# Robot-Supervised Learning for Object Segmentation

## TL;DR

This paper presents a robot-supervised learning approach for pixelwise object segmentation that eliminates the need for human-labeled training data by leveraging robot kinematics and self-recognition networks, improving adaptability in unstructured environments.

## Contribution

It introduces a novel self-supervised segmentation method combining kinematics-based foreground detection with a self-recognition network trained without human labels.

## Key findings

- Outperforms state-of-the-art adaptable in-hand object segmentation.
- Automatically labeled training data enhances segmentation accuracy.
- Method enables effective segmentation in unstructured robotic environments.

## Abstract

To be effective in unstructured and changing environments, robots must learn to recognize new objects. Deep learning has enabled rapid progress for object detection and segmentation in computer vision; however, this progress comes at the price of human annotators labeling many training examples. This paper addresses the problem of extending learning-based segmentation methods to robotics applications where annotated training data is not available. Our method enables pixelwise segmentation of grasped objects. We factor the problem of segmenting the object from the background into two sub-problems: (1) segmenting the robot manipulator and object from the background and (2) segmenting the object from the manipulator. We propose a kinematics-based foreground segmentation technique to solve (1). To solve (2), we train a self-recognition network that segments the robot manipulator. We train this network without human supervision, leveraging our foreground segmentation technique from (1) to label a training set of images containing the robot manipulator without a grasped object. We demonstrate experimentally that our method outperforms state-of-the-art adaptable in-hand object segmentation. We also show that a training set composed of automatically labelled images of grasped objects improves segmentation performance on a test set of images of the same objects in the environment.