Simulation

Dissect LAFAN1_MCAP_WORKING.py and convert G1 CSV poses into /tf MCAP for kinematic playback in Foxglove.

Bring up Unitree G1 in MuJoCo through SDK2 DDS: robot, scene, domain, interface, joystick, and real low-level topics.

Trace the Isaac Lab Mimic GR-1 nut-pouring pipeline and separate ownership of seed demos, generated HDF5 rollouts, and normalization params.

Beginner-friendly walkthrough of Wheeled Lab — open-source ecosystem to train RC cars to drift, climb, and visually navigate in Isaac Lab and deploy zero-shot to real hardware under $1000.

Hands-on guide to NVIDIA Newton 1.0 — the fastest open-source GPU physics engine for sim-to-real robotics, 475x faster than MJX.

Step-by-step guide to setting up Genie Sim 3.0 — AGIBOT's open-source simulation platform on Isaac Sim for training humanoid robots.

Industrial simulation applications — digital twins, ROS 2 + Gazebo/Isaac integration for smart manufacturing.

Simulate robots in Gazebo Harmonic, record/replay data with rosbag2 (MCAP), and master the ROS 2 debugging toolkit — the series finale for beginners (Jazzy, June 2026).

End-to-end guide: train policies in simulation, evaluate, apply domain randomization, deploy to real robot, and iterate.

Setup Isaac Lab, train locomotion policies with 4,096 parallel environments and domain randomization on GPU.

Hands-on MuJoCo tutorial — installation, MJCF model creation, robot arm simulation, and visualization with Python.

Compare 3 leading simulators for robotics — physics accuracy, speed, ecosystem, and when to use each.

Theory and practice of domain randomization — visual, dynamics, sensor randomization with successful case studies.

Benchmark physics accuracy, GPU throughput, ecosystem — choose the right simulator for your robotics project.

Digital Twin in manufacturing allows smart factory simulation, process optimization and significantly reduced deployment costs.