Kai Sun

Kai Sun

Auto-generated profile, based on publicly available information

Kai Sun

School of Surveying and Mapping, Information Engineering University, Zhengzhou, China

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 May 2025 in IEEE Access
Verified
Journal Article
Open access
RZRuixin Zhang
Ruixin Zhang
QXQing Xu
Qing Xu
KSKai Sun
Kai Sun
YLYi Liu
Yi Liu
XZXimming Zhu
Ximming Zhu
XCXiang Cheng
Xiang Cheng
Autonomous vehicles require highly reliable collision-free capabilities, necessitating extensive research in path planning. Path planning determines an optimal path, crucial for safe and efficient driving. The Rapidly-exploring Random Tree (RRT) algorithm, while widely used, suffers from slow search speeds, numerous inflection points, and redundant operations. To address these issues, We propose a global path planning algorithm: Quick Dynamic Directional Guidance-RRT (QDDG-RRT) algorithm. Key improvements include dynamically constraining the search space using a direction guidance strategy, employing steering techniques to avoid obstacles, optimizing path length to minimize global cost, and refining trajectories using second-order Bessel curves. Simulation experiments compare QDDG-RRT with P-RRT(Probabilistic Rapidly-exploring Random Tree), P-RRT*, APF(Artificial Potential Field), and A* algorithms. Results show that QDDG-RRT outperforms others in execution speed, path length, and smoothness, effectively avoiding obstacles and maintaining safe distances in complex environments.

1 October 2025 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
KSKai Sun
Kai Sun
YSYouneng Su
Youneng Su
QXQing Xu
Qing Xu
RZRuixin Zhang
Ruixin Zhang
YLYi Liu
Yi Liu
XZXinming Zhu
Xinming Zhu
Off-road path planning, as an important direction in the field of intelligent navigation, has significant application value in complex scenarios such as emergency rescue, geological exploration, and military deployment. Unlike conventional path planning, which relies on fixed road networks, off-road path planning requires the establishment of a dynamic traversal model to support the planning results. Based on this issue, this study introduces knowledge graphs into the calculation of traversal cost modeling, addressing problems such as low data update efficiency and storage redundancy. First, a multidimensional quantitative analysis model is constructed, including vehicle dynamics parameters, terrain slope characteristics, and surface cover types, to extract the traversal impact factors of various elements through feature engineering. Secondly, based on knowledge graph technology, semantic modeling of multi-source heterogeneous data is achieved, and a dynamic weighted traversal cost map is generated using a rule-based reasoning mechanism. Finally, the performance of path planning is evaluated in a dynamic environment constraint system through a dual-engine validation framework with the improved A* algorithm and Dijkstra algorithm. Experimental results show that, compared to traditional cost map construction methods, our approach improves the construction efficiency in large areas by 30.7%, reduces redundant operations effectively in medium and small areas, and increases efficiency by 75% to 99.4%, which can, to some extent, improve the efficiency of path planning.