Dapeng Feng

About

Dapeng Feng is a leading researcher in robotic perception, with a core focus on advancing simultaneous localization and mapping (SLAM) for both single and multi-robot systems. His work addresses critical challenges in autonomous navigation, particularly in GPS-denied and geometrically degenerate environments. Feng’s major contributions include the development of S3E, a pioneering multi-robot multimodal dataset for collaborative SLAM (28 citations), and a heterogeneous LiDAR dataset specifically designed to benchmark robust localization in challenging, feature-poor scenarios (15 citations). He introduced CaRtGS, a novel method for computational alignment in real-time Gaussian Splatting SLAM (12 citations), enhancing the efficiency and quality of photorealistic scene reconstruction. His SCL-SLAM framework (9 citations) integrates Scan Context descriptors with factor graph optimization for robust LiDAR SLAM, while CoLRIO (8 citations) tackles the complex problem of centralized state estimation for robotic swarms using heterogeneous sensors. With over 70 total citations and a portfolio of highly practical, dataset-driven innovations, Feng is shaping the future of collaborative and resilient robotic autonomy.

Research Focus

Key Achievements

Top Papers

1. 1
   S3E: A Multi-Robot Multimodal Dataset for Collaborative SLAM

   28 citations · 2024
2. 2
   Heterogeneous LiDAR dataset for benchmarking robust localization in diverse degenerate scenarios

   15 citations · 2025
3. 3
   CaRtGS: Computational Alignment for Real-Time Gaussian Splatting SLAM

   12 citations · 2025
4. 4
   SCL-SLAM: A Scan Context-enabled LiDAR SLAM Using Factor Graph-Based Optimization

   9 citations · 2022
5. 5
   CoLRIO: LiDAR-Ranging-Inertial Centralized State Estimation for Robotic Swarms

   8 citations · 2024

Key Collaborators

Contact & Links