Temporal Arm Tracking and Probabilistic Pointed Object Selection for Robot to Robot Interaction using Deictic Gestures

Polychronis Kontaxakis, Khurram Gulzar, Ville Kyrki

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference contributionScientificvertaisarvioitu

3 Sitaatiot (Scopus)

Abstrakti

This paper discusses advancements on alternative communication methods between robots utilizing deictic gestures and body language. The provided approach boosts the performance of the formerly developed ROS-oriented system and grants increased accuracy and robustness. More precisely, the paper presents: a) a temporal tracking technique responsible to detect and track the arm of the pointing agent and b) a probabilistic pointed object selection method. On one hand, a model registration approach based on the Interactive Closest Point (ICP) algorithm, continuously tracks a detected pointing arm over time. On the other hand, a probabilistic method weights a number of features to estimate which of the available objects is the pointed one. The provided results indicate that the enhanced system outperforms the formerly developed approach and efficiently tackles any identified problems, such as the correct pointed object selection in ambiguous situations.
AlkuperäiskieliEnglanti
Otsikko16th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2016
KustantajaIEEE
Sivut186-193
Sivumäärä8
ISBN (elektroninen)978-1-5090-4718-5
DOI - pysyväislinkit
TilaJulkaistu - 2 tammik. 2017
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa
TapahtumaIEEE-RAS International Conference on Humanoid Robots - Cancun, Meksiko
Kesto: 15 marrask. 201617 marrask. 2016
Konferenssinumero: 16

Julkaisusarja

NimiIEEE-RAS International Conference on Humanoid Robots
KustantajaInstitute of Electrical and Electronics Engineers, Inc.
ISSN (painettu)2164-0572
ISSN (elektroninen)2164-0580

Conference

ConferenceIEEE-RAS International Conference on Humanoid Robots
LyhennettäHumanoids 2016
Maa/AlueMeksiko
KaupunkiCancun
Ajanjakso15/11/201617/11/2016

Sormenjälki

Sukella tutkimusaiheisiin 'Temporal Arm Tracking and Probabilistic Pointed Object Selection for Robot to Robot Interaction using Deictic Gestures'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä