Ivan Hernandez Dalas - Mechatronics

Why robot safety assurance must account for attacks that can change how a machine sees, decides, and acts. Robot safety has traditionally asked: Can a machine remain safe when something goes wrong? Physical AI raises a harder question: Can it remain safe when an attacker changes what it sees, decides, or does even when nothing appears to have failed? Modern robots perceive through multimodal sensors, interpret context using AI models, and translate those interpretations into physical action. As they move into dynamic environments, their safety increasingly depends on the integrity of the data guiding their decisions. That dependence creates risks conventional safety assessments may not fully capture. Recent research has demonstrated that manipulating what a robot sees, hears, or interprets can redirect its behavior without requiring direct control. Such manipulation can occur across the robotic brain — a layered attack surface encompassing training pipelines, system infrastructure...

Robotics Australia Group and HowToRobot are offering AI to help businesses get automation. Source: HowToRobot Australia lags behind most other industrialized countries in terms of robot adoption, with a robot density of 134 robots per 10,000 manufacturing employees, according to the International Federation of Robotics, or IFR. The world average is 162. HowToRobot and Robotics Australia Group today said they are collaborating to accelerate the adoption of automation across Australian industry. “Most businesses don’t yet have the structure, bandwidth, and expertise internally to move automation projects forward with the confidence and pace they need,” stated Søren Peters, founder and CEO of HowToRobot. “”We launched a new version of our platform, where AI is helping companies describe their projects. Instead of hiring an engineer to spend 18 months, they can use it to mature the project description so you can go to your manager and say, ‘Look, I need $200,000 to autom...

For generations, farmers tracked their fields on paper ledgers and spreadsheets; now, John Deere is letting them talk directly to their operational data with JD, a new conversational AI tool it said is designed to turn years of private field metrics into instant, profit-boosting answers. JD operates exclusively on the historical data for each farm. Operations Center helps farmers wade through data For generations, farmers have tracked their data, first on paper and then in spreadsheets. Analyzing that information was always a challenge, depending on the farmer’s analytical skills — or lack thereof — noted John Deere. The Moline, Ill.-based company said Operations Center is the new heart of digital operations for its customers. Farmers and growers can use the mobile platform to track inputs and outputs and manage the variables that control modern farm equipment. Seeking to reinforce customer trust alongside the rollout of JD, Deere stated that farm data belongs ...

Skild AI said S1 enables in-context learning for robotics. | Source: Skild AI Skild AI recently unveiled S1, the company’s flagship robot foundation model. Since it was founded in 2023, the company has raised nearly $1.7 billion in funding to create a general-purpose robot brain. With S1, robots can learn new, complex tasks from watching a single video, Skild AI claimed. To do this, the company ‘s model uses in-context learning, Deepak Pathak , Skild AI co-founder and CEO, told The Robot Report . “You just add a video of a human doing something in the prompt, also called the context of the model, and it can just follow it on the robot,” Pathak said. “The tasks we are showing are extremely complex and long horizon. They are not three-second, four-second tasks, not those tiny, simple tasks.” S1 pretrains on a range of data types Typically, when faced with new tasks, AI models on robots need to be post-trained to handle them. This can be a lengthy process, and it holds r...

Models can generate actions, but hardware must execute those actions. | Credit: OnRoot Physical AI promises robots that can perceive, act and adapt in the real world with far less task-specific engineering than traditional automation. It’s a compelling proposition: robots powered by AI models trained on vast amounts of data, capable of improving over time and operating effectively in far less structured environments. But how do we get there? As AI systems move from the digital to the physical world, new requirements emerge. Intelligent models and policies remain essential, but they are only a part of the equation. Robots ultimately interact with the physical world through grippers, sensors and tools that make direct contact with objects. For physical AI to deliver on its promise, it needs a reliable physical interaction layer: End-of-arm tooling (EOAT) that combines adaptability, sensing and feedback so robots can respond effectively to uncertainty and variation. In selecting the ...

Reframe Systems combines robotics, Pixels to Parts software, and a network of microfactories to build homes. | Source: Reframe Systems Reframe Systems, a robotics company using physical AI to industrialize home construction, today announced said it has raised $40 million. The company said the funding will help it scale its microfactory network across North America. Currently, the U.S. is short 4.5 million homes. Reframe said this problem stems from the construction industry’s fragmented nature. Most houses are build by hand, involving 25 or more subcontractors that are drawing on a shrinking pool of skilled trades. Reframe hopes to address this issue by building a network of automated microfactories near communities where homes are needed. This allows the company to adapt production to different zoning requirements, climate conditions, and architectural styles. “The housing shortage is an abstraction until you’re the person who can’t find a home in the communit...

Photo by Alex Knight on Unsplash . By Hasan Ayaz , Drexel University ; Ewart J. de Visser , United States Air Force Academy ; Frank Krueger , George Mason University , and Yigit Topoglu , United States Air Force Academy People become more suspicious of a humanoid robot that makes errors, especially when the robot is an expressive conversation partner. In our new study published in the journal Science Robotics, we had 50 people hold conversations and make joint decisions with the commercial humanoid robot Pepper , which is designed to be expressive and recognize emotions. Sometimes we had the robot give sound advice. Sometimes we had it make conversational mistakes, interrupting people or pushing illogical suggestions. For some participants, the robot was animated, using gestures, eye contact and nods. For others, it stayed motionless. We measured four things: brain activity, levels of the hormone oxytocin, self-reported trust and our observations of the robot’s influence on part...

The ‘edge AI wall.’ Click here to enlarge. Credit: Zhengis Tileubay My previous article for The Robot Report examined the problem of computational instability in autonomous mobile robots, or AMRs. Since then, the rapid development of artificial intelligence over the past year has led to a broader perspective about edge AI. The article, “ Phase stability regulator based on two dynamic parameters for autonomous mobile robots ,” focused on situations in which a machine operates in a complex, rapidly changing environment characterized by a progressive growth of alternative trajectories and scenarios. In such cases, sensors , actuators , and core software may remain fully operational, yet the quality of decision-making starts to deteriorate. My main argument was that behavioral degradation often results not from hardware failure, but from an information overload within the planner, which is forced to evaluate an excessive number of alternatives in real time, leading to redu...