Jinghang Mao
Papers
3
Total Citations
19
H-Index
2
About
Jinghang Mao is a leading researcher in the field of autonomous underwater robotics, with a primary focus on localization, navigation, and control for deep-sea mining vehicles. His work addresses the critical challenges of operating robots in complex, unstructured underwater environments. Mao’s major contributions include the development of an error-state Kalman filter-based localization algorithm that integrates velocity estimation, achieving 16 citations and providing a robust solution for deep-sea mining vehicle positioning. He has also pioneered an optimized deep reinforcement learning framework for dual-task control—simultaneously enabling path following and obstacle avoidance—a breakthrough for autonomous operations in hazardous seafloor terrains. Additionally, Mao introduced a direct forward-looking sonar odometry method, a two-stage approach that enhances localization accuracy for underwater robots during near-bottom operations. His research, though early in its citation impact, demonstrates significant potential for advancing autonomous underwater vehicle capabilities. Mao’s work is notable for its practical application to deep-sea mining, a field with growing industrial importance, and his innovative integration of sensor fusion and machine learning techniques positions him as a rising expert in underwater robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3