Keyou Guo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Keyou Guo has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Caili Wei
School of Artificial Intelligence, Beijing Technology and Business University, Beijing 100048, China
2 shared publications - Chengbo He
School of Artificial Intelligence, Beijing Technology and Business University, Beijing 100048, China
2 shared publications - Peipeng Shi
School of Artificial Intelligence, Beijing Technology and Business University, Beijing 100048, China
2 shared publications - Pengshuo Wang
School of Artificial Intelligence, Beijing Technology and Business University, Beijing 100048, China
2 shared publications - Chunyu Zhang
Beijing University of Aeronautics & Astronautics, School of Economics and Business Management, China, Beijing 100191, No. 37 Xueyuan Rd., Haidian District
1 shared publication - Gang Li
School of Computer and Artificial Intelligence, Beijing Technology and Business University, Beijing 100048, China
1 shared publication
Latest Publications
- Open Access
Fuzzy Disturbance Observer-Based Adaptive Nonsingular Terminal Sliding Mode Control for Multi-Joint Robotic Manipulators
This study proposes a novel fuzzy disturbance observer (FDO)-augmented adaptive nonsingular terminal sliding mode control (NTSMC) framework for multi-joint robotic manipulators, addressing critical challenges in trajectory tracking precision and disturbance rejection. Unlike conventional disturbance observers requiring prior knowledge of disturbance bounds, the proposed FDO leverages fuzzy logic principles to dynamically estimate composite disturbances—including unmodeled dynamics, parameter perturbations, and external torque variations—without restrictive assumptions about disturbance derivatives. The control architecture achieves rapid finite-time convergence by integrating the FDO with a singularity-free terminal sliding manifold and an adaptive exponential reaching law while significantly suppressing chattering effects. Rigorous Lyapunov stability analysis confirms the uniform ultimate boundedness of tracking errors and disturbance estimation residuals. Comparative simulations on a 2-DOF robotic arm demonstrate a 97.28% reduction in root mean square tracking errors compared to PD-based alternatives and a 73.73% improvement over a nonlinear disturbance observer-enhanced NTSMC. Experimental validation on a physical three-joint manipulator platform reveals that the proposed method reduces torque oscillations by 58% under step-type disturbances while maintaining sub-millimeter tracking accuracy. The framework eliminates reliance on exact system models, offering a generalized solution for industrial manipulators operating under complex dynamic uncertainties.
Open AccessFuzzy Disturbance Observer-Based Adaptive Nonsingular Terminal Sliding Mode Control for Multi-Joint Robotic Manipulators
This study proposes a novel fuzzy disturbance observer (FDO)-augmented adaptive nonsingular terminal sliding mode control (NTSMC) framework for multi-joint robotic manipulators, addressing critical challenges in trajectory tracking precision and disturbance rejection. Unlike conventional disturbance observers requiring prior knowledge of disturbance bounds, the proposed FDO leverages fuzzy logic principles to dynamically estimate composite disturbances—including unmodeled dynamics, parameter perturbations, and external torque variations—without restrictive assumptions about disturbance derivatives. The control architecture achieves rapid finite-time convergence by integrating the FDO with a singularity-free terminal sliding manifold and an adaptive exponential reaching law while significantly suppressing chattering effects. Rigorous Lyapunov stability analysis confirms the uniform ultimate boundedness of tracking errors and disturbance estimation residuals. Comparative simulations on a 2-DOF robotic arm demonstrate a 97.28% reduction in root mean square tracking errors compared to PD-based alternatives and a 73.73% improvement over a nonlinear disturbance observer-enhanced NTSMC. Experimental validation on a physical three-joint manipulator platform reveals that the proposed method reduces torque oscillations by 58% under step-type disturbances while maintaining sub-millimeter tracking accuracy. The framework eliminates reliance on exact system models, offering a generalized solution for industrial manipulators operating under complex dynamic uncertainties.
- Open Access
The Design and Validation of a High-Precision Angular Vibration Calibration System Based on a Laser Vibrometer
This paper presents the design and validation of a high-precision angular vibration calibration system based on a laser vibrometer, aimed at meeting the high-precision requirements for measuring small angular vibrations. The system primarily consists of a self-driving angular vibration platform and a laser vibrometer. The platform is isolated from ground interference via an air-floating platform and uses a split-type motor to control the platform, generating specific angular vibrations. Detailed simulations of the platform’s modal characteristics and the stability of the spring plates were conducted using the finite element analysis software ANSYS 11. Moreover, fundamental frequency testing and measurement accuracy testing were conducted on the system. Experimental results demonstrate that the system has a fundamental frequency of 2.69 Hz and a maximum measurement error of 0.00172″, confirming the system’s effectiveness in dynamic characteristics, stability, and measurement accuracy. This research provides essential technical support for high-precision angular vibration control in spacecraft.
