Lunan Zheng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Lunan Zheng has a total of 78 co-authors. Here are the top co-authors by number of shared publications:
- Zhijun Zhang
South China University of Technology
31 shared publications Yamei Luo
School of Automation Science and Engineering, South China University of Technology, Guangzhou, China
4 shared publications- Feiqi Deng
South China University of Technology
3 shared publications Jindong Jiang
The School of Automation Science and Engineering South China University of Technology 510640 Guangzhou China
3 shared publications- Lingdong Kong
National University of Singapore, Singapore
3 shared publications - Siyuan Chen
Shien-Ming Wu School of Intelligent Engineering, South China University of Technology, Guangzhou 510640, China
3 shared publications
Latest Publications
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (10) , 11745-11752
Diff4RadBEV: Conditional Diffusion for 4D Radar BEV Enhancement
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (10) , 11745-11752
Diff4RadBEV: Conditional Diffusion for 4D Radar BEV Enhancement
- 23 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. PP (02780046) , 1-13
An Improved Barrier Neural Network-Based Mutual Collision Avoidance Scheme for Dual Redundant Manipulators
In the field of robotics, developing a rapid, accurate, and reliable motion planning and collaboration scheme for dual redundant manipulators is highly valuable. In this article, an improved barrier neural network (IBNN)-based mutual collision avoidance scheme is proposed for dual manipulators, offering faster calculation speed, higher tracking accuracy, and a larger safe distance compared to state-of-the-art methods. First, to enhance iterative calculation speed, an improved critical points search method is designed and incorporated into the proposed scheme based on the minimum mutual distance and iterative threshold. Second, an IBNN is proposed to address the iteration-stop problem of the traditional barrier learning network when it reaches the inequality boundary. Third, the equivalence and convergence theorems are provided to demonstrate the properties of the proposed scheme. Simulation and comparison of dual AMR-PT2 manipulators also verify that the proposed method exhibits superior convergence rate, safe distance, and computational precision. Finally, some real-world experiments with dual 6-DOFs xArm6 manipulators are conducted to illustrate the reliability and superiority of the proposed method.
- 23 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. PP (02780046) , 1-13
An Improved Barrier Neural Network-Based Mutual Collision Avoidance Scheme for Dual Redundant Manipulators
In the field of robotics, developing a rapid, accurate, and reliable motion planning and collaboration scheme for dual redundant manipulators is highly valuable. In this article, an improved barrier neural network (IBNN)-based mutual collision avoidance scheme is proposed for dual manipulators, offering faster calculation speed, higher tracking accuracy, and a larger safe distance compared to state-of-the-art methods. First, to enhance iterative calculation speed, an improved critical points search method is designed and incorporated into the proposed scheme based on the minimum mutual distance and iterative threshold. Second, an IBNN is proposed to address the iteration-stop problem of the traditional barrier learning network when it reaches the inequality boundary. Third, the equivalence and convergence theorems are provided to demonstrate the properties of the proposed scheme. Simulation and comparison of dual AMR-PT2 manipulators also verify that the proposed method exhibits superior convergence rate, safe distance, and computational precision. Finally, some real-world experiments with dual 6-DOFs xArm6 manipulators are conducted to illustrate the reliability and superiority of the proposed method.
- 17 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 73 (2) , 2690-2700
A VP-CDNN-Based Dynamic Multicriteria Motion Planner for Redundant Robots With Repetitive Tasks
To overcome the inherent difficulties in the traditional motion planning problem for redundant manipulators with the multicriteria objective function, a novel dynamic multicriteria motion planning (DMCMP) method, based on a varying-parameter convergent-different neural network (VP-CDNN), is proposed by designing a dynamic mixer. Given that the objective function is dynamically adjusted based on the task progress in the dynamic mixer, the proposed DMCMP method enhances overall performance and improves the optimal performance through the dynamic prioritization of criteria. By incorporating both the joint-angle drift-free criterion and other common criteria, the repetitive motion planning problem (RMP) is formulated as a time-varying quadratic programming (TVQP) problem and solved using a variant of the VP-CDNN. Finally, simulations and physical experiments are conducted and their results are compared with the demonstrate the effectiveness and feasibility of the proposed method. Following normalization, the optimal performance achieved by the DMCMP method is approximately 11.4 times better than that of the traditional method for specific tasks.
