AWS Physical AI Blog
Author: Frantz Lohier
Frantz Lohier, PhD has 20 years of experience in Robotics and AI, strategy and business development across the consumer, industrial and automotive domains. At AWS, Frantz is a Senior Worldwide BD/GTM Leader focusing on AI/ML, and autonomous systems.
Training World Models on Scene Semantics, Not Pixels
A different recipe for training robot world models: compose pre-trained AI modules with classical computer vision to extract scene semantics from ordinary monocular video — no domain data, no synthetic frames. Introduction Today’s recipe for training robot AI looks the same almost everywhere: feed a giant neural network billions of pixels paired with text instructions […]
Automate mining site compliance monitoring with AI-powered 3D scene understanding on AWS
Introduction New techniques in 3D world modeling and AI-driven scene interpretation are unleashing a revolution in industries such as mining and construction. The global LiDAR market — valued at USD 2.74 billion in 2024 and projected to reach USD 4.71 billion by 2030 (9.5% CAGR) is generating unprecedented volumes of spatial sensor data. A single […]
A Maturity Level Framework for Industrial Inspection Report Automation
Introduction Vision systems are increasingly being deployed for industrial inspection. Mounted on drones, ground robots, or integrated into fixed and portable monitoring cameras, these systems capture massive volumes of 2D and 3D data that must be processed to yield actionable insights. Advances in computer vision—enhanced more recently by AI and agentic AI—are transforming what was […]