EulerAtlas

8-Domain Robot Behavioral Learning Unified Framework

A CLI-based imitation learning framework that trains policies from expert demonstrations and evaluates them in simulation. Spanning 4 classic domains (car, drone, humanoid, robot dog) and 4 industrial domains (mobile manipulation, warehouse AGV, smart farm agri-robot, shipyard crane) — 8 domains total — initialize, train, and simulate on a unified obs/action schema in 3 commands. Now with 11 command groups including edge deployment and a Domain Plugin architecture.

Open Source

Core Features

8 domains, 5 policy models, Domain Plugin architecture, complexity-level-controlled unified workflow

Classic Domains (01-04)

Internal Schema Boundary — all modules communicate consistently through domain-specific fixed-dimension schemas.

Car (Road)	4D state + 2D action — CARLA integration, nuScenes adapter
Drone (Aerial)	6D state + 3D action — AirSim skeleton
Humanoid	12D state + 6D action — MuJoCo Humanoid-v5 integration
Robot Dog (Quadruped)	12D state + 8D action — MuJoCo Ant-v5 integration

Industrial Domains (05-08)

Factory, logistics, agriculture, shipyard — each domain includes a dedicated mock simulator and data adapter.

Mobile Manipulation	18D state + 8D action — Recommended model: ACT
Warehouse AGV	14D state + 4D action — Recommended model: BC-RNN
Smart Farm Agri-Robot	16D state + 6D action — Recommended model: Diffusion
Shipyard Crane	20D state + 9D action — Recommended model: ACT

Policy Models (5 types)

BC-MLP	Basic behavioral cloning (fastest training)
BC-RNN	Time-series behavioral cloning
BC-CNN	Vision-based behavioral cloning
ACT	Action Chunking Transformer (manipulation SOTA)
Diffusion Policy	Diffusion model-based policy (DDPM)

Domain Plugin Architecture

Extensible plugin system for adding new domains, simulators, and data adapters without modifying the core framework.

L0 (Toy)	Mock simulator + BC-MLP — for tutorials/CI
L1 (Intermediate)	Domain-recommended model + Mock — algorithm research
L2 (Advanced)	Real backends (CARLA/MuJoCo/Isaac Lab) + SOTA models

Data Pipeline & Simulation

Complete pipeline from synthetic data generation to simulation rollout

Data Pipeline

Perform the complete data workflow via CLI — from synthetic data generation and external data collection to augmentation and editing.

Pull: Generate/collect synthetic or real expert demonstration data.
Ingest: Convert JSONL/CSV to internal format.
Augment: Data augmentation with noise, mirroring, time jitter, etc.
Edit: Statistics review, filtering, merging, splitting.

Simulation & Evaluation

Run trained policies in simulation and automatically compute evaluation metrics.

Mock Simulator: 8 domain-dedicated built-in simulators — run immediately (no dependencies).
Real Backends: CARLA (cars), MuJoCo (robots), AirSim/IsaacLab (skeleton).
Parallel Simulation: Run N instances concurrently with ParallelSimManager.
Scenario Suite: Build corner-case scenarios and generate pass/fail reports.

CLI Reference

11 command groups cover the entire workflow including edge deployment

`init`

Auto-generate YAML configuration from role and level.

`train`

Train BC policies. Supports resume, GPU, checkpoints, and project tracking.

`sim`

rollout/replay — Run and evaluate policies in simulation.

`data`

pull, ingest, augment, edit — Execute the data pipeline.

`model`

export/load — Manage model cards (SafeTensors + config.json).

`skill`

Query built-in skills, initialize, and perform cross-domain transfer.

`deploy`

Deploy policies via MessageBridge (mock/ROS2/ZeroMQ).

`scenario`

Build corner-case scenarios and run scenario suites.

`validate`

Validate YAML configuration files (50+ rules).

`doctor`

System health check — verify dependencies, backends, and configuration.

`edge`

Edge deployment — export models to ONNX/TFLite, optimize for edge devices.

Architecture

A 4-layer abstraction stack separates roles, configuration, training, and evaluation

4-Layer Stack

Layer 4	Skill/Meta-Agent — Role/mission-based recommendations
Layer 3	Config/Validator — YAML manifest + 50+ validation rules
Layer 2	Data/Model/Training — Pipeline, policy networks, BCTrainer
Layer 1	Sim/Eval/Backend — Simulator, evaluation, trajectories

Technical Specifications

Language	Python 3.12+
Framework	PyTorch, Gymnasium
Simulators	Mock (built-in), CARLA, MuJoCo
Logging	W&B, MLflow (optional)
Model Format	SafeTensors + config.json
Error Format	3-line format (Category / Fix / See)

Tutorials

Step-by-step guides to get started with EulerAtlas quickly

Tutorials coming soon.

Installation & Getting Started

Install EulerAtlas and train your first policy

Installation

pip install -e ".[dev]"

# Get started in 3 lines
euleratlas init --role road --level 0
euleratlas train -c config.yml
euleratlas sim rollout -c config.yml

Requirements

Python 3.12+, PyTorch

MuJoCo, W&B (optional)

GitHub

eulerwa/euleratlas