Papers
2
Total Citations
7
H-Index
1
About
Huilin Jiang is a researcher advancing the frontiers of 3D perception and autonomous robotics, with key contributions in point cloud object detection and semantic mapping. Their most influential work introduces the Scale-Aware Attention-Based PillarsNet (SAPN), a novel deep learning architecture for 3D object detection from LiDAR point clouds. This method, which has garnered 6 citations, enhances the precision of object localization—a critical capability for self-driving cars, service robots, and autonomous navigation systems. By incorporating scale-aware attention mechanisms, SAPN effectively handles objects of varying sizes in complex scenes, improving detection robustness. More recently, Jiang has tackled the challenging integration of semantic SLAM with multi-object tracking for indoor environments. Their 2025 study combines ORB-SLAM2 with 3D object detection to create dense semantic maps without relying on expensive sensors, addressing a key bottleneck in affordable robot perception. This work demonstrates Jiang’s commitment to practical, cost-effective solutions for real-world robotics. Through these contributions, Huilin Jiang is helping to build the perceptual foundation for the next generation of intelligent, autonomous machines.
Research Focus
Key Achievements
Top Papers
- 1
- 2