Purpose: This paper aims to present a method to improve the sensitive and low probabilities of false alarm of a manipulator in a human–robot interaction environment, which can improve the performance of the system owing to non-linear uncertainty in the model of the robot controller. Design/methodology/approach: A novel collision detection method based on adaptive residual estimation is proposed, promoting the detection accuracy of the collision of the manipulator during operation. First, a general momentum residual estimator is designed to incorporate the non-linear factors of the manipulator (e.g. joint friction, speed and acceleration) into the residual-related uncertainty of the model. Second, model parameters are estimated through gradient correction. The residual filter is used to determine the dynamic threshold, resulting in higher detection accuracy. Finally, the performance of the residual estimation scheme is evaluated by comparing the dynamic threshold with residual in real-time experiments where a single Universal Robot 5 robot end–effector collides with the obstacle. Findings: Experimental results demonstrate that the collision detection system can improve sensitivity and lead to low probabilities of false alarm of non-linear uncertainty in the model. Practical implications: The method proposed in this article can be applied to industry and human–robot interaction area. Originality/value: An adaptive collision detection method is proposed in this paper to address non-linear uncertainties of the model in industrial application.

RFID (radio-frequency identification) technology is rapidly emerging for the localization of moving objects and humans. Due to the blockage of radio signals by the human body, the localization accuracy achieved with a single tag is not satisfactory. This paper proposes a method based on an RFID tag array and laser ranging information to address the localization of live moving objects such as humans or animals. We equipped a human with a tag array and calculated the phase-based radial velocity of every tag. The laser information was, first, clustered through the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm and then laser-based radial velocity was calculated. This velocity was matched with phase-based radial velocity to get best matching clusters. A particle filter was used to localize the moving human by fusing the matching results of both velocities. Experiments were conducted by using a SCITOS G5 service robot. The results verified the feasibility of our approach and proved that our approach significantly increases localization accuracy by up to 25% compared to a single tag approach.

Exposed aggregate is a typical feature of the abrasion erosion in stilling basin slabs concrete surface. Although a variety of underwater robots are designed for inspection, the exposed aggregate detection for identifying abrasion is often done by manual work. The scarcity of image samples, large differences in aggregate size, color and shape are the main difficulties in automatic detection. To address this problem, an improved Attention U-Net deep fully convolutional network-based detection method was proposed. To realize this method, underwater images in site were captured via a self-developed operated underwater robot. Through randomly separating and the cropping of the 128 underwater images, the 512×512 pixels images dataset was built according to the ratio of 8:1:1, including 408 training images, 52 validation images and 52 test images. After the data augmentation, loss function and the optimizer were carefully designed and selected, the proposed Attention U-Net architecture was evaluated on this dataset. For comparative research, the full convolution network (FCN) and U-Net network were trained with the same training and validation dataset. The performance comparison on the test dataset showed that the Attention U-Net architecture has better detection accuracy.

The essence of Chinese calligraphy inheritance resides in calligraphy education. However, it encounters challenges such as a scarcity of calligraphy instructors, time-consuming and inefficient manual assessment methods, and inconsistent evaluation criteria. In response to these challenges, this paper introduces a deep learning-based automatic calligraphy evaluation model. Initially, hard-pen handwriting samples from 100 volunteers were collected and preprocessed to create a dataset consisting of 4800 samples, along with the corresponding label files for hard-pen calligraphy evaluation. Subsequently, YOLOv5 was utilized for region detection and character recognition on the evaluation samples to obtain the corresponding standard samples. Lastly, a Siamese metric model, with VGG16 as the primary feature extraction submodule, was developed for hard-pen calligraphy evaluation. To improve feature extraction and propagation, a transformer structure was introduced to extract global information from both the evaluated and standard samples, thereby optimizing the evaluation results. Experimental results demonstrate that the proposed model achieves a precision of 0.75, recall of 0.833, and mAP of 0.990 on the hard-pen calligraphy evaluation dataset, effectively realizing automatic calligraphy evaluation. This model presents a novel approach for intelligently assessing hard-pen calligraphy.

Take the handstand-stabilization-control problem of cart-double-pendulum system (CDPS) as an example, this paper detailed a general control parameters optimization and system implementation method for human-simulated intelligent controller. Firstly, the physical and dynamic models of CDPS were analyzed, and then the research platform for the controller of CDPS is also built. Next, the parameters optimization method based on improved genetic algorithm (IGA) for human-simulated controller was introduced in detail, and the effectiveness of parameters optimization method was testified by simulation and experiments. In the end, the conclusion is summarized