iOS Engineer - Graphics and Rendering

NVIDIA unveils Jetson Orin Nano 2 robotics computer. Delivers 2x inference performance of predecessor and consumes 40% less power at the same performance. By Robotics 24/7 Staff August 25, 2026 NVIDIA said that Jetson Orin Nano 2 enables developers to build a new class of robots, delivery and inspection drones and vision AI systems with a significant leap in AI and video-processing performance. Stay up-to-date with news and resources you need to do your job. Research industry trends, compare companies and get weekly market intelligence with Robotics 24/7. NVIDIA announced the NVIDIA Jetson Orin Nano 2, a new robotics computer set that the company said will redefine entry-level edge AI - putting frontier-class generative AI performance in the hands of millions of developers. As AI models grow smaller and more efficient, more edge devices can become autonomous systems that understand context, interpret language and images, and act in real time. To bring these capabilities into physical machines like robots, delivery and inspection drones, and vision AI systems, NVIDIA said that developers need compact, energy-efficient robotics computers built for edge AI. The company said that Cognex, Doosan Bobcat and Matic are among the first to adopt and explore Jetson Orin Nano 2. A leap for entry-level edge Featuring 78 trillion operations per second of AI compute, 8GB of memory and an 8-core Arm CPU, NVIDIA said that Jetson Orin Nano 2 delivers a significant leap in AI and video-processing performance in a cost-effective, power-efficient system. "Today's small and medium frontier models have reached the accuracy of last year's largest frontier models, unlocking real-time intelligence for edge devices," said Deepu Talla, vice president of robotics and edge AI at NVIDIA. "The Jetson Orin Nano 2 computer puts that breakthrough within reach of millions of developers, delivering the performance and energy efficiency needed for real-time reasoning at the edge." The company said that Jetson Orin Nano 2 achieves 2x the inference performance of Jetson Orin Nano Super through improved Tensor Cores and higher memory bandwidth, while maintaining the same compact form factor. In 15-watt mode, NVIDIA said that Jetson Orin Nano 2 consumes 40% less power to deliver the same performance as its predecessor. Powered by NVIDIA's open software stack, NVIDIA Jetson agent skills and a large AI ecosystem, the company said that Jetson Orin Nano 2 enables developers to run the latest large language models and vision language models optimized for memory-efficient edge inference - including open models like NVIDIA Cosmos and NVIDIA Nemotron, Gemma 4 and Qwen 3 - to rapidly build advanced AI applications. Partner ecosystem and millions of robotics developers build on Jetson. NVIDIA said that over 3 million developers are building on its robotics stack. With Jetson Orin Nano 2, the company said that partners like Cognex, Doosan Bobcat, Matic and Wing are bringing real-world edge AI applications to compact devices. Wing, a drone delivery company and subsidiary of Alphabet, is using Jetson Orin Nano Super and the NVIDIA software stack in its delivery drone fleet - and plans to evaluate Jetson Orin Nano 2 to advance real-time AI perception and reasoning for faster, safer delivery from local businesses to residential yards. "Drone delivery depends on AI that can enable fast, reliable understanding of the real world," said Dinuka Abeywardena, head of perception at Wing. "Wing is exploring Jetson Orin Nano 2 to give us a path to more responsive, energy-efficient drones that can help make deliveries quicker and more dependable for customers." Matic Robots, an advanced consumer robotics company, said that it is adopting Jetson Orin Nano 2 to enable more intuitive interactions with its home cleaning robots, enabling them with conversational AI, gesture detection, deeper context of the home with precision mapping and semantic understanding, and autonomous cleaning capabilities. "Home robots need to understand people, map spaces precisely, understand the layout of objects and spaces, and clean autonomously in dynamic and constantly changing environments," said Navneet Dalal, cofounder and CEO of Matic Robotics. "With Jetson Orin Nano 2, Matic can run state-of-the-art AI models at the edge in a compact home robotics platform built for real-time perception, interaction and navigation." Latest in precision. Latest in artificial intelligence. Latest robotics news.

Matic's $1,245 robot vacuum follows spoken commands in more than 70 languages. Say "Hey Matic" and this robot vacuum will clean what you point at. Image: Matic Aug 14, 2026 eWeek content and product recommendations are editorially independent. eWEEK may make money when you click on links to its partners. Learn More "Hey Matic, clean this" is now all it takes. Matic Robots Inc. began rolling out a firmware update Thursday that transforms how its $1,245 robot vacuum operates. The new feature, called Matic Cues, lets users control the device through natural voice commands in more than 70 languages or by simply pointing at a mess and saying "clean this." The Mountain View, California-based company, founded by former Google Nest engineers Mehul Nariyawala and Navneet Dalal, has been working toward this moment for nine years. "When we started, we wrote down on a piece of paper that we're never going to get acquired," Nariyawala told Bloomberg. "It's good to finally ship what we dreamed about almost nine years ago." The robot responds to the wake word "Hey Matic," turns toward the speaker, and can follow commands like "clean the kitchen," "come here," or "follow me." Users can even chain instructions, such as asking the robot to vacuum one room and mop another in a single sentence. How it works. Unlike competing models that rely on smart home platforms like Alexa or Google Home, Matic's voice control is built directly into the robot itself. Gesture detection uses the device's five onboard cameras to see where a user is pointing, something the company says is impossible for lidar-only systems that "see nothing." "A truly intelligent robot that is intuitive to use should learn how humans naturally communicate, instead of asking families to learn yet another new interface," Nariyawala said in a company announcement. "That is the only way a robot can truly belong inside a home and become part of a family." Privacy considerations. Matic has built its reputation on privacy, processing visual data on the device rather than in the cloud. With Matic Cues, the company maintains that approach for the wake word and gesture detection - both handled entirely on the robot. However, voice commands are sent to Google's Gemini API for parsing, meaning the feature requires cloud connectivity. "We anonymously send the Gemini model your command," the company explained in a blog post. "No user info is sent." Microphones are off by default, and users must opt in to enable the feature. Matic says it plans to develop a smaller on-device model for the most common commands in the future, potentially eliminating the cloud dependency. Business context. The update arrives at a pivotal moment for the US robot vacuum industry. iRobot Corp., the pioneer behind Roomba, filed for bankruptcy late last year, while Chinese competitors like Roborock and Dreame have captured market share with lower-priced models, Bloomberg reported. The FCC's recent addition of foreign-produced "advanced robotic devices" to its Covered List could restrict new models from China entering the US market. Matic, which designs and assembles its robots in California, has sold over 13,000 units to date. The company announced $60 million in new financing in January, bringing total funding to $115 million. A price hike to $1,495 is scheduled for early September, which the company attributes to rising component costs, according to Bloomberg. What Matic has demonstrated with Cues is that the most advanced home robot isn't necessarily the one with the most sensors or the fastest processor; it's the one that disappears into the background and responds to eWEEK the way eWEEK already talk to each other. Additional reading: For more on how robots are mastering increasingly complex real-world tasks, see how Figure 03 autonomously climbed a ladder without human control. Aminu Abdullahi is a B2C and B2B technology and finance writer with more than six years of experience covering enterprise IT, cybersecurity, cloud computing, artificial intelligence, fintech, business software, and emerging technologies. His work has appeared in publications including TechRepublic, eWEEK, Channel Insider, Geekflare, Enterprise Networking Planet, eSecurity Planet, CIO Insight, and Webopedia. With a technical background in computer science, he specializes in translating complex technology topics into clear, accessible content for business leaders and decision-makers.