Query：
学者姓名：卢宗兴
Refining：
Year
Type
Indexed by
Source
Complex
Co-
Language
Clean All
Abstract ：
The wheeled bipedal robots have great application potential in environments with a mixture of structured and unstructured terrain.However,wheeled bipedal robots have problems such as poor balance ability and low movement level on rough roads.In this paper,a novel and low-cost wheeled bipedal robot with an asymmetrical five-link mechanism is proposed,and the kinematics of the legs and the dynamics of the Wheeled Inverted Pendulum(WIP)are modeled.The primary bal-ance controller of the wheeled bipedal robot is built based on the Linear Quadratic Regulator(LQR)and the compensation method of the virtual pitch angle adjusting the Center of Mass(CoM)position,then the whole-body hybrid torque-position control is established by combining attitude and leg controllers.The stability of the robot's attitude control and motion is verified with simulations and prototype experiments,which confirm the robot's ability to pass through complex terrain and resist external interference.The feasibility and reliability of the proposed control model are verified.
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Yi Xiong , Haojie Liu , Bingxing Chen et al. Whole-Body Hybrid Torque-Position Control for Balancing with a New Wheeled Bipedal Robot [J]. | 仿生工程学报（英文版） , 2025 , 22 (2) : 626-641 . |
| MLA | Yi Xiong et al. "Whole-Body Hybrid Torque-Position Control for Balancing with a New Wheeled Bipedal Robot" . | 仿生工程学报（英文版） 22 . 2 (2025) : 626-641 . |
| APA | Yi Xiong , Haojie Liu , Bingxing Chen , Yanjie Chen , Ligang Yao , Zongxing Lu . Whole-Body Hybrid Torque-Position Control for Balancing with a New Wheeled Bipedal Robot . | 仿生工程学报（英文版） , 2025 , 22 (2) , 626-641 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Miniature robots are increasingly used in unstructured environments and require higher mobility, robustness, and multifunctionality. However, existing purely soft and rigid designs suffer from inherent defects, such as low load capacity and compliance, respectively, restricting their functionality and performance. Here, we report new soft-rigid hybrid miniature robots applying the tensegrity principle, inspired by biological organisms' remarkable multifunctionality through tensegrity micro-structures. The miniature robot's speed of 25.07 body lengths per second is advanced among published miniature robots and tensegrity robots. The design versatility is demonstrated by constructing three bio-inspired robots using miniature tensegrity joints. Due to its internal load-transfer mechanisms, the robot has self-adaptability, deformability, and high impact resistance (withstand dynamic load 143,868 times the robot weight), enabling the robot to navigate diverse barriers, pipelines, and channels. The robot can vary its stiffness to greatly improve load capacity and motion performance. We further demonstrate the potential biomedical applications, such as drug delivery, impurity removal, and remote heating achieved by integrating metal into the robot.
Keyword ：
high-speed and adaptive locomotion high-speed and adaptive locomotion tunable stiffness tunable stiffness untethered miniature tensegrity robot untethered miniature tensegrity robot
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Chen, Bingxing , He, Zhiyu , Ye, Fang et al. Untethered Miniature Tensegrity Robot with Tunable Stiffness for High-Speed and Adaptive Locomotion [J]. | SOFT ROBOTICS , 2025 . |
| MLA | Chen, Bingxing et al. "Untethered Miniature Tensegrity Robot with Tunable Stiffness for High-Speed and Adaptive Locomotion" . | SOFT ROBOTICS (2025) . |
| APA | Chen, Bingxing , He, Zhiyu , Ye, Fang , Yang, Yi , Chen, Wenhu , Ding, Fuhui et al. Untethered Miniature Tensegrity Robot with Tunable Stiffness for High-Speed and Adaptive Locomotion . | SOFT ROBOTICS , 2025 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Hand gesture recognition(HGR) is a key technology in human-computer interaction and human communication. This paper presents a lightweight, parameter-free attention convolutional neural network (LPA-CNN) approach leveraging Gramian Angular Field(GAF)transformation of A-mode ultrasound signals for HGR. First, this paper maps 1-dimensional (1D) A-mode ultrasound signals, collected from the forearm muscles of 10 healthy participants, into 2-dimensional (2D) images. Second, GAF is selected owing to its higher sensitivity against Markov Transition Field (MTF) and Recurrence Plot (RP) in HGR. Third, a novel LPA-CNN consisting of four components, i.e., a convolution-pooling block, an attention mechanism, an inverted residual block, and a classification block, is proposed. Among them, the convolution-pooling block consists of convolutional and pooling layers, the attention mechanism is applied to generate 3-D weights, the inverted residual block consists of multiple channel shuffling units, and the classification block is performed through fully connected layers. Fourth, comparative experiments were conducted on GoogLeNet, MobileNet, and LPA-CNN to validate the effectiveness of the proposed method. Experimental results show that compared to GoogLeNet and MobileNet, LPA-CNN has a smaller model size and better recognition performance, achieving a classification accuracy of 0.98 +/- 0.02. This paper achieves efficient and high-accuracy HGR by encoding A-mode ultrasound signals into 2D images and integrating the LPA-CNN model, providing a new technological approach for HGR based on ultrasonic signals.
