Jiakun Pu
Papers
1
Total Citations
18
H-Index
1
About
Jiakun Pu is a researcher advancing the field of autonomous driving through innovative work in perception-aware path planning. His primary research areas include multi-modal sensor fusion, neural feature integration, and real-time obstacle detection for self-driving vehicles operating in complex urban environments. Pu’s most cited paper, "Multi-Modal Neural Feature Fusion for Automatic Driving Through Perception-Aware Path Planning" (2021), with 18 citations, introduces a novel framework that combines visual and LiDAR data using deep neural networks to generate robust, perception-aware trajectories. This work directly addresses the critical challenge of navigating dynamic, cluttered road scenes by enabling vehicles to anticipate and react to obstacles with greater accuracy. By fusing heterogeneous sensor modalities at the feature level, Pu’s approach improves path smoothness and safety compared to traditional planning methods. His contributions are particularly relevant for applications in autonomous driving, robotic navigation, and aircraft tracking. Pu’s research stands out for its practical focus on bridging perception and planning, offering a scalable solution for real-world deployment. As autonomous systems continue to evolve, his work provides a foundational step toward more reliable and context-aware navigation in unpredictable environments.
Research Focus
Key Achievements
Top Papers
- 1