sim2real

Adapt a policy trained in any external codebase into the sim2real codebase for integrated sim2sim/deploy by tracing the training observation/action implementation, exporting one complete ONNX, implementing matching sim2real observations, writing deploy YAML, and validating tracking behavior.

Configure and repair the G1 sim2real robot computer environment for root policy deployment and teleop. Use when a task mentions g1-cable, g1-deploy, deploy_5G WiFi, Hugging Face or g1_xmls cache failures, sim2real root project setup, any4hdmi sync to G1, teleop uv sync, GMR or smplx GitHub hangs, XRoboToolkit, xrobotoolkit_sdk, or JetPack 5 G1 deployment bringup.

Install, convert, debug, and benchmark sim2real ONNX GPU and TensorRT inference backends on onboard JetPack 5 Orin hosts such as g1-cable. Use when a task mentions JetPack 5, L4T R35, onboard Orin, onnx-gpu, CUDAExecutionProvider, TensorRT 8.5, policy ONNX conversion, or sim2real inference benchmark failures on the robot computer.