Welcome, on board!
Despite knowing the journey and where it leads, I embrace it, and I welcome every moment of it.
-- Dr. Louise Banks, Arrival (2016)
Vision
Inspired by Chinese philosopher 'Mozi' (墨子) and the ideas from Mohism about 'Universal Love, non-attack' (非攻 兼爱), I believe that technology should contribute to humanity toward a healthier, safer, and higher quality of life.
I am an enthusiast and believer in the new revolution for robotics (Artificial General Intelligence for Robotics and Embedded Agent). I believe that the 'real2sim (meta-verse) and sim2real' can bring the community (machine learning, computer vision and graphics, and robotics) towards the era of technology beyond first-principle-based methods and control theory. Yet, there is a huge research gap towards this revolution. I believe robotics can be one of the solutions for population aging via the autonomous system and human-robot collaboration.
I am a part-time researcher in AI for Health and Science (medical imaging, intra-operative imaging for surgical robotics, ML for accelerating CFD optimization and more to be explored).
Biography
I am currently a PhD student at ProrokLab in the Digital Technology Group (DTG) at the University of Cambridge under the supervision of Prof Amanda Prorok. During my PhD, I focus on communication-aware motion planning for multi-robot coordination. I am investigating Graph Neural Networks (GNN) to build communication channels for multi-agent and multi-robot systems so that they can learn how to communicate between each other explicitly. My research can be applied to mobility-on-demand systems, automated warehouses, and smart cities.
Prior to joining Cambridge, I was working in the Hamlyn Centre at Imperial College London, founded by Prof Guang-Zhong Yang and the Lord Ara Darzi, in the field of medical robotics and healthcare to earn my MRes in Medical Robotics and Image-Guided Intervention. I was supervised by Prof Daniel Elson for an eight-month research project about oxygen saturation (StO2) estimation, and graduated with a distinction. I also hold an MEng degree in Mechanical Engineering from the University of Edinburgh.
I have published papers in the medical imaging area (IJCARS) and the robotics field (IEEE Humanoids, IEEE IROS, IEEE ICRA, IEEE RA-L and AAMAS). I have served as a reviewer for IEEE IROS, IEEE ICRA, IEEE RA-L, IEEE T-RO, Autonomous Robots (AURO) and AAMAS.
I am actively looking for Postdoctoral Researcher Positions and Research Scientist Positions in Industry. I am also open to collaboration opportunities. Feel free to contact by Email (ql295[AT]cam.ac.uk). Details of my CV can be found in PDF.
Research Interest
- Robot Learning
- Multi-robot Path Planning
- Graph Neural Networks (GNNs)
- Imitation Learning
- Reinforcement Learning
- Computer Vision (Medical Imaging)
News
2022 News: As there is way more noise that interrupts our daily study and work, let us come here to study and work with quiet music and a nice view of Cambridge on my personal YouTube called 'Study Room of Qingbiao Li' and Douyu Channel called '格拉夫暖男的自习室' daily. Welcome to join our 'Study_Room_Graphnuannan' and Bilibili.
2022 News: I am deeply appreciated to receive Chui Wen Mei Memorial Bursary to support my final period of my PhD.
2022 News: Our paper got accepted in SSRR 2022.
2022 News: Our paper was awarded Publication of the Year by the Department of Computer Science and Technology at the University of Cambridge.
2022 News: Our paper got accepted in TSP 2022.
2022 News: Our (MPhil student co-supervised by me, Matthew Malencia, Prof Amanda Prorok) paper (GNNs for TSP) got accepted in ICLR 2022.
2022 News: Our system paper (the first truly decentralized robotics system based on GNNs) got accepted in ICRA 2022. Feel free to access our public repo.
2022 News: Our blue-sky paper got accepted in AAMAS 2022.
2022 News: Invited talk about 'Graph Neural Networks from Robot Learning and Beyond' at ShenlanXueyuan as part of an online course related to Graph Neural Networks developed by Prof Jiliang Tang. Obtain over 1k view till now.
2021 News: My Google Scholar reached 100 citations. My paper ( Graph MAPF) published at IROS 2020 got 90 citations, and our GitHub repo [1] got 115 stars and [2] got 22 stars so far.
2021 News: From July 2021 to Nov 2021, I am working on Project Silica during my internship at Microsoft Research Cambridge. I am exploring explainable RL-based approaches to scheduling in the Silica glass library, towards a scheduler for production deployment.