Open AccessThe Design and Validation of a High-Precision Angular Vibration Calibration System Based on a Laser Vibrometer
This paper presents the design and validation of a high-precision angular vibration calibration system based on a laser vibrometer, aimed at meeting the high-precision requirements for measuring small angular vibrations. The system primarily consists of a self-driving angular vibration platform and a laser vibrometer. The platform is isolated from ground interference via an air-floating platform and uses a split-type motor to control the platform, generating specific angular vibrations. Detailed simulations of the platform’s modal characteristics and the stability of the spring plates were conducted using the finite element analysis software ANSYS 11. Moreover, fundamental frequency testing and measurement accuracy testing were conducted on the system. Experimental results demonstrate that the system has a fundamental frequency of 2.69 Hz and a maximum measurement error of 0.00172″, confirming the system’s effectiveness in dynamic characteristics, stability, and measurement accuracy. This research provides essential technical support for high-precision angular vibration control in spacecraft.
- Open Access
- 16 August 2024
- Published by MDPI AG in Electronics
- Vol. 13 (16) , 3252
A Novel Ant Colony Algorithm for Optimizing 3D Printing Paths
The advancement of 3D printing technology has enabled the fabrication of intricate structures, yet the complexity of the print head’s motion path significantly hampers production efficiency. Addressing the challenges posed by the dataset of section points in 3D-printed workpieces, this study introduces an innovative ant colony optimization algorithm tailored to enhance the print head’s trajectory. By framing the optimization of the motion path as a Traveling Salesman Problem (TSP), the research employs a custom-designed K-means clustering algorithm to categorize the dataset into distinct clusters. This clustering algorithm partitions each printing point into different subsets based on density, optimizes these subsets through improved K-means clustering computations, and then aggregates the results to classify the entire dataset. Subsequently, the ant colony algorithm arranges the printing sequence of these clusters based on the cluster centers, followed by computing the shortest path within each cluster. To form a cohesive motion trajectory, the nearest nodes between adjacent clusters are linked, culminating in a globally optimal solution. Comparative experiments repeatedly demonstrate significant enhancements in the print head’s motion path, leading to marked improvements in printing efficiency.
- 16 August 2024
- Published by MDPI AG in Electronics
- Vol. 13 (16) , 3252
Open AccessA Novel Ant Colony Algorithm for Optimizing 3D Printing Paths
The advancement of 3D printing technology has enabled the fabrication of intricate structures, yet the complexity of the print head’s motion path significantly hampers production efficiency. Addressing the challenges posed by the dataset of section points in 3D-printed workpieces, this study introduces an innovative ant colony optimization algorithm tailored to enhance the print head’s trajectory. By framing the optimization of the motion path as a Traveling Salesman Problem (TSP), the research employs a custom-designed K-means clustering algorithm to categorize the dataset into distinct clusters. This clustering algorithm partitions each printing point into different subsets based on density, optimizes these subsets through improved K-means clustering computations, and then aggregates the results to classify the entire dataset. Subsequently, the ant colony algorithm arranges the printing sequence of these clusters based on the cluster centers, followed by computing the shortest path within each cluster. To form a cohesive motion trajectory, the nearest nodes between adjacent clusters are linked, culminating in a globally optimal solution. Comparative experiments repeatedly demonstrate significant enhancements in the print head’s motion path, leading to marked improvements in printing efficiency.
- Open Access
- 8 February 2023
- Published by MDPI AG in Electronics
- Vol. 12 (4) , 849
Non-Singular Terminal Sliding Mode Controller with Nonlinear Disturbance Observer for Robotic Manipulator
Aiming at the problems of model uncertainties and other external interference in trajectory tracking control of n-degree of freedom manipulators, a non-singular terminal sliding mode controller with nonlinear disturbance observer (NDO–NTSMC) trajectory tracking method is proposed. A nonlinear disturbance observer (NDO) is designed to forecast and compensate the system external interference, and a nonlinear gain is designed to make the observer error achieve the expected exponential convergence rate so that the feedforward compensation control is realized. Then, a non-singular terminal sliding mode controller (NTSMC) built on nonlinear sliding surface is designed to surmount the singularity fault of classic terminal sliding mode controller (TSMC). Therefore, the time required from any initial state to reach the equilibrium point is finite. In addition, the redesign of the sliding surface ensures the tracking accuracy rate of uncertain systems. Then, based on Lyapunov principle, we complete the stability analysis. Finally, the method is applied to a 2-DOF robotic manipulator model compared with other methods. In the simulation, the manipulator needs to track a continuous trajectory under the condition of joint friction disturbance. The simulation result shows that the torque output of the designed method is chattering-free and smooth, and the tracking effect is precise. Simulation results indicate that the proposed controller has the advantages of excellent tracking performance, strong robustness, and a fast response.
