Rate My Professor Hao Cheng

Cheng's research centers on accessible and responsible GeoAI, deep learning applications for perception, reconstruction, and motion modeling in geo-sciences, intelligent transport systems, and autonomous driving, with emphasis on safety analysis between vehicles and vulnerable road users, ethical AI, computer vision, and human-AI interaction. His contributions align with UN Sustainable Development Goals 9 (Industry, Innovation, and Infrastructure) and 11 (Sustainable Cities and Communities). Notable publications include "Gaussian on-the-fly splatting: A progressive framework for robust near real-time 3DGS optimization" (IEEE Robotics and Automation Letters, 2026), "Explainable few-shot learning workflow for detecting invasive and exotic tree species" (Scientific Reports, 2025), "LDPoly: Latent diffusion for polygonal road outline extraction in large-scale topographic mapping" (ISPRS Journal of Photogrammetry and Remote Sensing, 2025), "RoIPoly: Vectorized building outline extraction using vertex and logit embeddings" (ISPRS Journal of Photogrammetry and Remote Sensing, 2025), "Gatraj: A graph-and attention-based multi-agent trajectory prediction model" (ISPRS Journal of Photogrammetry and Remote Sensing, 2023), and "AMENet: Attentive maps encoder network for trajectory prediction" (ISPRS Journal of Photogrammetry and Remote Sensing, 2021). Awards include the MSCA European Postdoctoral Fellowship, top reviewer recognitions for the ISPRS Journal of Photogrammetry and Remote Sensing in 2024 and 2025, and a best paper award in 2023. He teaches courses such as AI for Autonomous Robots, GenAI Models and Robotic Applications, and Space for Ethics.