Random Interviews 3
summary
A company booth shows a hobby Raspberry Pi autonomous robot that navigates between poles using a trained machine learning model, built to demonstrate cloud-to-edge workflows. The model is trained in the cloud then deployed to run locally on the device for obstacle avoidance, with behavior improved by offline testing; the prototype does not support live on-device retraining so fleet updates require redeploying updated models. Tools mentioned include Azure and AWS.
AI-written summary · about
related talks
01h 02mAI on the Edge
45mFrom Data to AI on The Edge
49mEnable IoT with Edge Computing and Machine Learning
43mPatterns for cloud-enabled robots
55mIoT Solution Recipes - Beyond your first slice of Raspberry Pi
21mAI, Embedded System and Robotics
28mBuild smart robots and operate them easily with AWS Robotics
01h 02mThe Modern Trolley Problem - Responsible AI Principals