Keyword ：
Accuracy Accuracy A-mode ultrasound A-mode ultrasound Computational modeling Computational modeling convolutional neural network (CNN) convolutional neural network (CNN) Convolutional neural networks Convolutional neural networks deep learning deep learning Encoding Encoding Gesture recognition Gesture recognition gramian angular field (GAF) gramian angular field (GAF) hand gesture recognition (HGR) hand gesture recognition (HGR) Hands Hands Image coding Image coding Muscles Muscles Time series analysis Time series analysis Ultrasonic imaging Ultrasonic imaging
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Shangguan, Qican , Lian, Yue , Liao, Zhiwei et al. A Lightweight CNN Approach for Hand Gesture Recognition via GAF Encoding of A-Mode Ultrasound Signals [J]. | IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING , 2025 , 33 : 3734-3743 . |
| MLA | Shangguan, Qican et al. "A Lightweight CNN Approach for Hand Gesture Recognition via GAF Encoding of A-Mode Ultrasound Signals" . | IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING 33 (2025) : 3734-3743 . |
| APA | Shangguan, Qican , Lian, Yue , Liao, Zhiwei , Chen, Jinshui , Song, Yiru , Yao, Ligang et al. A Lightweight CNN Approach for Hand Gesture Recognition via GAF Encoding of A-Mode Ultrasound Signals . | IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING , 2025 , 33 , 3734-3743 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
The wheeled bipedal robots have great application potential in environments with a mixture of structured and unstructured terrain. However, wheeled bipedal robots have problems such as poor balance ability and low movement level on rough roads. In this paper, a novel and low-cost wheeled bipedal robot with an asymmetrical five-link mechanism is proposed, and the kinematics of the legs and the dynamics of the Wheeled Inverted Pendulum (WIP) are modeled. The primary balance controller of the wheeled bipedal robot is built based on the Linear Quadratic Regulator (LQR) and the compensation method of the virtual pitch angle adjusting the Center of Mass (CoM) position, then the whole-body hybrid torque-position control is established by combining attitude and leg controllers. The stability of the robot's attitude control and motion is verified with simulations and prototype experiments, which confirm the robot's ability to pass through complex terrain and resist external interference. The feasibility and reliability of the proposed control model are verified.
Keyword ：
Wheeled Robots Legged Robots Motion Control Mechanism Design Wheeled Robots Legged Robots Motion Control Mechanism Design
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Xiong, Yi , Liu, Haojie , Chen, Bingxing et al. Whole-Body Hybrid Torque-Position Control for Balancing with a New Wheeled Bipedal Robot [J]. | JOURNAL OF BIONIC ENGINEERING , 2025 , 22 (2) : 626-641 . |
| MLA | Xiong, Yi et al. "Whole-Body Hybrid Torque-Position Control for Balancing with a New Wheeled Bipedal Robot" . | JOURNAL OF BIONIC ENGINEERING 22 . 2 (2025) : 626-641 . |
| APA | Xiong, Yi , Liu, Haojie , Chen, Bingxing , Chen, Yanjie , Yao, Ligang , Lu, Zongxing . Whole-Body Hybrid Torque-Position Control for Balancing with a New Wheeled Bipedal Robot . | JOURNAL OF BIONIC ENGINEERING , 2025 , 22 (2) , 626-641 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Traditional quadruped robots are known for their agile movement and versatility across varied terrains. However, their foot structures struggle to navigate unstructured terrains such as pipes, slopes, and protrusions. This paper proposes a novel tensegrity foot structure consisting of a tensegrity ankle joint and an X-shaped adaptive tensegrity footpad, which enhances the terrain adaptability of legged robots. The equilibrium equation of the ankle joint is established, and the relationship between the translational stiffness of the ankle joint and the spring stiffness is derived. Additionally, a mathematical model for the number of X-shaped tensegrity footpad units and their relationship with the deformation height and length of the tensegrity footpad is established. A physical prototype of the tensegrity foot was fabricated using 3D printing. Experiments are conducted to validate the adaptability of both the ankle joint and the tensegrity footpad. The results indicate that the proposed adaptive tensegrity foot structure exhibits good adaptability on unstructured terrains with varying radii, slopes, steps, S-curves, and spherical surfaces. The tensegrity foot structure can enhance the environmental adaptability of quadruped robots and has excellent impact resistance effects.
