Save StorySave this storySave StorySave this story<\/p>\n
A four-legged robot that keeps crawling even after all four of its legs have been hacked off with a chainsaw is the stuff of nightmares for most people.<\/p>\n
For Deepak Pathak, cofounder and CEO of the startup Skild AI, the dystopian feat of adaptation is an encouraging sign of a new, more general kind of robotic intelligence.<\/p>\n
\u201cThis is something we call an omni-bodied brain,\u201d Pathak tells me. His startup developed the generalist artificial intelligence algorithm to address a key challenge with advancing robotics: \u201cAny robot, any task, one brain. It is absurdly general.\u201d<\/p>\n
Many researchers believe the AI models used to control robots could experience a profound leap forward, similar to the one that produced language models and chatbots, if enough training data can be gathered.<\/p>\n The AI-controlled robot is able to adapt to new, extreme circumstances, such as the loss of limbs.<\/p>\n<\/figure>\n Existing methods for training robotic AI models, such as having algorithms learn to control a particular system through teleoperation or in simulation, do not generate enough data, Pathak says.<\/p>\n Skild\u2019s approach is to instead have a single algorithm learn to control a large number of different physical robots across a wide range of tasks. Over time, this produces a model which the company calls Skild Brain, with a more general ability to adapt to different physical forms\u2014including ones it has never seen before. The researchers created a smaller version of the model, called LocoFormer, for an academic paper outlining its approach.<\/p>\n The model is also designed to adapt quickly to a new situation, such as missing leg or treacherous new terrain, figuring out how to apply what it has learned to its new predicament. Pathak compares the approach to the way large language models can take on particularly challenging problems by breaking it down and feeding its deliberations back into its own context window\u2014an approach known as in-context learning.<\/p>\n Other companies, including the Toyota Research Institute and a rival startup called Physical Intelligence, are also racing to develop more generally capable robot AI models. Skild is unusual, however, in how it is building models that generalize across so many different kinds of hardware.<\/p>\n