Skip to content
Log in
Sponsored Artificial Intelligence: A Modern Approach, Global Edition Artificial Intelligence: A Modern Approach, Global Edition

Author

Zhonggang Xiong

View on Semantic Scholar

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Open access Jul 2026

Adaptive Trajectory Tracking Control for Manipulators Based on Receding Horizon Optimization and Sliding Mode Robust Compensation

With the rapid development of modern industry, robotic manipulators are required to achieve increasingly high trajectory-tracking accuracy and robustness in practical applications. To enhance tracking performance under complex operating conditions, this paper proposes an Adaptive Model Predictive Control with Sliding-Mode Robust Compensation (AMPC–SMC) scheme that integrates an adaptive mechanism with sliding-mode control theory. First, a dynamic model of the manipulator is established, and parameter linearization is employed to transform the nonlinear dynamics into a linearly parameterized form with unknown parameters. Second, an adaptive law is derived based on Lyapunov stability theory to update the model parameters online, thereby mitigating the adverse effects of parametric perturbations and external disturbances on tracking accuracy. Building on this, a receding-horizon optimization strategy is introduced by formulating a quadratic cost function that penalizes both tracking errors and control effort, and the optimal control input is obtained by solving the resulting optimization problem. Meanwhile, a sliding-mode term is incorporated as a robust compensator to eliminate residual tracking errors. Finally, the desired trajectory is generated via point-to-point path planning in Cartesian space, and the proposed method is validated on a real six-degree-of-freedom robotic manipulator. Comparative experiments against conventional model predictive control (MPC) and traditional sliding-mode control (SMC) demonstrate that the proposed AMPC-SMC controller achieves remarkably superior tracking performance compared with the conventional MPC and SMC controllers. In terms of tracking accuracy, the mean absolute errors (MAE) of Joint 2, Joint 4 and Joint 5 under AMPC-SMC are reduced by 91.7%, 92.1% and 86.1% respectively relative to MPC, and decreased by 76.1%, 77.3% and 85.1% compared with the standalone SMC controller.

Zhonggang Xiong, Deqing Liu, Mengyi Li et al. · 0 citations
Conference Jul 2026

A YOLO V11 classification model for tomato leaf diseases and pests based on weighted convolution and gating mechanism

Aiming at the problems of insufficient modeling of local fine-grained features and strong interference from redundant background information in tomato leaf disease and pest recognition, this paper proposes an improved yolov11 classification model based on weighted convolution and gating mechanism. The proposed method embeds a weighted convolution module and a C2PSA_CGLU module into the backbone of the yolov11 classification network. The weighted convolution module adaptively enhances discriminative channel features, while the C2PSA_CGLU module dynamically suppresses redundant information through a gating mechanism. Ablation experiments and comparison experiments are conducted on a public tomato leaf disease dataset containing ten categories. Experimental results show that the proposed model achieves a top-1 accuracy of 0.9958, which is 0.64% higher than the baseline yolov11 model. Meanwhile, the computational complexity is reduced to 1.80 GFLOPs and the Fitness value reaches 0.9979. The proposed model maintains high recognition accuracy while ensuring lightweight characteristics and stable convergence, providing an effective solution for refined recognition of agricultural diseases and pests in engineering applications.

Wenqiang Hu, Zhonggang Xiong, Deqing Liu et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.