合成可能なロボット学習のための微分可能アルゴリズムネットワーク
Differentiable Algorithm Networks for Composable Robot Learning
微分可能なロボットアルゴリズムとモデルをニューラルモジュールとして組み込み、モデル駆動の構造とデータ駆動の端到端学習を融合したDANを提案し、局所視覚と不完全な2D地図のみから複雑な3D環境をナビゲートする事例で有効性を示した。
著者: Peter Karkus, Xiao Ma, David Hsu, Leslie Pack Kaelbling, Wee Sun Lee, Tomas Lozano-Perez
分類: cs.LG, cs.AI, cs.RO, stat.ML
原文アブストラクト
This paper introduces the Differentiable Algorithm Network (DAN), a composable architecture for robot learning systems. A DAN is composed of neural network modules, each encoding a differentiable robot algorithm and an associated model; and it is trained end-to-end from data. DAN combines the strengths of model-driven modular system design and data-driven end-to-end learning. The algorithms and models act as structural assumptions to reduce the data requirements for learning; end-to-end learning allows the modules to adapt to one another and compensate for imperfect models and algorithms, in order to achieve the best overall system performance. We illustrate the DAN methodology through a case study on a simulated robot system, which learns to navigate in complex 3-D environments with only local visual observations and an image of a partially correct 2-D floor map.