- 17 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 73 (2) , 2690-2700
A VP-CDNN-Based Dynamic Multicriteria Motion Planner for Redundant Robots With Repetitive Tasks
To overcome the inherent difficulties in the traditional motion planning problem for redundant manipulators with the multicriteria objective function, a novel dynamic multicriteria motion planning (DMCMP) method, based on a varying-parameter convergent-different neural network (VP-CDNN), is proposed by designing a dynamic mixer. Given that the objective function is dynamically adjusted based on the task progress in the dynamic mixer, the proposed DMCMP method enhances overall performance and improves the optimal performance through the dynamic prioritization of criteria. By incorporating both the joint-angle drift-free criterion and other common criteria, the repetitive motion planning problem (RMP) is formulated as a time-varying quadratic programming (TVQP) problem and solved using a variant of the VP-CDNN. Finally, simulations and physical experiments are conducted and their results are compared with the demonstrate the effectiveness and feasibility of the proposed method. Following normalization, the optimal performance achieved by the DMCMP method is approximately 11.4 times better than that of the traditional method for specific tasks.
- 5 February 2025
- Published by Springer Nature
- p. 389-401
An Adaptive Varying-Parameter Projection Neural Network for Redundant Manipulator with Unknown Physical Parameters
- 5 February 2025
- Published by Springer Nature
- p. 389-401
An Adaptive Varying-Parameter Projection Neural Network for Redundant Manipulator with Unknown Physical Parameters
- 18 January 2025
- Published by Elsevier in European Journal of Operational Research
- Vol. 324 (1) , 276-289
Novel adaptive parameter fractional-order gradient descent learning for stock selection decision support systems
- 18 January 2025
- Published by Elsevier in European Journal of Operational Research
- Vol. 324 (1) , 276-289
Novel adaptive parameter fractional-order gradient descent learning for stock selection decision support systems
- Open Access
- 26 January 2024
- Published by Qeios Ltd
Review of: "Modelling of Quadcopter for Precision Agriculture and Surveillance Purposes"
This paper describes UAV modeling and its application in agriculture. However, there are many problems with this paper, which are listed below: 1: The focus of this paper is not clear; the author introduces agriculture and UAVs in the introduction....
- 26 January 2024
- Published by Qeios Ltd
Open AccessReview of: "Modelling of Quadcopter for Precision Agriculture and Surveillance Purposes"
This paper describes UAV modeling and its application in agriculture. However, there are many problems with this paper, which are listed below: 1: The focus of this paper is not clear; the author introduces agriculture and UAVs in the introduction....
- Open Access
- 13 December 2023
- Published by Qeios Ltd
Review of: "Optimal Latency Compensator for Improved Performance of Teleoperated UGVs on Soft Terrains"
In this paper, the authors presented the solution they used to address the degradation of UGV control quality caused by communication delays in Bilateral teleoperation. The authors provide a more detailed overview, and their work seems to be solid an...
- 13 December 2023
- Published by Qeios Ltd
Open AccessReview of: "Optimal Latency Compensator for Improved Performance of Teleoperated UGVs on Soft Terrains"
In this paper, the authors presented the solution they used to address the degradation of UGV control quality caused by communication delays in Bilateral teleoperation. The authors provide a more detailed overview, and their work seems to be solid an...
- Open Access
- 24 November 2023
- Published by Qeios Ltd
Review of: "Neuro-Fuzzy-Based Adaptive Control for Autonomous Drone Flight"
1: Many of the symbols in this article are not uniform, and the format is confusing, such as p_a and p_d. 2: The description of its own controller in this paper is not sufficient, the specific controller form and parameters are not clearly described....
- 24 November 2023
- Published by Qeios Ltd
Open AccessReview of: "Neuro-Fuzzy-Based Adaptive Control for Autonomous Drone Flight"
1: Many of the symbols in this article are not uniform, and the format is confusing, such as p_a and p_d. 2: The description of its own controller in this paper is not sufficient, the specific controller form and parameters are not clearly described....