グラフネットワークを用いた両手動作デモンストレーションからの物体-動作関係の学習
Learning Object-Action Relations from Bimanual Human Demonstration Using Graph Networks
ロボット視点のRGB-D動画から物体間の空間関係をグラフ表現として抽出し、グラフネットワークで各手の動作をフレーム単位で分類・認識する手法を提案した論文。
著者: Christian R. G. Dreher, Mirko Wächter, Tamim Asfour
分類: cs.RO
原文アブストラクト
Recognizing human actions is a vital task for a humanoid robot, especially in domains like programming by demonstration. Previous approaches on action recognition primarily focused on the overall prevalent action being executed, but we argue that bimanual human motion cannot always be described sufficiently with a single action label. We present a system for frame-wise action classification and segmentation in bimanual human demonstrations. The system extracts symbolic spatial object relations from raw RGB-D video data captured from the robot's point of view in order to build graph-based scene representations. To learn object-action relations, a graph network classifier is trained using these representations together with ground truth action labels to predict the action executed by each hand. We evaluated the proposed classifier on a new RGB-D video dataset showing daily action sequences focusing on bimanual manipulation actions. It consists of 6 subjects performing 9 tasks with 10 repetitions each, which leads to 540 video recordings with 2 hours and 18 minutes total playtime and per-hand ground truth action labels for each frame. We show that the classifier is able to reliably identify (action classification macro F1-score of 0.86) the true executed action of each hand within its top 3 predictions on a frame-by-frame basis without prior temporal action segmentation.