2021 News: Invited talk about 'Message-Aware Graph Attention Networks for Large-Scale Multi-Robot Path Planning' at the University of Pennsylvania.
2021 News: Our paper got accepted in TAC 2021.
2021 News: Our paper (MAGAT) got accepted in RA-L 2021.
2020 News: Invited talk about 'From Graph Neural Networks to Decentralized Multi-Robot Path Planning' at Zhejiang University.
2020 News: Our paper got accepted in ICRA 2021.
2020 News: Our paper (G2RL) got accepted in RA-L 2020.
2020 News: Our paper (Graph-MAPF) got accepted in IROS 2020.
2021 News: Invited talk about 'Graph Neural Networks for Decentralized Path Planning' at Robotics X Tencent, Shenzhen, China.
2019 News: Our paper got accepted in IPCAI-IPCAI Special Issue 2019.
2018 News: Our papers ( [1] [2] ) got accepted in Hamlyn Symposium.
2017 News: Our paper got accepted in IEEE Humanoid 2017.
Publications
Journal
Graph Neural Networks for Decentralized Multi-Robot Submodular Action Selection
Published in IEEE Robotics and Automation Letters (RA-L), 2022
Recommended citation: Lifeng Zhou, Vishnu D Sharma, Li, Qingbiao, Amanda Prorok, Alejandro Ribeiro, Vijay Kumar. “Graph Neural Networks for Decentralized Multi-Robot Submodular Action Selection,” IEEE Robotics and Automation Letters (JCR Q2, IF 3.74), Under Review PDF
Message-Aware Graph Attention Networks for Large-Scale Multi-Robot Path Planning
Published in IEEE Robotics and Automation Letters (RA-L), 2020
Recommended citation: Q. Li, W. Lin, Z. Liu and A. Prorok, "Message-Aware Graph Attention Networks for Large-Scale Multi-Robot Path Planning," in IEEE Robotics and Automation Letters (JCR Q2, IF 3.74), vol. 6, no. 3, pp. 5533-5540, July 2021, doi: 10.1109/LRA.2021.3077863. PDF
Looking At The Body: Automatic Analysis of Body Gestures and Self-Adaptors in Psychological Distress
Published in IEEE Transactions on Affective Computing, 2020
Recommended citation: Lin, W., Orton, I., Li, Q., Pavarini, G. and Mahmoud, M., 2020. Looking At The Body: Automatic Analysis of Body Gestures and Self-Adaptors in Psychological Distress. IEEE Transactions on Affective Computing (JCR Q1, IF 10.506). Springer, 2020. PDF
Mobile Robot Path Planning in Dynamic Environments through Globally Guided Reinforcement Learning
Published in IEEE Robotics and Automation Letters (RA-L), 2020
Recommended citation: B. Wang, Z. Liu, Q. Li and A. Prorok, "Mobile Robot Path Planning in Dynamic Environments Through Globally Guided Reinforcement Learning," in IEEE Robotics and Automation Letters (JCR Q2, IF 3.74), vol. 5, no. 4, pp. 6932-6939, Oct. 2020, doi: 10.1109/LRA.2020.3026638. PDF
Estimation of Tissue Oxygen Saturation from RGB Images and Sparse Hyperspectral Signals based on Conditional Generative Adversarial Network
Published in International Journal of Computer Assisted Radiology and Surgery (IJCARS), 2019
Recommended citation: Qingbiao Li, Jianyu Lin, Neil T Clancy, Daniel S Elson. “Estimation of Tissue Oxygen Saturation from RGB Images and Sparse Hyperspectral Signals based on Conditional Generative Adversarial Network,” International Journal of Computer Assisted Radiology and Surgery (JCR Q3, IF 2.924). pp. 987–995. Springer, 2019. PDF
Conference
Graph Neural Network Guided Local Search for the Traveling Salesperson Problem
Published in International Conference on Learning Representations (ICLR), 2022
Recommended citation: Hudson Benjamin, Qingbiao Li, Matthew Malencia, and Amanda Prorok. “Graph Neural Network Guided Local Search for the Traveling Salesperson Problem,” International Conference on Learning Representations (CCF-A, Qualis-A1), 2022 PDF
A Framework for Real-World Multi-Robot Systems Running Decentralized GNN-Based Policies
