BeBOP-Combining Reactive Planning and Bayesian Optimization to Solve Robotic Manipulation Tasks
(2024) 2024 IEEE International Conference on Robotics and Automation, ICRA 2024 p.16459-16466- Abstract
Robotic systems for manipulation tasks are increasingly expected to be easy to configure for new tasks. While in the past, robot programs were often written statically and tuned manually, the current, faster transition times call for robust, modular and interpretable solutions that also allow a robotic system to learn how to perform a task. We propose the method Behavior-based Bayesian Optimization and Planning (BeBOP) that combines two approaches for generating behavior trees: we build the structure using a reactive planner and learn specific parameters with Bayesian optimization. The method is evaluated on a set of robotic manipulation benchmarks and is shown to outperform state-of-the-art reinforcement learning algorithms by being up... (More)
Robotic systems for manipulation tasks are increasingly expected to be easy to configure for new tasks. While in the past, robot programs were often written statically and tuned manually, the current, faster transition times call for robust, modular and interpretable solutions that also allow a robotic system to learn how to perform a task. We propose the method Behavior-based Bayesian Optimization and Planning (BeBOP) that combines two approaches for generating behavior trees: we build the structure using a reactive planner and learn specific parameters with Bayesian optimization. The method is evaluated on a set of robotic manipulation benchmarks and is shown to outperform state-of-the-art reinforcement learning algorithms by being up to 46 times faster while simultaneously being less dependent on reward shaping. We also propose a modification to the uncertainty estimate for the random forest surrogate models that drastically improves the results.
(Less)
- author
- Styrud, Jonathan
; Mayr, Matthias
LU
; Hellsten, Erik LU
; Krueger, Volker LU
and Smith, Christian
- organization
- publishing date
- 2024
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- Bayesian Optimization, Behavior Trees, Robotic manipulation, Task Planning
- host publication
- 2024 IEEE International Conference on Robotics and Automation, ICRA 2024
- pages
- 8 pages
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- conference name
- 2024 IEEE International Conference on Robotics and Automation, ICRA 2024
- conference location
- Yokohama, Japan
- conference dates
- 2024-05-13 - 2024-05-17
- external identifiers
-
- scopus:85190848983
- ISBN
- 9798350384574
- DOI
- 10.1109/ICRA57147.2024.10611468
- language
- English
- LU publication?
- yes
- id
- 0366b67b-99d0-4268-b011-1d4c746381b0
- date added to LUP
- 2025-01-16 12:00:39
- date last changed
- 2025-01-16 12:12:24
@inproceedings{0366b67b-99d0-4268-b011-1d4c746381b0, abstract = {{<p>Robotic systems for manipulation tasks are increasingly expected to be easy to configure for new tasks. While in the past, robot programs were often written statically and tuned manually, the current, faster transition times call for robust, modular and interpretable solutions that also allow a robotic system to learn how to perform a task. We propose the method Behavior-based Bayesian Optimization and Planning (BeBOP) that combines two approaches for generating behavior trees: we build the structure using a reactive planner and learn specific parameters with Bayesian optimization. The method is evaluated on a set of robotic manipulation benchmarks and is shown to outperform state-of-the-art reinforcement learning algorithms by being up to 46 times faster while simultaneously being less dependent on reward shaping. We also propose a modification to the uncertainty estimate for the random forest surrogate models that drastically improves the results.</p>}}, author = {{Styrud, Jonathan and Mayr, Matthias and Hellsten, Erik and Krueger, Volker and Smith, Christian}}, booktitle = {{2024 IEEE International Conference on Robotics and Automation, ICRA 2024}}, isbn = {{9798350384574}}, keywords = {{Bayesian Optimization; Behavior Trees; Robotic manipulation; Task Planning}}, language = {{eng}}, pages = {{16459--16466}}, publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}}, title = {{BeBOP-Combining Reactive Planning and Bayesian Optimization to Solve Robotic Manipulation Tasks}}, url = {{http://dx.doi.org/10.1109/ICRA57147.2024.10611468}}, doi = {{10.1109/ICRA57147.2024.10611468}}, year = {{2024}}, }