Newest papers

LocoPilot: Single-Operator Bilateral Teleoperation for Loco-Manipulation Policy Learning

Antonio Langella, Giovanni Minelli, Giovanni Dessy, Lorenzo Amatucci, Giulio Turrisi, Victor Barasuol, Claudio Semini · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.27998 · cited by 0 works (OpenAlex) · open-access PDF

German

Das Lernen der Pick-Place-Validierungspolitiken erfordert Datendemonstrationen, die die koordinierte Basis- und Armbewegung auf dem Ziel-Implementierungsmodus erfassen. Robot-freie Schnittstellen ermöglichen es, Demonstrationen unabhängig vom Zielroboter zu sammeln, die gleiche Flexibilität erhöhen, aber ohne direkt plattformspezifische Befehle zu erfassen, proprioception und körpermontierte Beobachtungen. On-Robot-Teleoperation erlaubt es, diese Signale direkt zu erfassen, erfordert aber eine Schnittstelle, die in der Lage ist, das komplette System gleichzeitig zu befehlen. Dieses Papier präsentiert die vollständige Bewegungskamera LocoPilot, ein einzelner Operator bilaterale Teleoperation und Datener

Machine translation (Meta M2M100); the English original follows.

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 teleoperation 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-DoF 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 teleoperation 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 demonstrations and deploying on the physical robot without action retargeting or additional inverse kinematics. Code available at: https://github.com/iit-DLSLab/LocoPilot

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Teleoperation, Haptic technology, Computer science, Interface (matter), Pipeline (software), Retargeting

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange