Yuezhan Tao
Papers
10
Total Citations
208
H-Index
7
About
Yuezhan Tao is pioneering autonomous flight for micro aerial vehicles (MAVs) in GPS-denied, unstructured environments—from dense forests to multi-floor indoor buildings. Their core research integrates real-time semantic SLAM, learning-driven exploration, and adaptive planning to enable size, weight, and power (SWaP)-constrained robots to navigate and map complex spaces without human intervention. Tao’s landmark 2022 paper on large-scale autonomous flight with real-time semantic SLAM under forest canopy (97 citations) demonstrated how semantically meaningful object-based maps can replace traditional geometric representations, enabling efficient, long-duration missions in highly cluttered settings. Their 2023 work on SEER (41 citations) introduced learning to predict information gain, dramatically improving exploration efficiency for indoor MAVs. More recently, Tao has advanced multi-robot collaboration with decentralized metric-semantic SLAM (SlideSLAM) and real-time Gaussian splatting for dense mapping (RT-GuIDE), pushing the frontier of active perception. With over 200 total citations and a string of first-author publications in top robotics venues, Tao is defining how agile, intelligent aerial robots can autonomously explore and understand the world around them.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 33D Active Metric-Semantic SLAM21 citations · 2024
- 4
- 5Experiments in Adaptive Replanning for Fast Autonomous Flight in Forests12 citations · 2022
- 6
- 7Swarm of Inexpensive Heterogeneous Micro Aerial Vehicles7 citations · 2021
- 8
- 9
- 10