Boston Dynamics robot dog can answer your questions now, thanks to ChatGPT

Now even robot dogs are using ChatGPT.
Written by Sabrina Ortiz, Editor

Boston Dynamics is an engineering and robotics company that has gained popularity for its viral videos showcasing its futuristic robots performing impressive feats such as parkour.

A new video shared by AI expert Santiago Valdarrama, showcases Boston Dynamics' robot dog, Spot, performing a few new tricks that involve artificial intelligence.

Also: What is HuggingChat? Everything to know about this open-source AI chatbot

In the almost two minute video, Spot is able to answer natural language questions such as "Are you standing?" and "What is your battery level?".

To do so, Spot first uses Open AI's ChatGPT to query information and then uses Google's text-to-speech AI to vocalize the answer. 

"At the end of each mission, the robots capture a ton of data. There's no simple way to query all of it on demand. That's where ChatGPT comes in," said Valdaramma. 

AlsoThis AI chatbot can sum up any PDF and answer any question you have about it

"We show it the configuration files and the mission results. We then ask questions using that context. Put that together with a voice-enabled interface, and we have an awesome way to query our data!"

The video, which takes place at Levatas' lab, also shows Spot answering mission specific questions such as, "Spot, how many inspections in your next mission?" or "Describe your last mission."

Also: This new technology could blow away GPT-4 and everything like it

Spot has the ability to carry up to 14kg of equipment, can perform repeatable missions, gather data, navigate different terrains, conduct thermal inspections, detect radiation and more. 

The robots' advanced abilities, paired with AI, caused some people to jump to the usual apocalyptic concerns about AI and robots. Valdarrama took to Twitter to put those worries to rest. 

"90% of the comments were people talking about the end of civilization. Meanwhile, 99% of data scientists are still figuring out how to split their tabular datasets," said Valdaramma. 

Editorial standards