Papers
7
Total Citations
110
H-Index
5
About
Zhenyu Wu is a robotics and artificial intelligence researcher whose work spans autonomous navigation, embodied intelligence, and vision-language integration for robotic systems. With a career tracing from foundational path-planning algorithms to cutting-edge large language model applications, Wu has consistently pushed the boundaries of how robots perceive, reason about, and navigate complex environments. Wu's early contributions focused on robust path-planning strategies, including a hybrid static-dynamic obstacle prediction framework for mobile robots (2012, 30 citations) that addressed real-world environmental complexity. This work laid the groundwork for his later research on deep reinforcement learning-based indoor patrol navigation using PTZ camera systems (2022, 32 citations), which significantly improved exploration efficiency and convergence in autonomous patrol tasks. More recently, Wu has embraced the frontier of embodied AI, contributing influential work on task planning with large language models (2023, 18 citations) and transformer-based vision-language alignment for robot navigation and question answering (2024, 19 citations). His 2025 work on MoManipVLA advances generalizable mobile manipulation by transferring vision-language-action models across diverse environments. Collectively, Wu's research portfolio reflects a cohesive and forward-looking vision for intelligent, adaptable robotic systems capable of assisting humans in everyday life.
Research Focus
Key Achievements
Top Papers
- 1
- 2Obstacle Prediction-based Dynamic Path Planning for a Mobile Robot30 citations · 2012
- 3
- 4Embodied Task Planning with Large Language Models18 citations · 2023
- 5
- 6E^2TAD: An Energy-Efficient Tracking-based Action Detector3 citations · 2022
- 7