Posts

Iván Hernández Dalas: We know how to build smarter robots. Now, we need to learn smarter ways to test them

Image
Right now, today, you can spend $14,000 and buy a humanoid robot. There is no safety certification reviewed, no standardized test protocol verified. You get a machine capable of physical force and real-time autonomous decision-making. And the frameworks for validating its behavior are still catching up to what it can do. That’s not a criticism of the engineers building these systems. The intelligence side of robotics is advancing at a pace that genuinely deserves the excitement it gets: better perception, more robust locomotion, faster inference, and tighter control loops. But here’s the question I keep coming back to: As the control architecture of these systems evolves from simple teleoperation all the way to fully autonomous reinforcement learning, are our testing methodologies and safety validation processes evolving with them? I don’t think they are. Not yet. And I think that gap is worth talking about, not to slow the industry down, but to help it scale res...

Iván Hernández Dalas: How compact cobot integration enhances autonomous mobile robot applications

Image
Kassow said its cobots can reach difficult-to-access areas, handle heavier objects, and perform demanding tasks with accuracy. | Source: Kassow Robots The increasing automation of warehouse pick-and-place, palletizing, and machine-tending tasks has introduced new technologies. Robotics and automation have drastically changed operations as productivity needs and labor shortages impact the industry. Workers are interacting with autonomous mobile robots and collaborative robots, or cobots, integrated into mobile manipulators. Cobots are quickly shaping the future of warehousing , with  their use  rising tenfold from 2018 to 2025. Some seven-axis models of force- and power-limited arms are gaining popularity because they can be mounted on AMRs , enabling a greater range of motion and access into harder-to-reach areas. Cobots offer numerous precision-enhancing capabilities across industrial environments, improving repetitive tasks such as picking , assembly , screwing, labeling, and we...

Iván Hernández Dalas: General Intuition raises $320M to use video game data to train robots

Image
General Intuition is testing world models that will act as training environments for agentic models. | Source: General Intuition General Intuition US Inc. this week raised $320 million in Series A funding. The company said it plans to use the financing to build AI models that can perceive, predict, and act in virtual and physical environments. While physical AI has become a dominating topic in robotics, General Intuition claimed that it is taking a unique approach. Instead of gathering hundreds or thousands of hours of real-world data or generating simulated data, the company uses billions of gameplay clips uploaded to Medal , a platform that allows users to post gaming moments. Pim de Witte, founder and CEO of General Intuition, also co-founded Medal. The gaming clips capture humans perceiving an environment and deciding how to move through it. This is what makes it valuable, said the company. Text-based models only provide descriptions of reality, which aren’t enough for trainin...

Iván Hernández Dalas: Orbbec shows AI-powered vision systems at Automate 2026

Image
Orbbec exhibited its robotic vision systems at Automate 2026. Source: Orbbec In Chicago this week, Orbbec showed off its latest 3D vision products to meet growing industry demand for intelligent automation. The Shenzhen, China-based company said it has tailored its industrial-grade 3D cameras for challenging scenarios. Its portfolio also includes integrated AI systems designed to enhance robotic perception capabilities. AI-enhanced 3D vision addresses industrial blind spots As industrial vision increasingly converges with edge AI ,  Orbbec said it has combined high-precision 3D vision hardware with an advanced AI model. The company claimed that this improves robots’ spatial perception and environmental understanding, helping overcome sensing challenges in complex industrial scenarios. LingBot-Depth for Gemini 330 offers spatial intelligence at the edge Common automation bottlenecks where conventional 3D vision hardware often struggles include transparent objects, low-texture or...

Iván Hernández Dalas: Robot Talk Episode 162 – The robot doctor will see you now

Image
Since the first robot-assisted surgery was performed, over 40 years ago, major advances in robotics, computer vision and artificial intelligence have fundamentally changed medicine and healthcare. Innovative new technologies are already aiding skilled medical professionals in diagnosis, surgery, rehabilitation and beyond. But many questions remain: What ethical issues arise as medical tools become increasingly autonomous? How do we regulate technologies that can learn and change over time? And how can we ensure that cutting-edge medical devices are accessible to all? In this special live recording at the Great Exhibition Road Festival in London, Claire chatted to George Mylonas (Imperial College London), Antonia Tzemanaki (University of Bristol) and Tom Vercauteren (King’s College London) about robotics and AI in medicine and healthcare. George Mylonas  is an Associate Professor in Robotics and Technology in Cancer at Imperial College London, and the director of the  Human-centred...

Iván Hernández Dalas: Robust.AI chooses Aptiv PULSE sensor for Gen 3 Carter mobile robot

Image
Carter uses Aptiv’s PULSE sensor, which is designed for environments that demand precise detection and involve complex maneuvering. | Source: Robust.AI Robust.AI this week said it has selected Aptiv PLC’s intelligent perception systems, including AI and machine learning-based sensor fusion powered by the Aptiv PULSE sensor, for its Gen 3 Carter collaborative mobile robot. For industrial applications, reliability across operating environments such as warehouses , manufacturing floors, and cold  storage is critical. These environments are dynamic and frequently contain obstructions, dust, glare, moisture changes, and reflective surfaces that can degrade conventional perception systems, said Aptiv. By combining the strengths of radar and vision, the  company  said it enables better decision-making and reliability when operating around people, equipment, and other obstacles. “Scale adoption of robotics requires safety-critical perception that spans the dynamic conditions experienced i...

Iván Hernández Dalas: ARM Institute expands RoboticsCareer.org into physical AI

Image
The ARM Institute operates as a nonprofit organization, with the aim of being an honest broker between robotics and manufacturing stakeholders. | Source: ARM Institute The Advanced Robotics for Manufacturing, or ARM, Institute today issued an expanded version of the RoboticsCareer.org website with an increased emphasis on physical AI. With the release, the ARM Institute said it aims to demystify the skills and training needed to work alongside physical AI. RoboticsCareer.org now lists the growing job opportunities in this area and enables employers to connect to qualified talent. These new capabilities are now available. “Physical AI is the next frontier of manufacturing roles,” said Lisa Masciantonio, chief workforce officer at the ARM Institute . “We are proud of the key role that RoboticsCareer.org will play in enabling greater adoption of robotics in manufacturing by providing access to a ready workforce. RoboticsCareer.org acts as a direct bridge from awareness t...