Mingyu Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Mingyu Li has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Aiguo Song
Southeast University
3 shared publications - Huailiang Ma
Southeast University
2 shared publications - Mutian He
Southeast University
2 shared publications Yibing Yan
School of Instrument Science and Engineering, Southeast University, Nanjing, China
2 shared publicationsAiguo Song
Southeast Univ, Sch Instrument Sci & Engn, State Key Lab Digital Med Engn, Jiangsu Key Lab Remote Measurement & Control, Nanjing 210096, Peoples R China
1 shared publication- Bingcong Jian
Tongji University
1 shared publication
Latest Publications
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (12) , 14220-14227
HandSSR: Synergy- and Structure-Preserving Neural Retargeting for Dexterous Hand Teleoperation
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (12) , 14220-14227
HandSSR: Synergy- and Structure-Preserving Neural Retargeting for Dexterous Hand Teleoperation
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (10) , 12024-12031
The Assessment of 3D Force Feedback for Closed-Loop Control of Myoelectric Hand Prosthesis
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (10) , 12024-12031
The Assessment of 3D Force Feedback for Closed-Loop Control of Myoelectric Hand Prosthesis
- 30 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (6) , 6935-6942
AutoTrialGen: Automated Data Generation From Few Human Demonstrations via Trajectory Annotation and Simulation Trials
While imitation learning is a powerful paradigm for teaching robots complex manipulation skills, its effectiveness is often bottlenecked by the need for large-scale, human-collected datasets. This paper presents AutoTrialGen, an automated framework designed to generate large and diverse datasets of successful simulated demonstrations through trial-and-error, from only a few human demonstrations. Initially, AutoTrialGen employs a vision-language model to automatically decompose unprocessed human demonstrations into a library of object-centric and reusable skill primitives. Within a simulated environment, it then intelligently composes these primitives to solve new task instances, employing a novel weighted manipulability selection mechanism to ensure the quality and efficiency of the generated trajectories. Policies trained using the proposed sim-augmented data demonstrate improved performance and enhanced data efficiency across six diverse and challenging real-world manipulation tasks, compared with the baseline method.
- 30 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (6) , 6935-6942
AutoTrialGen: Automated Data Generation From Few Human Demonstrations via Trajectory Annotation and Simulation Trials
While imitation learning is a powerful paradigm for teaching robots complex manipulation skills, its effectiveness is often bottlenecked by the need for large-scale, human-collected datasets. This paper presents AutoTrialGen, an automated framework designed to generate large and diverse datasets of successful simulated demonstrations through trial-and-error, from only a few human demonstrations. Initially, AutoTrialGen employs a vision-language model to automatically decompose unprocessed human demonstrations into a library of object-centric and reusable skill primitives. Within a simulated environment, it then intelligently composes these primitives to solve new task instances, employing a novel weighted manipulability selection mechanism to ensure the quality and efficiency of the generated trajectories. Policies trained using the proposed sim-augmented data demonstrate improved performance and enhanced data efficiency across six diverse and challenging real-world manipulation tasks, compared with the baseline method.
- 4 October 2023
- Published by Elsevier in Computers & Graphics
- Vol. 116, 464-473
Computational design of planet regolith sampler based on Bayesian optimization
- 4 October 2023
- Published by Elsevier in Computers & Graphics
- Vol. 116, 464-473
Computational design of planet regolith sampler based on Bayesian optimization