Deep Learning in Indoor Dynamic Blurred Scenes
-
A Spatial Layout Method Based on Feature Encoding and GA-BiLSTM
-
Combination of Iterated Cubature Kalman Filter and Neural Networks for GPS/INS During GPS Outages
- Authors: Fengyu Liu, Xiaohong Sun, Yufeng Xiong, Huang Haoqian, Xiao-ting Guo, Yu Zhang, Chong Shen
- Year: 2019
- DOI: 10.1063/1.5094559
