リーマン多様体上のベイズ最適化によるロボット学習
Bayesian Optimization Meets Riemannian Manifolds in Robot Learning
ロボットで頻出する非ユークリッドなパラメータ空間（姿勢や剛性行列など）をリーマン多様体として扱い、幾何を考慮したカーネルと獲得関数の最適化によりベイズ最適化の性能を高める手法を提案し、7自由度ロボットの操作スキル学習で検証した。
著者: Noémie Jaquier, Leonel Rozo, Sylvain Calinon, Mathias Bürger
分類: cs.RO, cs.LG
原文アブストラクト
Bayesian optimization (BO) recently became popular in robotics to optimize control parameters and parametric policies in direct reinforcement learning due to its data efficiency and gradient-free approach. However, its performance may be seriously compromised when the parameter space is high-dimensional. A way to tackle this problem is to introduce domain knowledge into the BO framework. We propose to exploit the geometry of non-Euclidean parameter spaces, which often arise in robotics (e.g. orientation, stiffness matrix). Our approach, built on Riemannian manifold theory, allows BO to properly measure similarities in the parameter space through geometry-aware kernel functions and to optimize the acquisition function on the manifold as an unconstrained problem. We test our approach in several benchmark artificial landscapes and using a 7-DOF simulated robot to learn orientation and impedance parameters for manipulation skills.
