Li He
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Li He has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Mei Liu
Multi-Scale Medical Robotics Center, The Chinese University of Hong Kong, Hong Kong, China
2 shared publications Dan Su
School of Information Science and Engineering, Lanzhou University, Lanzhou, China
1 shared publication- Fan Zhang
School of Information Science and Engineering, Lanzhou University, Lanzhou, China
1 shared publication Jun Wang
Gansu Institute of Food Inspection and Research, Lanzhou 730000, China
1 shared publication- Long Jin
Guangdong Provincial Engineering Technology Research Center for Sports Assistive Device, Guangzhou Sport University, Guangzhou 510000, China and School of Information Science and Engineering, Lanzhou University, Lanzhou 730000, China
1 shared publication - Mingsheng Shang
Chongqing Key Laboratory of Edge AI Computing, Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, Chongqing, China
1 shared publication
Latest Publications
- 8 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 71 (10) , 12559-12569
Dynamic Neural Network for Motion/Force Control of Manipulators With Polynomial Noises
Merely relying on precise motion control alone, a manipulator faces significant challenges when attempting to perform tasks involving interactions with objects, such as polishing. Furthermore, the presence of noises further impedes the successful completion of such tasks. Given these problems, this article proposes a neural-dynamics-based planning (NDP) scheme, which contains a neural-dynamics-based motion/force periodic motion control (MFPMC) strategy and a neural-dynamics-based fuzzy-parameter and dynamic neural network (FP-DNN) solver. Specifically, the MFPMC strategy enables the tracking of the desired task trajectory while exerting a necessary force on the object's surface. Subsequently, an improved FP-DNN solver, incorporating automatic adjustment on the convergent parameter, assists the MFPMC strategy in mitigating the effects of noises. Furthermore, theoretical analyses are conducted to prove the convergence and robustness of the proposed NDP scheme. Finally, comparative simulations under noise-free and noisy cases are conducted to showcase the effectiveness, robustness, and superiority of the proposed NDP scheme, while experiments on a robotic platform are performed to verify its feasibility.
- 8 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 71 (10) , 12559-12569
Dynamic Neural Network for Motion/Force Control of Manipulators With Polynomial Noises
Merely relying on precise motion control alone, a manipulator faces significant challenges when attempting to perform tasks involving interactions with objects, such as polishing. Furthermore, the presence of noises further impedes the successful completion of such tasks. Given these problems, this article proposes a neural-dynamics-based planning (NDP) scheme, which contains a neural-dynamics-based motion/force periodic motion control (MFPMC) strategy and a neural-dynamics-based fuzzy-parameter and dynamic neural network (FP-DNN) solver. Specifically, the MFPMC strategy enables the tracking of the desired task trajectory while exerting a necessary force on the object's surface. Subsequently, an improved FP-DNN solver, incorporating automatic adjustment on the convergent parameter, assists the MFPMC strategy in mitigating the effects of noises. Furthermore, theoretical analyses are conducted to prove the convergence and robustness of the proposed NDP scheme. Finally, comparative simulations under noise-free and noisy cases are conducted to showcase the effectiveness, robustness, and superiority of the proposed NDP scheme, while experiments on a robotic platform are performed to verify its feasibility.
- Open Access
- 9 December 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 221051-221060
Analysis and Verification on the Equivalence Between Jerk-Level and Acceleration-Level Schemes Applied to Manipulators Controlling
Two different-level schemes are researched in this article for achieving the kinematic control of redundant manipulators, one of which is exploited at the acceleration level, and the other is at the jerk level. Firstly, they are both reconstructed as a standard quadratic programming problem with different parameter definitions and addressed by a gradient neural network (GNN) method. Secondly, from the perspective of the GNN algorithm, a theoretical interpretation of the intrinsic equivalence between the acceleration-level scheme and jerk-level scheme is performed. Further, simulations on the manipulator synthesized by the two schemes aided with the GNN method tracking two different trajectories are conducted. Finally, comparisons of relevant joint data (i.e., joint angles, joint velocities, and joint accelerations) are presented to substantiate the equivalence between the two schemes, and simulative experiments are carried out at the same time.
- 9 December 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 221051-221060
Open AccessAnalysis and Verification on the Equivalence Between Jerk-Level and Acceleration-Level Schemes Applied to Manipulators Controlling
Two different-level schemes are researched in this article for achieving the kinematic control of redundant manipulators, one of which is exploited at the acceleration level, and the other is at the jerk level. Firstly, they are both reconstructed as a standard quadratic programming problem with different parameter definitions and addressed by a gradient neural network (GNN) method. Secondly, from the perspective of the GNN algorithm, a theoretical interpretation of the intrinsic equivalence between the acceleration-level scheme and jerk-level scheme is performed. Further, simulations on the manipulator synthesized by the two schemes aided with the GNN method tracking two different trajectories are conducted. Finally, comparisons of relevant joint data (i.e., joint angles, joint velocities, and joint accelerations) are presented to substantiate the equivalence between the two schemes, and simulative experiments are carried out at the same time.
- Open Access
- 15 June 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 109783-109790
Recurrent Neural Network for State Adjustment of Redundant Manipulators
To make joints of a redundant manipulator moving automatically to a target state, a stateadjustment (SA) scheme is studied and modified in this paper. Specifically, owing to the problem of non-zero initial joint velocity in the SA scheme leading to a potential hazard to redundant manipulators, a modified state-adjustment (MSA) scheme is obtained on the basis of the SA scheme. The MSA scheme achieves the state adjustment by minimizing the differences between the joint angles and the target values. For solving the MSA scheme, a recurrent neural network (RNN) model is derived, of which the critical component is to iterate over the joint angles and joint velocities. The MSA scheme solved by the RNN model enables the redundant manipulator to adjust to the target state automatically while ensuring that the initial joint velocity is zero. Beyond that, several comparative simulations demonstrate the availability and accuracy of the MSA scheme solved by the RNN model in controlling the state adjustment of redundant manipulators.
- 15 June 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 109783-109790
Open AccessRecurrent Neural Network for State Adjustment of Redundant Manipulators
To make joints of a redundant manipulator moving automatically to a target state, a stateadjustment (SA) scheme is studied and modified in this paper. Specifically, owing to the problem of non-zero initial joint velocity in the SA scheme leading to a potential hazard to redundant manipulators, a modified state-adjustment (MSA) scheme is obtained on the basis of the SA scheme. The MSA scheme achieves the state adjustment by minimizing the differences between the joint angles and the target values. For solving the MSA scheme, a recurrent neural network (RNN) model is derived, of which the critical component is to iterate over the joint angles and joint velocities. The MSA scheme solved by the RNN model enables the redundant manipulator to adjust to the target state automatically while ensuring that the initial joint velocity is zero. Beyond that, several comparative simulations demonstrate the availability and accuracy of the MSA scheme solved by the RNN model in controlling the state adjustment of redundant manipulators.