Learning from Successful and Failed Demonstrations via Optimization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hertel, Brendan, Ahmadzadeh, S. Reza
Format: Preprint
Published: 2021
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916304275898368
author Hertel, Brendan
Ahmadzadeh, S. Reza
author_facet Hertel, Brendan
Ahmadzadeh, S. Reza
contents Learning from Demonstration (LfD) is a popular approach that allows humans to teach robots new skills by showing the correct way(s) of performing the desired skill. Human-provided demonstrations, however, are not always optimal and the teacher usually addresses this issue by discarding or replacing sub-optimal (noisy or faulty) demonstrations. We propose a novel LfD representation that learns from both successful and failed demonstrations of a skill. Our approach encodes the two subsets of captured demonstrations (labeled by the teacher) into a statistical skill model, constructs a set of quadratic costs, and finds an optimal reproduction of the skill under novel problem conditions (i.e. constraints). The optimal reproduction balances convergence towards successful examples and divergence from failed examples. We evaluate our approach through several 2D and 3D experiments in real-world using a UR5e manipulator arm and also show that it can reproduce a skill from only failed demonstrations. The benefits of exploiting both failed and successful demonstrations are shown through comparison with two existing LfD approaches. We also compare our approach against an existing skill refinement method and show its capabilities in a multi-coordinate setting.
format Preprint
id arxiv_https___arxiv_org_abs_2107_11918
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle Learning from Successful and Failed Demonstrations via Optimization
Hertel, Brendan
Ahmadzadeh, S. Reza
Robotics
Learning from Demonstration (LfD) is a popular approach that allows humans to teach robots new skills by showing the correct way(s) of performing the desired skill. Human-provided demonstrations, however, are not always optimal and the teacher usually addresses this issue by discarding or replacing sub-optimal (noisy or faulty) demonstrations. We propose a novel LfD representation that learns from both successful and failed demonstrations of a skill. Our approach encodes the two subsets of captured demonstrations (labeled by the teacher) into a statistical skill model, constructs a set of quadratic costs, and finds an optimal reproduction of the skill under novel problem conditions (i.e. constraints). The optimal reproduction balances convergence towards successful examples and divergence from failed examples. We evaluate our approach through several 2D and 3D experiments in real-world using a UR5e manipulator arm and also show that it can reproduce a skill from only failed demonstrations. The benefits of exploiting both failed and successful demonstrations are shown through comparison with two existing LfD approaches. We also compare our approach against an existing skill refinement method and show its capabilities in a multi-coordinate setting.
title Learning from Successful and Failed Demonstrations via Optimization
topic Robotics
url https://arxiv.org/abs/2107.11918