Proprioceptive Image: An Image Representation of Proprioceptive Data from Quadruped Robots for Contact Estimation Learning

Abstract-- This paper presents a novel approach for representing proprioceptive time-series data from quadruped robots as structured two-dimensional images, enabling the use of convolutional neural networks for learning locomotion-related tasks. The proposed method encodes temporal dynamics from multiple proprioceptive signals, such as joint positions, IMU readings, and foot velocities, while preserving the robot's morphological structure in the spatial arrangement of the image. We apply this concept in the problem of contact estimation, a key capability for stable and adaptive locomotion on diverse terrains. Experimental evaluations on both real-world datasets and simulated environments show that our image-based representation consistently enhances prediction accuracy and generalization over conventional sequence-based models, underscoring the potential of cross-modal encoding strategies for robotic state learning. Our method achieves superior performance on the contact dataset, improving contact state accuracy from 87.7% to 94.5% over the recently proposed MI-HGNN method, using a 15 times shorter window size. I. INTRODUCTION Deep learning has achieved remarkable success in domains where sequential or high-dimensional data can be transformed into visual representations suitable to convolu-tional architectures. In speech recognition, for instance, raw audio signals are often converted into spectrograms, two-dimensional time-frequency images, that serve as powerful inputs to convolutional neural networks (CNNs) and other image-based models.