Aetina is exhibiting its newest built-in AI programs at GTC in San Jose, Calif. Supply: Aetina Corp.
Aetina Corp., a number one world supplier of edge AI programs, is demonstrating high-precision 3D imaginative and prescient know-how and enterprise-grade generative AI brokers this week at GTC 2026. The corporate stated its programs use NVIDIA’s Blackwell structure to allow robots and automatic programs “to advance toward end-to-end autonomy.”
In bodily AI utility eventualities, robots and automation require real-time, dependable spatial notion. Additionally they want a “decision-making brain” able to executing advanced process reasoning on the edge for dynamic orchestration amid shifting duties, exceptions, and altering operational priorities, stated Aetina.
The corporate claimed that its presence at GTC highlights its function as a key infrastructure enabler for each robotic and enterprise autonomy. Aetina stated it offers the “eyes of perception” and the “brain of intelligence” required for autonomous programs, accelerating deployment of AI on the edge throughout industries.
The New Taipei Metropolis, Taiwan-based firm affords a variety of AI computing programs, platforms, {hardware}, and software program instruments for the creation of several types of vertical AI. Aetina stated its built-in programs empower its Arm, x86 computer systems, GPUs, ASIC {hardware}, cloud administration software program, and improvement instruments with AI.
With its ecosystem community, Aetina added that its world companions’ applied sciences make the creation and deployment of particular AI-powered purposes simpler.
Stereolabs GMSL2 3D Imaginative and prescient companions to advance notion
Aetina is exhibiting the DeviceEdge AIB-AT78/68 sequence, which it claimed is among the trade’s first production-ready platforms powered by NVIDIA Jetson T5000 and T4000 modules. The DeviceEdge sequence offers edge computing and real-time notion, in addition to resolution skills to help more and more advanced robotic behaviors and AI abilities, in keeping with the corporate.
It added that the AIB-AT78/68 has already been built-in into onboard computing platforms for humanoid robots throughout manufacturing, logistics, and repair sectors.
The AIB-AT78/68 sequence delivers as much as 2070 FP4 TFLOPS of AI efficiency with intensive I/O, together with QSFP28 (100 Gbps), EtherCAT, and twin 10 GbE industrial-grade connectivity interfaces. This exactly addresses in-field calls for for sensor fusion and high-speed movement management, stated Aetina.
By combining NVIDIA Isaac, NVIDIA Isaac GR00T, and Imaginative and prescient AI workflows, the corporate stated its platform might help shut the hole between simulation and real-world deployment, driving scalable bodily AI adoption.
As well as, by way of a collaboration with Stereolabs, Aetina plans to reveal the Humanoid Encompass Imaginative and prescient Answer onsite. Constructed on the AIB-AT78/68 platform, the GMSL2 (Gigabit Multimedia Serial Hyperlink 2) system integrates two ZED X stereo cameras for frontal depth sensing and two ZED X One cameras for peripheral consciousness.
Utilizing GMSL2’s excessive bandwidth and low latency, the DeviceEdge system allows sub-millisecond 3D notion processing, which Aetina stated offers robots human-like navigation capabilities. The platform helps an working temperature vary of -25° to 80°C (-13° to 176°F) and a 130W power-efficient design, engineered particularly for industrial environments.
Aetina builds a call ‘mind’ with NVIDIA MGX edge servers
At GTC, Aetina additionally plans to current its improvements powered by NVIDIA Blackwell structure, that includes the DeviceEdge AIB-AT78/68 sequence edge supercomputing platform powered by NVIDIA Jetson Thor and modular NVIDIA MGX edge servers with NVIDIA NIM microservices help.
“Aetina is deeply integrating GMSL2 3D visual perception technology with the NVIDIA Jetson Thor platform, while leveraging the outstanding inference capabilities of NVIDIA MGX modular edge servers to build diversified, deployable infrastructure for the physical AI era,” stated Joe Lo, president of Aetina. “In addition to empowering next-generation robots with comprehensive environmental perception, we are helping construct an autonomous ‘brain’ that connects sharp sensing to intelligent decision-making—accelerating the journey from lab prototypes to real-world, multi-scenario deployments.”
Past robotics, Aetina may even showcase the SuperEdge AEX-2UA1 2U short-depth edge server primarily based on the MGX structure, accelerated by NVIDIA RTX PRO 6000 Blackwell Server Version GPUs.
By combining NIM microservices to run massive language fashions (LLMs) on the edge, the corporate stated it helps enterprises quickly undertake agentic AI. It can carry out on-premises reasoning, analyze operational information, and generate real-time insights and suggestions, whereas preserving information sovereignty and safety.
This structure is appropriate for latency-sensitive eventualities reminiscent of warehouses and factories, the place information can’t be simply moved to the cloud or the place native real-time decision-making is required, famous Aetina. “It enables seamless edge-side integration of high-fidelity perception and workflow reasoning, propelling AI applications to a new level of autonomy,” the corporate stated.
Aetina invited world companions and media to go to Sales space 139 to see its stay demonstrations. It stated it expects the AIB-AT78/68 sequence to be commercially out there in late March.
The publish Aetina reveals 3D imaginative and prescient and enterprise generative AI at GTC 2026 appeared first on The Robotic Report.
