Bridging available as preprint version on arxiv: the gap between learning-to-plan, motion primitives and safe reinforcement learning
Kicki, Piotr ; Tateo, Davide LU
; Liu, Puze
; Guenster, Jonas
; Peters, Jan
and Walas, Krzysztof
(2025)
8th Conference on Robot Learning, CoRL 2024
In Proceedings of Machine Learning Research
270.
p.2655-2678
- Abstract
Trajectory planning under kinodynamic constraints is fundamental for advanced robotics applications that require dexterous, reactive, and rapid skills in complex environments. These constraints, which may represent task, safety, or actuator limitations, are essential for ensuring the proper functioning of robotic platforms and preventing unexpected behaviors. Recent advances in kinodynamic planning demonstrate that learning-to-plan techniques can generate complex and reactive motions under intricate constraints. However, these techniques necessitate the analytical modeling of both the robot and the entire task, a limiting assumption when systems are extremely complex or when constructing accurate task models is prohibitive. This paper... (More)
Trajectory planning under kinodynamic constraints is fundamental for advanced robotics applications that require dexterous, reactive, and rapid skills in complex environments. These constraints, which may represent task, safety, or actuator limitations, are essential for ensuring the proper functioning of robotic platforms and preventing unexpected behaviors. Recent advances in kinodynamic planning demonstrate that learning-to-plan techniques can generate complex and reactive motions under intricate constraints. However, these techniques necessitate the analytical modeling of both the robot and the entire task, a limiting assumption when systems are extremely complex or when constructing accurate task models is prohibitive. This paper addresses this limitation by combining learning-to-plan methods with reinforcement learning, resulting in a novel integration of black-box learning of motion primitives and optimization. We evaluate our approach against state-of-the-art safe reinforcement learning methods, showing that our technique, particularly when exploiting task structure, outperforms baseline methods in challenging scenarios such as planning to hit in robot air hockey. This work demonstrates the potential of our integrated approach to enhance the performance and safety of robots operating under complex kinodynamic constraints.
(Less)
- author
- Kicki, Piotr
; Tateo, Davide
LU
; Liu, Puze
; Guenster, Jonas
; Peters, Jan
and Walas, Krzysztof
- publishing date
- 2025
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- Motion planning, Motion primitives, Safe reinforcement learning
- host publication
- 8th Conference on Robot Learning, CoRL 2024
- series title
- Proceedings of Machine Learning Research
- volume
- 270
- pages
- 24 pages
- conference name
- 8th Conference on Robot Learning, CoRL 2024
- conference location
- Munich, Germany
- conference dates
- 2024-11-06 - 2024-11-09
- external identifiers
-
- scopus:86000728353
- ISSN
- 2640-3498
- language
- English
- LU publication?
- no
- id
- 36f78571-1e3c-40ac-8426-1bb9c8422901
- alternative location
- https://proceedings.mlr.press/v270/kicki25a.html
- date added to LUP
- 2025-10-16 14:11:56
- date last changed
- 2025-11-03 16:18:21
@inproceedings{36f78571-1e3c-40ac-8426-1bb9c8422901,
abstract = {{<p>Trajectory planning under kinodynamic constraints is fundamental for advanced robotics applications that require dexterous, reactive, and rapid skills in complex environments. These constraints, which may represent task, safety, or actuator limitations, are essential for ensuring the proper functioning of robotic platforms and preventing unexpected behaviors. Recent advances in kinodynamic planning demonstrate that learning-to-plan techniques can generate complex and reactive motions under intricate constraints. However, these techniques necessitate the analytical modeling of both the robot and the entire task, a limiting assumption when systems are extremely complex or when constructing accurate task models is prohibitive. This paper addresses this limitation by combining learning-to-plan methods with reinforcement learning, resulting in a novel integration of black-box learning of motion primitives and optimization. We evaluate our approach against state-of-the-art safe reinforcement learning methods, showing that our technique, particularly when exploiting task structure, outperforms baseline methods in challenging scenarios such as planning to hit in robot air hockey. This work demonstrates the potential of our integrated approach to enhance the performance and safety of robots operating under complex kinodynamic constraints.</p>}},
author = {{Kicki, Piotr and Tateo, Davide and Liu, Puze and Guenster, Jonas and Peters, Jan and Walas, Krzysztof}},
booktitle = {{8th Conference on Robot Learning, CoRL 2024}},
issn = {{2640-3498}},
keywords = {{Motion planning; Motion primitives; Safe reinforcement learning}},
language = {{eng}},
pages = {{2655--2678}},
series = {{Proceedings of Machine Learning Research}},
title = {{Bridging available as preprint version on arxiv: the gap between learning-to-plan, motion primitives and safe reinforcement learning}},
url = {{https://proceedings.mlr.press/v270/kicki25a.html}},
volume = {{270}},
year = {{2025}},
}