个人信息
参与实验室科研项目
学术成果
共撰写/参与撰写专利 0 项，录用/发表论文 2 篇，投出待录用论文1篇。
Conference Articles
-
Human-AI Shared Control via Motor Knowledge Neuron Stimulation
Jinwei Liu,
Pengfei Li,
Sibin Huang,
Yun-Bo Zhao ,
and Yu Kang
In 23rd IFAC World Congress
2026
[Abs]
[pdf]
Neuron-level control offers an effective approach to enabling human-AI shared control without retraining pretrained policies. However, existing methods assume motor primitives are encoded by individual neurons, limiting control precision and robustness. We propose Motor Knowledge Neuron Stimulation (MKNS), which recognizes that motor primitives distribute across neuron assemblies. MKNS identifies these assemblies via frequency-domain analysis and trains compact neural stimulators through iterative data aggregation using only 1% of the original training data. Experiments validate MKNS effectiveness while revealing fundamental properties of motor knowledge: directional asymmetry, the necessity of distributed encoding, and cross-talk between primitives.
Journal Articles
-
Delay-Aware Shared Control for Teleoperation Systems: Intent Trajectory Prediction Under Communication Latency
Jinwei Liu,
Pengfei Li,
Yaqing Zhou,
Tao Wang,
Yu Kang,
and Yun-Bo Zhao
IEEE Internet Things J.
2026
[doi]
[pdf]