Representation Handoffs for OpenArm-Based Laboratory Mobile Manipulation
This work addresses the challenge of reliably aligning language instructions and observations to safe actions for language-guided laboratory automation, providing a practical debugging interface for embodied AI system integrators.
This paper presents an OpenArm-based mobile manipulation prototype for laboratory tasks, integrating dual OpenArm manipulators with a mobile base, RGB-D sensing, and ROS2/MoveIt execution. The system uses representation handoffs to constrain natural language requests into skill calls and ground sensor observations into maps and object poses, which helps expose deployment blockers like missing calibration and incomplete object assets.
Open-source robotics and foundation models have lowered the barrier to embodied AI, yet language-guided laboratory automation still requires reliable alignment from instructions and observations to safe actions. This field report presents an OpenArm-based mobile manipulation prototype for laboratory-style tasks, built by integrating dual OpenArm manipulators with a mobile base, vertical slide, RGB-D sensing, lidar-based mapping, ROS2/MoveIt execution, and profile-defined skill interfaces. The system is organized around representation handoffs: natural language requests are constrained into registered skill calls, sensor observations are grounded into maps and object poses, object priors provide role and skill constraints, and runtime bindings compile validated skills into executable motion goals. We use dry-run traces and startup checks to evaluate this integration path, showing how the prototype exposes missing calibration, incomplete object assets, and unfinished real-scene visual grounding as explicit deployment blockers. These intermediate representations serve as practical debugging interfaces for integrating language, perception, planning, and robot safety in embodied systems.