TAILOR: Teaching with Active and Incremental Learning for Object Registration
Abstract
When deploying a robot to a new task, one often has to train it to detect novel objects, which is time-consuming and labor- intensive. We present TAILOR - a method and system for ob- ject registration with active and incremental learning. When instructed by a human teacher to register an object, TAILOR is able to automatically select viewpoints to capture informa- tive images by actively exploring viewpoints, and employs a fast incremental learning algorithm to learn new objects without potential forgetting of previously learned objects. We demonstrate the effectiveness of our method with a KUKA robot to learn novel objects used in a real-world gearbox as- sembly task through natural interactions.
Cite
Text
Xu et al. "TAILOR: Teaching with Active and Incremental Learning for Object Registration." AAAI Conference on Artificial Intelligence, 2021. doi:10.1609/AAAI.V35I18.18031Markdown
[Xu et al. "TAILOR: Teaching with Active and Incremental Learning for Object Registration." AAAI Conference on Artificial Intelligence, 2021.](https://mlanthology.org/aaai/2021/xu2021aaai-tailor/) doi:10.1609/AAAI.V35I18.18031BibTeX
@inproceedings{xu2021aaai-tailor,
title = {{TAILOR: Teaching with Active and Incremental Learning for Object Registration}},
author = {Xu, Qianli and Gauthier, Nicolas and Liang, Wenyu and Fang, Fen and Tan, Hui Li and Sun, Ying and Wu, Yan and Li, Liyuan and Lim, Joo-Hwee},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2021},
pages = {16120-16123},
doi = {10.1609/AAAI.V35I18.18031},
url = {https://mlanthology.org/aaai/2021/xu2021aaai-tailor/}
}