In medical and surgical scenarios, the trajectory planning of a collaborative robot arm is a difficult problem. The artificial potential field (APF) algorithm is a classic method for robot trajectory planning, which has the characteristics of good real-time performance and low computing consumption. There are many variants of the APF algorithm, among which the most widely used variants is the velocity potential field (VPF) algorithm. However, the traditional VPF algorithm has inherent defects and problems, such as easily falling into local minimum, being unable to reach the target, poor dynamic obstacle avoidance ability, and safety and efficiency problems. Therefore, this work presents the improved velocity potential field (IVPF) algorithm, which considers direction factors, obstacle velocity factor, and tangential velocity. When encountering dynamic obstacles, the IVPF algorithm can avoid obstacles better to ensure the safety of both the human and robot arm. The IVPF algorithm also does not easily fall into a local problem when encountering different obstacles. The experiments informed the RRT* algorithm, VPF algorithm, and IVPF algorithm for comparison. Compared with the informed RRT* and VPF algorithm, the result of experiments indicate that the performances of the IVPF algorithm have significant improvements when dealing with different obstacles. The main aim of this paper is to provide a safe and efficient path planning algorithm for the robot arm in the medical field. The proposed algorithm can ensure the safety of both the human and the robot arm when the medical and surgical robot arm is working, and enables the robot arm to cope with emergencies and perform tasks better. The application of the proposed algorithm could make the collaborative robots work in a flexible and safe condition, which could open up new opportunities for the future development of medical and surgical scenarios.

Thermogalvanic hydrogel, an environmentally friendly power source, enable the conversion of low-grade thermal energy to electrical energy and powers microelectronic devices in a variety of scenarios without the need for additional batteries. Its toxicity, mechanical fragility and low output performance are a hindrance to its wide application. Here, we demonstrate thermoelectric gels with safe non-toxic, recyclable, highly transparent and flexible stretchable properties by introducing gelatin as a polymer network and SO${{}_{3/4}}^{2-}$ as a redox electric pair. When the temperature difference is 10 K, the gel-based thermogalvanic cell achieves an open-circuit voltage of about 16.2 mV with a maximum short-circuit current of 39 $\mathsf{\mu }$A. Furthermore, we extended the application of the Gel-SO${{}_{3/4}}^{2-}$ gel to monitor the temperature of hot or cold food, enabling self-powered sensing for food temperature detection. This research provides a novel concept for harvesting low-grade thermal energy and achieving safe and harmless self-driven temperature monitoring.

Due to the uncertainty existing in the actual industrial environment, the rolling bearing compound fault features present coupling and complexity, which brings challenges to the compound fault feature extraction. To address this problem, this paper proposes a rolling bearing compound fault diagnosis method AMOMCKD-CNN based on adaptive multi-objective maximum correlation kurtosis deconvolution (AMOMCKD) and convolutional neural network (CNN) with parameter optimization. Firstly, the key parameters of MCKD are optimized using the adaptive Non-dominated Sorting Genetic Algorithm (NSGA-II) with a new multi-objective evaluation index Hyperarea (HA). Secondly, the optimized MCKD is used as a filter to extract the periodic pulse characteristics of the original vibration acceleration signal. Finally, the kernel size of the CNN is optimized based on the length of the filtered periodic pulse signal, which enables the CNN to achieve deeper feature extraction and classification. Experimental results from two different datasets highlight that AMOMCKD-CNN outperforms other classical diagnostic methods under the same conditions, and it is more conducive to the detection of compound faults.

Emotion recognition based on electroencephalography (EEG) signals has garnered substantial attention in recent years and finds extensive applications in the domains of medicine and psychology. However, individual differences in EEG signals pose a challenge to accurate emotion recognition and limit the widespread adoption of such techniques. To address this issue, this study proposes a model that combines random forest weights (RFWs) and four-dimensional convolutional recurrent neural network (4DCRNN) to minimize individual differences and captures emotion-relevant information. By integrating, the proposed model aims to improve the accuracy and generalization capability of emotion recognition. To evaluate the performance of the proposed model, experiments were conducted using the DEAP and SEED datasets. The results demonstrate the effectiveness of the RFW-4DCRNN in emotion recognition. Specifically, the proposed model achieves mean accuracy of 94.98% and 94.21% for Subject-dependent recognition using the DEAP and SEED datasets, respectively. For Subject-independent emotion recognition, the model achieved mean accuracy of 81.70% and 91.12% using two datasets, respectively. The result highlights the capability of the RFW-4DCRNN to effectively recognize emotions and improves generalization performance. Overall, this study presents an approach to addressing individual differences in EEG-based emotion recognition. The RFW-4DCRNN demonstrates promising results in terms of accuracy and generalization capability, offering potential for the advancement and application of emotion recognition techniques.

In current industrial production, robots have increasingly been taking the place of manual workers. With the improvements in production efficiency, accidents that involve operators occur frequently. In this study, a flexible sensor system was designed to promote the security performance of a collaborative robot. The flexible sensors, which was made by adsorbing graphene into a sponge, could accurately convert the pressure on a contact surface into a numerical signal. Ecoflex was selected as the substrate material for our sensing array so as to enable the sensors to better adapt to the sensing application scenario of the robot arm. A 3D printing mold was used to prepare the flexible substrate of the sensors, which made the positioning of each part within the sensors more accurate and ensured the unity of the sensing array. The sensing unit showed a correspondence between the input force and the output resistance that was in the range of 0–5 N. Our stability and reproducibility experiments indicated that the sensors had a good stability. In addition, a tactile acquisition system was designed to sample the tactile data from the sensor array. Our interaction experiment results showed that the proposed electronic skin could provide an efficient approach for secure human–robot interaction.

The retinal vessels in the human body are the only ones that can be observed directly by non-invasive imaging techniques. Retinal vessel morphology and structure are the important objects of concern for physicians in the early diagnosis and treatment of related diseases. The classification of retinal vessels has important guiding significance in the basic stage of diagnostic treatment. This paper proposes a novel method based on generative adversarial networks with improved U-Net, which can achieve synchronous automatic segmentation and classification of blood vessels by an end-to-end network. The proposed method avoids the dependency of the segmentation results in the multiple classification tasks. Moreover, the proposed method builds on an accurate classification of arteries and veins while also classifying arteriovenous crossings. The validity of the proposed method is evaluated on the RITE dataset: the accuracy of image comprehensive classification reaches 96.87%. The sensitivity and specificity of arteriovenous classification reach 91.78% and 97.25%. The results verify the effectiveness of the proposed method and show the competitive classification performance.