Introduction: The use of surgery robotics is getting more and more important worldwide. In the present study, we propose a novel small-size six-dimensional force/torque sensor with the structure of double cross beams. This technology can be applied in robotic tele-operation systems used in minimally invasive surgery (MIS) robotic systems. Material and methods: The proposed sensor is made of duralumin which totally meets the stiffness requirement. The output voltage of the sensor will alter with the deformation of the elastic body and strain gauges. The feasibility was discussed by finite element analysis (FEA) and the coupling coefficient matrix was established with dimension reduced according to FEA. In addition, we designed a calibration platform and completed static calibration for the sensor. The methods and principles of measurements and data analysis were provided. Results: The calibration curves and coupling coefficient matrix were acquired by using the least squares method (LSM). Conclusion: Experimental tests and calibration error analysis showed that the proposed sensor has high accuracy, appropriate range, and played a role in promoting the application of force feedback technology in MIS.

Hand gesture recognition is getting more and more important in the area of rehabilitation and human machine interface (HMI). However, most current approaches are difficult to achieve practical application because of an excess of sensors. In this work, we proposed a method to recognize six common hand gestures and establish the optimal relationship between hand gesture and muscle by utilizing only two channels of surface electromyography (sEMG). We proposed an integrated approach to process the sEMG data including filtering, endpoint detection, feature extraction, and classifier. In this study, we used one-order digital lowpass infinite impulse response (IIR) filter with the cutoff frequency of 500 Hz to extract the envelope of the sEMG signals. The energy was utilized as a feature to detect the endpoint of motion. The short-time energy, zero-crossing rate and linear predictive coefficient (LPC) with 12 levels were chosen as the features and back propagation (BP) neural network was utilized to classify. In order to test the method, five subjects were involved in the experiment to test the hypothesis. With the proposed method, 96.41% to 99.70% recognition rate was obtained. The experimental results revealed that the proposed method is highly efficient both in sEMG data acquisition and hand motions recognition, and played a role in promoting hand rehabilitation and HMI.

Situational detection in the traffic system is of great significance to traffic management and even urban management. Traditional detection methods are generally based on roadside equipment monitoring roads, and it is difficult to support large-scale and fine-grained traffic incident detection. In this study, we propose a detection method applied to the mobile edge, which detects traffic incidents based on the video captured by vehicle cameras, so as to overcome the limitations of roadside terminal perception. For swarm intelligence detection, we propose an improved YOLOv5s object detection network, adding an atrous pyramid pooling layer to the network and introducing a fusion attention mechanism to improve the model accuracy. Compared with the raw YOLOv5s, the mAP metrics of our improved model are increased by 3.3% to 84.2%, enabling it to detect vehicles, pedestrians, traffic accidents, and fire traffic incidents on the road with high precision in real time. This provides information for city managers to help them grasp the abnormal operation status of roads and cities in a timely and effective manner.

This study aimed to predict and fit the nonlinear dynamic grip force of the human upper limb using surface electromyographic (sEMG) signals. The research employed a time-series-based neural network, NARX, to establish a mapping relationship between the electromyographic signals of the forearm muscle groups and dynamic grip force. Three-channel electromyographic signal acquisition equipment and a grip force sensor were used to record muscle signals and grip force data of the subjects under specific dynamic force conditions. After preprocessing the data, including outlier removal, wavelet denoising, and baseline drift correction, the NARX model was used for fitting analysis. The model compares two different training strategies: regularized stochastic gradient descent (BRSGD) and conjugate gradient (CG). The results show that the CG greatly shortened the training time, and performance did not decline. NARX demonstrated good accuracy and stability in dynamic grip force prediction, with the model with 10 layers and 20 time delays performing the best. The results demonstrate that the proposed method has potential practical significance for force control applications in smart prosthetics and virtual reality.