16775 research outputs found
Sort by
Safety-optimized Strategy for Grasp Detection in High-clutter Scenarios
Get PDFThe detection accuracy and speed of grasp detection models on benchmarks are the focal points of concern in the robotic grasping community. Especially in a collaborative robot setting, the safety of the model is an essential aspect that cannot be overlooked. In this paper, we explore how to enhance the safety of grasp detection models in autonomous vision-guided grasping. Specifically, we propose a simple yet practical Safety-optimized Strategy, which consists of two parts. The first part involves depth prioritization, optimizing the grasp sequence from top to bottom based on the order of depth values, which can mitigate the issue of grasp collisions that may arise when the depth value of the object with the highest grasp quality is significantly higher than that of other objects in high-clutter scenarios. The second part is false-positive protection, where we introduce the robust ArUco marker as the lowest grasp priority. The marker is fixed at certain positions within the camera’s field of view, enabling the robot to halt its movement, thereby restraining the robot from grasping objects that should not be grasped. Once the marker disappears, the robot can resume its operations. We validate our method through real grasping experiments with a parallel-jaw gripper and an industrial robotic arm, demonstrating its effectiveness in high-clutter scenarios.2024 21st International Conference on Ubiquitous Robots (UR), New York, NY, USA, June 24-27, 202
S3M: Semantic Segmentation Sparse Mapping for UAVs with RGB-D Camera
Get PDFUnmanned Aerial Vehicles (UAVs) hold immense potential for critical applications, such as search and rescue operations, where accurate perception of indoor environments is paramount. However, the concurrent amalgamation of localization, 3D reconstruction, and semantic segmentation presents a notable hurdle, especially in the context of UAVs equipped with constrained power and computational resources. This paper presents a novel approach to address challenges in semantic information extraction and utilization within UAV operations. Our system integrates state-of-the-art visual SLAM to estimate a comprehensive 6-DoF pose and advanced object segmentation methods at the back end. To improve the computational and storage efficiency of the framework, we adopt a streamlined voxel-based 3D map representation - OctoMap to build a working system. Furthermore, the fusion algorithm is incorporated to obtain the semantic information of each frame from the front-end SLAM task, and the corresponding point. By leveraging semantic information, our framework enhances the UAV’s ability to perceive and navigate through indoor spaces, addressing challenges in pose estimation accuracy and uncertainty reduction. Through Gazebo simulations, we validate the efficacy of our proposed system and successfully embed our approach into a Jetson Xavier AGX unit for real-world applications.2024 IEEE/SICE International Symposium on System Integration (SII), Ha Long, Vietnam, January 8-11, 202
Iterative Model Identification and Tracking with Distributed Sensors
Get PDFIn this report, we propose a new iterative model identification and tracking technique for distributed sensor systems using a factor graph (FG). The idea is initiated from a position identification technique we proposed [4], however, this report aims to provide an algorithm which is applicable to more generic identification and tracking purposes. With the proposed technique, each sensor performs signal processing for compression of the measurement data and sends the compressed data to the fusion center. The marginal probability of the compressed sensing results are calculated over the FG at the fusion center. At the final stage, a maximum a posteriori probability (MAP) estimate of the model can be obtained during the tracking phase through the FG. The MAP over FG will be used for the prediction at the next state of model identification to further improve the estimation accuracy without requiring unacceptably high computation effort.2022 International Symposium on Information Theory and Its Applications (ISITA), Tsukuba, Japan, October 17-19, 202
Machine learning-aided structure determination of the heterogeneous Ziegler-Natta catalyst: insight into donor adsorption
Get PDFSupervisor:谷池 俊明先端科学技術研究科修士(マテリアルサイエンス
