Software for Embedded Vision
What are the Key Engineering Challenges in Autonomous Docking Systems and How are they Solved? (Part 2)
This blog post was originally published at e-con Systems’ website. It is reprinted here with the permission of e-con Systems. Designing an ROS 2-based autonomous docking system is only half the story. Deploying it in the real world is another matter entirely. Since real industrial environments don’t cooperate with textbook assumptions, understanding these challenges will help
How Robot Fleets achieve Full Mission Autonomy – From ROS 2 Autonomous Docking to Self-Charging (Part 1)
This blog post was originally published at e-con Systems’ website. It is reprinted here with the permission of e-con Systems. True operational autonomy requires more than mapping since robots have stringent expectations to meet. They must manage their own energy, return to charge when needed, and resume their missions without human intervention. e-con Systems has developed
NVIDIA Expands NVIDIA Agent Toolkit With NVIDIA PhysicsNeMo and CUDA-X Libraries to Transform How the World Engineers, Designs and Builds
News Summary: NVIDIA expands NVIDIA Agent Toolkit with re-architected NVIDIA PhysicsNeMo libraries and updated NVIDIA CUDA-X libraries, enabling software developers to build autonomous AI engineers with AI physics skills, accelerated solvers and quantum chemistry capabilities. NVIDIA Nemotron 3 Ultra leads among open models in agentic register-transfer level coding with the ACE-RTL agent from NVIDIA Research,
Free Webinar on Automotive Perception in the Physical AI Era
On September 29, 2026 at 9 am PT (noon ET), Pierrick Boulay, Principal Analyst, Automotive Semiconductors, and Anas Chalak, Technology & Market Analyst, Imaging at Yole Group, will present the free hour webinar “Automotive Perception in the Physical AI Era: Imaging, Sensors and Computing,” organized by the Edge AI and Vision Alliance. Here’s the description,
Avocado OS x Grinn: Rapid Physical AI Development on Edge Vision Hardware
At EVS 2026, Bill Brock, CEO of Peridio, joins Robert Atrea, CEO of Grinn Global, to announce a co-development partnership bringing Avocado OS to Grinn’s AstroSOM 1680 platform. Together, they demonstrate how Avocado OS integrates with Grin’s edge vision hardware to accelerate development of production-ready computer vision and physical AI applications. The demo highlights a
Avocado Connect: From Dev Kit to Production for Physical AI Fleets (with Advantech)
In this video, Justin Schneck, CTO and Co-Founder of Peridio, introduces Avocado Connect, the fleet management platform for deploying and operating Avocado OS in production physical AI environments. He explains the gap between building on dev kits like NVIDIA Jetson and running reliable, scalable systems in the field—and how Avocado Connect is designed to bridge
Device Infrastructure for Physical AI: Introducing Avocado OS
Justin Schneck, CTO and Co-Founder of Peridio, introduces Avocado OS, the company’s modern embedded Linux operating system designed for teams building physical AI devices and products. In this video, Schneck explains how the rise of physical AI has created one of the deepest and most complex software stacks engineering teams have faced—combining embedded Linux, AI
How Robotic Color Sorting Works: Vision, Classification, and Motion Control from Camera to Gripper.
This blog post was originally published at Geisel Software’s website. It is reprinted here with the permission of Geisel Software. Sorting apples by color sounds simple enough. In fact, it is the kind of project that often produces an impressive demo in a matter of hours. Put a camera above a conveyor, detect red apples,
Nota AI Demonstration of LLM Acceleration on Mobilint NPU, Optimized with NetsPresso
Thibault Castells, Research Engineer at Nota AI, demonstrates the company’s latest edge AI technologies at the 2026 Embedded Vision Summit. Specifically, he demonstrates Qwen3-4B running as a real-time LLM Coding Assistant entirely on Mobilint MLA100 NPU, optimized with NetsPresso. Achieving 179–478ms Time to First Token and 8.5–10.8 tokens per second, the demo proves that high-performance
Nota AI Demonstration of VLA Robotics on Dragonwing, Enhanced by NetsPresso
Thibault Castells, Research Engineer at Nota AI, demonstrates the company’s latest edge AI and vision technologies at the 2026 Embedded Vision Summit. Specifically, he demonstrates VLA optimization on Qualcomm Dragonwing IQ-9075, powered by NetsPresso. Using an Action Head-only optimization approach, Nota AI achieves 7x faster Action Head speed (218ms → 31ms) and 1.6x faster end-to-end
Nota AI Demonstration of NetsPresso Agentic Optimization Platform
Thibault Castells, Research Engineer at Nota AI, demonstrates the company’s latest edge AI and vision technologies at the 2026 Embedded Vision Summit. Specifically, Castells demonstrates newly updated NetsPresso, Nota AI’s AI model optimization platform, which now features an agentic optimization loop that automates the entire optimization pipeline. NetsPresso supports optimization across edge and server environments,
Product Engineering Trends 2026
The next era of product engineering will be defined by 10 shifts reshaping industry leadership This article was originally published at HCLTech’s website. It is reprinted here with the permission of HCL Tech. At HCLTech, we believe product engineering has entered a more consequential era; an environment where AI, compute, energy, resilience, regulation and sovereignty
NVIDIA Agent Toolkit Expands With New Omniverse Libraries, Putting AI Agents to Work Building Simulation-Ready Worlds
News Summary: NVIDIA Agent Toolkit now includes NVIDIA Omniverse libraries, giving AI agents tools and skills to help software developers integrate physical AI capabilities into their existing applications. New Omniverse libraries for NVIDIA RTX sensor simulation, GPU-accelerated physics simulation and simulation-ready asset validation are openly available on GitHub. SideFX and PTC are integrating Omniverse libraries
From Silicon to Ecosystems: The New Edge AI Competitive Model
This blog post was originally published at Macnica America’s website. It is reprinted here with the permission of Macnica America. For years, silicon providers have benefited from a well-established stakeholder ecosystem of traditional sales, direct markets and customer solutions that have been pioneering the physical AI deployment. Today, that success requires a lot more work. Silicon
NXP Tech Days Comes to Silicon Valley
NXP Semiconductors will host “NXP Tech Days,” on August 18, 2026, from 9:00 am to 6:00 pm PDT in Santa Clara, California. The event will feature hands-on workshops, expert-led sessions, and real-world insights across embedded systems, edge AI, connectivity, and security. From the event page: The Future, Engineered During the general session, discover how NXP
Real-Time Vision-Language Inference on AMD Radeon™ iGPU Using ROCm™
This demonstration showcases a real-time vision-language inference pipeline running on an AMD Radeon™ integrated GPU, highlighting multimodal AI capabilities on power-efficient embedded platforms. The system processes live or recorded video streams and enables interactive question answering based on visual scene understanding. A lightweight Vision-Language Model (VLM) is deployed to jointly interpret visual inputs and natural
From Silicon to Scale: How DEEPX Is Scaling Developer Support
When your chip is running inside 30 partner ecosystems across 8 countries, how you manage and deliver technical knowledge becomes as critical as the silicon itself. This blog post was originally published at Rapidflare’s website. It is reprinted here with the permission of Rapidflare. DEEPX is one of the most technically credentialed companies in edge AI.
AI Agents on AMD – Secure Agent Computing at the Edge
See how agentic AI workflows can use both local AMD hardware and cloud resources to improve privacy, performance, and cost efficiency. This demo showcases AI agents running with the AMD ROCm™ software platform. Private and data-sensitive tasks can remain on the local system, while more demanding workloads can be sent to cloud-based models when needed.
