BeyondContact: A Reinforcement Learning Framework for Airflow-Based Non-Contact Manipulation
BeyondContact: A Reinforcement Learning Framework for Airflow-Based Non-Contact Manipulation
This research introduces BeyondContact, a robot- and task-agnostic airflow extension for Isaac Lab that enables reinforcement learning for non-contact manipulation. The framework combines contact-based pushing with airflow manipulation (HPB policy) and uses airflow alone for reorientation (RR policy). A lightweight, high-speed blower was designed to coexist with a gripper. In zero-shot real-world tests, the hybrid push-blow policy achieved an 80% success rate over 20 trials, while the rectangular reorientation policy achieved a mean absolute heading error of 2.6 degrees across four target headings. The project materials are available on GitHub.
The authors present a reinforcement learning framework for non-contact manipulation using airflow, validated in zero-shot real-world deployment with specific success metrics and error rates.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
Reported numbers
Reported success rate
80%
Reported zero-shot result; the excerpt does not specify an evaluation protocol.
Reported trials
View original evidence
policy that combines contact-based pushing with airflow manipulation and a rectangular reorientation (RR) policy that controls a cuboid's heading using airflow alone. To enable physical execution, we design a lightweight, high-speed blower that coexists with a gripper. In zero-shot real-world deployment, HPB achieves an 80% success rate over 20 trials, while RR achieves a mean absolute heading error of 2.6 degrees a
Open source S4heading error
2.6
View original evidence
policy that combines contact-based pushing with airflow manipulation and a rectangular reorientation (RR) policy that controls a cuboid's heading using airflow alone. To enable physical execution, we design a lightweight, high-speed blower that coexists with a gripper. In zero-shot real-world deployment, HPB achieves an 80% success rate over 20 trials, while RR achieves a mean absolute heading error of 2.6 degrees a
Open source S4
What remains unknown
Not established in the collected evidence: Environment, Control, Data origin.
Reported performance applies to the described task. It does not establish general autonomy or deployment readiness.
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
arXiv:2611.03059v1 Announce Type: new Abstract: Contact-based robotic manipulation is constrained by end-effector reachability and the mechanical properties of objects. Airflow can exert forces without direct robot-object contact, enabling manipulation of objects beyond the reach or when direct contact is undesirable. However, the lack of suitable simulation has hindered the application of reinforcement learning to a
Open source S2
policy that combines contact-based pushing with airflow manipulation and a rectangular reorientation (RR) policy that controls a cuboid's heading using airflow alone. To enable physical execution, we design a lightweight, high-speed blower that coexists with a gripper. In zero-shot real-world deployment, HPB achieves an 80% success rate over 20 trials, while RR achieves a mean absolute heading error of 2.6 degrees a
Open source S4
cross four target headings. The project materials are available at https://github.com/iit-DLSLab/BeyondContact.
Open source S5
Source：arXiv Robotics — research abstracts · arxiv.org