Google DeepMind has incorporated its advanced large language model, Gemini, into robots, enabling them to perform tasks like slam dunking a basketball without prior human demonstration. The initiative aims to develop general-purpose robots that can understand natural language and interpret their physical surroundings. While this approach holds promise for creating adaptable machines, it also raises safety concerns due to the potential for harmful outputs from AI models. The Gemini Robotics model represents a significant progression in achieving these ambitious goals through enhanced spatial reasoning and real-world application training.
Using the model, machines can perform some tasks - such as 'slam dunking' a miniature basketball through a desktop hoop - despite never having watched another robot do the action.
The hope is to create machines that are intuitive to operate and can tackle a range of physical tasks, without relying on human supervision or being preprogrammed.
By connecting to Gemini's robotic models, a developer could enhance their robot so that it comprehends natural language and understands the physical world in more detail.
Gemini Robotics is a 'small but tangible step' towards creating versatile robots equipped with advanced AI capabilities.
Collection
[
|
...
]