Prof. TAO Yifu, Ethan 陶奕甫

Assistant Professor

Area of Specialization: Robotic Perception; Simultaneous Localization and Mapping (SLAM); Sensor Fusion; Uncertainty Estimation; Field Robotics, Robot Navigation and Manipulation; Deep Learning for Robotics; 3D Computer Vision; Simulation for Robotics

PolyU Scholars Hub

ORCID ID

Google Scholar

Biography

BA & MEng (Oxford), DPhil (Oxford)

Short Description

Prof. Yifu Tao completed his undergraduate studies and DPhil at the University of Oxford in 2020 and 2025, respectively. He subsequently worked as a postdoctoral researcher at Oxford until 2026 and was a visiting researcher at ETH Zürich in 2025.

His research focuses on mobile robotic perception, including spatial AI (SLAM and 3D reconstruction), temporal modelling (dynamics and environmental changes), semantic understanding and physical perception. One of his focuses is on large-scale outdoor scene reconstruction, combining different sensors, including vision and LiDAR. He is also interested in building simulations from robot perception systems to enable robot learning algorithms. He has published as first author in leading robotics journals, including T-RO and IJRR, and is serving as Associate Editor for IROS 2026. Dr. Tao has contributed to the Horizon Europe project DigiForest on forest mapping, and is an organiser of the Hilti-SLAM Challenge 2026 on Visual SLAM in construction environments. He has also appeared on the BBC to present robotics research for forestry.

Selected Publications

Tao, Y. and Fallon, M., 2025. SiLVR: Scalable Lidar-Visual Radiance Field Reconstruction with Uncertainty Quantification, IEEE Transactions on Robotics, 42, pp.98-114.
Tao, Y., Muñoz-Bañón, M.Á., Zhang, L., Wang, J., Fu, L.F.T. and Fallon, M., 2026. The Oxford Spires Dataset: Benchmarking Large-Scale LiDAR-Visual Localisation, Reconstruction and Radiance Field Methods. The International Journal of Robotics Research, 45(6), pp.839-857.
Tao, Y., Bhalgat, Y., Fu, L.F.T., Mattamala, M., Chebrolu, N. and Fallon, M., 2024, May. SiLVR: Scalable Lidar-Visual Reconstruction with Neural Radiance Fields for Robotic Inspection . In 2024 IEEE International Conference on Robotics and Automation (ICRA) (pp. 17983-17989). IEEE.
Tao, Y., Popović, M., Wang, Y., Digumarti, S.T., Chebrolu, N. and Fallon, M., 2022, October. 3D Lidar Reconstruction with Probabilistic Depth Completion for Robotic Navigation. In 2022 IEEE/RSJ international conference on intelligent robots and systems (IROS) (pp. 5339-5346). IEEE.
Zhang, L., Tao, Y., Lin, J., Zhang, F. and Fallon, M., 2026. Visual Localization in 3D Maps: Comparing Point cloud, Mesh, and Nerf Representations. Autonomous Robots, 50(1), p.14.
Lee, D., Yang, W., Tao, Y., Fallon, M. and Kim, A., 2026. LAPS: Improving Incremental LiDAR Mapping using Active Pooling and Sampling for Neural Distance Fields. IEEE Robotics and Automation Letters.
Wang, J., Chebrolu, N., Tao, Y., Zhang, L., Kim, A. and Fallon, M., 2025, October. PlanarMesh: Building Compact 3D Meshes from LiDAR using Incremental Adaptive Resolution Reconstruction. In 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (pp. 15726-15733). IEEE.
Wang, Z., Bian, W., Li, X., Tao, Y., Wang, J., Fallon, M. and Prisacariu, V., 2026. Seeing in the dark: Benchmarking Egocentric 3D Vision with the Oxford Day-and-Night Dataset. Advances in Neural Information Processing Systems, 38.
Border, R., Chebrolu, N., Tao, Y., Gammell, J.D. and Fallon, M., 2024. Osprey: Multisession Autonomous Aerial Mapping with LiDAR-based SLAM and Next Best View Planning. IEEE Transactions on Field Robotics, 1, pp.113-130.