No abstract

A new approach to through‐the‐floor localization of a static person using an ultra‐wide band (UWB) radar is introduced in this article. The proposed solution is based on a multilateration method appropriately modified for target localization by a multistatic UWB radar employing 1 transmitting (Tx) and 4 receiving antennas (Rxi). Due to an appropriate radar antenna array layout, a geometrical interpretation of the considered problem of localization allows finding the target coordinates by a simple computation of 2 intersections of 2 pairs of ellipses. The mentioned ellipses are defined by the antenna layout and time‐of‐arrivals corresponding to the target that were estimated for the particular pairs of Tx–Rxi antennas. Experimental analysis of the proposed method of through‐the‐floor localization of a person confirmed its good accuracy, despite being such a complex scenario.

No abstract

No abstract

The assisted assembly of customized products supported by collaborative robots combined with mixed reality devices is the current trend in the Industry 4.0 concept. This article introduces an experimental work cell with the implementation of the assisted assembly process for customized cam switches as a case study. The research is aimed to design a methodology for this complex task with full digitalization and transformation data to digital twin models from all vision systems. Recognition of position and orientation of assembled parts during manual assembly are marked and checked by convolutional neural network (CNN) model. Training of CNN was based on a new approach using virtual training samples with single shot detection and instance segmentation. The trained CNN model was transferred to an embedded artificial processing unit with a high-resolution camera sensor. The embedded device redistributes data with parts detected position and orientation into mixed reality devices and collaborative robot. This approach to assisted assembly using mixed reality, collaborative robot, vision systems, and CNN models can significantly decrease assembly and training time in real production.