Ivan Hernandez Dalas - Mechatronics

The Festo HPSX gripper comes in different finger configurations and is available complete or as components. Source: Festo Soft or compliant grippers allow robots to manipulate a wide range of objects. Festo Corp. this week introduced the HPSX gripper, which it described as a “hygienic soft gripper engineered to handle delicate, irregularly shaped, and hygienically sensitive products.” “The design of this pneumatic gripper is a significant advancement over traditional, rigid gripping solutions and addresses long-standing challenges in automating tasks in the food, pharmaceutical, and cosmetics industries, where product damage is a concern,” said the Esslingen, Germany-based company . The Festo HPSX is superior to suction grippers because it can handle objects of varying size, shape, and orientation, said Michael Guelker, product manager for pneumatic actuators at Festo. Suction grippers need flat surfaces to be picked up, he told  The Robot Report . “HPSX is also easier to cle...

Heven AeroTech’s flagship Z1 platform. | Source: Heven AeroTech Heven AeroTech, a developer of hydrogen-powered uncrewed aerial systems, or UAS, this week said it has closed a $100 million Series B round. This latest round of funding values the company at $1 billion. “Reaching unicorn status validates not just our technology, but [also] our execution,” stated Bentzion Levinson, founder and CEO of Heven AeroTech. “This capital will enable us to scale U.S. manufacturing capacity, accelerate quantum-enabled capabilities across our platform, and deliver long-endurance hydrogen-powered systems at the speed and volume our national security customers demand,” he added. “We’re building for the battlefield of today and tomorrow.” Founded in 2019, Heven AeroTech specializes in the development and manufacturing of hydrogen fuel cell propulsion for extended-endurance aerial systems. The Sterling, Va.-based company said its flagship Z1 platform achieves flight times exceeding 10 hours and r...

The ReWiND method, which consists of three phases: learning a reward function, pre-training, and using the reward function and pre-trained policy to learn a new language-specified task online. In their paper ReWiND: Language-Guided Rewards Teach Robot Policies without New Demonstrations , which was presented at CoRL 2025, Jiahui Zhang, Yusen Luo, Abrar Anwar, Sumedh A. Sontakke, Joseph J. Lim, Jesse Thomason, Erdem Bıyık and Jesse Zhang introduce a framework for learning robot manipulation tasks solely from language instructions without per-task demonstrations. We asked Jiahui Zhang and Jesse Zhang to tell us more. What is the topic of the research in your paper, and what problem were you aiming to solve? Our research addresses the problem of enabling robot manipulation policies to solve novel, language-conditioned tasks without collecting new demonstrations for each task. We begin with a small set of demonstrations in the deployment environment, train a language-conditioned rewar...

A rendering of the 6th-generation Waymo Driver on Hyundai’s all-electric IONIQ 5 SUV. | Source: Waymo Waymo plans to bring its robotaxi service to Baltimore, Philadelphia, Pittsburgh, and St. Louis. However, the unit of Alphabet did not specify when it plans to launch services in these cities.  Waymo is starting manual testing with safety drivers in Baltimore, Pittsburgh, and St. Louis this week. Waymo started operations in Philadelphia over the summer, and after a period of manual testing, it recently shifted to autonomous testing with safety drivers still present.  Waymo has been rapidly announcing new cities for its robotaxi service. Two weeks ago, it announced it would be bringing its technology to New Orleans, Minneapolis, and Tampa, Fla. In each of these cities, Waymo said it will begin laying the groundwork for a commercial launch. However, it did not give a timeline. A few days before that, Waymo said  it is bringing autonomous vehicles ( AVs ) to Miami, Da...

SPAD sensors handle noise differently than a CMOS sensor, reducing blur in video images. Credit: Ubicept Ubicept last month released the Ubicept Toolkit, which it said brings physics-based imaging to modern computer vision systems. The company claimed that its approach delivers high-quality, trustworthy data. The toolkit allows offline and live processing of complementary metal-oxide-semiconductor (CMOS) videos and single-photon avalanche diode (SPAD) cameras, aiding in object recognition and spatial awareness. Ubicept asserted that its SPAD sensors offer superior low-light and high-contrast imaging in comparison with conventional cameras . Industrial cameras in use for the past four decades have used CMOS sensors . This is also the same technology used in digital photography cameras and security cameras, so their production volume makes CMOS sensors relatively cheap. The problem with CMOS cameras is that low-light images can be noisy, and videos captured with a CMOS sensor are ...

EY is collaborating with NVIDIA and other partners on physical AI. Source: EY EY, the collection of firms under Ernst & Young Global Ltd., is known as a consultancy, and it is moving into physical AI and robotics. The company today said it is adding a focus on the potential of artificial intelligence with a new platform and solutions, a leadership appointment, and a new laboratory. Before robotics and AI can advance together, organizations must have the right data, said Joe Depa , EY global chief innovation officer. “A tremendous amount of data is required to simulate physical AI in an environment before a robot is launched,” he told  The Robot Report . “And there are several common challenges when using data for physical AI: data quality, accessibility, and data scarcity. If you don’t address these data challenges, your robots won’t work.” “There is no physical AI without AI-ready data. A meal is only as good as its ingredients,” said Depa. “AI-ready data must be r...