Zhilun Hu
Ph.D. student · Huazhong University of Science and Technology
I am Zhilun Hu (胡至伦), a Ph.D. student at Huazhong University of Science and Technology, advised by Prof. Weiming Shen.
My research focuses on reliable robotic manipulation: improving what robots observe, checking the actions they propose, and adapting their behavior during physical interaction. My interests span active visual servoing, dual-arm deformable-object manipulation, visuotactile policy learning, and failure recovery.
我是胡至伦，华中科技大学博士研究生，导师为沈卫明教授。我的研究围绕机器人操作的可靠性展开，关注主动视觉伺服、双臂柔性物体操作、视觉触觉策略学习，以及故障恢复与经验记忆。
Research interests
- Active perception and visual servoing for manipulation under occlusion.
- Vision-language reasoning for dual-arm and deformable-object manipulation.
- Visuotactile policy adaptation and reinforcement learning for contact-rich tasks.
- Failure recovery and experience memory for robot policies.
Selected papers
Active Observation for Robust Visual Servoing in Robotic Manipulation
Zhilun Hu, Yuqi Cheng, Yuxiang Tan, Wen-pan Li, Weiming Shen.
IEEE CASE 2026 · Accepted · First author
An active camera arm and relative visual servoing help preserve or recover a shared view of the target and gripper during grasping.
Iterative Verify-and-Refine Vision-Language Agent for Reliable Dual-Arm Manipulation
Yuqi Cheng, Zhilun Hu, Cheng Jiang, Qingyu Peng, Weiming Shen.
Manuscript under review · Second author
VR-Loop combines iterative visual verification and geometric constraints for dual-arm rope untangling.
Current research
- T-Rex / Sticks — visuotactile policy adaptation and reinforcement learning for contact-rich manipulation, building on the open-source T-Rex framework. Ongoing research.
- HELIX — robot failure recovery through value assessment, reflex feedback, and experience memory. Ongoing simulation research.
Explore projects · CV · GitHub