Plugin-based robot behavioral-learning framework — first public: Car · Humanoid
A plugin-based CLI robot behavioral learning framework running on an RL→IL pipeline that combines imitation learning (IL) with FastTD3 reinforcement learning (RL). The first two flagship domains we are releasing are car (EulerDrive) and humanoid (EulerWalk) — EulerDrive delivers multi-camera BEV autonomous driving (closed-loop verified on CARLA Town01), and EulerWalk delivers a humanoid RL→IL loco-manipulation policy, with both bundling pretrained models in the package so you can load and run them with no training or simulator at all. The unified obs/action schema is designed to cover 8 domains — car, drone, humanoid, robot dog, mobile manipulation, logistics AGV, agri-robot, shipyard crane — and each domain ships and keeps expanding independently as a Domain Plugin.
Open Source · v0.5.0First-public 2 domains (car · humanoid) + 8-domain schema expanding via plugins · IL + FastTD3 RL · SOTA policy models
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 | 33D state + 14D action (loco-manip) — MuJoCo Humanoid-v5 / HumanoidBench integration |
| Robot Dog (Quadruped) | 12D state + 8D action — MuJoCo Ant-v5 integration |
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 |
| BC-MLP / RNN / CNN | Basic / time-series / vision-based behavioral cloning |
|---|---|
| ACT | Action Chunking Transformer + CVAE (manipulation SOTA) |
| Diffusion Policy | Diffusion model-based policy (DDPM) |
| SOTA (plugin) | BEVFuser (multi-camera BEV), TemporalTransformer (Tesla-FSD style), WholeBodyACT (separate loco/manip heads) |
| RL Actor NEW | FastTD3 off-policy RL (twin critic, n-step) — RL→IL workflow |
| L0 (Toy) | Mock simulator + BC-MLP — for tutorials/CI |
|---|---|
| L1 (Intermediate) | Domain-recommended model + Mock — algorithm research |
| L2 (Advanced) | Real backends (CARLA / MuJoCo / HumanoidBench) + SOTA models |
The first two domains we are releasing. Pretrained models ship in the package, so you can load and run policies with no training or simulator. The remaining domains roll out incrementally as plugins.
Multi-camera BEV-fusion autonomous driving. Built from BEVFuserPolicy + IPM BEV projection + a PID waypoint controller, verified closed-loop on CARLA Town01 3-camera data.
bevfuser_lite_carla_town01.pt.A complete RL→IL pipeline. FastTD3 reinforcement learning (RLTrainer) builds an expert, generates demonstrations, then distills them into a WholeBodyACT imitation policy.
wholebodyact_locomanip.pt, rl_actor_walk.pt.※ The 2 first-public domains (car/humanoid) are research-grade and built on real backends and datasets. The other 6 domains roll out as plugins on the same unified schema.
Complete pipeline from synthetic data generation to simulation rollout
Perform the complete data workflow via CLI — from synthetic data generation and external data collection to augmentation and editing.
Run trained policies in simulation and automatically compute evaluation metrics.
Command groups cover the entire workflow (--lang supports 5 languages)
initAuto-generate YAML configuration from role and level.
trainTrain BC/IL policies. Supports resume, GPU, checkpoints, and project tracking.
train-rl NEWTrain an expert policy with FastTD3 reinforcement learning (RL→IL workflow).
simrollout/replay — Run and evaluate policies. Supports --render / --save-video (MP4).
datapull, ingest, augment, edit, collect, generate-demos — the data pipeline.
modelexport/load — Manage model cards (SafeTensors + config.json).
skillQuery built-in skills, initialize, and perform cross-domain transfer.
deployDeploy policies via MessageBridge (mock/ROS2/ZeroMQ).
scenarioBuild corner-case scenarios and run scenario suites.
validateValidate YAML configuration files (50+ rules).
edgeManage the edge training lifecycle — on-device training, deployment, monitoring.
pluginManage Domain Plugins — register, query, and initialize custom domains.
A 4-layer abstraction stack separates roles, configuration, training, and evaluation
| 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 |
| Domain Plugin | Register custom domains (obs/action schema, simulator, adapters) as plugins |
| Language | Python 3.11+ |
|---|---|
| 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) |
Step-by-step guides to get started with EulerAtlas quickly
Tutorials coming soon.
Install EulerAtlas and train your first policy
Python 3.11+, PyTorch
MuJoCo, W&B (optional)
From cars to shipyard cranes, from expert demonstrations to policies in 3 CLI commands.
Get Started on GitHub Contact Us