Perceived Constraint Identification Using Physics-Informed Deep Neural Networks

Abstract Autonomous manipulation for robots in unstructured environments is challenging due to the technical gap between perception and acting in the physical world. This challenge becomes even more difficult when an object’s motion is constrained in space. This article presents a method to rapidly estimate mechanical constraint models of systems in the environment using physics-informed deep neural networks (PINNs). We develop a single network capable of estimating the motion of constrained mechanisms and present the methods for model training using synthetic data. By leveraging six-dimensional constraints to selectively inform the loss function for different motions within the deep neural network, we achieve high accuracy in estimating the motions for linear and rotation constraints with sub-1 deg error. We experimentally evaluate our model on three real examples, validating the applicability of the approach.