Training networks separately on static and dynamic obstacles improves collision avoidance during indoor robot navigation

Viktor Schmuck, David Meredith

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

1 Citationer (Scopus)

Abstract

Autonomous robot navigation and dynamic obstacle avoidance in complex, cluttered, indoor environments is a challenging task. A robust solution would allow robots to be deployed in hospitals, airports or shopping centres to serve as guides and fulfil other functions requiring safe human--robot interaction. Previous studies have explored various approaches to selecting sensor types, collecting data, and training models capable of safely avoiding unmapped, possibly dynamic obstacles in an indoor environment. In this paper we address the problem of recognizing and anticipating collisions, in order to determine when avoidance manoeuvres are required. We propose and compare two sensor-fusion and neural-network-based solutions, one in which models are trained separately on static and dynamic samples and another in which a model is trained on samples of collisions with both dynamic and static obstacles. The measured accuracies confirmed that the separately trained, ensemble models had better recognition performance, but were slower at calculation than the models trained without taking the obstacle types into account.
OriginalsprogEngelsk
TitelESANN 2019 - Proceedings, 27th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
RedaktørerMichel Verleysen
Antal sider6
UdgivelsesstedBelgium
ForlagESANN
Publikationsdato28 apr. 2019
Sider655-660
KapitelDynamical systems and reinforcement learning
ISBN (Trykt)9782875870650
ISBN (Elektronisk)9782875870667
StatusUdgivet - 28 apr. 2019
BegivenhedEuropean Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning - Bruges, Belgien
Varighed: 24 apr. 201926 apr. 2019
Konferencens nummer: 27
https://www.elen.ucl.ac.be/esann/

Konference

KonferenceEuropean Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
Nummer27
Land/OmrådeBelgien
ByBruges
Periode24/04/201926/04/2019
Internetadresse

Fingeraftryk

Dyk ned i forskningsemnerne om 'Training networks separately on static and dynamic obstacles improves collision avoidance during indoor robot navigation'. Sammen danner de et unikt fingeraftryk.

Citationsformater