Seq2Seq Imitation Learning for Tactile Feedback-based Manipulation
Wenyan Yang, Alexandre Angleraud, Roel S. Pieters, Joni Pajarinen, Joni-Kristian Kämäräinen
Abstract
Robot control for tactile feedback based manip-ulation can be difficult due to modeling of physical contacts, partial observability of the environment, and noise in perception and control. This work focuses on solving partial observability of contact-rich manipulation tasks as a Sequence-to-Sequence (Seq2Seq) Imitation Learning (IL) problem. The proposed Seq2Seq model first produces a robot-environment interaction sequence to estimate the partially observable environment state variables, and then, the observed interaction sequence is transformed to a control sequence for the task itself. The proposed Seq2Seq IL for tactile feedback based manipulation is experimentally validated on a door-open task in a simulated environment and a snap-on insertion task with a real robot. The model is able to learn both tasks from only 50 expert demonstrations while state-of-the-art reinforcement learning and imitation learning methods fail.
BibTeX
@inproceedings{icra2023_seq2seqimitation,
title = {Seq2Seq Imitation Learning for Tactile Feedback-based Manipulation},
author = {Wenyan Yang and Alexandre Angleraud and Roel S. Pieters and Joni Pajarinen and Joni-Kristian Kämäräinen},
booktitle = {ICRA 2023},
year = {2023}
}