Learning to Open and Traverse Doors with a Legged Manipulator

Mike Zhang, Yuntao Ma, Takahiro Miki, Marco Hutter
Proceedings of The 8th Conference on Robot Learning, PMLR 270:2913-2927, 2025.

Abstract

Using doors is a longstanding challenge in robotics and is of significant practical interest in giving robots greater access to human-centric spaces. The task is challenging due to the need for online adaptation to varying door properties and precise control in manipulating the door panel and navigating through the confined doorway. To address this, we propose a learning-based controller for a legged manipulator to open and traverse through doors. The controller is trained using a teacher-student approach in simulation to learn robust task behaviors as well as estimate crucial door properties during the interaction. Unlike previous works, our approach is a single control policy that can handle both push and pull doors through learned behaviour which infers the opening direction during deployment without prior knowledge. The policy was deployed on the ANYmal legged robot with an arm and achieved a success rate of 95.0% in repeated trials conducted in an experimental setting. Additional experiments validate the policy’s effectiveness and robustness to various doors and disturbances. A video overview of the method and experiments is provided in the supplementary material.

Cite this Paper

BibTeX
@InProceedings{pmlr-v270-zhang25g, title = {Learning to Open and Traverse Doors with a Legged Manipulator}, author = {Zhang, Mike and Ma, Yuntao and Miki, Takahiro and Hutter, Marco}, booktitle = {Proceedings of The 8th Conference on Robot Learning}, pages = {2913--2927}, 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/zhang25g/zhang25g.pdf}, url = {https://proceedings.mlr.press/v270/zhang25g.html}, abstract = {Using doors is a longstanding challenge in robotics and is of significant practical interest in giving robots greater access to human-centric spaces. The task is challenging due to the need for online adaptation to varying door properties and precise control in manipulating the door panel and navigating through the confined doorway. To address this, we propose a learning-based controller for a legged manipulator to open and traverse through doors. The controller is trained using a teacher-student approach in simulation to learn robust task behaviors as well as estimate crucial door properties during the interaction. Unlike previous works, our approach is a single control policy that can handle both push and pull doors through learned behaviour which infers the opening direction during deployment without prior knowledge. The policy was deployed on the ANYmal legged robot with an arm and achieved a success rate of 95.0% in repeated trials conducted in an experimental setting. Additional experiments validate the policy’s effectiveness and robustness to various doors and disturbances. A video overview of the method and experiments is provided in the supplementary material.} }
Endnote
%0 Conference Paper %T Learning to Open and Traverse Doors with a Legged Manipulator %A Mike Zhang %A Yuntao Ma %A Takahiro Miki %A Marco Hutter %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-zhang25g %I PMLR %P 2913--2927 %U https://proceedings.mlr.press/v270/zhang25g.html %V 270 %X Using doors is a longstanding challenge in robotics and is of significant practical interest in giving robots greater access to human-centric spaces. The task is challenging due to the need for online adaptation to varying door properties and precise control in manipulating the door panel and navigating through the confined doorway. To address this, we propose a learning-based controller for a legged manipulator to open and traverse through doors. The controller is trained using a teacher-student approach in simulation to learn robust task behaviors as well as estimate crucial door properties during the interaction. Unlike previous works, our approach is a single control policy that can handle both push and pull doors through learned behaviour which infers the opening direction during deployment without prior knowledge. The policy was deployed on the ANYmal legged robot with an arm and achieved a success rate of 95.0% in repeated trials conducted in an experimental setting. Additional experiments validate the policy’s effectiveness and robustness to various doors and disturbances. A video overview of the method and experiments is provided in the supplementary material.
APA
Zhang, M., Ma, Y., Miki, T. & Hutter, M.. (2025). Learning to Open and Traverse Doors with a Legged Manipulator. Proceedings of The 8th Conference on Robot Learning, in Proceedings of Machine Learning Research 270:2913-2927 Available from https://proceedings.mlr.press/v270/zhang25g.html.

Related Material