Search results

Traditional visual simultaneous localization and mapping (SLAM) systems are primarily based on the assumption that the environment is static, which makes them struggle with the interference caused by dynamic objects in complex industrial production environments. This paper aims to improve the stability of visual SLAM in complex dynamic environments through semantic segmentation and its optimization.

This paper proposes a real-time visual SLAM system for complex dynamic environments based on YOLOv5s semantic segmentation, named YLS-SLAM. The system combines semantic segmentation results and the boundary semantic enhancement algorithm. By recognizing and completing the semantic masks of dynamic objects from coarse to fine, it effectively eliminates the interference of dynamic feature points on the pose estimation and enhances the retention and extraction of prominent features in the background, thereby achieving stable operation of the system in complex dynamic environments.

Experiments on the Technische Universität München and Bonn data sets show that, under monocular and Red, Green, Blue - Depth modes, the localization accuracy of YLS-SLAM is significantly better than existing advanced dynamic SLAM methods, effectively improving the robustness of visual SLAM. Additionally, the authors also conducted tests using a monocular camera in a real industrial production environment, successfully validating its effectiveness and application potential in complex dynamic environment.

This paper combines semantic segmentation algorithms with boundary semantic enhancement algorithms to effectively achieve precise removal of dynamic objects and their edges, while ensuring the system's real-time performance, offering significant application value.

When handling small-sized shafts and holes, achieving optimal safety, size compatibility and shape adaptability using rigid grippers presents significant problems. Recent advancements have introduced soft end-effectors that offer enhanced safety and adaptability for gripping parts. However, these soft end-effectors often struggle to maintain the necessary gripping positional accuracy. The purpose of this paper is to design a soft end-effector specifically engineered to address these problems, combining precise gripping capabilities with improved safety, positional accuracy and adaptability to the size and shape of fragile, small-sized components.

A soft finger with multilayer decreasing drive air chambers is designed to achieve the finger bending increasing from the root to the tip of the finger to improve the flexibility of the fingertip. Additionally, a three-finger self-centering configuration is employed, coupled with an expandable structure to increase the gripping range. Furthermore, a theoretical mathematical model of the finger is established. The physical prototype is manufactured and subjected to experimental testing, including gripping tests on small-sized, fragile shaft holes, to validate its operational performance.

The grasping experiments confirm that the designed end-effector can maintain coaxial positioning and meet adaptability requirements when handling fragile components with small-sized shaft holes. Furthermore, the addition of expanding palm structure increases the gripping attitude and enriches the application scene and gripping space.

The design of multilayer decreasing air chamber structure to solve the problem of poor gripping stability and low positional accuracy of soft manipulator; the expandable palm design is introduced to enhance gripping space; and solved the problem of gripping accuracy in the assembly of fragile parts with small-size shafts and holes.