Sample Pipelines#

Sample pipelines are provided to demonstrate the capabilities of the Humanoid Toolkit. Review the validated hardware configuration before running a pipeline.

These pipelines are designed to showcase core Humanoid Toolkit features, including imitation learning, vision-based manipulation and SLAM. Each pipeline includes a detailed description, along with instructions for running the sample code on your system.

Imitation Learning - ACT

Train and evaluate an Action Chunking Transformer policy in simulation or on a robot.

clickable cards
Model Predictive Control Demo

Combine ACT, OCS2 model predictive control, and MuJoCo simulation.

clickable cards
Diffusion Policy

Evaluate Transformer- and CNN-based diffusion policies on the Push-T task.

clickable cards
VSLAM: ORB-SLAM3

Run visual and visual-inertial SLAM with RGB-D, stereo, or monocular cameras.

clickable cards
LIO SLAM: Point-LIO

Build and run point-cloud lidar-inertial odometry and mapping.

clickable cards
LLM Robotics Demo

Use large-language-model planning and perception in a robotics workflow.

clickable cards
Robotics Diffusion Transformer

Deploy a diffusion-transformer policy for robot manipulation tasks.

clickable cards
Pi0.5 with Real-Time Chunking

Run a Pi0.5 vision-language-action model with real-time action chunking.

clickable cards
OpenClaw + AgenticROS Deployment

Deploy an OpenClaw agent with AgenticROS and an OpenVINO Model Server.

clickable cards
Fast-LIVO2 Demo

Run real-time lidar-inertial-visual odometry and mapping.

clickable cards
LIO SLAM: FAST-LIO2

Build and run high-performance lidar-inertial odometry and mapping.

clickable cards
GEAR-SONIC Introduction

Explore whole-body control for GROOT-based humanoid robotics.

clickable cards
gr00t-n1.7

Optimize and deploy the GR00T N1.7 model with OpenVINO.

clickable cards