Everyone can afford to play with AI robots, HuggingFace open source low-cost solution LeRobot
HuggingFace open-source the low-cost AI robot LeRobot, and guides everyone to build AI-controlled robots from scratch, including assembly, configuration, and training of neural networks to control the robot.
The project was led by former Tesla engineer Remi Cadene (now a principal research scientist at HuggingFace) and gave a detailed guide. The project is based on the open source Koch v1.1 robot kit (which can also be another hardware or virtual platform), which contains two six-motor robotic arms that can use one or more cameras as vision sensors.
LeRobot aims to provide models, datasets and tools for real-world robots in PyTorch. The goal is to lower the barrier to entry into robotics so that everyone can contribute and benefit from shared datasets and pre-trained models.
LeRobot contains state-of-the-art methods that have been proven to be transferable to the real world, with a focus on imitation learning and reinforcement learning.
Le Robot already provides a set of pre-trained models, a dataset containing human collection and demonstrations, and a simulation environment that can be used without assembling the robot. In the next few weeks, the plan will add increasing support for real-world robotics on the most affordable and powerful robots.
LeRobot hosts pre-trained models and datasets on the Hugging Face community page: https://huggingface.co/lerobot
If you want to learn more, you can click on the link below the video.
Thank you for watching this video. If you like it, please subscribe and like it. thank
GitHub：https://github.com/huggingface/lerobot
Oil tubing: