One of the key challenges in semantic segmentation for path planning of mobile robots (MR) lies in deploying effective segmentation models on embedded automatic systems with limited processing capability. This study suitably improves a Binary Neural Network (BNN)-based semantic segmentation for monocular images, with the proposed backbone being ResNet18 and incorporating an efficient decoder based on PSP-Net. In detail, by reducing processing parameter magnitudes and optimizing network propagation, the proposed method enhances training efficiency, speeds up inference, and reduces computational cost. The introduced method's outcomes outperform those of convolutional neural network (CNN) architectures, particularly with a notable 3.11-fold increase in inference velocity while maintaining an accuracy of 97.7 and mean intersection over union (mIoU) of 74.36 based on Cityscapes dataset. Moreover, BNNs facilitate the deployment of semantic segmentation models on hardware with restricted physical or resource capacities. The proposed method achieves an intersection over union (IoU) and Dice scores of 83.14 and 88.21, respectively, with throughput improvements of 1.6 to 2.5 times and latency reduced to 0.2 times the average of other models evaluated. From experimental results, the suggested Binary-SegNet framework can be well integrated in intelligent MR, especially in advancing knowledge systems for effective MR's navigation in diverse environments. Copyright 2026 Dang et al. Distributed under Creative Commons CC-BY 4.0. http://www.creativecommons.org/licenses/by/4.0/

As global industry enters the digital era, automation is becoming increasingly pervasive. Due to their superior efficiency and reliability, Permanent Magnet Synchronous Motors (PMSMs) are playing an increasingly prominent role in industrial applications. Sliding Mode Control (SMC) has emerged as a modern control strategy that is widely employed not only in PMSM drive systems, but also across broader power and industrial control domains. This technique effectively mitigates key challenges associated with PMSMs, such as nonlinear behavior and susceptibility to external disturbances, thereby enhancing the precision of speed and torque regulation. This paper provides a thorough review and evaluation of recent advancements in SMC as applied to PMSM control. It outlines the fundamentals of SMC, explores various SMC-based strategies, and introduces integrated approaches that combine SMC with optimization algorithms. Furthermore, it compares these methods, identifying their respective strengths and limitations. This paper concludes by discussing current trends and potential future developments in the application of SMC for PMSM systems.

This study investigates the impact of control-sampling frequencies on a Permanent Magnet Synchronous Motor (PMSM) driven by a Pulse Amplitude Modulation (PAM) inverter, with particular emphasis on motor current balance, core loss, and copper loss at operating speeds of 1500 rpm and 2250 rpm. Experiments were conducted at six sampling frequencies, including 0.5,1,2,3,4, and 5 kHz. By increasing the sampling frequency, core and copper losses are minimized, leading to higher efficiency. At 1500 rpm, the efficiency rose from 77.43% at 0.5 kHz to 80.77% at 5 kHz, while at 2250 rpm, it improved more significantly, increasing from 64.92% to 82.6% over the same frequency range. The higher the sampling frequency, the lower the Total Harmonic Distortion (THD) of phase currents, especially between 0.5 kHz and 1 kHz. Based on waveform inspection and Fast Fourier Transform (FFT) analysis, higher frequencies result in smoother and more balanced three-phase currents with reduced harmonic distortion. The results suggest that a frequency range of 3-4 kHz is appropriate for achieving the best balance, minimizing harmonic distortion, and facilitating superior system control. The study emphasizes the importance of controlling the sampling frequency to enhance motor losses, efficiency, and the quality of the current waveform. © 2025 IEEE.

In structured and complex environments such as warehouses, the possibility of the robots moving around is based on the existence of accurate and detailed maps. This paper proposes a concept for the integration of occupancy grid maps created by two robots consisting in a singular and detailed picture of the surroundings. One such topic is occupancy grid map which is created by each of the two robots that identify know, occupied, and unknown territory and posted on separate, relevant ROS2 topics. To have a complete picture of the environment, the map's boundary coordinates are computed, and every individual map grid is copied as a coordinate system that is then translated to the merged images. One map is used as a prominent source, but other maps are permitted to help fill voids in the primary map so that a consolidated, complete occupancy grid map is produced and distributed on ROS2 topic /merge_map. The final unified map facilitates better coordination between the robots and navigation, including better exploration within the warehouse. © 2025 IEEE.

Battery management system (BMS) technology has taken a vital part in the electrical industries, specifically in renewable energy resources, electric vehicles (EV) and mobile robots. BMS has a variety of applications, monitoring the State of Charge (SOC) and the State of Health (SOH) are discussed in this paper. A new model based on control algorithms is proposed, and battery current and voltage are involved in the process. A few of the current approaches are being mentioned but just focus on a few methods. In detail, the SOC from the Extended Kalman Filter has an accuracy almost similar to the real-time performance. Moreover, the State of Health's performance is inverse to that of the State of Charge. Besides that, all the following methods are examined in detail for the estimation and real-time performance, furthermore, estimation errors are also being carefully examined to enhance the battery accuracy. © 2025 IEEE.