Keyword ：
adaptive locomotion adaptive locomotion ankle joint ankle joint quadruped robot quadruped robot shock absorption shock absorption tensegrity tensegrity
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Dong, Hui , Gan, Jiahao , Xia, Rongbiao et al. Adaptive tensegrity foot design for quadruped robots in unstructured terrains [J]. | SMART MATERIALS AND STRUCTURES , 2025 , 34 (2) . |
| MLA | Dong, Hui et al. "Adaptive tensegrity foot design for quadruped robots in unstructured terrains" . | SMART MATERIALS AND STRUCTURES 34 . 2 (2025) . |
| APA | Dong, Hui , Gan, Jiahao , Xia, Rongbiao , Lu, Zongxing , Chen, Bingxing , Chen, Muhao . Adaptive tensegrity foot design for quadruped robots in unstructured terrains . | SMART MATERIALS AND STRUCTURES , 2025 , 34 (2) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Robot learning from human demonstration pioneers an effective mapping paradigm for endowing robots with human-like operational capabilities. This paper proposes a bio-signal-guided robot adaptive stiffness learning framework grounded in the conclusion that muscle activation of the human arm is positively correlated with the endpoint stiffness. First, we propose a human-teleoperated demonstration platform enabling real-time modulation of robot end-effector stiffness by human tutors during operational tasks. Second, we develop a dual-stage probabilistic modeling architecture employing the Gaussian mixture model and Gaussian mixture regression to model the temporal-motion correlation and the motion-sEMG relationship, successively. Third, a real-world experiment was conducted to validate the effectiveness of the proposed skill transfer framework, demonstrating that the robot achieves online adaptation of Cartesian impedance characteristics in contact-rich tasks. This paper provides a simple and intuitive way to plan the Cartesian impedance parameters, transcending the classical method that requires complex human arm endpoint stiffness identification before human demonstration or compensation for the difference in human-robot operational effects after human demonstration.
Keyword ：
Gaussian mixture model (GMM) Gaussian mixture model (GMM) Gaussian mixture regression (GMR) Gaussian mixture regression (GMR) human-teleoperated demonstration human-teleoperated demonstration surface electromyogram (sEMG) surface electromyogram (sEMG) variable impedance control variable impedance control
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Xia, Wei , Liao, Zhiwei , Lu, Zongxin et al. Bio-Signal-Guided Robot Adaptive Stiffness Learning via Human-Teleoperated Demonstrations [J]. | BIOMIMETICS , 2025 , 10 (6) . |
| MLA | Xia, Wei et al. "Bio-Signal-Guided Robot Adaptive Stiffness Learning via Human-Teleoperated Demonstrations" . | BIOMIMETICS 10 . 6 (2025) . |
| APA | Xia, Wei , Liao, Zhiwei , Lu, Zongxin , Yao, Ligang . Bio-Signal-Guided Robot Adaptive Stiffness Learning via Human-Teleoperated Demonstrations . | BIOMIMETICS , 2025 , 10 (6) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Joints are the core components of robotic actuation systems. Their performance directly affects the system's dynamic characteristics. However, rigid and flexible joints both face a trade-off between environmental adaptability and response velocity due to their structural properties. A bionic tensegrity joint inspired by biological tensegrity principle is proposed. We present its structural design and stiffness model. The joint features tunable bistability, allowing synergistic optimization between adaptability and response velocity. Experiments show that the joint has negative stiffness and fast response. To validate the effectiveness of the proposed joint design, a gripper and a swimmer were developed. The gripper demonstrates a high response velocity of 56 ms while maintaining a payload capacity of up to 4 kg. Leveraging the bistable tensegrity joint, the swimmer achieves a swimming speed of 1.1 body lengths per second (BL s-1). A novel robotic design framework centered on rotational tensegrity joints has been developed, which demonstrates significant potential for agile locomotion, human-robot interaction, and adaptive manipulation.
