Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Learning to Adapt the Parameters of Behavior Trees and Motion Generators (BTMGs) to Task Variations

Ahmad, Faseeh LU ; Mayr, Matthias LU orcid and Krueger, Volker LU orcid (2023) IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2023
Abstract
The ability to learn new tasks and quickly adapt to different variations or dimensions is an important attribute in agile robotics. In our previous work, we have explored Behavior Trees and Motion Generators (BTMGs) as a robot arm policy representation to facilitate the learning and execution of assembly tasks. The current implementation of the BTMGs for a specific task may not be robust to the changes in the environment and may not generalize well to different variations of tasks. We propose to extend the BTMG policy representation with a module that predicts BTMG parameters for a new task variation. To achieve this, we propose a model that combines a Gaussian process and a weighted support vector machine classifier. This model predicts... (More)
The ability to learn new tasks and quickly adapt to different variations or dimensions is an important attribute in agile robotics. In our previous work, we have explored Behavior Trees and Motion Generators (BTMGs) as a robot arm policy representation to facilitate the learning and execution of assembly tasks. The current implementation of the BTMGs for a specific task may not be robust to the changes in the environment and may not generalize well to different variations of tasks. We propose to extend the BTMG policy representation with a module that predicts BTMG parameters for a new task variation. To achieve this, we propose a model that combines a Gaussian process and a weighted support vector machine classifier. This model predicts the performance measure and the feasibility of the predicted policy with BTMG parameters and task variations as inputs. Using the outputs of the model, we then construct a surrogate reward function that
is utilized within an optimizer to maximize the performance of a task over BTMG parameters for a fixed task variation. To demonstrate the effectiveness of our proposed approach, we conducted experimental evaluations on push and obstacle avoidance tasks in simulation and with a real KUKA iiwa robot. Furthermore, we compared the performance of our approach with four baseline methods. (Less)
Please use this url to cite or link to this publication:
author
; and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
host publication
2023 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2023
publisher
IEEE - Institute of Electrical and Electronics Engineers Inc.
conference name
IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2023
conference location
Detroit, United States
conference dates
2023-10-01 - 2023-10-05
external identifiers
  • scopus:85174790851
ISBN
978-1-6654-9191-4
978-1-6654-9190-7
DOI
10.1109/IROS55552.2023.10341636
project
RobotLab LTH
Efficient Learning of Robot Skills
Robotics and Semantic Systems
WASP Professor Package: Cognitive Robots for Manufacturing
language
English
LU publication?
yes
id
ba5621f9-3313-4b69-afa9-8870c57cd5b3
alternative location
https://arxiv.org/abs/2303.08209
date added to LUP
2023-11-02 09:45:25
date last changed
2024-04-19 04:47:02
@inproceedings{ba5621f9-3313-4b69-afa9-8870c57cd5b3,
  abstract     = {{The ability to learn new tasks and quickly adapt to different variations or dimensions is an important attribute in agile robotics. In our previous work, we have explored Behavior Trees and Motion Generators (BTMGs) as a robot arm policy representation to facilitate the learning and execution of assembly tasks. The current implementation of the BTMGs for a specific task may not be robust to the changes in the environment and may not generalize well to different variations of tasks. We propose to extend the BTMG policy representation with a module that predicts BTMG parameters for a new task variation. To achieve this, we propose a model that combines a Gaussian process and a weighted support vector machine classifier. This model predicts the performance measure and the feasibility of the predicted policy with BTMG parameters and task variations as inputs. Using the outputs of the model, we then construct a surrogate reward function that<br/>is utilized within an optimizer to maximize the performance of a task over BTMG parameters for a fixed task variation. To demonstrate the effectiveness of our proposed approach, we conducted experimental evaluations on push and obstacle avoidance tasks in simulation and with a real KUKA iiwa robot. Furthermore, we compared the performance of our approach with four baseline methods.}},
  author       = {{Ahmad, Faseeh and Mayr, Matthias and Krueger, Volker}},
  booktitle    = {{2023 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2023}},
  isbn         = {{978-1-6654-9191-4}},
  language     = {{eng}},
  publisher    = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
  title        = {{Learning to Adapt the Parameters of Behavior Trees and Motion Generators (BTMGs) to Task Variations}},
  url          = {{http://dx.doi.org/10.1109/IROS55552.2023.10341636}},
  doi          = {{10.1109/IROS55552.2023.10341636}},
  year         = {{2023}},
}