Transfer of Inter-Robotic Inductive Classifier

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F20%3A00346395" target="_blank" >RIV/68407700:21230/20:00346395 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/ICACR51161.2020.9265509" target="_blank" >https://doi.org/10.1109/ICACR51161.2020.9265509</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICACR51161.2020.9265509" target="_blank" >10.1109/ICACR51161.2020.9265509</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Transfer of Inter-Robotic Inductive Classifier

Popis výsledku v původním jazyce

In multi-robot deployments, the robots need to share and integrate their own experience and perform transfer learning. Under the assumption that the robots have the same morphology and carry equivalent sensory equipment, the problem of transfer learning can be considered incremental learning. Thus, the transfer learning problem inherits the challenges of incremental learning, such as catastrophic forgetting and concept drift. In catastrophic forgetting, the model abruptly forgets the previously learned knowledge during the learning process. The concept drift arises with different experiences between consecutively sampled models. However, state-of-the-art robotic transfer learning approaches do not address both challenges at once. In this paper, we propose to use an incremental classifier on a transfer learning problem. The feasibility of the proposed approach is demonstrated in a real deployment. The robot consistently merges two classifiers learned on two different tasks into a classifier that performs well on both tasks.

Název v anglickém jazyce

Transfer of Inter-Robotic Inductive Classifier

Popis výsledku anglicky

In multi-robot deployments, the robots need to share and integrate their own experience and perform transfer learning. Under the assumption that the robots have the same morphology and carry equivalent sensory equipment, the problem of transfer learning can be considered incremental learning. Thus, the transfer learning problem inherits the challenges of incremental learning, such as catastrophic forgetting and concept drift. In catastrophic forgetting, the model abruptly forgets the previously learned knowledge during the learning process. The concept drift arises with different experiences between consecutively sampled models. However, state-of-the-art robotic transfer learning approaches do not address both challenges at once. In this paper, we propose to use an incremental classifier on a transfer learning problem. The feasibility of the proposed approach is demonstrated in a real deployment. The robot consistently merges two classifiers learned on two different tasks into a classifier that performs well on both tasks.

Druh

D - Stať ve sborníku

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/GA18-18858S" target="_blank" >GA18-18858S: Metody kontinuálního učení řízení pohybu vícenohých kráčejích robotů v úlohách autonomního sběru dat</a><br>

Návaznosti

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

Rok uplatnění

2020

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the 2020 4 th International Conference on Automation, Control and Robots

ISBN

978-1-7281-9207-9

ISSN

—

e-ISSN

—

Počet stran výsledku

5

Strana od-do

32-36

Název nakladatele

IEEE Service Center

Místo vydání

Piscataway

Místo konání akce

Rome

Datum konání akce

11. 11. 2020

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—