Published in IEEE International Conference on Robotics and Automation (ICRA), 2022
Recommended citation: Jan Blumenkamp, Steven Morad, Jennifer Gielis, Qingbiao Li, Amanda Prorok. “A Framework for Real-World Multi-Robot Systems Running Decentralized GNN-Based Policies,” IEEE International Conference on Robotics and Automation (CCF-B, Qualis-A1), Under Review, 2021 PDF
The Holy Grail of Multi-Robot Planning: Learning to Generate Online-Scalable Solutions from Offline-Optimal Experts
Published in Conference on Robot Learning (CoRL), 2021
Recommended citation: Amanda Prorok, Jan Blumenkamp, Qingbiao Li, Ryan Kortvelesy, Zhe Liu, Ethan Stump. “The Holy Grail of Multi-Robot Planning: Learning to Generate Online-Scalable Solutions from Offline-Optimal Experts,” Conference on Robot Learning. 2021 PDF
Evaluating the Sim-to-Real Gap of Graph Neural Network Policies for Multi-Robot Coordination
Published in IEEE International Conference on Robotics and Automation (ICRA), 2021
Recommended citation: Jan Blumenkamp, Qingbiao Li, Amanda Prorok. “Evaluating the Sim-to-Real Gap of Graph Neural Network Policies for Multi-Robot Coordination,” IEEE International Conference on Robotics and Automation (CCF-B, Qualis-A1), Real World Swarms Workshop, 2021. arXiv preprint arXiv:1912.06095. PDF
Real-time Surgical Environment Enhancement for Robot-Assisted Minimally Invasive Surgery Based on Super-Resolution
Published in IEEE International Conference on Robotics and Automation (ICRA), 2020
Recommended citation: Ruoxi Wang, Dandan Zhang, Qingbiao Li, Benny Lo. “Real-time Surgical Environment Enhancement for Robot-Assisted Minimally Invasive Surgery Based on Super-Resolution,” IEEE International Conference on Robotics and Automation (CCF-C, ERA-A, Qualis-A1), 2021. arXiv preprint arXiv:1912.06095. PDF
Graph Neural Networks for Decentralized Multi-Robot Path Planning
Published in IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) , 2020
Recommended citation: Qingbiao Li, Fernando Gama, Alejandro Ribeiro, Amanda Prorok. “Graph Neural Networks for Decentralized Multi-robot Path Planning,” IEEE/RSJ International Conference on Intelligent Robots and Systems (CCF-C, ERA-A, Qualis-A1), 2020. PDF
Graph Neural Networks for Decentralized Path Planning
Published in International Conference on Autonomous Agents and MultiAgent Systems (AAMAS), 2020
Recommended citation: Li, Q., Gama, F., Ribeiro, A. and Prorok, A., 2020, May. Graph Neural Networks for Decentralized Path Planning. In Proceedings of the 19th International Conference on Autonomous Agents and MultiAgent Systems (ERA-A, Qualis-A1), pp. 1901-1903, 2020 PDF
Estimation of Tissue Oxygen Saturation from RGB Images based on Pixel-level Image Translation
Published in The Hamlyn Symposium on Medical Robotics, 2018
Recommended citation: Li, Q. B., Zhou, X. Y., Lin, J., Zheng, J. Q., Clancy, N. T., & Elson, D. S. (2018). Estimation of Tissue Oxygen Saturation from RGB Images based on Pixel-level Image Translation. arXiv preprint arXiv:1804.07116. PDF
Abdominal Aortic Aneurysm Segmentation with a Small Number of Training Subjects
Published in The Hamlyn Symposium on Medical Robotics, 2018
Recommended citation: J. Q. Zheng, X. Y. Zhou, Q. B. Li, C. Riga and G. Z. Yang, Abdominal Aortic Aneurysm Segmentation with a Small Number of Training Subjects, The Hamlyn Symposium on Medical Robotics, 2018 PDF
Robust Foot Placement Control for Dynamic Walking Using Online Parameter Estimation
Published in IEEE Humanoids, 2017
Recommended citation: Qingbiao Li, Iordanis Chatzinikolaidis, Yiming Yang, Sethu Vijayakumar, and Zhibin Li. Robust Foot Placement Control for Dynamic Walking Using Online Parameter Estimation. IEEE Humanoids (ERA-C, Qualis-B2), 2017. PDF