Please confirm you are human

This browser or connection looks automated. Press and continuously hold the control for 3 seconds to enable Google-hosted web results and, when separately allowed, AI-assisted answers.

A successful check enables 100 search requests. Interactive access does not authorize scraping, systematic collection, or reuse of search output.

Hold with a pointer, or hold Space or Enter.

News

nvlabs.github.io
nvlabs.github.io > COMPASS > docs > workflows > training.html

Training residual RL specialists??? COMPASS Handbook

3+ day, 20+ hour ago   (241+ words) run.py trains a residual RL policy on top of the X-Mobility base policy for a given embodiment + scene. The residual head adapts X-Mobility’s language-conditioned navigation behaviour to embodiment-specific dynamics. GPU memory scales linearly with the parallel-env count: 32 envs ≈ 30 GB....

nvlabs.github.io
nvlabs.github.io > GR00T-WholeBodyControl > tutorials > vla_workflow.html

VLA Workflow: Collect, Fine-tune, Deploy — GR00T-WholeBodyControl Documentation

3+ mon, 1+ week ago   (470+ words) This tutorial walks through the end-to-end workflow for training and deploying a VLA policy on the Unitree G1 with SONIC whole-body control: Collect teleop demonstrations using the SONIC stack Fine-tune the Isaac-GR00T N1.7 model on your collected data Deploy the finetuned policy…...

nvlabs.github.io
nvlabs.github.io > GR00T-WholeBodyControl > getting_started > installation_deploy.html

Installation (Deployment) — GR00T-WholeBodyControl Documentation

5+ mon, 5+ day ago   (270+ words) Required for all setups: CUDA Toolkit (for GPU acceleration) TensorRT (for inference optimization) — Install this first! Jetpack 6 (for onboard deployment) Git with LFS support Download TensorRT from NVIDIA Developer: Jetson / G1 onboard Orin 10.7 (required; requires JetPack 6 — flashing guide) Download the TAR…...