n TECHNOLOGY February 2026 www.drivesncontrols.com 18 For more Technology News visit www.drivesncontrols.com US RESEARCHERS HAVE DEVELOPED an AIdriven robotic assembly system that builds physical objects requested as text descriptions. It builds the objects automatically from a set of prefabricated parts, and can iterate on the design based on user feedback. The project aims to make design faster and more accessible for non-experts. Current CAD (computer-aided design) platforms require expertise to master, and often incorporate such a high level of detail that they don’t lend themselves to brainstorming or rapid prototyping. The new system, developed by experts from MIT and elsewhere, including Google Deepmind and Autodesk Research, uses a generative AI model to build a 3D representation of an object’s geometry based on user prompts. A second generative AI model then figures out where different components should go, according to the object’s function and geometry. The researchers have used the system to build furniture, such as chairs and shelves, from two types of premade parts (structural and panel components). The parts can be disassembled and reassembled, reducing waste. The researchers found that more than 90% of participants in a survey preferred the objects made by the AI-driven system to those made using other approaches. The technique could be particularly useful for rapid prototyping of complex objects such as aerospace components and architectural objects. “Sooner or later, we want to be able to communicate and talk to a robot and AI system the same way as we talk to each other to make things together,” says lead researcher Alex Kyaw, a graduate student in the MIT’s departments of Electrical Engineering and Computer Science, and Architecture. “Our system is a first step towards enabling that future.” The user prompts the system with text – such as “make me a chair” – and gives it an AIgenerated image of a chair to start. A visionlanguage model (VLM) then determines where to place the panel components on top of the structural components, based on example objects that it has seen before. The system outputs this information as text – such as “seat” or “backrest.” Each surface of the chair is then numbered, and the information is fed back to the VLM. The model chooses labels that correspond to the geometric parts of the chair that should receive panels on the 3D mesh to complete the design. The user can refine the design by giving new prompts, such as “only use panels on the backrest, not the seat.” Once the 3D mesh is finalised, the robot assembly system builds the object from prefabricated parts. The researchers compared the results of their technique with an algorithm that places panels on all upward-facing horizontal surfaces, and another that places panels randomly. More than 90% of those surveyed preferred the designs made by AI system. The researchers now want to enhance their system to handle more complex and nuanced user prompts – such as tables made out of glass and metal. They also want to incorporate additional prefabricated components, such as gears, hinges and other moving parts, giving the objects more functionality. “Our hope is to drastically lower the barrier of access to design tools,” says senior researcher Professor Randall Davis, a member of MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL). “We have shown that we can use generative AI and robotics to turn ideas into physical objects in a fast, accessible, and sustainable manner.” p Mitsubishi Electric has launched two series of HV IGBT modules that reduce switching losses by about 5% compared to previous models, and offer moisture resistance that is around 20 times higher. The standard-isolation (6kV rms) and high-isolation (1.2kV) modules in in the 1.2kA XB series are predicted to result in more efficient and reliable inverters for high-power industrial and rail applications. They can be used in adverse environments, including outdoors. www.mitsubishielectric.com p Digid, a German specialist in nanoscale sensing technologies, has started mass production of 1μm-long temperature and force sensors – thought to be the world’s smallest. The company has patented a printed electronics technology that deposits the sensors on silicon, metal, polymer and other materials. Nanoscale 16 x 16 arrays of these sensors could be applied to robots’ surfaces to mimic human sensing capabilities. Digid’s roadmap forecasts future sensors that are just 10nm long. www.digid.com p The semiconductor developer Wolfspeed has produced a single-crystal 300mm-diameter (12-inch) silicon carbide wafer which, it says, represents a major advance for high-efficiency power devices, with potential applications including next-generation industrial, AI, augmented and virtual reality, and HV grid systems. The 300mm platform will also support a new class of integrated optical, photonic, thermal and power technologies. p The German wireless power supply developer, Wiferion, has announced “a new phase” in supplying energy to fleets of AMRs and AGVs. Having established inductive charging as a standard for intralogistics applications, the company now says it is solving another bottleneck. It says it is no longer the energy transfer that limits efficiency, but the type and structure of charging points. It is launching a new family of products at the LogiMat show in March that address these changes without altering the fundamentals of contactless energy supply. www.wiferion.com/en p The Ethernet Alliance has released its 2026 Ethernet Roadmap, highlighting the technologies, trends and breakthroughs set to define the next era of highperformance, AI-driven networking. The Roadmap shows how upgrades such as 1.6Tb/s interfaces, linear pluggable optics, improved copper and fibre options, and energy-efficient designs, will facilitate growth in manufacturing, AI, cloud services, automotive and edge computing applications. https://bit.ly/EA-2026EthernetRoadmap TECHNOLOGY BRIEFS ‘Make me a chair’: robotic assembly system responds to text requests A robot assembles a chair and places panels on modular lattice cubes in response to text-based user prompts. Image: Courtesy of the researchers
RkJQdWJsaXNoZXIy MjQ0NzM=