About

Dingyuan Zhang is a researcher advancing the fields of 3D scene understanding, autonomous navigation, and social robotics. His most notable contribution, **AVS-Net**, introduces a novel point-sampling method with adaptive voxel size for 3D scene understanding (2025, 7 citations), offering a more efficient approach to processing complex spatial data. In autonomous robotics, Zhang developed a **continual reinforcement learning framework** for mobile robot navigation (2020, 6 citations), addressing the critical challenge of generalizing across obstacle-cluttered environments—a key limitation in practical deployment. He also proposed a **robust method for static 3D point cloud mapping** using multi-view images with multi-resolution (2021, 3 citations), which effectively eliminates "ghost tracks" caused by dynamic objects, enhancing long-term autonomy. Expanding into social robotics, Zhang applied **Botometer model interpretation** to detect social bots on platforms like Twitter (2022, 2 citations), linking robotic perception to online misinformation challenges. With a total of 18 citations across his top works, Zhang’s research bridges physical and digital environments, from 3D mapping and navigation to social media analysis, demonstrating a versatile impact on both embodied AI and cyber-physical systems.

Research Focus

Key Achievements

3
H-Index
4
Papers
18
Total Citations
5
Avg Citations/Paper
🏆 Most Cited Paper
AVS-Net: Point sampling with adaptive voxel size for 3D scene understanding
7 citations · 2025
📈 Most Prolific Year: 2025 (1 Papers)
🤝 Key Collaborators: 14
🏛 Institutions: Huazhong University of Science and Technology, University of Science and Technology of China, Southern University of Science and Technology, Nanjing University of Posts and Telecommunications

Top Papers

  1. 1
  2. 2
  3. 3
  4. 4

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago