ROG Ally

Frank R Dillon, Roger L. Worthington, H. Savoy, S. Rooney, Ann M. Becker-Schutte, Rachael Guerra

Lulu Li, A. Cherouat, H. Snoussi, Tianhua Wang

Robotic arm target grasping by vision support is a commonly used method in grasping tasks and is usually used for multi-target complex scenes. Where vision support is generally used to identify the targets and to get their positions, categories and sizes. Most robotic arm grasping tasks using target recognition methods as visual inspection ignore the relationship between target objects such as the occlusion problem between objects. This limits the targets to be grasped and makes the crawling task inefficient. We propose Grasping with Occlusion-Aware aLly (GOAL) method based on binocular stereo-vision. Firstly, occlusion relationships in the view are directly inferred and targets are segmented as well as localized. Subsequently, multi-target grasping pose estimation is performed to obtain effective grasping positions. Ultimately, validation is conducted on a high-resolution dataset using the EPSON robotic arm. Note to Practitioners—This research significantly advances the field by addressing occlusion challenges in robotic grasping, offering effective methods, a valuable dataset, and practical insights. The proposed Grasping with Occlusion-Aware aLly (GOAL) method was validated on a high-resolution dataset using the EPSON robotic arm, showcasing its applicability and efficiency in real-world scenarios. This work provides valuable contributions to practitioners in the field of robotic manipulation and grasping tasks.

Charlotte E. Moser, Shaun Wiley

Academic Abstract Advantaged group allies have multiple motives for supporting equality, raising questions about their sincerity. We draw upon the covariation model of attributions to explain how disadvantaged group members make attributions about whether advantaged group “allies” are sincerely motivated to empower the disadvantaged group. We propose an Attribution-Identity Model of Sincerity (AIMS) which posits that disadvantaged group members view advantaged group members as sincere allies when they support equality in the presence of inhibitory causes and in the absence of facilitative causes, exceed expectations for the advantaged group, and provide support across time and contexts. Furthermore, those who identify strongly with their disadvantaged group and perceive intergroup inequality as illegitimate are most motivated to ascertain the sincerity of advantaged group members’ allyship. AIMS suggests how members of disadvantaged groups seek to maximize benefits and minimize risks of advantaged group members’ allyship. Public Abstract Advantaged group members (e.g., men, White Americans) can act as allies for disadvantaged groups (e.g., women, Americans belonging to minoritized racial groups), but members of disadvantaged groups sometimes have reason to question whether their motives are sincere. We argue that members of disadvantaged groups view advantaged group allies as more sincere when they support equality when they do not stand to benefit from it and even when they stand to lose. We also argue that members of disadvantaged groups view advantaged group allies as more sincere when their support for equality goes beyond expectations for their advantaged group, consistently over time, and is not limited to particular situations, forms, or contexts. Members of disadvantaged groups like sincere allies, want to work with them, and feel safe around them. Sincere allies also serve as moral exemplars to other members of advantaged groups.

Yunpeng Mei, Jian Sun, Zhihong Peng, Fang Deng, Gang Wang, Jie Chen

Robotic grasping is a crucial topic in robotics and computer vision, with broad applications in industrial production and intelligent manufacturing. Although some methods have begun addressing instance-level grasping, most remain limited to predefined instances and categories, lacking flexibility for open-vocabulary grasp prediction based on user-specified instructions. To address this, we propose RoG-SAM, a language-driven, instance-level grasp detection framework built on Segment Anything Model (SAM). RoG-SAM utilizes open-vocabulary prompts for object localization and grasp pose prediction, adapting SAM through transfer learning with encoder adapters and multi-head decoders to extend its segmentation capabilities to grasp pose estimation. Experimental results show that RoG-SAM achieves competitive performance on single-object datasets (Cornell and Jacquard) and cluttered datasets (GraspNet-1Billion and OCID), with instance-level accuracies of 91.2% and 90.1%, respectively, while using only 28.3% of SAM's trainable parameters. The effectiveness of RoG-SAM was also validated in real-world environments.

S. Steffens, K. Schröder, Martina Krüger, Christoph Maack, K. Streckfuss-Bömeke, Johannes Backs, R. Backofen, Bettina Baeßler, Yvan Devaux, R. Gilsbach, J. Heijman, J. Knaus, R. Kramann, Dominik Linz, Allyson L. Lister, H. Maatz, L. Maegdefessel, Manuel Mayr, B. Meder, S. Nussbeck, Eva A. Rog-Zielinska, Marcel H. Schulz, A. Sickmann, G. Yigit, P. Kohl

The sharing and documentation of cardiovascular research data are essential for efficient use and reuse of data, thereby aiding scientific transparency, accelerating the progress of cardiovascular research and healthcare, and contributing to the reproducibility of research results. However, challenges remain. This position paper, written on behalf of and approved by the German Cardiac Society and German Centre for Cardiovascular Research, summarizes our current understanding of the challenges in cardiovascular research data management (RDM). These challenges include lack of time, awareness, incentives, and funding for implementing effective RDM; lack of standardization in RDM processes; a need to better identify meaningful and actionable data among the increasing volume and complexity of data being acquired; and a lack of understanding of the legal aspects of data sharing. While several tools exist to increase the degree to which data are findable, accessible, interoperable, and reusable (FAIR), more work is needed to lower the threshold for effective RDM not just in cardiovascular research but in all biomedical research, with data sharing and reuse being factored in at every stage of the scientific process. A culture of open science with FAIR research data should be fostered through education and training of early-career and established research professionals. Ultimately, FAIR RDM requires permanent, long-term effort at all levels. If outcomes can be shown to be superior and to promote better (and better value) science, modern RDM will make a positive difference to cardiovascular science and practice. The full position paper is available in the supplementary materials.