Chenxi Tu
Papers
1
Total Citations
84
H-Index
1
About
Chenxi Tu is a researcher at the forefront of 3D LiDAR data processing and autonomous systems, with a primary focus on point cloud compression and efficient deep learning architectures. His most influential work, "Point Cloud Compression for 3D LiDAR Sensor using Recurrent Neural Network with Residual Blocks" (2019), has garnered 84 citations and addresses a critical bottleneck in autonomous driving and robotics: the transmission and storage of massive, sparse point cloud data. By pioneering the use of recurrent neural networks combined with residual blocks, Tu developed a compression method that significantly reduces data size while preserving geometric fidelity, enabling faster and more reliable data sharing across robotic networks. This contribution is particularly impactful as 3D LiDAR expands beyond autonomous vehicles into fields like environmental monitoring and industrial automation. Tu’s work stands out for its practical engineering focus, directly tackling real-world constraints in bandwidth and latency. His research not only advances the efficiency of autonomous perception systems but also lays the groundwork for scalable, real-time 3D data handling in next-generation robotics.
Research Focus
Key Achievements
Top Papers
- 1