Alter3: the new humanoid robot powered by ChatGPT-4

It has the ability to mimic complex human actions, such as taking selfies or pretending to be a ghost, learning in a similar way to a young child.
Share on social networks
new humanoid robot Alter3

A group of researchers has linked with GPT-4 (OpenAI’s artificial intelligence model) a new humanoid robot known as Alter3, which has been developed by a team consisting of engineers from the University of Tokyo and Osaka University.

Thanks to this connection, the humanoid now has the ability to assume various poses, such as those designed for selfies or even pretend to be a ghost, without the need for these to be previously programmed in its database.

How does ChatGPT-4 influence the new humanoid robot?

Until now, controlling low-level aspects of robots, such as movement, has been a challenge for large language models, as it involves hardware aspects that are not included in the training data. To overcome this obstacle, the Japanese team has devised a way to translate the expression of human movement into a code understandable to the humanoid.

This enabled Alter3 to generate spontaneous movements even though it is currently unable to perform complex movements, since its mobility is limited to the upper part of its body and its lower section is fixed to a support. In the following video you can observe the “anatomy” of this humanoid while conducting an orchestra.

video
play-rounded-outline

The robot can generate spontaneous movements. Source: Scary Beauty.

This approach implies that the robot can generate sequences of actions over time without the need for developers to program each specific body movement. It is able to learn to move in a manner similar to a small child, progressively moving from shuffling to crawling and finally walking.

Ask Alter3 for a selfie and he will do it.

Users also have the ability to adjust posture or help the android discern between various postures. If a human gives Alter3 instructions, such as “take a selfie with your iPhone,” the robot will execute a series of requests to OpenAI’s GPT-4 model, including asking the artificial intelligence what is involved in taking a selfie. GPT-4 then translates this into Python code that the robot can understand and use to perform the necessary movements.

video
play-rounded-outline

The robot interprets the command to take a selfie. Source: Takahide Yoshida.

It is worth noting that the group responsible for the robot and the novel text-to-motion translation strategy based on GPT-4 intends to share their findings so that they can be used in other humanoid robots. humanoid robots. According to them, this represents a notable step forward in the progress of robotics.

Surprisingly, Alter3 can imitate ghosts, animals, and human-like expressions of emotions. Its response to the content of a conversation through facial expressions and gestures represents a significant advance in humanoid robotics, easily adaptable to other androids with minimal modifications.

wrote in the research article.

Don’t miss any of our posts and follow us on social media!

Inspenet.com YouTube LinkedIn Facebook Instagram

Source: tomsguide.com

Share this news on your social networks
Rate this post
1 star2 stars3 stars4 stars5 stars (No rating yet)
Post Rating LoaderLoading...
Hide picture