In this paper, we propose a tree trunk and obstacle detection method in a semistructured apple orchard environment based on improved YOLOv5s, with an aim to improve the real-time detection performance. The improvement includes using the K-means clustering algorithm to calculate anchor frame and adding the Squeeze-and-Excitation module and 10% pruning operation to ensure both detection accuracy and speed. Images of apple orchards in different seasons and under different light conditions are collected to better simulate the actual operating environment. The Gradient-weighted Class Activation Map technology is used to visualize the performance of YOLOv5s network with and without improvement to increase interpretability of improved network on detection accuracy. The detected tree trunk can then be used to calculate the traveling route of an orchard carrier platform, where the centroid coordinates of the identified trunk anchor are fitted by the least square method to obtain the endpoint of the next time traveling rout. The mean average precision values of the proposed model in spring, summer, autumn, and winter were 95.61%, 98.37%, 96.53%, and 89.61%, respectively. The model size of the improved model is reduced by 13.6 MB, and the accuracy and average accuracy on the test set are increased by 5.60% and 1.30%, respectively. The average detection time is 33 ms, which meets the requirements of real-time detection of an orchard carrier platform.

This article proposes a single-transmitter-controlled multiple-channel constant current outputs scheme, which can energize multiple hovering drones over the air simultaneously. As an unmanned and cost-effective solution to extend the cruising range of drones, the multiple-drone in-flight wireless charging has to deal with two key technical challenges, namely the continuous disturbance of multiple mutual inductances ( M ) caused by the hovering attitude of drones, as well as the limit of drone-side payload. Accordingly, this article adopts the multifrequency resonating compensation to establish multiple transmission channels and achieves the single-transmitter-controlled multiple-channel constant current outputs based on a communication-free multiple- M estimation method. The simulated and experimental results are both given in this article, which shows that the accuracy of the multiple- M estimation is up to 97% and the steady-state accuracy of the current output control is up to 95%. What is more, the current output control can effectively restrain the output current fluctuation of the battery load under continuous multiple- M disturbance, indicating that the proposed scheme is feasible to improve the stability and reliability of the multiple-drone in-flight wireless charging system.

This paper investigates a closed-loop brain stimulation method based on model predictive control strategy to suppress epileptic seizures. A neural mass model (NMM), exhibiting the normal and various epileptic seizures by changing physiologically meaningful parameters, is used as a black-box model of the brain. Based on system identification, an auto-regressive moving-average Volterra model is established to reveal the relationship between stimulation and neuronal responses. Then, the model predictive control strategy is implemented based the Volterra model, which can generate an optimal stimulation waveform to eliminate epileptiform waves. The computational simulation results indicate the proposed closed-loop control strategy can optimize the stimulation waveform without particular knowledge of the physiological properties of the system. The robustness of the proposed control strategy to system disturbances makes it more appropriate for future clinical application.

For the drone wireless in-flight charging system, the challenge is to keep a constant charging power under the large range of continuous fluctuation of mutual inductance ( M ), the variation of battery load ( R ), and the limited payload of drones, which has been rarely studied in previous research. To address the issue, this paper presents a primary-series and secondary-series-inductor-series-parallel-capacitor (SLSPC) high-order topology for the parity-time (PT) symmetric wireless power transfer (WPT) system, which can greatly expand the exact PT-symmetric region (constant power range) by the reduction of critical coupling coefficient in comparison with the traditional series-series topology. Besides, the constant power control scheme is proposed based on the series-SLSPC high-order topology to overcome the change of M and R . With the proposed control method, only the primary current needs to be detected, which enhances the real-time performance of the WPT system and reduces the payload of drones. Simulated and experimental results validate the expansion capability of the PT-symmetric range with the proposed series-SLSPC PT-WPT system and the feasibility of the proposed control scheme.

In this paper, a weighted-free continuous control set model predictive control (CCS-MPC) is proposed and implemented for dual three-phase permanent magnet synchronous motors (DTP-PMSMs), which can not only reduce the current harmonics, but also eliminate the impact of weighting factor adjustment, as well as reducing the computational complexity of high-dimensional optimization. Specifically, the proposed weighted-free CCS-MPC formulates predictive control as solving two positive definite quadratic programming (QP) problems separately and thus avoids the trouble of adjusting the weighting factor. More importantly, a conventional 4-D optimization problem is mathematically transformed into two separate subdimensional ones, thereby successfully reducing the computational burden of CCS-MPC schemes. In order to obtain the globally optimal voltage vector, moreover, an implicit modulator scheme is implemented by combining the control and the modulation. Lastly, the effectiveness of the proposed weighted-free CCS-MPC scheme is verified theoretically and experimentally.

Deep brain stimulation (DBS) is an effective clinical treatment for epilepsy. However, the individualized setting and adaptive adjustment of DBS parameters are still facing great challenges. This paper investigates a data-driven hardware-in-the-loop (HIL) experimental system for closed-loop brain stimulation system individualized design and validation. The unscented Kalman filter (UKF) is utilized to estimate critical parameters of neural mass model (NMM) from the electroencephalogram recordings to reconstruct individual neural activity. Based on the reconstructed NMM, we build a digital signal processor (DSP) based virtual brain platform with real time scale and biological signal level scale. Then, the corresponding hardware parts of signal amplification detection and closed-loop controller are designed to form the HIL experimental system. Based on the designed experimental system, the proportional-integral controller for different individual NMM is designed and validated, which proves the effectiveness of the experimental system. This experimental system provides a platform to explore neural activity under brain stimulation and the effects of various closed-loop stimulation paradigms.