Supervised Training of Dense Object Nets using Optimal Descriptors for Industrial Robotic Applications

TL;DR

This paper introduces a supervised training method for Dense Object Nets using optimal descriptors derived from 3D models, improving industrial object grasping without relying on depth images.

Contribution

It presents a novel supervised training approach using Laplacian Eigenmaps for descriptor generation, effective for small and reflective industrial objects.

Findings

Enhanced grasping accuracy for industrial objects

Supervised training reduces reliance on depth images

Improved performance in pick-and-place tasks

Abstract

Dense Object Nets (DONs) by Florence, Manuelli and Tedrake (2018) introduced dense object descriptors as a novel visual object representation for the robotics community. It is suitable for many applications including object grasping, policy learning, etc. DONs map an RGB image depicting an object into a descriptor space image, which implicitly encodes key features of an object invariant to the relative camera pose. Impressively, the self-supervised training of DONs can be applied to arbitrary objects and can be evaluated and deployed within hours. However, the training approach relies on accurate depth images and faces challenges with small, reflective objects, typical for industrial settings, when using consumer grade depth cameras. In this paper we show that given a 3D model of an object, we can generate its descriptor space image, which allows for supervised training of DONs. We rely on Laplacian Eigenmaps (LE) to embed the 3D model of an object into an optimally generated space. While our approach uses more domain knowledge, it can be efficiently applied even for smaller and reflective objects, as it does not rely on depth information. We compare the training methods on generating 6D grasps for industrial objects and show that our novel supervised training approach improves the pick-and-place performance in industry-relevant tasks.