- 8 February 2023
- Published by MDPI AG in Electronics
- Vol. 12 (4) , 849
Open AccessNon-Singular Terminal Sliding Mode Controller with Nonlinear Disturbance Observer for Robotic Manipulator
Aiming at the problems of model uncertainties and other external interference in trajectory tracking control of n-degree of freedom manipulators, a non-singular terminal sliding mode controller with nonlinear disturbance observer (NDO–NTSMC) trajectory tracking method is proposed. A nonlinear disturbance observer (NDO) is designed to forecast and compensate the system external interference, and a nonlinear gain is designed to make the observer error achieve the expected exponential convergence rate so that the feedforward compensation control is realized. Then, a non-singular terminal sliding mode controller (NTSMC) built on nonlinear sliding surface is designed to surmount the singularity fault of classic terminal sliding mode controller (TSMC). Therefore, the time required from any initial state to reach the equilibrium point is finite. In addition, the redesign of the sliding surface ensures the tracking accuracy rate of uncertain systems. Then, based on Lyapunov principle, we complete the stability analysis. Finally, the method is applied to a 2-DOF robotic manipulator model compared with other methods. In the simulation, the manipulator needs to track a continuous trajectory under the condition of joint friction disturbance. The simulation result shows that the torque output of the designed method is chattering-free and smooth, and the tracking effect is precise. Simulation results indicate that the proposed controller has the advantages of excellent tracking performance, strong robustness, and a fast response.
- Open Access
- 28 January 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (3) , 1647
A New Partitioned Spatial–Temporal Graph Attention Convolution Network for Human Motion Recognition
At present, human action recognition can be used in all walks of life, because the skeleton can transmit intuitive information without being affected by environmental factors. However, it only focuses on local information. In order to solve these problems, we introduce a neural network model for human body recognition in this paper. We propose a model named NEW-STGCN-CA. The model is based on a spatial–temporal graph convolution network (ST-GCN), which contains a new partition strategy and coordination attention (CA) mechanism. By integrating the CA attention mechanism model, we enable the network to focus on input-related information, ignore unnecessary information, and prevent information loss. Second, a new partitioning strategy is proposed for the sampled regions, which is used to enhance the connection between local information and global information. We proved that the Top-1 accuracy of the NEW-STGCN-CA model in the NTU-RGB+D 60 dataset reached 84.86%, which was 1.7% higher than the original model; the accuracy of Top-1 on the Kinetics-Skeleton dataset reached 32.40%, which was 3.17% higher than the original model. The experimental results show that NEW-STGCN-CA can effectively improve the algorithm’s accuracy while also having high robustness and performance.
- 28 January 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (3) , 1647
Open AccessA New Partitioned Spatial–Temporal Graph Attention Convolution Network for Human Motion Recognition
At present, human action recognition can be used in all walks of life, because the skeleton can transmit intuitive information without being affected by environmental factors. However, it only focuses on local information. In order to solve these problems, we introduce a neural network model for human body recognition in this paper. We propose a model named NEW-STGCN-CA. The model is based on a spatial–temporal graph convolution network (ST-GCN), which contains a new partition strategy and coordination attention (CA) mechanism. By integrating the CA attention mechanism model, we enable the network to focus on input-related information, ignore unnecessary information, and prevent information loss. Second, a new partitioning strategy is proposed for the sampled regions, which is used to enhance the connection between local information and global information. We proved that the Top-1 accuracy of the NEW-STGCN-CA model in the NTU-RGB+D 60 dataset reached 84.86%, which was 1.7% higher than the original model; the accuracy of Top-1 on the Kinetics-Skeleton dataset reached 32.40%, which was 3.17% higher than the original model. The experimental results show that NEW-STGCN-CA can effectively improve the algorithm’s accuracy while also having high robustness and performance.
- 16 September 2018
- Published by Springer Nature
- p. 463-473
Research on Evaluation Model of Danger Degree in Driving
- 16 September 2018
- Published by Springer Nature
- p. 463-473
Research on Evaluation Model of Danger Degree in Driving
- 23 July 2012
- Published by American Society of Civil Engineers (ASCE)
- p. 2407-2414
A Fast Video Mosaic Algorithm Based on Optimal Homography Matrix
Mosaic technology is widely used in traffic surveillance. In this paper, we propose a fast video mosaic algorithm based on optimal homography matrix. First, we extract characteristic feature points using SURF method. Second, we match corresponding feature points using NN (Nearest Neighbor) and RANSAC (Random Sample Consensus) method. Third, we calculate the optimal homography matrix using the normalized covariance correlation of the overlapped area between corresponding video frames. Lastly, we obtain the mosaic video image using the optimal homography matrix. Experiments in traffic video surveillance show that our algorithm can meet the needs of real-time requirements with processing speed per frame about 40 ms in average. It is more robust, has higher accuracy, has lower computational complexity, and has faster operational speed. So, it has value in both theoretical research and practical application.
- 23 July 2012
- Published by American Society of Civil Engineers (ASCE)
- p. 2407-2414
A Fast Video Mosaic Algorithm Based on Optimal Homography Matrix
Mosaic technology is widely used in traffic surveillance. In this paper, we propose a fast video mosaic algorithm based on optimal homography matrix. First, we extract characteristic feature points using SURF method. Second, we match corresponding feature points using NN (Nearest Neighbor) and RANSAC (Random Sample Consensus) method. Third, we calculate the optimal homography matrix using the normalized covariance correlation of the overlapped area between corresponding video frames. Lastly, we obtain the mosaic video image using the optimal homography matrix. Experiments in traffic video surveillance show that our algorithm can meet the needs of real-time requirements with processing speed per frame about 40 ms in average. It is more robust, has higher accuracy, has lower computational complexity, and has faster operational speed. So, it has value in both theoretical research and practical application.