Chenchen Ding

Southern University of Science and Technology

Papers

Total Citations

H-Index

About

Chenchen Ding is a researcher advancing the frontiers of robotic perception and edge-deployable artificial intelligence, with a primary focus on visual simultaneous localization and mapping (VSLAM), monocular visual odometry, and loop closure detection. Their work addresses critical challenges in autonomous systems—from sweeping robots to drones and autonomous vehicles—by developing deep learning models that are both highly accurate and computationally efficient enough for deployment on edge devices. Ding’s major contributions include the ATFVO framework, which integrates attentive tensor-compressed LSTMs with optical flow features to solve monocular visual odometry, and the TLCD and TT-LCD systems, which leverage transformer architectures and tensorized transformers for robust loop closure detection to correct drift in VSLAM. These innovations have garnered attention in the field, with papers accumulating citations that reflect their growing impact. Notably, Ding’s work on tensorized transformers for edge-based loop closure detection represents a significant step toward making advanced SLAM capabilities practical for real-world, resource-constrained robotic platforms, bridging the gap between high-performance deep learning and on-device autonomy.