International Journal of Humanoid Robotics

This work is to explore the application of intelligent algorithms based on deep learning in human–computer interaction systems, hoping to promote the development of human–computer interaction systems in the field of behavior recognition. Firstly, the design scheme of the human–computer interaction system is presented, and the establishment of the robot visual positioning system is emphasized. Then, the fast-region convolutional neural networks (fast-RCNN) algorithm is introduced, and it is combined with deep convolutional residual network (ResNet101). A candidate region extraction algorithm based on ResNet and long short-term memory network is proposed, and a residual network (ResNet) for spatial context memory is proposed. Both algorithms are employed in human–computer interaction systems. Finally, the performance of the algorithm and the human–computer interaction system are analyzed and characterized. The results show that the proposed candidate region extraction algorithm can significantly reduce the loss value of training set and test set after training. In addition, the corresponding accuracy, recall, and F-value of the model are all above 0.98, which proves that the model has a good detection accuracy. Spatial context memory ResNet shows good accuracy in speech expression detection. The detection accuracy of single attribute, double attribute, and multi-attribute speech expression is above 89%, and the detection accuracy is good. In summary, the human–computer interaction system shows good performance in capturing target objects, even for unlabeled objects, the corresponding grasping success rate is 95%. Therefore, this work provides a theoretical basis and reference for the application of intelligent optimization algorithm in human–computer interaction system.

Today, with the rapid development of science and technology, the value of education is more and more valued by people, but the research and development of quality education in film and television are still relatively traditional. The objective is to explore the application and effect of the combination of artificial intelligence and deep learning algorithm in the quality education of youth film and television. In view of the current problems in the quality education of film and television, this work innovatively introduces the augmented reality (AR) technology, and applies artificial intelligence and AR technology to the quality education of film and television for young people. At the same time, a deep learning algorithm is introduced to build a youth film and television quality education system based on artificial intelligence combined with deep learning, and further empirical analysis of the system is carried out in the form of a questionnaire survey. The questionnaire survey shows that, from the perspective of various dimensions of learning attitude, the two groups of learners had significant differences in emotional experience and self-cognition ($P<0.05$), and more than 90% of the teenagers thought the system resource interface was beautiful; from the perspective of the perceived usefulness of the system, 68.24% of the teenagers believe that the system is easy to operate and useful, and as many as 82.82% of the teenagers believe that the system improves their interest in learning about quality education courses in film and television. Therefore, it is found that the constructed system can improve the learning interest of young people in the quality education course of film and television and make their learning attitude more positive, providing experimental reference for the latter research in the field of youth education.

The present work aims to promote the development of intelligent image processing technology for badminton robots and optimize the application effect of badminton robots in national fitness. Firstly, the problems and common needs of the badminton robot currently in use are investigated. Secondly, a shuttlecock aerodynamic model is established to simulate the effects of air resistance and gravity on the aerial flight of shuttlecock. Besides, the convolution neural network (CNN) is combined with traditional image processing technology to denoise and recognize the collected shuttlecock images. Finally, the badminton robot vision system is constructed and its performance is tested. The results demonstrate that the image denoising method based on CNN and the traditional image processing method can effectively process and denoise the captured moving image. Under the noise level of $\sigma =25$, the peak signal-to-noise ratio index of this method is better than the Gaussian Scale Model, k-Singular Value Decomposition, and Color Names methods, slightly better than that of the Multilayer Perceptron (MLP) network. In terms of the time consumed in processing the same number of pictures, the method reported here takes the least time. But when $\sigma >50$, the MLP method has a better denoising effect because the noise is overlarge and the features are not easy to learn. Moreover, the detection accuracy of the optimized Single Shot MultiBox Detector (SSD) method adopted here is 79.0%. This accuracy is 1.7% higher than that of the traditional SSD method, and 2.3% higher than that of Faster Region-Convolutional Neural Network based on Region Proposal Network. The optimized network structure reported here provides a certain idea for the software design of the badminton robot.

With the rapid development of artificial intelligence, the related technologies and applications that accompany it emerge as the times require. The industry based on artificial intelligence is booming. Image recognition and target tracking technology are widely used in various fields, especially in the fields of security monitoring and augmented reality. Combined with the characteristics of athletes’ sports, an auxiliary information system is developed to supervise and guide the training in real time. It can track and analyze the characteristics of individual athletes’ sports function, the arrangement of coaches’ training plan, the state of brain function, the index of routine physiology and biochemistry, nutrition regulation, and the condition of injuries and injuries in the middle of the day, so as to reveal the athletes’ training in the middle of the day the changing rule of various indexes in the training state. Based on the mobile artificial intelligence terminal technology, this paper develops and designs a monitoring system for athletes’ training process in C/S mode. GPS is used to obtain athletes’ position information in real time and provide real-time guidance for athletes.

The purpose is to improve the application of museum robots in museum scenes, enhance the service capabilities of robots in museums, break tourists’ boring concepts of museum environment, manual explanation, services, etc., and promote tourists’ exhibition experience. A method for sentiment analysis of humanoid robots in museums is proposed by studying the transformation of museums with the help of artificial intelligence (AI) technology, as well as the function and significance of museums in history education. First, the function of museums in history education and the role of AI in constructing intelligent museums are described. Second, on account of the multimodal sentiment analysis method of speech and emotion, a scenario model of the visitor museum is established. An uncertain reasoning method for robot service tasks based on Multi-entity Bayesian network (MEBN) is also proposed. Finally, the proposed model is validated by experiments. The results show that compared with the recognition rates of Arousal and Valence dimensions, the consistency correlation coefficient value of the Kalman filter is higher. The Consistency Correlation Coefficient (CCC) value of the Arousal dimension is 0.703, and the CCC value of the Valence dimension is 0.766. Besides, in different tour times, the proportion of services that tourists want to be provided with varies in different emotional states. From time t1 to time t2, the proportion of tourists who want to hear explanations of cultural relics dropped by 11.5%, while the proportion of tourists who want to be provided with tea service increased by 24%. This indicates that when the Kalman filter algorithm performs continuous emotion recognition of a multimodal fusion, the final emotion recognition accuracy is higher, and emotion analysis can help humanoid robots to be more intelligent and humanized. The proposed sentiment analysis based on the multimodal analysis and MEBN’s uncertainty reasoning method for robot service tasks not only broadens the practical application field of intelligent robots under human–computer interaction technology but also has important research significance for the innovative education development of museum history education.

Robots are now working outside of industrial fences more and more closely with humans. Safety is the primary requirement for intimate human–robot interactions. Contacts could happen at any and multipoints of robot. Tactile sensors have great potentials for contact sensing. However, their implementation for the whole-body compliance of robots upon unknown contacts is still challenging. In this work, a systematic solution is proposed. A dual-arm humanoid platform is constructed with distributed tactile sensors on its arms and body. Cheap and easy accessed resistive flexible tactile sensors are used. A data collection and signal processing system is developed for the sensing system with scalable capabilities. External contacts on the robot can be monitored by a visualized system. The multipoint contact force is calculated with the sensor positions taken into consideration. A PD controller-based compliant force control algorithm is proposed in the joint space of the robot. Particularly, a geometry-based force propagation method is introduced in order to achieve overall whole-body compliance of the robot. Experiments verified the whole-body compliance of the robot arms. Safety could then be maintained for frequent human–robot interactions.