ROSClaw: An OpenClaw ROS 2 Framework for Agentic Robot Control and Interaction
For robotics researchers and engineers, ROSClaw offers a standardized, reproducible framework to evaluate and deploy foundation models on physical robots, addressing the bespoke integration bottleneck.
ROSClaw provides a model-agnostic executive layer integrating OpenClaw with ROS 2, enabling any foundation model to control diverse robots via dynamic capability discovery, multimodal observation normalization, pre-execution safety validation, and audit logging. Deployed on three platforms with four backends, it reveals up to 4.8x differences in out-of-policy action proposal rates and shows that executive-layer design significantly affects task completion and safety.
Foundation models can endow robots with open-ended reasoning, language understanding, and adaptive planning, yet connecting a model to a physical robot today requires bespoke integration that couples perception, actuation, and safety to a single model and platform. We present ROSClaw, a model-agnostic executive layer that integrates the OpenClaw agent runtime with ROS 2, enabling any foundation model to perceive, reason about, and act on any ROS-enabled robot through (i) dynamic capability discovery with standardized affordance injection, (ii) multimodal observation normalization, (iii) pre-execution action validation within a configurable safety envelope, and (iv) structured audit logging. Swapping model backends or robot platforms is a configuration change; tool schemas, safety enforcement, and provenance logging remain invariant. We deploy ROSClaw on three platforms (wheeled, quadruped, humanoid) with four foundation-model backends. Under this controlled substrate, models exhibit up to 4.8 x differences in out-of-policy action proposal rates (3.4 x among frontier models alone) and produce qualitatively distinct physical behaviors from identical commands. A cross-framework parity protocol against ROSA confirms that executive-layer design, not just prompt wording, significantly affects both task completion and safety behavior, establishing ROSClaw as both practical agentic-robot infrastructure and a reproducible measurement instrument for embodied AI.