TAILOR: Teaching with Active and Incremental Learning for Object Registration

Authors

  • Qianli Xu Institute for Infocomm Research
  • Nicolas Gauthier Institute for Infocomm Research
  • Wenyu Liang Institute for Infocomm Research
  • Fen Fang Institute for Infocomm Research
  • Hui Li Tan Institute for Infocomm Research
  • Ying Sun Institute for Infocomm Research
  • Yan Wu Institute for Infocomm Research
  • Liyuan Li Institute for Infocomm Research
  • Joo-Hwee Lim Institute for Infocomm Research

Keywords:

Interactive Learning, Object Detection, Collaborative Robot, Incremental Learning

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.

Downloads

Published

2021-05-18

How to Cite

Xu, Q., Gauthier, N., Liang, W., Fang, F., Tan, H. L., Sun, Y., Wu, Y., Li, L., & Lim, J.-H. (2021). TAILOR: Teaching with Active and Incremental Learning for Object Registration. Proceedings of the AAAI Conference on Artificial Intelligence, 35(18), 16120-16123. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/18031