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.

中文翻译：

---

用于身体感知和动作的端到端基于像素的深度主动推理

我们提出了一种受人体感知和动作启发的基于像素的深度主动推理算法（PixelAI）。我们的算法结合了源于变分推理的神经科学的自由能原理，以及深度卷积解码器来扩展算法以直接处理原始视觉输入并提供在线自适应推理。我们的方法通过在模拟和真实 Nao 机器人中研究身体感知和动作来验证。结果表明，我们的方法允许机器人执行 1) 仅使用单目相机图像对其手臂进行动态身体估计，以及 2) 自主到达视觉空间中的“想象”手臂姿势。这表明，通过将两者视为由持续的感官输入引导的主动推理问题，可以有效地解决机器人和人体的感知和动作。