QUB-PHEO: A Visual-Based Dyadic Multi-View Dataset for Intention Inference in Collaborative Assembly

被引：0

作者：

Adebayo, Samuel ^{[1
,2
]}

Mcloone, Sean ^{[1
,2
]}

Dessing, Joost C. ^{[1
,3
]}

机构：

[1] Queens Univ Belfast, Ctr Intelligent Autonomous Mfg Syst, Belfast BT7 1NN, North Ireland

[2] Queens Univ Belfast, Sch Elect Elect Engn & Comp Sci, Belfast BT7 1NN, North Ireland

[3] Queens Univ Belfast, Sch Psychol, Belfast BT7 1NN, North Ireland

来源：

IEEE ACCESS | 2024年 / 12卷

关键词：

Human-robot interaction; Robots; Assembly; Visualization; Complexity theory; Encoding; Collaboration; Annotations; Service robots; Inference algorithms; Computer vision; dyadic interaction; multi-cue dataset; multi-view dataset; computer vision; task-oriented interaction; DATABASE; GAZE;

D O I：

10.1109/ACCESS.2024.3485162

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

QUB-PHEO introduces a visual-based, dyadic dataset with the potential of advancing human-robot interaction (HRI) research in assembly operations and intention inference. This dataset captures rich multimodal interactions between two participants, one acting as a 'robot surrogate,' across a variety of assembly tasks that are further broken down into 36 distinct subtasks. With rich visual annotations-facial landmarks, gaze, hand movements, object localization, and more-for 70 participants, QUB-PHEO offers two versions: full video data for 50 participants and visual cues for all 70. Designed to improve machine learning models for HRI, QUB-PHEO enables deeper analysis of subtle interaction cues and intentions, promising contributions to the field.

引用

页码：157050 / 157066

页数：17