Siang Chen

Siang Chen

Ph.D. Candidate at Department of Electronic Engineering, Tsinghua University.

Biography

I am a fifth-year PhD student at Visual Computing Laboratory, Department of Electronic Engineering, Tsinghua University, supervised by Prof. Guijin Wang. Previously I received my bachelor’s degree at Department of Electronic Engineering, Tsinghua University in July, 2021.

My research focus is on robot manipulation, embodied AI and applications of 3D scene understanding. Currently, I’m working on building a more unified representation for manipulation with a more efficient general algorithm, especially for more difficult scenes.

Recent Publications

  • 2025.09.19: Our paper “Rainbow Delay Compensation: A Multi-Agent Reinforcement Learning Framework for Mitigating Delayed Observation” has been accepted by The Thirty-ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2025).
  • 2025.08.13: Our paper “Active-Perceptive Language-Oriented Grasp Policy for Heavily Cluttered Scenes” has been accepted by IEEE Robotics and Automation Letters. [Link]
  • 2025.07.05: Our paper “Rethinking 6-dof grasp detection: A flexible framework for high-quality grasping” has been accepted by Pattern Recognition. [Link]
  • 2025.06.23: Our paper “Region-Centric 6-Dof Grasp Detection: A Data-Efficient Solution for Cluttered Scenes” has been accepted by IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2025.
  • 2025.06.23: Our paper “FEG-VON: Frontier Embedding Graph for Efficient Visual Object Navigation” has been accepted by IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2025.
  • 2025.03.03: Our paper “Uncertainty-Aware Laser Stripe Segmentation with Non-Local Mechanisms for Welding Robots” has been accepted by IEEE Transactions on Instrumentation and Measurement. [Link]
  • 2025.01.21: Our paper “Efficient End-to-End 6-Dof Grasp Detection Framework for Edge Devices with Hierarchical Heatmaps and Feature Propagation” has been accepted by 2025 IEEE International Symposium on Circuits and Systems. [Link]
  • 2025.01.01: Our paper “Variation-Robust Few-Shot 3D Affordance Segmentation for Robotic Manipulation “ has been accepted by IEEE Robotics and Automation Letters. [Link]
  • 2024.10.04: Our paper “GAP-RL: Grasps As Points for RL Towards Dynamic Object Grasping” has been accepted by IEEE Robotics and Automation Letters. [Link]
  • 2024.09.05: Our paper “Region-aware Grasp Framework with Normalized Grasp Space for Efficient 6-DoF Grasping” has been accepted by 8th Annual Conference on Robot Learning (CoRL 2024). [Link]

Selected Research

  • Chen, S., Tang, W., Xie, P., Hu, D., Yang, W., & Wang, G. (2025). Region-Centric 6-Dof Grasp Detection: A Data-Efficient Solution for Cluttered Scenes. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2025. [Video]
  • Chen, S., Xie, P., Tang, W., Hu, D., & Wang, G. (2024). Region-aware Grasp Framework with Normalized Grasp Space for Efficient 6-DoF Grasping. 8th Annual Conference on Robot Learning (CoRL 2024). [Link] [Github] [Video]
  • Chen, S., Tang, W., Xie, P., Yang, W., & Wang, G. (2023). Efficient heatmap-guided 6-DoF grasp detection in cluttered scenes. IEEE Robotics and Automation Letters. [Link] [Github] [Video]
  • Fu, S., Chen, S. (co-first author), Zhao, S., Bai, L., Li, T. & Yan, Y. (2025). Rainbow Delay Compensation: A Multi-Agent Reinforcement Learning Framework for Mitigating Delayed Observation. The Thirty-ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2025).
  • Dai, Y., Chen, S. (co-first author, project leader), Yang, K., Hu, D., Xie, P., Li, G., & Wang, G. (2025). Active-Perceptive Language-Oriented Grasp Policy for Heavily Cluttered Scenes. IEEE Robotics and Automation Letters. [Link] [Video]
  • Xie, P., Chen, S. (co-first author, project leader), Tang, W., Yang, K., & Wang, G. & Wang, G. (2026). Rethinking 6-dof grasp detection: A flexible framework for high-quality grasping. Pattern Recognition. [Link] [Github] [Video]
  • Xie, P., Chen, S. (co-first author, project leader), Chen, Q., Tang, W., … & Wang, G. (2024). GAP-RL: Grasps As Points for RL Towards Dynamic Object Grasping. IEEE Robotics and Automation Letters. [Link] [arxiv] [Github]
  • Xie, P., Chen, R., Chen, S. (co-first author), Qin, Y., … & Su, H. (2023). Part-Guided 3D RL for Sim2Real Articulated Object Manipulation. IEEE Robotics and Automation Letters. [Link] [Github] [Video]
  • Yang, K., Dai, Y., Wang, G. & Chen, S. (corresdponding author, project leader). (2025). Efficient End-to-End 6-Dof Grasp Detection Framework for Edge Devices with Hierarchical Heatmaps and Feature Propagation. 2025 IEEE International Symposium on Circuits and Systems. [Link]
  • Xie, P., Chen, S. (project leader), Hu, D., Dai, Y., Yang, K., & Wang, G. (2024). “Target-Oriented Object Grasping via Multimodal Human Guidance”. ECCV 2024 Workshop on Assistive Computer Vision and Robotic (ACVR 2024). [Link]
  • Dai, Y., Chen, S. (project leader), Sun, T., Fan, Z., Zhang, C., Feng, X., & Wang, G. (2025). Uncertainty-Aware Laser Stripe Segmentation with Non-Local Mechanisms for Welding Robots. IEEE Transactions on Instrumentation and Measurement. [Link]
  • Hu, D., Chen, S., Yang, H., & Wang, G. (2023). Query-guided Support Prototypes for Few-shot 3D Indoor Segmentation. IEEE Transactions on Circuits and Systems for Video Technology. [Link]

Services

  • Reviewer of TMECH, TCSVT, RA-L, RAS, ICRA, IROS, AAAI, SMCA, Neurocomputing