Defo-Net: Learning Body Deformation using Generative Adversarial Networks

TL;DR

Defo-Net is a generative adversarial network that predicts 3D object deformations from a single RGB-D image, enabling real-time terrain modeling for robotic navigation.

Contribution

It introduces a novel invertible conditional GAN for fast, accurate deformation prediction, generalizing to unseen objects and enabling real-time robotic applications.

Findings

Successfully predicts terrain deformations in real-world scenarios.

Enables robots to navigate safely by anticipating object and terrain deformations.

Outperforms traditional finite element methods in speed for deformation prediction.

Abstract

Modelling the physical properties of everyday objects is a fundamental prerequisite for autonomous robots. We present a novel generative adversarial network (Defo-Net), able to predict body deformations under external forces from a single RGB-D image. The network is based on an invertible conditional Generative Adversarial Network (IcGAN) and is trained on a collection of different objects of interest generated by a physical finite element model simulator. Defo-Net inherits the generalisation properties of GANs. This means that the network is able to reconstruct the whole 3-D appearance of the object given a single depth view of the object and to generalise to unseen object configurations. Contrary to traditional finite element methods, our approach is fast enough to be used in real-time applications. We apply the network to the problem of safe and fast navigation of mobile robots carrying payloads over different obstacles and floor materials. Experimental results in real scenarios show how a robot equipped with an RGB-D camera can use the network to predict terrain deformations under different payload configurations and use this to avoid unsafe areas.