Papers
9
Total Citations
66
H-Index
4
About
Xingdong Li is a robotics researcher whose work centers on autonomous navigation, legged locomotion, and multi-sensor perception for mobile robots operating in complex, unstructured environments. Li’s most impactful contribution is a hierarchical control framework for path planning that integrates global guidance with reinforcement learning, enabling mobile robots to navigate dynamic environments efficiently and safely (29 citations, 2024). In quadruped robotics, Li has pioneered hierarchical gait planning for rough terrain, using cost map searches and foothold selection algorithms to generate stable static gaits (14 citations, 2019), and has further refined foothold selection through learned cost functions (5 citations, 2019). Li has also advanced multi-modal perception by developing fire detection frameworks that fuse feature enhancement with multimodal data (5 citations, 2025), and by creating methods to generate colored 3D point clouds through calibration of Time-of-Flight and RGB cameras (4 citations, 2013). More recently, Li has introduced novel nature-inspired optimization algorithms—the MYIGWO grey wolf optimizer and the Gekko Japonicus Algorithm—for engineering problems and path planning (2025). With a total of over 60 citations across these works, Li’s research provides foundational tools for autonomous systems in challenging real-world settings.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4Learning the Cost Function for Foothold Selection in a Quadruped Robot5 citations · 2019
- 5
- 6
- 7
- 8Combining two point clouds generated from depth camera2 citations · 2013
- 9Design of Control System for Educational Robot with Six-Degree Freedom2 citations · 2018