Qingtao Liu
I work on dexterous robotic manipulation at Galbot, building skills that enable multi-fingered hands to interact with the physical world. My research brings together visual–tactile perception, hand–object representations, and reinforcement learning to make manipulation more reliable and generalizable.
About
I joined Galbot (银河通用) in July 2026 as a Research Scientist, focusing on dexterous manipulation with multi-fingered robotic hands. I am interested in learning manipulation skills that generalize across objects and tasks, and transferring them from simulation to real robots.
I received my Ph.D. from the College of Control Science and Engineering, Zhejiang University, where I was advised by Prof. Qi Ye and Prof. Jiming Chen.
- Dexterous manipulation: Learning grasping, in-hand manipulation, and bimanual skills with multi-fingered hands.
- Perception & representations: Combining vision, touch, and hand–object geometry for contact-rich interaction.
- Policy learning & transfer: Reinforcement learning and pretraining for generalization across objects and tasks, with deployment on real robots.
News
- 2026.09 · Our study of GPT-6 Astra as embodied policies is available on arXiv.
- 2026.09 · Relational Dexterity at IROS 2026.
- 2026.08 · Collision-Free Humanoid Traversal published in IEEE RA-L.
- 2026.07 · Joined Galbot as a Research Scientist, working on dexterous robotic manipulation.
- 2026.02 · DexRepNet++ (IEEE T-RO 2026) is available on arXiv; code is available.
- 2026.01 · Visual-tactile pretraining and online multitask learning for humanlike manipulation dexterity published in Science Robotics.
- 2025.10 · Co-organized Dexterous Grasp Motion Challenge @ ICCV 2025 HANDS Workshop.
- 2025.07 · Contact2Motion accepted to IJRR (student second author).
- 2025.06 · Two papers accepted to IROS 2025.
- 2025.01 · VTDexManip accepted to ICLR 2025.
Publications
Recent and representative papers. See Google Scholar for the full publication list. * denotes equal contribution.
Journals
Conferences
Preprints
Research Experience & Activities
- Galbot · Research Scientist (July 2026–present) · Research on dexterous manipulation and skill learning for multi-fingered robotic hands.
- Zhejiang University · Ph.D. · Research on hand–object representations, visual–tactile learning, and dexterous manipulation.
- NSFC Center: Autonomous Intelligent Unmanned Systems · Worked on dexterous hand skill learning for multi-task generalization in unstructured environments.
- Central Univ. Fund: Humanoid tactile skin sensor · Led tactile sensor benchmarking during my Ph.D.
- ZJU–Borui Joint Lab · SDF-based arm-hand online obstacle avoidance and replanning (2023).
- Dexterous Grasp Motion Challenge @ ICCV 2025 · Organizer and baseline code contributor.
Academic Service
Reviewer for the following journals and conferences:
- Journals: IEEE Transactions on Robotics (T-RO), IEEE Transactions on Robot Learning (T-RL), IEEE Robotics and Automation Letters (RA-L), IEEE Transactions on Multimedia (TMM).
- Conferences: Robotics: Science and Systems (RSS), IEEE International Conference on Robotics and Automation (ICRA), Conference on Robot Learning (CoRL), IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).