Deploying Custom Control Policies on the Unitree G1

This hands-on course teaches you to deploy reinforcement-learning locomotion policies on the Unitree G1 humanoid using RoboJuDo. Across twelve lessons you will install the stack, learn MuJoCo simulation, explore neural-network policies for walking, dancing, and martial arts, and understand the pipeline architecture that connects controllers, environments, and policies. You will test every configuration in simulation—single-policy, multi-policy switching, and locomotion-mimic blending—then move to real hardware for calibration, a first-walk checklist, and troubleshooting. By the end you will confidently take a policy from an ONNX checkpoint to stable execution on a 29-DOF humanoid

Course•By Fred

GR00T-Whole Body Control
with the Unitree G1

Course•By Fred

HDMI: Video-Based Humanoid Control

This course teaches how to learn humanoid robot movements directly from human videos and deploy them on real humanoid robots. Students will start by capturing and analyzing videos of human motion, then converting those videos into structured motion datasets compatible with the Unitree G1 humanoid. The course covers motion extraction, data cleaning, and dataset formatting for whole-body control. Students will retrain these datasets into movement policies using modern robot learning techniques, visualize and debug motions in simulators such as MuJoCo or Isaac Sim, and iteratively refine performance. The course concludes with deploying trained movement policies onto real Unitree G1 hardware, bridging simulation and real-world humanoid control. By the end of the course, students will understand the full pipeline from human video → motion dataset → learned policy → simulated validation → real humanoid deployment.

Course•By Fred

Introduction to ROS 2 with Unitree G1

System Architecture – From Algorithm to Robot Motion Installing ROS 2 and Verifying the Environment ROS 2 Workspace & Package Creation ROS 2 Communication Fundamentals Writing ROS 2 Control Node (Python) Writing ROS 2 Control Node (C++) Unitree G1 SDK Setup & Exploration Direct Robot Control Using SDK ROS ↔ SDK Bridge Node MuJoCo Simulation with ROS 2

Course•By Lentin Joseph

Intro to the Unitree G1

Course•By Fred

Mastering Humanoid Simulation with MuJoCo & the G1

Course Outline: 1️⃣ Install MuJoCo and verify setup. 2️⃣ Import and explore the Unitree G1 humanoid model. 3️⃣ Learn MuJoCo’s interface—start, pause, reset, and analyze runtime stats. 4️⃣ Understand physics solvers, integrators, and balance mechanics. 5️⃣ Tune simulation parameters for smooth, stable motion. 6️⃣ Adjust environmental physics like gravity, wind, and friction. 7️⃣ Run G1 motion demos (walk, run, squat). 8️⃣ Load human motion data and try interactive control. 9️⃣ Visualize datasets in 3D using Rerun to replay humanoid motion. 🔟 Use Rerun for analysis—compare walking vs dancing, identify motion differences, and evaluate realism.

Course•By Fred

OM1 Integration on G1: Powered by OpenMind

Unlock the full potential of the Unitree G1 Humanoid Robot with this advanced, hands-on course — developed in collaboration with the team at OpenMind. Designed for researchers, engineers, and advanced robotics enthusiasts, this training takes you from setup and connectivity to intelligent motion control and teleoperation using NVIDIA Jetson Orin, ROS2 Humble, and OM1 Agent Architecture. Through real-world examples and guided exercises, you’ll learn how to connect, configure, and program the G1 for powerful AI-driven applications. Master ROS2 networking, CycloneDDS optimization, Python customization, and VR-based teleoperation, all while understanding the underlying agent architecture that powers the robot’s intelligence.

Course•By Fred

OpenMind Course Bundle

Bundle

RoboUniversity Multi Course Bundle

Bundle

Sim2Real: Embodied AI with Isaac Sim and Unitree G1

Course Outline Orientation – Overview, outcomes, system requirements Install & Verify – Install Isaac Sim, set up Isaac Lab, project structure USD & PhysX – USD basics, PhysX physics, scene assembly Sensors & Observations – IMU, force sensors, height data, observation terms Commands & Actions – Velocity/waypoint commands, action spaces, scaling MDP – Rewards, terminations, events, randomization hooks Terrain & Curriculum – Terrain generators and difficulty progression Perf & VecEnv – Vectorized environments, async/headless rendering RL (RSL-RL) – PPO training, key hyperparameters, debugging rewards Go1 Task – Go1 model, locomotion env, domain randomization Obstacles & Cues – Goals, markers, obstacles, navigation cues Eval & Logs – TensorBoard/W&B, saving and loading policies Sim2Sim – ROS 2 bridging, packaging policies as ROS nodes Sim2Real (Go1) – Bring-up, safety, deployment, tuning, validation Troubleshooting – Common issues and fixes

Course•By Dave Erath

Unitree Go2: Setup and Operation Essentials

Module 1: Getting Started – Unbox your Unitree Go2, connect it to the app, update firmware, and perform calibration for optimal performance. Module 2: Core Setup & Movement – Learn posture and movement control, set up accompanying and Benben modes, switch perspectives in the app, and connect the remote for manual operation. Module 3: Programming & Advanced Features – Explore graphic programming, audio playback, leash mode, AI mode, advanced controls, and mapping/navigation tools to unlock the full potential of your Go2.

Course•By Fred

VLA on the Unitree G1: Vision-Language-Action

Course Outline Module 1: Visual Navigation Foundations 1.0 Install and Environment Setup 1.1 G1 Startup and Obstacle Avoidance 1.2 Walk Toward an Orange Chair 1.3 Walk Through a Doorway Module 2: UniFoLM-VLA 2.0 Install UniFoLM-VLA 2.1 Pick-and-Place 2.2 Sequential Block Placement Module 3: UniFoLM World Model Action (WMA) 3.0 Install UniFoLM-WMA 3.1 Anticipatory Reach-and-Grasp Module 4: GR00T Whole-Body Control & VLA Deployment 4.0 Install GEAR-SONIC and GR00T Dependencies 4.1 GEAR-SONIC Locomotion Showcase with Keyboard Control 4.2 GEAR-SONIC Locomotion with Gamepad Control 4.3 VR Teleoperation Data Collection for Loco-Manipulation 4.4 Fine-Tune GR00T N1.6 on G1 Demonstration Data

Course•By Fred

WebRTC Control for 
Unitree G1 and GO2

This course, “Zero-to-Robot WebRTC: Controlling Unitree Go2 & G1 from Scratch,” guides learners through building a complete real-time control pipeline for robotic systems using WebRTC, starting with establishing secure connections and network discovery, progressing into sending motion, posture, and expressive commands, and ultimately streaming video, audio, and LiDAR data from the robot. Across Modules 1–3, students gain hands-on experience with CLI-based control, REPL interaction, and media pipelines while developing a deep understanding of networking (SDP/ICE), real-time communication, and sensor data handling, culminating in the ability to remotely operate and monitor advanced robots like the Unitree Go2 and G1 using a modern, low-latency communication stack

Course•By Fred