Bridging the gap between Learning-to-plan, Motion Primitives and Safe Reinforcement Learning

Piotr Kicki, Davide Tateo, Puze Liu, Jonas Günster, Jan Peters, Krzysztof Walas
Proceedings of The 8th Conference on Robot Learning, PMLR 270:2655-2678, 2025.

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 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.

Cite this Paper


BibTeX
@InProceedings{pmlr-v270-kicki25a, title = {Bridging the gap between Learning-to-plan, Motion Primitives and Safe Reinforcement Learning}, author = {Kicki, Piotr and Tateo, Davide and Liu, Puze and G{\"{u}}nster, Jonas and Peters, Jan and Walas, Krzysztof}, booktitle = {Proceedings of The 8th Conference on Robot Learning}, pages = {2655--2678}, year = {2025}, editor = {Agrawal, Pulkit and Kroemer, Oliver and Burgard, Wolfram}, volume = {270}, series = {Proceedings of Machine Learning Research}, month = {06--09 Nov}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v270/main/assets/kicki25a/kicki25a.pdf}, url = {https://proceedings.mlr.press/v270/kicki25a.html}, 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 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.} }
Endnote
%0 Conference Paper %T Bridging the gap between Learning-to-plan, Motion Primitives and Safe Reinforcement Learning %A Piotr Kicki %A Davide Tateo %A Puze Liu %A Jonas Günster %A Jan Peters %A Krzysztof Walas %B Proceedings of The 8th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2025 %E Pulkit Agrawal %E Oliver Kroemer %E Wolfram Burgard %F pmlr-v270-kicki25a %I PMLR %P 2655--2678 %U https://proceedings.mlr.press/v270/kicki25a.html %V 270 %X 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.
APA
Kicki, P., Tateo, D., Liu, P., Günster, J., Peters, J. & Walas, K.. (2025). Bridging the gap between Learning-to-plan, Motion Primitives and Safe Reinforcement Learning. Proceedings of The 8th Conference on Robot Learning, in Proceedings of Machine Learning Research 270:2655-2678 Available from https://proceedings.mlr.press/v270/kicki25a.html.

Related Material