LocoPilot: Single-Operator Bilateral Teleoperation for Loco-Manipulation Policy Learning
LocoPilot: Single-Operator Bilateral Teleoperation for Loco-Manipulation Policy Learning
This paper presents LocoPilot, a single-operator bilateral teleoperation framework for loco-manipulation policy learning. It enables direct capture of robot-specific signals like proprioception and body-mounted observations without motion-capture instrumentation. The system integrates a 12-DoF quadruped with a 6-DoF manipulator, using two handheld controllers and a follower arm for force feedback. A ROS~2 pipeline records synchronized multimodal data and a unified 11D action space, validated through deployment on a physical robot without retargeting or additional inverse kinematics.
LocoPilot introduces a novel teleoperation framework for loco-manipulation policy learning, combining human control with direct robot signal capture without motion-capture instrumentation. The system enables seamless data collection and deployment on a 12-DoF quadruped with a manipulator, validated through fine-tuning and physical deployment without additional kinematics.
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
degrees of freedom
12
View original evidence
tion allows to capture these signals directly, but requires an interface capable of commanding the complete system concurrently. This paper presents LocoPilot, a single-operator bilateral teleoperation and data-collection framework implemented on a 12-DoF Unitree Go2 quadruped equipped with a 6-DoF AgileX Piper L manipulator, an Intel RealSense D435 wrist camera, and an Intel RealSense D405 head camera. A second 6-Do
Open source S3
- code: Available Artifact link Open source S6
- paper: not_reported
- weights: not_reported
- dataset: not_reported
- code: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
arXiv:2610.27998v1 Announce Type: new Abstract: Learning loco-manipulation policies requires demonstrations that capture coordinated base and arm motion on the target embodiment. Robot-free interfaces allow demonstrations to be collected independently of the target robot, increasing flexibility but without directly capturing platform-specific commands, proprioception, and body-mounted observations. On-robot teleopera
Open source S2
tion allows to capture these signals directly, but requires an interface capable of commanding the complete system concurrently. This paper presents LocoPilot, a single-operator bilateral teleoperation and data-collection framework implemented on a 12-DoF Unitree Go2 quadruped equipped with a 6-DoF AgileX Piper L manipulator, an Intel RealSense D435 wrist camera, and an Intel RealSense D405 head camera. A second 6-Do
Open source S3
F Piper L arm, used as the leader and two handheld controllers provide simultaneous control of the base, body posture, manipulator, and gripper. The follower arm interaction forces are estimated without a dedicated force/torque sensor and rendered to the operator through a passivity-constrained haptic channel. A ROS~2 pipeline records synchronized multimodal observations together with a unified 11D action shared by t
Open source S4
eleoperation and policy deployment. Compared to prior work, LocoPilot uniquely unifies robot-in-the-loop legged data collection, force feedback without motion-capture instrumentation, and the same action interface at deployment. We evaluate the interface across multiple loco-manipulation tasks and validate the complete collection-to-deployment pipeline by fine-tuning MolmoAct2 \cite{MOLMO} on pick-and-place demonstra
Open source S5
tions and deploying on the physical robot without action retargeting or additional inverse kinematics. Code available at: https://github.com/iit-DLSLab/LocoPilot
Open source S6
Source：arXiv Robotics — research abstracts · arxiv.org