As a typical visual positioning system, monocular ranging is widely used in various fields. However, when the distance increases, there is a greater error. YOLOv8 network has the advantages of fast recognition speed and high accuracy. This paper proposes a method by combining YOLOv8 network recognition with a monocular ranging method to achieve target localization and grasping for the NAO robots. By establishing a visual distance error compensation model and applying it to correct the estimation results of the monocular distance measurement model, the accuracy of the NAO robot’s long-distance monocular visual positioning is improved. Additionally, a grasping control strategy based on pose interpolation is proposed. Throughout, the proposed method’s advantage in measurement accuracy was confirmed via experiments, and the grasping strategy has been implemented to accurately grasp the target object.

Conventional repetitive control (RC) with an internal model constant $Q$ less than 1 has a limited resonant bandwidth and a limited open-loop gain and then has mediocre steady-state and dynamic performance when the frequencies of reference and disturbance signals fluctuate. To solve the problem, in this article, we present a feedforward repetitive control (FRC) scheme for grid-tied inverters in microgrids to track the fundamental reference signal and suppress the harmonic signals simultaneously. The proposed FRC scheme consists of a proportional controller in parallel with a modified RC controller with a feedforward channel. Compared with conventional RC, the proposed FRC has wider resonant bandwidths and much larger open-loop gains at the frequencies of interest. Taking the feedforward odd harmonic repetitive control (FORC) as an example, the stability analysis and the detailed parameter optimization design guideline of FORC are given. Experimental results verify that the proposed FORC scheme has a better immunity to grid frequency fluctuation and a faster dynamic response when the grid frequency fluctuates.

The operating state of bearing affects the performance of rotating machinery; thus, how to accurately extract features from the original vibration signals and recognise the faulty parts as early as possible is very critical. In this study, the one‐dimensional ternary model which has been proved to be an effective statistical method in feature selection is introduced and shapelet transformation is proposed to calculate the parameter of one‐dimensional ternary model that is usually selected by trial and error. Then XGBoost is used to recognise the faults from the obtained features, and artificial bee colony algorithm (ABC) is introduced to optimise the parameters of XGBoost. Moreover, for improving the performance of intelligent algorithm, an improved strategy where the evolution is guided by the probability that the optimal solution appears in certain solution space is proposed. The experimental results based on the failure vibration signal samples show that the average accuracy of fault signal recognition can reach 97%, which is much higher than the ones corresponding to traditional extraction strategies. And with the help of improved ABC algorithm, the performance of XGBoost classifier could be optimised; the accuracy could be improved from 97.02% to 98.60% compared with the traditional classification strategy.

Dual humanoid robot collaborative control systems possess better flexibility and adaptability in complex environments due to their similar structures to humans. This paper adopts a distributed model predictive controller based on the leader–follower approach to address the collaborative transportation control issue of dual humanoid robots. In the dual-robot collaborative control system, network latency issues may arise due to unstable network conditions, affecting the consistency of dual-robot collaboration. To solve this issue, a communication protocol was constructed through socket communication for dual-robot collaborative consistency, thereby resolving the problem of consistency in dual humanoid robot collaboration. Additionally, due to the complex structure of humanoid robots, there are deficiencies in position tracking accuracy during movement. To address the poor accuracy in position tracking, this paper proposes a distributed model predictive control that considers historical cumulative error, thus enhancing the position tracking accuracy of dual-robot collaborative control.

The NAO robot integrates sensors, vision systems, and control systems. Its monocular vision system is adopted to locate the target object in the three-dimensional space of robots. Firstly, a positioning model based on monocular vision is established according to the principle of small hole perspective. Then, the position coordinates of the target center are obtained in the image coordinate system. In the model mentioned above, the relationship between position coordinates and image coordinates is established at a certain space height. According to this relationship, the two-dimensional coordinates in the image are converted into the three-dimensional coordinates in the robot coordinate system. After getting the target location, we establish the navigation map and find the optimal path under the unknown environment. Based on the simultaneous localization and the mapping (SLAM) theory, the sonar sensor of the NAO robot is used to detect the distance between the robot and the obstacles or between the robot and the end landmark. Moreover, the sonar sensor and the camera are used to distinguish the obstacle and the landmark. After the navigation map is built, the bi-directional parallel search strategy and the simulated annealing algorithm are introduced to improve the traditional artificial bee colony algorithm, and the improved artificial bee colony algorithm is proposed to find an optimal path in the navigation map. Finally, the experimental results show that based on the built environment map, the robot can find an optimal path from the origin to the landmark on the premise of avoiding obstacles.

The harmonic suppression performance of the odd-harmonic repetitive controller (ORC) will decrease when the microgrid frequency fluctuates due to power imbalance. This article presents a novel fractional order feedforward odd-harmonic repetitive controller (FO-FORC) for grid-tied inverters in microgrids. The feedforward ORC (FORC) with a feedforward channel has a much higher open-loop gain and a wider bandwidth at odd-harmonic frequencies than conventional ORC (CORC) without a feedforward channel. Therefore, the FORC can more efficiently suppress the odd harmonic of grid current while using fewer storage units. Nevertheless, the ratio of the sampling frequency of the FORC to the microgrid frequency can only be an integer, which degrades the harmonics suppression performance of the FORC with a fixed sampling frequency when the fundamental grid frequency changes in a relatively wide range. In order to settle the problem, based on a Thiran infinite impulse response (IIR) filter, this article proposes the FO-FORC with frequency adaptability to ensure that the resonance peaks of FO-FORC maintain at the real disturbance signal frequencies by online adjusting only a few coefficients of low-order IIR filter. The stability analysis, parameters design, and performance estimation are given. Comparative experiments verify the feasibility and superiority of the presented FO-FORC.