1X releases World Model so NEO humanoid robots can learn new skills from videos

Neo humanoid maker 1X releases world model to help bots learn what they see

1X, the robotics company behind the Neo humanoid robot, has unveiled a new AI model that it says understands the dynamics of the real world and can help bots learn new information on their own. This physics-based model, called 1X World Model, uses a combination of video and prompts to give Neo robots new abilities. The video allows Neo robots to learn new tasks they weren't previously trained on, according to 1X. This release comes as 1X is gearing up to release its Neo humanoids into the home. The company opened up pre-orders for its humanoids in October with plans to ship the bots this year. A 1X spokesperson declined to share a timeline of when these bots were shipping or share any information regarding how many have been ordered beyond saying pre-orders exceeded expectations. "After years of developing our world model and making Neo's design as close to human as possible, Neo can now learn from internet-scale video and apply that knowledge directly to the physical world," Bernt Børnich, founder and CEO of 1X said in a company in a statement. "With the ability to transform any prompt into new actions -- even without prior examples -- this marks the starting point of Neo's ability to teach itself to master nearly anything you could think to ask." Saying that the bot can transform any prompt into a new action is a lofty claim and not entirely accurate; you can't tell a Neo to drive a car and it will suddenly know how to parallel park, for instance. But there is some learning going on. 1X isn't saying the world model allows today's Neo bots to do a new task right away from capturing video and being prompted, a company spokesperson clarified. Instead, the bot takes video data linked to specific prompts and then sends that back into the world model. That model is then fed back into the network of bots to give them a better understanding of the physical world and more know-how. It also gives users insight into how Neo is thinking of behaving or reacting to a certain prompt. That kind of behavioral information could help 1X train these models to a point where robots will be able to react to a prompt of something they've never done before.

NEO can now teach itself new skills using video-based AI models

1X has rolled out a major AI update for its humanoid robot NEO, introducing what it calls the 1X World Model. The company says the system allows NEO to turn simple voice or text prompts into new physical skills, even in situations it has never encountered before. At the core of the update is a video-based AI model grounded in real-world physics. Instead of relying only on pre-programmed behaviors or large volumes of human-operated robot data, NEO can now learn from internet-scale video and apply that knowledge directly to the physical world, the company said in a release.

US's 1X humanoid robot learns new skills from videos without human trainers - VnExpress International

According to 1X, its new AI model, the 1X World Model, released on Jan. 12, enables NEO to transform simple voice or text prompts into complex actions, even in situations it has never encountered before. At the core of this update is a video-based AI model grounded in real-world physics. Rather than relying on pre-programmed behaviors or large volumes of human-collected data, NEO can now learn from internet-scale video content and apply that knowledge to real-world tasks, as reported by Interesting Engineering. In a demonstration video, NEO is shown completing everyday tasks, such as packing a lunchbox. Even when faced with unfamiliar objects, the robot is able to plan and execute the task smoothly. Additionally, NEO now performs entirely new actions, including opening a sliding door, operating a toilet seat, ironing clothes, and brushing a human's hair. 1X said these actions showcase the robot's ability to transfer broad human knowledge captured in videos into practical robotic behavior. This advancement also changes how NEO improves over time. Unlike traditional robots that rely on data collected by human operators, often slow and expensive, NEO's new model allows it to learn directly from video captured by the robot itself. This approach could significantly reduce the reliance on human operators, whose jobs can be physically demanding and tedious. According to Business Insider, robot operators, including those working on Tesla's Optimus project, have reported injuries due to the physical nature of their work. Positions are often advertised on a shift basis, with pay starting at $25 an hour at both Tesla and 1X. 1X CEO Bernt Bornich told Business Insider that the new world model "does the same thing as the operator would do." "The big unlock is essentially now that intelligence scales with the number of deployed robots, instead of the number of operators you have gathering data," Bornich said. NEO is priced at $20,000 as a one-time payment or available via a $500 monthly subscription. The robot is expected to ship later this year. Early adopters can expect NEO to be piloted by a remote human operator for tasks that the robot cannot yet perform autonomously, while also collecting data to further train the AI model.