身体知覚と行動のためのピクセルベース深層能動推論
End-to-End Pixel-Based Deep Active Inference for Body Perception and Action
脳科学の自由エネルギー原理と深層畳み込みデコーダを組み合わせ、生の画像入力からロボットの腕の姿勢推定と視覚空間上の到達行動を実現した。
著者: Cansu Sancaktar, Marcel van Gerven, Pablo Lanillos
分類: cs.CV, cs.AI, cs.LG, cs.RO, q-bio.NC
原文アブストラクト
We present a pixel-based deep active inference algorithm (PixelAI) inspired by human body perception and action. Our algorithm combines the free-energy principle from neuroscience, rooted in variational inference, with deep convolutional decoders to scale the algorithm to directly deal with raw visual input and provide online adaptive inference. Our approach is validated by studying body perception and action in a simulated and a real Nao robot. Results show that our approach allows the robot to perform 1) dynamical body estimation of its arm using only monocular camera images and 2) autonomous reaching to "imagined" arm poses in the visual space. This suggests that robot and human body perception and action can be efficiently solved by viewing both as an active inference problem guided by ongoing sensory input.
