視覚的妨害を無視してロボットの自己位置推定を改善する
Improving Robot Localisation by Ignoring Visual Distraction
ニューラルネットワークが特定の物体クラスを潜在空間で表現できなくする「Neural Blindness」を提案し、妨害物体を無視することでロボットの位置推定精度を向上させた論文。
著者: Oscar Mendez, Matthew Vowels, Richard Bowden
分類: cs.RO, cs.CV
原文アブストラクト
Attention is an important component of modern deep learning. However, less emphasis has been put on its inverse: ignoring distraction. Our daily lives require us to explicitly avoid giving attention to salient visual features that confound the task we are trying to accomplish. This visual prioritisation allows us to concentrate on important tasks while ignoring visual distractors. In this work, we introduce Neural Blindness, which gives an agent the ability to completely ignore objects or classes that are deemed distractors. More explicitly, we aim to render a neural network completely incapable of representing specific chosen classes in its latent space. In a very real sense, this makes the network "blind" to certain classes, allowing and agent to focus on what is important for a given task, and demonstrates how this can be used to improve localisation.
