An Open-Source Soft Robotic Platform for Autonomous Aerial Manipulation in the Wild

Erik Bauer, Marc Blöchlinger, Pascal Strauch, Arman Raayatsanati, Cavelti Curdin, Robert K. Katzschmann
Proceedings of The 8th Conference on Robot Learning, PMLR 270:3094-3106, 2025.

Abstract

Aerial manipulation combines the versatility and speed of flying platforms with the functional capabilities of mobile manipulation, which presents significant challenges due to the need for precise localization and control. Traditionally, researchers have relied on off-board perception systems, which are limited to expensive and impractical specially equipped indoor environments. In this work, we introduce a novel platform for autonomous aerial manipulation that exclusively utilizes onboard perception systems. Our platform can perform aerial manipulation in various indoor and outdoor environments without depending on external perception systems. Our experimental results demonstrate the platform’s ability to autonomously grasp various objects in diverse settings. This advancement significantly improves the scalability and practicality of aerial manipulation applications by eliminating the need for costly tracking solutions. To accelerate future research, we open source our modern ROS 2 software stack and custom hardware design, making our contributions accessible to the broader research community.

Cite this Paper


BibTeX
@InProceedings{pmlr-v270-bauer25a, title = {An Open-Source Soft Robotic Platform for Autonomous Aerial Manipulation in the Wild}, author = {Bauer, Erik and Bl{\"{o}}chlinger, Marc and Strauch, Pascal and Raayatsanati, Arman and Curdin, Cavelti and Katzschmann, Robert K.}, booktitle = {Proceedings of The 8th Conference on Robot Learning}, pages = {3094--3106}, 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/bauer25a/bauer25a.pdf}, url = {https://proceedings.mlr.press/v270/bauer25a.html}, abstract = {Aerial manipulation combines the versatility and speed of flying platforms with the functional capabilities of mobile manipulation, which presents significant challenges due to the need for precise localization and control. Traditionally, researchers have relied on off-board perception systems, which are limited to expensive and impractical specially equipped indoor environments. In this work, we introduce a novel platform for autonomous aerial manipulation that exclusively utilizes onboard perception systems. Our platform can perform aerial manipulation in various indoor and outdoor environments without depending on external perception systems. Our experimental results demonstrate the platform’s ability to autonomously grasp various objects in diverse settings. This advancement significantly improves the scalability and practicality of aerial manipulation applications by eliminating the need for costly tracking solutions. To accelerate future research, we open source our modern ROS 2 software stack and custom hardware design, making our contributions accessible to the broader research community.} }
Endnote
%0 Conference Paper %T An Open-Source Soft Robotic Platform for Autonomous Aerial Manipulation in the Wild %A Erik Bauer %A Marc Blöchlinger %A Pascal Strauch %A Arman Raayatsanati %A Cavelti Curdin %A Robert K. Katzschmann %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-bauer25a %I PMLR %P 3094--3106 %U https://proceedings.mlr.press/v270/bauer25a.html %V 270 %X Aerial manipulation combines the versatility and speed of flying platforms with the functional capabilities of mobile manipulation, which presents significant challenges due to the need for precise localization and control. Traditionally, researchers have relied on off-board perception systems, which are limited to expensive and impractical specially equipped indoor environments. In this work, we introduce a novel platform for autonomous aerial manipulation that exclusively utilizes onboard perception systems. Our platform can perform aerial manipulation in various indoor and outdoor environments without depending on external perception systems. Our experimental results demonstrate the platform’s ability to autonomously grasp various objects in diverse settings. This advancement significantly improves the scalability and practicality of aerial manipulation applications by eliminating the need for costly tracking solutions. To accelerate future research, we open source our modern ROS 2 software stack and custom hardware design, making our contributions accessible to the broader research community.
APA
Bauer, E., Blöchlinger, M., Strauch, P., Raayatsanati, A., Curdin, C. & Katzschmann, R.K.. (2025). An Open-Source Soft Robotic Platform for Autonomous Aerial Manipulation in the Wild. Proceedings of The 8th Conference on Robot Learning, in Proceedings of Machine Learning Research 270:3094-3106 Available from https://proceedings.mlr.press/v270/bauer25a.html.

Related Material