Keyword ：
bistable characteristics bistable characteristics intelligent robot intelligent robot rotational joint rotational joint tensegrity structure tensegrity structure tunable stiffness tunable stiffness
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Ye, Fang , Huang, Jianmeng , Yu, Jianming et al. A rapid tunable stiffness bistable adaptive tensegrity joint for gripper and swimmer [J]. | SMART MATERIALS AND STRUCTURES , 2025 , 34 (9) . |
| MLA | Ye, Fang et al. "A rapid tunable stiffness bistable adaptive tensegrity joint for gripper and swimmer" . | SMART MATERIALS AND STRUCTURES 34 . 9 (2025) . |
| APA | Ye, Fang , Huang, Jianmeng , Yu, Jianming , Zhang, Jiaze , Yang, Yi , Zhang, Jie et al. A rapid tunable stiffness bistable adaptive tensegrity joint for gripper and swimmer . | SMART MATERIALS AND STRUCTURES , 2025 , 34 (9) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Due to the current focus of research on ankle rehabilitation robots on structural design, there is still limited research on ankle human-machine interaction technology. In order to enable rehabilitation robots to conduct personalized rehabilitation training based on patients' ankle movement intentions, we propose a new ankle motion recognition method based on plantar pressure. First, we designed a plantar pressure collection system based on array sensors. Then, we collected nine types of ankle joint motion pressure data from five volunteers and conducted algorithm selection, data processing, and algorithm optimization. Finally, we proposed a small sample optimization algorithm based on support vector machine, with an average recognition rate of 93.16%. The recognition method proposed in this paper can be combined with ankle rehabilitation robots to achieve active rehabilitation functions, laying the foundation for the clinical application of active rehabilitation technology.
Keyword ：
acquisition system acquisition system algorithm optimization algorithm optimization data processing data processing motion recognition motion recognition Plantar pressure Plantar pressure
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lu, Zongxing , Xu, Zhiwei , Zhao, Dongzhe et al. ANKLE JOINT MOTION RECOGNITION SYSTEM AND ALGORITHM OPTIMIZATION BASED ON PLANTAR PRESSURE [J]. | JOURNAL OF MECHANICS IN MEDICINE AND BIOLOGY , 2024 , 24 (10) . |
| MLA | Lu, Zongxing et al. "ANKLE JOINT MOTION RECOGNITION SYSTEM AND ALGORITHM OPTIMIZATION BASED ON PLANTAR PRESSURE" . | JOURNAL OF MECHANICS IN MEDICINE AND BIOLOGY 24 . 10 (2024) . |
| APA | Lu, Zongxing , Xu, Zhiwei , Zhao, Dongzhe , Yang, Tianxue . ANKLE JOINT MOTION RECOGNITION SYSTEM AND ALGORITHM OPTIMIZATION BASED ON PLANTAR PRESSURE . | JOURNAL OF MECHANICS IN MEDICINE AND BIOLOGY , 2024 , 24 (10) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
The wearable A-mode ultrasound human-machine interface technology (HMI-A) is a promising sensing modality, with many researchers achieving good results in strictly controlled experimental environments. However, the instability of A-mode ultrasound signals makes gesture recognition technology associated with HMI-A difficult to apply in practical scenarios, and the anatomical variability of the forearm is a major factor contributing to the decrease in gesture recognition performance. Additionally, long-term application can lead to forearm posture changes and probe displacement, causing signal drift. If the distribution of signal data between the training set and the test set is inconsistent, the performance of the trained model on the test set will be poor. Addressing the above issues, this article makes three contributions: 1) a thorough investigation of forearm posture changes, including pronation, supination, flexion, and extension, and their impact on HMI-A gesture recognition performance; 2) proposing an unmarked calibration algorithm based on quantitative analysis to help users reposition the forearm after long-term use; and 3) introducing a domain-adversarial neural network (DANN) to mitigate the impact of signal drift on recognition performance. Through five interval experiments with eight subjects, the long-term gesture recognition performance of the combination of repositioning and DANN methods was validated. The average recognition accuracy (RA) of each experiment increased from 58.81% +/- 3.61% to 89.17% +/- 1.72%, with one subject's RA improving by 60.2%. This study confirms the feasibility of using ultrasound sensing technology for long-term muscle tissue-related applications.
