RESUMEN
In this work, we present a method that enables a mobile robot to hand over objects to humans efficiently and safely by combining mobile navigation with visual perception. Our robotic system can map its environment in real time and locate objects to pick up. It uses advanced algorithms to grasp objects in a way that suits human preference and employs path planning and obstacle avoidance to navigate back to the human user. The robot adjusts its movements during handover by analyzing the human's posture and movements through visual sensors, ensuring a smooth and collision-free handover. Tests of our system show that it can successfully hand over various objects to humans and adapt to changes in the human's hand position, highlighting improvements in safety and versatility for robotic handovers.
RESUMEN
Terrestrial self-reconfigurable robot swarms offer adaptable solutions for various tasks. However, most existing swarms are limited to controlled indoor settings, and often compromise stability due to their freeform connections. To address these issues, we present a snail robotic swarm system inspired by land snails, tailored for unstructured environments. Our system also employs a two-mode connection mechanism, drawing from the adhesive capabilities of land snails. The free mode, mirroring a snail's natural locomotion, leverages magnet-embedded tracks for freeform mobility, thereby enhancing adaptability and efficiency. The strong mode, analogous to a snail's response to disturbance, employs a vacuum sucker with directional polymer stalks for robust adhesion. By assigning specific functions to each mode, our system achieves a balance between mobility and secure connections. Outdoor experiments demonstrate the capabilities of individual robots and the exceptional synergy within the swarm. This research advances the real-world applications of terrestrial robotic swarms in unstructured environments.
RESUMEN
This article aims to improve the deep-learning-based surface defect recognition. In actual manufacturing processes, there are issues such as data imbalance, insufficient diversity, and poor quality of augmented data in the collected image data for product defect recognition. A novel defect generation method with multiple loss functions, DG2GAN is presented in this paper. This method employs cycle consistency loss to generate defect images from a large number of defect-free images, overcoming the issue of imbalanced original training data. DJS optimized discriminator loss is introduced in the added discriminator to encourage the generation of diverse defect images. Furthermore, to maintain diversity in generated images while improving image quality, a new DG2 adversarial loss is proposed with the aim of generating high-quality and diverse images. The experiments demonstrated that DG2GAN produces defect images of higher quality and greater diversity compared with other advanced generation methods. Using the DG2GAN method to augment defect data in the CrackForest and MVTec datasets, the defect recognition accuracy increased from 86.9 to 94.6%, and the precision improved from 59.8 to 80.2%. The experimental results show that using the proposed defect generation method can obtain sample images with high quality and diversity and employ this method for data augmentation significantly enhances surface defect recognition technology.