Florida-based AI solutions company Levatas has equipped Boston Dynamics’ famous robot dog Spot with ChatGPT and Google’s Text-to-Speech model, allowing the robot to answer questions about past and future missions. Humans can talk to the adapted Spot model using normal language commands, with Spot able to instantly parse high volumes of information and use insights from the data to answer questions.

“These robots run automated missions every day,” tweeted machine learning engineer Santiago Valdarrama, who worked on the project. “Each mission uses miles-long, hard-to-understand configuration files. Only technical people can handle them. 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. 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!”

We integrated ChatGPT with our robots.

We had a ton of fun building this!

Read on for the details: pic.twitter.com/DRC2AOF0eU
— Santiago (@svpino) April 25, 2023

In a construction setting, the ChatGPT-enabled Spot model could theoretically allow site managers or construction workers to converse with Spot about any potential safety hazards the robot dog observed during a walkaround, or discrepancies between a building model and the constructed reality. The team at Levatas is also currently investigating how the newly-released, superior GPT-4 large language model could be integrated locally on devices such as robots, instead of online.

“These Spot units will be able to explore facilities, discover a variety of equipment and conditions, and then report back with safety, security, and maintenance recommendations for the human teams to address,” Levatas CEO Chris Nielsen told Fast Company.

News of the ChatGPT-enabled Spot comes months after Spot’s creator Boston Dynamics released a new teaser video of its R&D humanoid robot Atlas lending a hand on a construction site.

This article is part of the Archinect In-Depth: Artificial Intelligence series.