arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1907.01879cs.CVcs.RO
收藏

学习预测机器人的关键点使用牺牲生成的图像

Learning to Predict Robot Keypoints Using Artificially Generated Images

PROFACTOR GmbH(PROFACTOR有限公司);Johannes Kepler University(约翰内斯·开普勒大学)

Christoph Heindl, Sebastian Zambal, Josef Scharinger

摘要:

这项工作认为机器人的关键点估计彩色图像作为一个监督机器学习任务。我们建议使用概率创建的渲染,以克服缺乏标记的真实图像。我们的方法不是从静态分布中采样,而是引入了一种反馈机制,根据当前的训练进度不断调整概率分布。初步结果表明,我们的方法在真实图像上达到了接近人类水平的精度。此外,我们还证明了反馈可以减少所需的训练步骤,同时在合成数据集上保持相同的模型质量。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