Wenjie Na
Papers
2
Total Citations
11
H-Index
2
About
Wenjie Na’s research lies at the intersection of autonomous navigation, multi-agent coordination, and intelligent decision-making for mobile robots. Their most cited work critically examines the Optimal Reciprocal Collision Avoidance (ORCA) algorithm, identifying and relaxing its fundamental limitations—such as the rigid assumption that each agent bears equal responsibility for collision avoidance—thereby enabling more natural and efficient robot motion in crowded, dynamic environments. This paper has already garnered 9 citations, signaling its timely impact on the field. Na also advances active SLAM by integrating Deep Reinforcement Learning (DRL) with intrinsic reward mechanisms, using 2D LiDAR data to guide goal-driven exploration and mapping. This work addresses a core challenge in laser SLAM: enabling robots to autonomously decide where to move next to improve map accuracy and localization reliability. By bridging theoretical limitations in collision avoidance with practical, learning-based solutions for mapping, Wenjie Na contributes directly to making mobile robots more autonomous, safe, and effective in real-world human environments.
Research Focus
Key Achievements
Top Papers
- 1
- 2