アルゴリズム計画と深層学習を統合した部分観測ナビゲーション
Integrating Algorithmic Planning and Deep Learning for Partially Observable Navigation
システムの各構成要素を微分可能なニューラルネットとして表現し、状態推定・計画・行動を単一の再帰型ネットワーク(NavNets)でエンドツーエンドに学習して、未知環境での部分観測ナビゲーションを実現した。
著者: Peter Karkus, David Hsu, Wee Sun Lee
分類: cs.RO, cs.AI, cs.LG
原文アブストラクト
We propose to take a novel approach to robot system design where each building block of a larger system is represented as a differentiable program, i.e. a deep neural network. This representation allows for integrating algorithmic planning and deep learning in a principled manner, and thus combine the benefits of model-free and model-based methods. We apply the proposed approach to a challenging partially observable robot navigation task. The robot must navigate to a goal in a previously unseen 3-D environment without knowing its initial location, and instead relying on a 2-D floor map and visual observations from an onboard camera. We introduce the Navigation Networks (NavNets) that encode state estimation, planning and acting in a single, end-to-end trainable recurrent neural network. In preliminary simulation experiments we successfully trained navigation networks to solve the challenging partially observable navigation task.
