English

Learning to Predict Robot Keypoints Using Artificially Generated Images

Computer Vision and Pattern Recognition 2019-07-04 v1 Robotics

Abstract

This work considers robot keypoint estimation on color images as a supervised machine learning task. We propose the use of probabilistically created renderings to overcome the lack of labeled real images. Rather than sampling from stationary distributions, our approach introduces a feedback mechanism that constantly adapts probability distributions according to current training progress. Initial results show, our approach achieves near-human-level accuracy on real images. Additionally, we demonstrate that feedback leads to fewer required training steps, while maintaining the same model quality on synthetic data sets.

Keywords

Cite

@article{arxiv.1907.01879,
  title  = {Learning to Predict Robot Keypoints Using Artificially Generated Images},
  author = {Christoph Heindl and Sebastian Zambal and Josef Scharinger},
  journal= {arXiv preprint arXiv:1907.01879},
  year   = {2019}
}

Comments

Work in progress

R2 v1 2026-06-23T10:11:04.987Z