OPENRGD · ROBOT GRAPH DEFINITION
OpenRGD is the project and open standard. Robot Graph Definition — RGD — is the modular machine-readable representation it defines for describing a robot body, its constraints, capabilities, provenance, lifecycle and higher-level embodiment context.
OPENRGD
OpenRGD owns the canonical specification source, authority model, maturity language, cross-component contracts, reference tooling and the governance process around Robot Graph Definition.
RGD
An RGD profile can represent physical evidence, operational constraints, declared capabilities, governance context and lifecycle state while preserving explicit boundaries between evidence, enrichment and downstream physical execution.
WHAT RGD ADDS
Profile identity, manifests and integrity commitments.
Physical facts can be imported while preserving source provenance.
Constraints and safety context stay explicit instead of hiding in runtime code.
Agency can declare what an embodiment can do and how actions are represented.
Wear, adaptation and continuity can evolve without rewriting historical evidence.
Semantic context stops before hardware-specific execution authority begins.
SEVEN DOMAINS
Identity, manifests, coordination and cross-domain orchestration.
Physical body, hardware reality and source-supported evidence.
Operational constraints, safety and runtime validation context.
Capabilities, world-model context and action semantics.
Values, alignment and decision governance.
Lifecycle, wear, adaptation and continuity.
Collective, social and inter-agent semantics.
CURRENT ARTIFACT AXES
Matching version numbers never imply equivalent maturity or compatibility. The standard bundle, Python toolchain and agent contracts remain separate release axes.
COMPLEMENTARY LAYERS
Links, joints, geometry, inertials, collision and joint constraints in a ROS-centric XML model.
Not a general scene-composition system or semantic embodiment graph.
USDComposable scene descriptionLarge hierarchical scenegraphs, references, variants, time-sampled data and physics schemas.
Not a robot-specific semantic capability or governance model by default.
SDFSimulation-oriented model and world descriptionRobots, environments, models, sensors, physics, lights, plugins and simulation context.
Not designed as a general AI embodiment-governance or provenance graph.
MJCFMuJoCo-native dynamic-system modelNested bodies, joints, actuators, tendons, sensors, defaults and simulator-native dynamic modeling.
Optimized for MuJoCo rather than cross-stack semantic embodiment.
RGDSemantic embodiment graphIdentity, physical evidence, operational constraints, capability semantics, provenance and lifecycle context.
Does not replace scene composition, a physics engine, middleware or a physical runtime.
The canonical repository does not ship a physical embodied runtime or Body Adapter. Validation, compilation and grounding context do not prove hardware compatibility, operational safety or execution authorization.
NEXT