確率的識別モデルによる触覚の知覚的エイリアシング問題の解決
Probabilistic Discriminative Models Address the Tactile Perceptual Aliasing Problem
触覚データにおける知覚的エイリアシング問題を指摘し、混合密度ネットワークを用いた確率的識別モデルで曖昧な触覚入力を精度良く予測できることを示した論文。
著者: John Lloyd, Yijiong Lin, Nathan F. Lepora
分類: cs.RO
原文アブストラクト
In this paper, our aim is to highlight Tactile Perceptual Aliasing as a problem when using deep neural networks and other discriminative models. Perceptual aliasing will arise wherever a physical variable extracted from tactile data is subject to ambiguity between stimuli that are physically distinct. Here we address this problem using a probabilistic discriminative model implemented as a 5-component mixture density network comprised of a deep neural network that predicts the parameters of a Gaussian mixture model. We show that discriminative regression models such as deep neural networks and Gaussian process regression perform poorly on aliased data, only making accurate predictions when the sources of aliasing are removed. In contrast, the mixture density network identifies aliased data with improved prediction accuracy. The uncertain predictions of the model form patterns that are consistent with the various sources of perceptual ambiguity. In our view, perceptual aliasing will become an unavoidable issue for robot touch as the field progresses to training robots that act in uncertain and unstructured environments, such as with deep reinforcement learning.
