Skip to main content

How to Store and Manage ROS Data

· 23 min read
Anthony Cavin
Co-founder & CEO - Data, ML & Robotics Systems

 

At ReductStore, we specialize in the high-performance storage and streaming of robotics data from edge devices to the cloud. In this tutorial, we will demonstrate how to develop a robust ROS 2 data logging pipeline for practical robotics applications.

First, we will set up a Raspberry Pi with a USB camera running a lightweight YOLOv5n object detection model via ONNX Runtime. Then, a recorder node will capture selected ROS 2 topics, including images, detection results, and logs. Next, these topics will be saved as segmented MCAP files locally with ReductStore. Finally, we will configure automatic replication to stream data to another ReductStore instance.

This minimal setup shows how to efficiently capture, store, and replicate ROS 2 data from a robot to a central server or cloud instance. These techniques can be applied to any ROS 2 system, whether it's a single robot or a fleet of autonomous systems.

Let's get started!

LeRobot Tutorial in Google Colab, No Robot Needed

· 16 min read
Ekaterina Marova
Data Scientist - ML, Python

Intro image

LeRobot is an open-source project by Hugging Face that makes it easy to explore the world of robotics with machine learning, even if you’ve never done anything like this before. It gives you pre-trained models, real-world data, and simple tools built with PyTorch, a popular machine learning framework. Whether you're just curious or ready to try your first robotics project, LeRobot is a great place to start.

Getting Started with MetriCal

· 14 min read
Ekaterina Marova
Data Scientist - ML, Python

Intro image

Sensor calibration is the process of determining the precise mathematical parameters that describe how a sensor perceives or measures the physical world. By comparing sensor outputs to known reference values, we can correct measurement errors and ensure data from different sensors align accurately.

There are two main categories of calibration parameters:

  • Intrinsic parameters (Intrinsics): These capture the internal characteristics of a sensor, such as lens distortion in cameras or bias and scaling errors in IMUs. Calibrating intrinsics helps eliminate built-in measurement errors.

  • Extrinsic parameters (Extrinsics): These define a sensor's position and orientation relative to another sensor or the environment. Accurate extrinsics are essential for transforming and combining data from multiple sensors into a shared coordinate system.