Shih-Hsi Hsu
Papers
2
Total Citations
29
H-Index
2
About
Shih-Hsi Hsu is a robotics researcher specializing in autonomous navigation and visual servoing for mobile manipulators. His work bridges deep reinforcement learning and computer vision to enable intelligent robot behavior in complex environments. Hsu’s most influential contribution, “Distributed Deep Reinforcement Learning based Indoor Visual Navigation” (2018, 27 citations), proposes a novel architecture that allows robots to directly convert environmental scenes into motor commands, effectively tackling indoor navigation tasks. This approach leverages distributed learning to improve efficiency and robustness, marking a significant step toward practical, learning-based robot autonomy. In related work, Hsu addresses critical real-world challenges in visual servoing, such as time-delay compensation for humanoid mobile manipulators (2017), where he mitigates delays caused by image processing and data transmission in commercial robotic systems. His research is notable for its focus on overcoming hardware limitations while advancing end-to-end learning paradigms. With growing citation impact, Hsu’s work is shaping how robots perceive and act in dynamic spaces, offering valuable insights for students and researchers in robotics, reinforcement learning, and autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1Distributed Deep Reinforcement Learning based Indoor Visual Navigation27 citations · 2018
- 2