Teaching robots to imitate a human with no on-teacher sensors. Whatare the key challenges?

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F18%3A00330073" target="_blank" >RIV/68407700:21730/18:00330073 - isvavai.cz</a>

Výsledek na webu

<a href="https://arxiv.org/pdf/1901.08335.pdf" target="_blank" >https://arxiv.org/pdf/1901.08335.pdf</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Teaching robots to imitate a human with no on-teacher sensors. Whatare the key challenges?

Popis výsledku v původním jazyce

In this paper, we consider the problem of learning object manipulation tasks from human demonstration using RGB or RGB-D cameras. We highlight the key challenges in capturing sufficiently good data with no tracking devices – starting from sensor selection and accurate 6DoF pose estimation to natural language processing. In particular, we focus on two show cases: gluing task with a glue gun and simple block-stacking with variable blocks. Furthermore, we discuss how a linguistic description of the task could help to improve the accuracy of task description. We also present the whole architecture of our transfer of the imitated task to the simulated and real robot environment.

Název v anglickém jazyce

Teaching robots to imitate a human with no on-teacher sensors. Whatare the key challenges?

Popis výsledku anglicky

In this paper, we consider the problem of learning object manipulation tasks from human demonstration using RGB or RGB-D cameras. We highlight the key challenges in capturing sufficiently good data with no tracking devices – starting from sensor selection and accurate 6DoF pose estimation to natural language processing. In particular, we focus on two show cases: gluing task with a glue gun and simple block-stacking with variable blocks. Furthermore, we discuss how a linguistic description of the task could help to improve the accuracy of task description. We also present the whole architecture of our transfer of the imitated task to the simulated and real robot environment.

Druh

O - Ostatní výsledky

CEP obor

—

OECD FORD obor

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

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

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

Rok uplatnění

2018

Kód důvěrnosti údajů

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