Daniel Brintzinger
From Code to Motion: Building an Autonomous Hat-Hunting Robot with Kubernetes & ML
#1about 3 minutes
Understanding the challenges of edge computing deployments
DevOps principles can be extended from the data center to manage workloads on disconnected or intermittently connected edge devices.
#2about 2 minutes
Introducing the robot's hardware and software stack
The robot is built on a Raspberry Pi running MicroShift, a lightweight Kubernetes distribution, and exposes a simple Flask REST API for motion control.
#3about 4 minutes
Designing the end-to-end system architecture
The system uses a central OpenShift cluster for development and model training, with Skupper for secure communication and ArgoCD for GitOps-based deployment to the robot.
#4about 7 minutes
Training an object detection model with OpenShift AI
A JupyterLab workbench is used to define and run an Elyra pipeline that trains a YOLOv5 model on the Open Images dataset to recognize fedora hats.
#5about 4 minutes
Deploying the trained model as an inference service
The trained ONNX model is deployed as a scalable and secure REST API endpoint using the model serving feature in OpenShift AI.
#6about 7 minutes
Developing the robot control application in a web IDE
A Python Flask application is developed using a web-based IDE (Eclipse Che) with a devfile to manage the workspace and connect to the inference service.
#7about 2 minutes
Live demonstration of the autonomous hat-hunting robot
The robot successfully uses its camera and the ML model to detect a red hat, calculate its position, and navigate towards it in real-time.
#8about 1 minute
Managing edge deployments with GitOps using ArgoCD
ArgoCD manages the robot as a remote Kubernetes cluster, enabling automated, Git-driven rollouts of new application and model versions to the edge device.
Related jobs
Jobs that call for the skills explored in this talk.
Matching moments
10:52 MIN
Deploying a RAG-enabled chatbot on a Kubernetes platform
Supercharge your cloud-native applications with Generative AI
01:51 MIN
Using Red Hat tools across the AI development lifecycle
Developer Experience, Platform Engineering and AI powered Apps
03:03 MIN
Real-world robot deployments and their challenges
Robots 2.0: When artificial intelligence meets steel
03:08 MIN
Enabling hybrid AI with an open software stack
Bringing AI Everywhere
07:33 MIN
Building an intelligent robot from the ground up
Robots 2.0: When artificial intelligence meets steel
01:30 MIN
Overlooked challenges of running AI applications in production
Chatbots are going to destroy infrastructures and your cloud bills
02:34 MIN
Exploring the modern robotics technology stack
Robots are coming into the wild! Full-Stack Robotics Engineers, be ready!
03:02 MIN
The future of AI in DevOps and MLOps
Navigating the AI Wave in DevOps
Featured Partners
Related Videos
17:34From Factory Floor to Kubernetes Core: Building an Edge Platform One Step at a Time
Dean Oren & Stefan Belsch
28:19Robots 2.0: When artificial intelligence meets steel
Thomas Tomow
31:38Developer Experience, Platform Engineering and AI powered Apps
Ignacio Riesgo & Natale Vinto
19:01Simplifying edge app delivery: one workflow, thousands of devices
Christian Koep
29:34Robots are coming into the wild! Full-Stack Robotics Engineers, be ready!
Falk-Moritz Schaefer
24:48How Robots Learn to be Robots
Alexander Schwarz
30:48One AI API to Power Them All
Roberto Carratalá
48:54Remote Driving on Plant Grounds with State-of-the-Art Cloud Technologies
Oliver Zimmert
Related Articles
View all articles
.gif?w=240&auto=compress,format)
From learning to earning
Jobs that call for the skills explored in this talk.
SYSKRON GmbH
Regensburg, Germany
Intermediate
Senior
.NET
Python
Kubernetes
autonomous-teaming
Munich, Germany
Remote
GIT
Linux
PyTorch
Machine Learning