Skip to main content

2 posts tagged with "simulation"

View All Tags

Controlling Robots using a Large Language Model

· 22 min read
Michael Hart
Mike Likes Robots

In the past, a human controlling a robot has depended entirely on what commands the human can send the robot, either through structured messages or through user interfaces. That's changing with Large Language Models (LLMs), because we can provide a few tools for controlling robots to an LLM and then give commands in natural language, and the LLM works out how to send the right commands to the robot. This gives us a lot more flexibility in how we can interact with robots.

In this post, I show an example project that runs a Gazebo simulation of a robot in a small house. The project uses Claude, an LLM from Anthropic, to interact with the robot, which allows the user to give the robot natural language commands and see those changes happen in simulation.

After the demo, I show how to set it up, then talk about how the code interfaces with Claude.

With Thanks

The demonstration project in this post is from a university-based robotics course. One of the groups on the course kindly released their submission on Github so that I could show it in this post. Therefore, I'd like to thank Senior Lecturer Giovanni Toffetti at Zurich University of Applied Sciences and his students Alexander Kolenaty, Jan Affeltranger, and Ilimea Gall.

This post is also available in video form. If you'd prefer to watch, click the link below:

Simulating Robots in the Cloud with EC2 and O3DE

· 18 min read
Michael Hart
Mike Likes Robots

Simulators such as Gazebo, NVIDIA Isaac Sim, and O3DE are incredibly helpful tools when it comes to robotics development. Robots are very slow and expensive to develop, and a large part of the reason is not being able to test how the robot works for real because of how slow it is to set up and run tests. With simulations, we can repeatedly run a robot through exactly the same setup every time to see how it behaves, allowing us to more quickly modify the robot software and run it again.

There's one issue - the more realistic the simulation, the more powerful the computer needed to run it. That's where the cloud comes in; instead of buying the hardware outright and running the computer in-house, you can run simulations on demand in the cloud, and only pay for the server while you're using it!

In this post, I'll show you how to run a multi-robot sample simulation using O3DE in the cloud, using an on-demand EC2 instance with graphics hardware available. If you'd like to follow along, this post is also available in video form using the link below: