Category
The models and systems that make robots perceive and act.
Foundation models, reinforcement learning, and computer vision are the engine behind autonomy — but benchmarks are not deployments.
The gap between a curated task and an unseen warehouse aisle is the whole problem.
Chemistry has become another frontier in the effort to connect artificial intelligence with the physical world. Glasgow-based Chemify is now preparing to expand the infrastructure needed to do exactly that, securing £22 million ($29.7 million) in grants to scale a platform that combines AI-driven molecular design with automated robotic synthesis. The funding includes £16 million from Scottish…
This article is brought to you by VicOne. Robot safety has traditionally asked: Can a machine remain safe when something goes wrong? Physical AI raises a harder question: Can a machine remain safe when an attacker changes what it sees, decides, or does even when nothing appears to have failed? As AI and robotics continue to advance at an unprecedented pace, modern robots perceive through…
The startup is developing tools that create georeferenced 2D maps from a small number of images, without requiring specialized infrastructure. INTERGEO brings together established geospatial companies and startups exploring new approaches to mapping. At the 2026 event in Munich, AIVE AI Systems demonstrated how artificial intelligence could simplify complex mapping tasks. The company’s software…
OpenRobOps gives robotics developers a foundation to deliver a fleet manager with support for the upcoming interoperability standard.
Dermot O'Driscoll, the VP of go-to-market for physical AI at Arm, will examine key compute principles behind trusted physical AI.
Universal Robots has released three new robot arms, a rebuilt core controller, a new AI-ready tool flange, and more.
The “HardFlow” algorithm could help generative AI models produce high-quality outputs that obey strict requirements when “pretty close” doesn’t cut it.
Ultrasound sensing can provide tactile perception for robotic hands while avoiding wear and tear, says UltraSense.
From 25–27 August, UK RAS STEPS members came together at the University of York’s Institute for Safe Autonomy for a three-day Micromaze Robot Hackathon. Working in teams, participants were challenged to design, build and program autonomous robots capable of navigating a series of increasingly complex mazes. Each team used a custom Raspberry Pi Pico W […]
NVIDIA on September 10, 2026 detailed how Skild AI built its S1 robot foundation model on NVIDIA AI infrastructure, and said the robotics company reached a $100 million annual revenue run rate 10 months after its first commercial deployment. In the NVIDIA blog post, the company said Skild built S1 and conducted the underlying research on its infrastructure as part of a broader collaboration…
Manufacturing floors, warehouses and production lines rarely stay fixed — tasks change, layouts shift and new products arrive, and most robots can’t keep up without significant reprogramming. Skild AI’s new S1 robot foundation model helps address this, designed to learn previously unseen, long-horizon tasks from a single video demonstration. The model, launched last week, uses […]
Read as Demo footage is a best take unless stated otherwise — the questions are teleoperation, cuts, retries, and speed.
Vision AI doesn't replace robots or human judgement; it provides the continuous perception that allows both to operate safely together.
