In this paper, a vision-based method is proposed for cable installation tasks in constrained environments. The main challenge of such tasks lies in the potential interference between the cable and surrounding obstacles. Model-based approaches are not well-suited for these industrial scenarios due to variations in the physical properties of workpieces. To address this, the proposed method integrates a potential field-based tip trajectory regulation with a shape deformation servo. In the shape deformation servo, a planner is employed to determine a feasible shape curve that avoids obstacles. This step is crucial, as an infeasible reference for shape control may result in unstable behavior. The effectiveness of the proposed method is validated through experiments. Notably, this approach does not rely on prior model information, making it highly adaptable for industrial deployment.

Industrial part reorientation remains a critical challenge in automated manufacturing workflows, particularly with parallel-jaw grippers lacking the dexterity for complex manipulations. This paper presents a systematic flipping strategy for structured environments. A quasi-static force equilibrium model is developed to characterize multi-contact manipulation systems, and stability criteria are derived through wrench space analysis, enabling A*-based optimal trajectory generation within the derived stable configuration space. To ensure persistent fingertip-object contact, adaptive impedance control dynamically adjusts gripper stiffness based on real-time force thresholds, preventing unintended detachment. Experimental validation demonstrates robust performance in two representative scenarios:1) cube flipping on a compliant surface(84.3g, 90% success over 50 trials), 2) vision-free continuous pivoting of an irregular part on a rigid substrate(56g, 88% success over 50 trials). The methodology requires neither environmental modification nor expensive tactile sensing, showing promise for practical deployment in structured manufacturing systems.

In recent years, tactile sensors have become essential for robotic systems, particularly in tasks requiring high-precision interaction and manipulation. The Vision-Based Tactile Sensor (VBTS) represents a significant advancement in tactile sensing, utilizing cameras to monitor the deformation of soft materials at the sensor tip. Pressure applied to the sensor alters the light propagation path, thereby changing the image captured by the camera. By combining image processing and deep learning, VBTS provides highly accurate estimates of contact position and force, achieving micrometer-level resolution. This paper presents a novel VBTS design that leverages a light-conductive plate and a silicone membrane to enhance the sensor’s sensitivity to force perception. The soft, thin nature of the silicone membrane allows for precise detection of minimal forces, making it suitable for tasks involving highly deformable objects. Experimental results demonstrate the sensor’s capability in detecting contact areas and force distributions, which can be applied in diverse domains such as soft object assembly, medical assistance, and food processing. Moreover, the proposed VBTS outperforms traditional sensors by utilizing computationally efficient algorithms that maintain real-time performance without compromising resolution.

In aeroengine maintenance, endoscopic imaging serves as a crucial tool for detecting blade defects and evolves toward intelligence driven by computer vision technology. Currently, supervised-learning-based defect segmentation methods mainly rely on extensive pixel-level annotations, making it laborious and time consuming. This article shifts focus to the abundant unlabeled data in real-world scenarios and introduces an innovative semisupervised defect segmentation method termed SAIT. Within this framework, three parallel self-supervised mechanisms are adeptly integrated with a semisupervised framework, aiming to bolster defect semantic segmentation with limited labeled samples. In the initial phase, by leveraging the capability of the vision transformer to dissect images into patches, four stochastic distortions are seamlessly infused into the patch sequence. Subsequently, three self-supervised tasks from image level to pixel level are achieved through a customized joint objective function paired with a tailored backbone network. In the second phase, SAIT undergoes pixel-level fine-tuning via the proposed class-centric loss, mitigating class imbalances in limited sample sizes and enhancing initial training. Experiments on a proprietary dataset demonstrate that SAIT achieved 78.42% and 86.70% in mean intersection over union and mean pixel accuracy metrics, respectively, with 25% labeled data, significantly improving the performance of existing semisupervised defect segmentation techniques. Meanwhile, experiments on the open-source dataset further indicate that SAIT holds promise for application in other industrial sectors beyond aeroengine inspection.

Vehicular edge computing (VEC) is a promising paradigm to satisfy the ever-growing computing demands by offloading computation tasks to vehicles equipped with computing servers. One of the major challenges in VEC system is the highly dynamic and uncertain moving route of vehicular servers. In order to address this challenge, a particular kind of vehicles (i.e., buses) is adopted as moving servers with the pre-designated route and timetable. On this basis, a fluctuation-aware learningbased computation offloading (FALCO) algorithm based on multi-armed bandit (MAB) theory is proposed. Specifically, base stations (BSs) are regarded as agents to learn the state of moving server so as to construct a stable observation set in the dynamic vehicular environment. In addition, the softmax function is applied to indicate the probability for each decision, which provides more flexible policies for obtaining better results. Simulation results demonstrate that our proposed FALCO algorithm can improve delay performance compared with the other existing learning algorithms.