An online training course run by the FIWARE Foundation in conjunction with the i4Trust project. The core part of this virtual training camp (21-24 June 2021) covered all the necessary skills to develop smart solutions powered by FIWARE. It introduces the basis of Digital Twin programming using linked data concepts - JSON-LD and NGSI-LD and combines these with common smart data models for the sharing and augmentation of context data.
In addition, it covers the supplementary FIWARE technologies used to implement the common functions typically required when architecting a complete smart solution: Identity and Access Management (IAM) functions to secure access to digital twin data and functions enabling the interface with IoT and 3rd systems, or the connection with different tools for processing and monitoring current and historical big data.
This 12-hour online training course can be used to obtain a good understanding of FIWARE and NGSI Interfaces and form the basis of studying for the FIWARE expert certification.
Extending this core part, the virtual training camp adds introductory and deep-dive sessions on how FIWARE and iSHARE technologies, brought together under the umbrella of the i4Trust initiative, can be combined to provide the means for the creation of data spaces in which multiple organizations can exchange digital twin data in a trusted and efficient manner, collaborating in the creation of innovative services based on data sharing. In addition, SMEs and Digital Innovation Hubs (DIHs) that go through this complete training and are located in countries eligible under Horizon 2020 will be equipped with the necessary know-how to apply to the recently launched i4Trust Open Call.
Rich Authorization Requests allows clients to pass fine grained authorization data in the OAuth authorization request. It's been developed based on experiences in open banking and other security sensitive areas.
An online training course run by the FIWARE Foundation in conjunction with the i4Trust project. The core part of this virtual training camp (21-24 June 2021) covered all the necessary skills to develop smart solutions powered by FIWARE. It introduces the basis of Digital Twin programming using linked data concepts - JSON-LD and NGSI-LD and combines these with common smart data models for the sharing and augmentation of context data.
In addition, it covers the supplementary FIWARE technologies used to implement the common functions typically required when architecting a complete smart solution: Identity and Access Management (IAM) functions to secure access to digital twin data and functions enabling the interface with IoT and 3rd systems, or the connection with different tools for processing and monitoring current and historical big data.
This 12-hour online training course can be used to obtain a good understanding of FIWARE and NGSI Interfaces and form the basis of studying for the FIWARE expert certification.
Extending this core part, the virtual training camp adds introductory and deep-dive sessions on how FIWARE and iSHARE technologies, brought together under the umbrella of the i4Trust initiative, can be combined to provide the means for the creation of data spaces in which multiple organizations can exchange digital twin data in a trusted and efficient manner, collaborating in the creation of innovative services based on data sharing. In addition, SMEs and Digital Innovation Hubs (DIHs) that go through this complete training and are located in countries eligible under Horizon 2020 will be equipped with the necessary know-how to apply to the recently launched i4Trust Open Call.
Rich Authorization Requests allows clients to pass fine grained authorization data in the OAuth authorization request. It's been developed based on experiences in open banking and other security sensitive areas.
セル生産方式におけるロボットの活用には様々な問題があるが,その一つとして 3 体以上の物体の組み立てが挙げられる.一般に,複数物体を同時に組み立てる際は,対象の部品をそれぞれロボットアームまたは治具でそれぞれ独立に保持することで組み立てを遂行すると考えられる.ただし,この方法ではロボットアームや治具を部品数と同じ数だけ必要とし,部品数が多いほどコスト面や設置スペースの関係で無駄が多くなる.この課題に対して音𣷓らは組み立て対象物に働く接触力等の解析により,治具等で固定されていない対象物が組み立て作業中に運動しにくい状態となる条件を求めた.すなわち,環境中の非把持対象物のロバスト性を考慮して,組み立て作業条件を検討している.本研究ではこの方策に基づいて,複数物体の組み立て作業を単腕マニピュレータで実行することを目的とする.このとき,対象物のロバスト性を考慮することで,仮組状態の複数物体を同時に扱う手法を提案する.作業対象としてパイプジョイントの組み立てを挙げ,簡易な道具を用いることで単腕マニピュレータで複数物体を同時に把持できることを示す.さらに,作業成功率の向上のために RGB-D カメラを用いた物体の位置検出に基づくロボット制御及び動作計画を実装する.
This paper discusses assembly operations using a single manipulator and a parallel gripper to simultaneously
grasp multiple objects and hold the group of temporarily assembled objects. Multiple robots and jigs generally operate
assembly tasks by constraining the target objects mechanically or geometrically to prevent them from moving. It is
necessary to analyze the physical interaction between the objects for such constraints to achieve the tasks with a single
gripper. In this paper, we focus on assembling pipe joints as an example and discuss constraining the motion of the
objects. Our demonstration shows that a simple tool can facilitate holding multiple objects with a single gripper.
【DLゼミ】XFeat: Accelerated Features for Lightweight Image Matchingharmonylab
公開URL:https://arxiv.org/pdf/2404.19174
出典:Guilherme Potje, Felipe Cadar, Andre Araujo, Renato Martins, Erickson R. ascimento: XFeat: Accelerated Features for Lightweight Image Matching, Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)
概要:リソース効率に優れた特徴点マッチングのための軽量なアーキテクチャ「XFeat(Accelerated Features)」を提案します。手法は、局所的な特徴点の検出、抽出、マッチングのための畳み込みニューラルネットワークの基本的な設計を再検討します。特に、リソースが限られたデバイス向けに迅速かつ堅牢なアルゴリズムが必要とされるため、解像度を可能な限り高く保ちながら、ネットワークのチャネル数を制限します。さらに、スパース下でのマッチングを選択できる設計となっており、ナビゲーションやARなどのアプリケーションに適しています。XFeatは、高速かつ同等以上の精度を実現し、一般的なラップトップのCPU上でリアルタイムで動作します。