Today, Matic, the fastest-growing American home robotics and autonomy company, becomes among the first to adopt, explore, and scale on NVIDIA Jetson Orin Nano 2, a new entry-level robotics computer for entry-level edge AI coming in early 2027. Matic will use it to enable more intuitive interactions with its home cleaning robots, including conversational AI, gesture detection, deeper context of the home through precision mapping and semantic understanding, and autonomous cleaning.
Matic, the only American-designed and assembled home robot that earned Wired’s first perfect 10/10 score in 17 years of testing, has been building on the NVIDIA Jetson platform since the beginning. It has deployed more than 13,000 robots in homes across America. Every Matic robot sees the world through five RGB cameras. No LiDAR. No depth sensor. Every frame is processed on the robot itself. That architecture is why a gain in 2x inference performance on the edge computer is double the benefits to Matic customers.
Jetson Orin Nano 2 delivers 78 trillion operations per second of AI compute, twice the inference performance of its predecessor in the same form factor, and consumes 40 percent less power at the same performance in 15-watt mode. In a home robot, that arithmetic is the product. More intelligence in the same chassis. Longer runtime on the same battery. At a price families can actually afford.
“Families do not want a robot in the cloud. They want a robot in their home that just works and never asks for their attention,” said Mehul Nariyawala, co-founder of Matic. “The industry keeps promising the intelligence will arrive once the connection is fast enough. We took the harder path and put all of it on the robot. Jetson Orin Nano 2 lets us keep taking it.”
The foundation is already deployed. Matic robots have navigated 450,000 miles and cleaned 400 million square feet inside real homes, adding 3 million square feet every day. The average customer runs it seven times a week. Matic’s visual SLAM is engineered to 99.999 percent accuracy and builds absolute maps rather than relative ones, so the robot knows where it is in a home the way a person does, not because it started at the dock. It tells a rug from a wood floor and vacuums both while mopping only the wood. It tells a shoe from a cable from a dog toy, and cleans around them the way a person would.
“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. “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.”
The additional compute capacity builds on top of features Matic already ships. On August 13, Matic launched Cues, spoken command and gesture control in more than 70+ languages, processed entirely on the robot. No app required. Audio and video are handled on-device, and nothing leaves the home without the customer’s explicit permission.
The NVIDIA Jetson Orin Nano 2 module and developer kit are expected to be available in the first half of 2027. Matic will begin working on that once they are available and incorporate them to be included 6-9 months after they are available. Matic’s current products ship on NVIDIA Jetson today.
About Matic
Matic builds intuitive robotic products that work in real homes, with pets, kids, and the chaos of a real life being lived. Founded in 2017 by Mehul Nariyawala and Navneet Dalal, Matic is a vision-only home robotics company headquartered in Mountain View, California, with products assembled in California. Matic robots use five RGB cameras and on-device NVIDIA Jetson processing, with no LiDAR, no depth sensors, and no cloud. Matic is backed by investors including Sutter Hill Ventures, Atreides, Valor Equity Partners, 8V, Jack Dorsey, Naval Ravikant, Nat Friedman, and John and Patrick Collison.
Press kit, product images, and b-roll: [maticrobots.com/press]
View source version on businesswire.com: https://www.businesswire.com/news/home/20260916039428/en/
Media gallery
