延晶坤
讲师
yanjingkun@ynu.edu.cn; jingkunyan@foxmail.com
研究领域
机器人、神经动力学、模型预测控制
研究概况
针对冗余机器人躲避障碍物、模型具有不确定性等问题，分别在模型已知与未知情形下，设计了多种鲁棒性强、计算高效的运动控制算法，涵盖避障、姿态控制与关节约束等复杂场景。所提算法兼顾控制精度与实时性，已通过仿真与实验证实其可行性与优越性。同时，围绕时变矩阵方程与优化问题，提出多种鲁棒的神经动力学模型，并应用于机器人控制与声源定位。
研究课题
国家自然科学基金面上项目：基于递归神经网络的分布式竞争-合作策略及群体系统应用（2022-2025），参与
学术成果
一、论文
1. Jingkun Yan, Long Jin, Zhanting Yuan, Zhiyi Liu. RNN for receding horizon control of redundant robot manipulators. IEEE Transactions on Industrial Electronics, 2022, 69(2): 1608-1619.
2. Jingkun Yan, Long Jin, Xin Luo, Shuai Li. Modified RNN for solving comprehensive Sylvester equation with TDOA application. IEEE Transactions on Neural Networks and Learning Systems, 2024, 35(9): 12553-12563.
3. Jingkun Yan, Long Jin, Bin Hu. Data-driven model predictive control for redundant manipulators with unknown model. IEEE Transactions on Cybernetics, 2024, 54(10): 5901-5911.
4. Jingkun Yan, Zhenming Su, Xin Ma, Long Jin. An obstacle avoidance scheme for manipulators aided by noise-tolerant neural dynamics. IEEE Transactions on Industrial Informatics, 2025, 21(1): 703-712.
5. Jingkun Yan, Mei Liu. Neural dynamics-based model predictive control for mobile redundant manipulators with improved obstacle avoidance. IEEE Transactions on Industrial Electronics, 2024, 72(3): 2769-2778.
6. Jingkun Yan, Mei Liu, Long Jin. Cerebellum-inspired model predictive control for redundant manipulators with unknown structure information. IEEE Transactions on Cognitive and Developmental Systems, 2024, 16(3): 1198-1210.
7. Long Jin, Jingkun Yan, Xiujuan Du, Xiuchun Xiao, Dongyang Fu. RNN for solving time-variant generalized Sylvester equation with applications to robots and acoustic source localization. IEEE Transactions on Industrial Informatics, 2020, 16(10): 6359-6369.
二、专利
《一种具有避障功能的移动冗余机械臂模型预测控制方法》，发明人：金龙，延晶坤，李帅，刘梅，国别：中国，专利号：202111117973.X，授权公告日：2023年07月21日，授权公告号：CN113843793B。