isaac-sim

Entry point for Isaac Sim synthetic data generation (SDG) with actors, humans, robots, events, incidents, captions, or cameras. Use when planning an Action and Event Data Generation (AEDG) run.

Generate deterministic USD lighting override sublayers for Actor SDG. Use when randomizing lights, creating lighting variations, or preparing IRA prop_asset_paths.

Generate validated Isaac Sim Replicator Agent YAML variations and optionally batch-run Actor SDG. Use when sweeping an IRA config or preparing batch Actor SDG runs.

LLM-driven Behavior Tree Generation for Isaac Sim: turn a natural-language scenario into behavior-tree files. Use when generating a tree, authoring context/schema, or scripting the planner.

Extract camera intrinsics, extrinsics, and FOV polygons to calibration.json. Use after cameras are placed; to place them first use place-camera-max-coverage.

Headless Replicator SDG for static scenes (writers, poses, Kitti). Use when collecting annotated training data. Do NOT use for mobile-robot SDG (use mobility-gen).

Author and validate the IRI event config YAML defining topple, fire, and spill incidents. Use when writing or debugging an incident config; to drive events use run-incident-events.

USD camera setup, render products, intrinsics, and lens distortion. Use when configuring Isaac Sim cameras.

Writes and validates Isaac Lab package changelog fragments using the repository fragment format and bump rules. Use when source package changes need release notes, migration guidance, or changelog validation.

Audits one open GitHub issue against current code to decide close or keep-open, and drafts the closing comment. Use when deciding whether a specific issue is still valid, whether a reported bug was fixed, or what to reply before closing.

Gates new or changed Isaac Lab tests at write time and audits existing tests for low-value, implementation-coupled, or duplicated coverage, including parametrize matrices and scene builds that repeat one code path. Use when writing, changing, reviewing,…

Keeps the generated environment browser synchronized with task registrations and preset selectors. Use when adding or renaming an Isaac Lab environment, changing its physics, renderer, or domain presets, or reviewing environment documentation completeness.

Installs Isaac Lab end-to-end with minimal user interaction. Auto-detects the system with read-only checks, picks the right install method (uv checkout, uv-managed environment, Isaac Sim source build, Isaac Lab wheel, or Docker) from the install docs, applies…

Migrates Isaac Lab 2.x projects to Isaac Lab 3.0 by routing agents through the official migration guide, current source APIs, and focused compatibility checks. Use when users mention Isaac Lab 3.0 migration, 2.x projects, actuator collection changes,…

Migrates Isaac Gym tasks, assets, vectorized environments, and training workflows to Isaac Lab. Use when porting Isaac Gym environments, legacy Gym tasks, or Isaac Gym reinforcement learning code to Isaac Lab.

Migrates PhysX-compatible robot, object, and scene assets to Isaac Lab's Newton backend with MJWarp. Use when handling existing Isaac Lab assets or new multi-physics conversion, per-solver asset configuration, mass or inertia warnings, contact slip and…

Create or modify Isaac Lab-Arena environments, scenes, tasks, completion predicates, placement constraints, and environment variations by composing existing features. Use for environment authoring and feature discovery; use run-experiment to execute an…

Runs existing Isaac Lab-Arena Experiment Definitions locally with experiment_runner.py in a ready native or Docker runtime, coordinates required local OpenPI or GR00T servers, applies local CLI overrides, and verifies generated result and report artifacts.…

Creates Arena-conformant commits and pull requests. Enforces DCO sign-off (git commit -s), no AI attribution lines (no Co-Authored-By, no Generated-with-Claude footers), <username>/<type>/<short-description> branch naming, separate new commits rather than…

Sets up and verifies a runnable Isaac Lab-Arena checkout using the supported native uv or Docker route. Use when installing Arena, preparing a fresh checkout to run examples or evaluations, choosing between uv and Docker, starting or attaching to the Arena…

Starts, reuses, verifies, and explicitly stops the local Dockerized OpenPI inference server used by Isaac Lab-Arena Pi0RemotePolicy experiments. Use when serving pi05 or pi0 locally, selecting an OpenPI port or variant, checking whether the OpenPI server is…

Downloads Isaac Lab-Arena OSMO workflow output (evaluation results, videos, HDF5 demos) to a local folder with `osmo data download`. Use when the user gives one or more OSMO workflow names and a destination folder and wants the data pulled down locally. Do…

Starts, reuses, verifies, and explicitly stops the local GR00T inference server used by Isaac Lab-Arena Gr00tRemoteClosedloopPolicy experiments. Use when serving the maintained N1.6-DROID policy locally, selecting a GR00T port or model, checking server…

Bootstraps and maintains the Docker environment used when contributing to Isaac Lab-Arena. Use when preparing a checkout for development, installing contributor hooks, rebuilding the Arena image with or without cache, inspecting the clone-specific container,…

Deploy and operate a cloud Isaac Workstation with Isaac Automator: provision a GPU VM running Isaac Sim, Isaac Lab, and/or Isaac Lab Arena on AWS, GCP, Azure, or Alibaba Cloud, connect to it, move data in and out, control cost with stop/start, repair, import…

Prepare and publish this repository's releases by selecting internal dev commits, squashing them into one commit on main, and creating an annotated release tag, using origin as the only remote. Use when checking release readiness, identifying unreleased…

Generate amplified robot-demonstration datasets with NVIDIA AutoData. Record and annotate demonstrations, author task-descriptor / embodiment / environment-profile YAML, choose the right generation algorithm (MimicGen for single-arm, DexMimicGen for bimanual,…