ロボットマニピュレーションのための確率的関節リアルタイム追跡
Probabilistic Articulated Real-Time Tracking for Robot Manipulation
関節計測と深度画像をカルマンフィルタと座標パーティクルフィルタで融合し、カメラ座標系でのエンドエフェクタ姿勢を高精度・リアルタイムに推定する手法を提案した。
著者: Cristina Garcia Cifuentes, Jan Issac, Manuel Wüthrich, Stefan Schaal, Jeannette Bohg
分類: cs.RO
原文アブストラクト
We propose a probabilistic filtering method which fuses joint measurements with depth images to yield a precise, real-time estimate of the end-effector pose in the camera frame. This avoids the need for frame transformations when using it in combination with visual object tracking methods. Precision is achieved by modeling and correcting biases in the joint measurements as well as inaccuracies in the robot model, such as poor extrinsic camera calibration. We make our method computationally efficient through a principled combination of Kalman filtering of the joint measurements and asynchronous depth-image updates based on the Coordinate Particle Filter. We quantitatively evaluate our approach on a dataset recorded from a real robotic platform, annotated with ground truth from a motion capture system. We show that our approach is robust and accurate even under challenging conditions such as fast motion, significant and long-term occlusions, and time-varying biases. We release the dataset along with open-source code of our approach to allow for quantitative comparison with alternative approaches.
