하나의 터미널에서 화면을 여러개씩 분리해서 사용할 수 있음 sudo apt install terminator

examples에 보면 drone 폴더가 있다.  fly.py 코드는 바로 실행된다.hover_train.py하고 hover_eval.py를 해야할것 같다.그럼 먼저 hover_train.py를 하려면, RL을 위한 라이브러리 설치를 진행해야한다. https://github.com/leggedrobotics/rsl_rl GitHub - leggedrobotics/rsl_rl: Fast and simple implementation of RL algorithms, designed to run fully on GPU.Fast and simple implementation of RL algorithms, designed to run fully on GPU. - leggedrobotics/rsl_rlgithub..

https://github.com/Genesis-Embodied-AI/Genesis GitHub - Genesis-Embodied-AI/Genesis: A generative world for general-purpose robotics & embodied AI learning.A generative world for general-purpose robotics & embodied AI learning. - Genesis-Embodied-AI/Genesisgithub.com Genesis 깃헙 레파지토리에 들어가서 git clone을 해준다.    examples에 tutorials 폴더를 보면 많은 예제를 확인할 수 있다. tutorials 폴더 밖에 differentialble_psuh.py등 예제 ..

1. 설치준비: 아니콘다, VScode가상환경 준비하기conda create -n genesis python=3.10 -y conda activate genesis Pytorch 설치하기conda install pytorch torchvision -c pytorch  확인 python import torch torch.cuda.is\_available()Genesis 설치하기pip install genesis-world 2. 예제코드 돌려보기import genesis as gs# -> 1. Initializationgs.init(backend=gs.cpu) # -> 2. Create a scenescene = gs.Scene(show_viewer=True) ..

OpenVLA 테스트를 위해 LIBERO 데이터셋을 불러보자. 먼저 OpenVLA 환경설치 후  https://github.com/openvla/openvla GitHub - openvla/openvla: OpenVLA: An open-source vision-language-action model for robotic manipulation.OpenVLA: An open-source vision-language-action model for robotic manipulation. - openvla/openvlagithub.com  https://github.com/openvla/openvla?tab=readme-ov-file#libero-setup GitHub - openvla/openvla: Open..

git clone 한 openvla 폴더에서  vla-scripts/deploy.py 파일에서 아래와 같이 코드를 바꿔준다. """deploy.pyProvide a lightweight server/client implementation for deploying OpenVLA models (through the HF AutoClass API) over aREST API. This script implements *just* the server, with specific dependencies and instructions below.Note that for the *client*, usage just requires numpy/json-numpy, and requests; example usage bel..