Wheeled mobile robots are prone to longitudinal slip, lateral sideslip, and combined slip when operating on wet, soft, and unstructured terrain, which degrades localization accuracy, trajectory tracking, traction performance, and energy consumption. Based on 36 studies, this paper reviews slip modeling and state estimation, trajectory compensation, slip-ratio and traction control, multi-wheel slip coordination and torque allocation, and integrated multi-constraint control. The methods are compared in terms of technological evolution, control objectives, applicable operating conditions, validation levels, and representative experimental results. Existing studies still face challenges in model... More >

This paper reviews the OpenCV-based vision system for robotic-arm grasping across three core modules-camera calibration, image preprocessing and recognition, and binocular 3D reconstruction-together with lightweight deployment on embedded platforms. Using the calib3d module, monocular, binocular, and hand-eye calibration procedures are described, which correct lens distortion and unify coordinate frames and thereby address grasping-positioning errors. Image processing algorithms, including grayscale transformation, Gaussian and median filtering, Otsu segmentation, and feature matching, are compared for static and dynamic assembly-line scenarios. Binocular stereo matching generates disparity... More >

To address the requirements of vision-based robotic manipulators for object detection accuracy, real-time performance, and lightweight deployment, this paper reviews lightweight You Only Look Once (YOLO) object detection techniques and their applications in robotic vision. First, the main techniques, including structural lightweighting, model compression, and edge deployment, are summarized. Representative algorithms for vision-based robotic manipulators are then categorized into three groups: backbone lightweighting, local structural optimization, and model compression, with their detection performance and lightweighting characteristics analyzed. On this basis, the limitations of existing m... More >

Robot simulation provides a repeatable and risk-controlled environment for developing increasingly integrated robotic systems. Within this field, the Robot Operating System (ROS) links robot models, sensors, controllers, and algorithms through modular communication interfaces and has formed a broad ecosystem with simulators such as Gazebo, Webots, and NVIDIA Isaac Sim. Recent progress has shifted from basic rigid-body and sensor simulation toward ROS~2-based interface unification, high-fidelity perception, GPU-accelerated synthetic-data generation, and Sim-to-Real transfer. This paper reviews these advances, discusses key developments in modeling, navigation, manipulation, and sensor simulat... More >

A flexible CNC machining system is developed for panel furniture manufacturing to improve equipment adaptability and reduce non-machining time in customized production. The proposed system integrates a modular machining structure, multi-axis motion platform, automatic positioning fixtures, and a digital control system to enable flexible drilling and grooving operations. A machining path optimization strategy is introduced to reduce unnecessary tool movements. Experiments on medium-density fiberboard (MDF) panels demonstrate that the optimized method reduces machining time from 986~s to 654~s for 20 machining tasks and from 1248~s to 812~s for 25 tasks. The proposed equipment achieves a posit... More >

Digital twin (DT) technology has evolved beyond static physical mapping into a dynamic intelligence layer for smart manufacturing. We argue that three capabilities are now decisive for advancing DT production lines in complex industrial environments: data-driven quality correction through nonlinear feature learning, real-time edge vision for surface defect sensing, and deep time-series modeling for predictive maintenance. We further contend that the next inflection point lies not in individual algorithmic improvements, but in the cognitive integration of structured engineering knowledge-such as Manufacturer Knowledge Packages (MKP) and the Theory of Inventive Problem Solving (TRIZ)-with gene... More >

The integrated sensing, communication, and computing (ISCC) network, as a core direction of the sixth-generation mobile communication system, provides a key enabling technology for efficient collaboration in future intelligent networks by deeply integrating communication, sensing, and computing capabilities. However, the dynamic management and joint optimization of multi-dimensional heterogeneous resources in ISCC networks face severe challenges such as high-dimensional state spaces, tightly coupled constraints, and time-varying environments. Traditional optimization methods struggle to achieve both real-time performance and optimality. Deep reinforcement learning (DRL), with its end-to-end... More >

Wheeled mobile robots are widely used in intelligent logistics, unmanned delivery, industrial inspection, service robots, and other fields due to their simple structure, flexible mobility, and low energy consumption. However, during actual operation, robots often encounter complex operating conditions such as tire slip, model uncertainty, input saturation, and external disturbances, which can lead to reduced trajectory tracking accuracy or even system instability. In recent years, scholars in China and abroad have proposed numerous advanced control methods for the control problems of wheeled robots under different operating conditions, including sliding mode control, disturbance observer-bas... More >