Chiang-Heng Chien
Papers
4
Total Citations
28
H-Index
4
About
Chiang-Heng Chien’s research focuses on advancing autonomous mobile robotics, particularly in the areas of Monte Carlo localization (MCL) and simultaneous localization and mapping (SLAM). His major contributions address the critical challenge of premature convergence in MCL—a problem where robots incorrectly settle on a wrong pose in symmetrical environments. To solve this, Chien pioneered a multi-objective evolutionary approach that integrates particle swarm optimization with MCL, preventing premature convergence and significantly improving global localization accuracy. His work also tackles computational bottlenecks in vision-based SLAM, proposing a more efficient FastSLAM algorithm that reduces landmark comparison overhead, enabling real-time performance in landmark-rich environments. With his most-cited papers accumulating over 28 citations, Chien’s research has directly influenced the reliability and efficiency of localization systems used in field robotics. Notably, his 2016 paper on enhanced Monte Carlo localization introduced a novel mechanism to both prevent premature convergence and reduce pose estimation errors, marking a key advancement in robust robot navigation. Chien’s work is essential reading for researchers developing resilient, real-time localization solutions for mobile robots operating in complex, real-world settings.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4