MovingCables software

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F24%3A00386016" target="_blank" >RIV/68407700:21730/24:00386016 - isvavai.cz</a>

Výsledek na webu

<a href="https://github.com/holesond/movingcables" target="_blank" >https://github.com/holesond/movingcables</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

MovingCables software

Popis výsledku v původním jazyce

MovingCables software contains MfnProb (FT) for estimating optical flow in scenes with moving cables and for densely segmenting moving cables in color images. It also contains custom image compositor software tools for creating new datasets derived from the MovingCables dataset.

Název v anglickém jazyce

MovingCables software

Popis výsledku anglicky

MovingCables software contains MfnProb (FT) for estimating optical flow in scenes with moving cables and for densely segmenting moving cables in color images. It also contains custom image compositor software tools for creating new datasets derived from the MovingCables dataset.

Druh

R - Software

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/EH22_008%2F0004590" target="_blank" >EH22_008/0004590: Robotika a pokročilá průmyslová výroba</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Interní identifikační kód produktu

MovingCables software

Technické parametry

Manipulating cluttered cables, hoses or ropes is challenging for both robots and humans. Humans often simplify these perceptually challenging tasks by pulling or pushing tangled cables and observing the resulting motions. We would like to build a similar system -- in accordance with the interactive perception paradigm -- to aid robotic cable manipulation. Implemented within MovingCables software, the MfnProb FT cable motion segmentation method that densely labels moving cable image pixels is a key building block of such a system. The MfnProb FT method reaches the highest recorded mean Intersection over Union (IoU) moving cable segmentation score of 0.7673 and the lowest mean endpoint error (EPE) of estimated optical flow of 0.32 pixels on the test set of the MovingCables dataset.

Ekonomické parametry

MovingCables software might become a key component of a robotic system able to autonomously assemble or install wiring harnesses in industrial settings. Such a system might reduce manufacturing costs by replacing human workers, enable wiring harness assembly in countries with high labour costs, or increase manufacturing process speed, precision and reliability. Autonomously maintaining data centers might be another possible application area in the future.

IČO vlastníka výsledku

68407700

Název vlastníka

České vysoké učení technické v Praze