Keyword ：
Accuracy Accuracy A-mode ultrasound A-mode ultrasound domain-adversarial neural network (DANN) domain-adversarial neural network (DANN) Electrodes Electrodes Gesture recognition Gesture recognition long-term gesture recognition long-term gesture recognition Muscles Muscles Thumb Thumb Training Training transfer learning transfer learning Ultrasonic imaging Ultrasonic imaging wearable ultrasound wearable ultrasound
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Shangguan, Qican , Lian, Yue , Cai, Shaoxiong et al. DANN-Repositing Strategy for Zero Retraining Long-Term Hand Gesture Recognition Using Wearable A-Mode Ultrasound [J]. | IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT , 2024 , 73 . |
| MLA | Shangguan, Qican et al. "DANN-Repositing Strategy for Zero Retraining Long-Term Hand Gesture Recognition Using Wearable A-Mode Ultrasound" . | IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 73 (2024) . |
| APA | Shangguan, Qican , Lian, Yue , Cai, Shaoxiong , Wu, Jun , Yao, Ligang , Lu, Zongxing . DANN-Repositing Strategy for Zero Retraining Long-Term Hand Gesture Recognition Using Wearable A-Mode Ultrasound . | IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT , 2024 , 73 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
The hand gesture recognition (HGR) technology in A-mode ultrasound human-machine interface (HMI-A), based on traditional machine learning, relies on intricate feature reduction methods. Researchers need prior knowledge and multiple validations to achieve the optimal combination of features and machine learning algorithms. Furthermore, anatomical differences in the forearm muscles among different subjects prevent specific subject models from applying to unknown subjects, necessitating repetitive retraining. This increases users' time costs and limits the real-world application of HMI-A. Hence, this article presents a lightweight 1-D four-branch squeeze-to-excitation convolutional neural network (CNN) (4-branch SENet) that outperforms traditional machine learning methods in both feature extraction and gesture classification. Building upon this, a weight fine-tuning strategy using transfer learning enables rapid gesture recognition across subjects and time. Comparative analysis indicates that the freeze feature and fine-tuning fully connected (FC) layers result in an average accuracy of 96.35% +/- 3.04% and an average runtime of 4.8 +/- 0.15 s, making it 52.9% faster than subject-specific models. This method further extends the application scenarios of HMI-A in fields such as medical rehabilitation and intelligent prosthetics.
Keyword ：
A-mode ultrasound A-mode ultrasound convolutional neural network (CNN) convolutional neural network (CNN) Convolutional neural networks Convolutional neural networks deep learning deep learning Feature extraction Feature extraction Gesture recognition Gesture recognition hand gesture recognition (HGR) hand gesture recognition (HGR) human-machine interaction (HMI) human-machine interaction (HMI) Muscles Muscles Sensors Sensors transfer learning transfer learning Transfer learning Transfer learning Ultrasonic imaging Ultrasonic imaging
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lian, Yue , Lu, Zongxing , Huang, Xin et al. A Transfer Learning Strategy for Cross-Subject and Cross-Time Hand Gesture Recognition Based on A-Mode Ultrasound [J]. | IEEE SENSORS JOURNAL , 2024 , 24 (10) : 17183-17192 . |
| MLA | Lian, Yue et al. "A Transfer Learning Strategy for Cross-Subject and Cross-Time Hand Gesture Recognition Based on A-Mode Ultrasound" . | IEEE SENSORS JOURNAL 24 . 10 (2024) : 17183-17192 . |
| APA | Lian, Yue , Lu, Zongxing , Huang, Xin , Shangguan, Qican , Yao, Ligang , Huang, Jie et al. A Transfer Learning Strategy for Cross-Subject and Cross-Time Hand Gesture Recognition Based on A-Mode Ultrasound . | IEEE SENSORS JOURNAL , 2024 , 24 (10) , 17183-17192 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
