Skild AI
Building general purpose robotic intelligence
Most AI today exists solely in cyberspace. Physical reality is far more information rich, and automating physical tasks offers immense returns. We are building AI that will interact with and affect change in the real world. To keep us grounded on our journey, we are building robot applications that deliver tangible, real-world value. The Skild Brain enables robots to navigate unstructured, dangerous environments, freeing humans from the burden of constant, manual inspections. Our AI can execute low-level skills like grasping, handover, and navigation on mobile platforms. These skills are abstracted away using an API call, allowing users to build applications without worrying about details of the unstructured, messy real world. Our AI can learn highly precise and dexterous skills. We are using these to automate repetitive tasks. Our model learns by watching human videos. This is a scalable solution for the robotics data problem. We are supported in our mission and vision by our amazing partners.
Physical Intelligence
Physical Intelligence is bringing general-purpose AI into the physical world.
Physical Intelligence is bringing general-purpose AI into the physical world. We are a group of engineers, scientists, roboticists, and company builders developing foundation models and learning algorithms to create a model that will control any robot to do any task. General-purpose physical intelligence models will enable a Cambrian explosion of robotics applications. See how our partners are already solving real-world problems. By fine-tuning our latest model, we were able to solve a series of very difficult manipulation challenge tasks. A method for training our generalist policies with RL to improve success rate and throughput on real-world tasks. Our latest generalist policy, π0.5, extends π0 and enables open-world generalization. Our new model can control a mobile manipulator to clean up an entirely new kitchen or bedroom. We are releasing the weights and code for π0 as well as our new π0-FAST autoregressive model. Our first generalist policy, π0, a prototype model that combines large-scale multi-task and multi-robot data collection with a new network architecture to enable the most capable and dexterous generalist robot policy to date.
Skild AI
Physical Intelligence
Skild AI
Physical Intelligence
Only in Skild AI (4)
Skild AI
Physical Intelligence
Skild AI
Physical Intelligence
