论文标题
基于端到端像素的深度主动推断身体感知和动作
End-to-End Pixel-Based Deep Active Inference for Body Perception and Action
论文作者
论文摘要
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活性推理算法（Pixelai）。我们的算法结合了神经科学的自由能原理，植根于各变化推断，深度卷积解码器以扩展算法，以直接处理原始的视觉输入并提供在线自适应推断。通过在模拟和真正的NAO机器人中研究身体的感知和行动来验证我们的方法。结果表明，我们的方法允许机器人仅使用单眼摄像头图像对其手臂进行动态估算，以及2）自动触及到视觉空间中“想象”的手臂姿势。这表明机器人和人体的感知和动作可以通过将两者视为由持续的感觉输入指导的主动推理问题来有效地解决。
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.
