Aetina is displaying 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 expertise 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 towards end-to-end autonomy.”
In bodily AI utility situations, robots and automation require real-time, dependable spatial notion. In addition they want a “decision-making mind” able to executing complicated process reasoning on the edge for dynamic orchestration amid shifting duties, exceptions, and altering operational priorities, stated Aetina.
The firm claimed that its presence at GTC highlights its position as a key infrastructure enabler for each robotic and enterprise autonomy. Aetina stated it offers the “eyes of notion” and the “mind of intelligence” required for autonomous programs, accelerating deployment of AI on the edge throughout industries.
The New Taipei Metropolis, Taiwan-based firm presents a spread 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 growth 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 displaying the DeviceEdge AIB-AT78/68 sequence, which it claimed is without doubt one of the business’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 assist more and more complicated robotic behaviors and AI expertise, based on 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 service sectors.
The AIB-AT78/68 sequence delivers as much as 2070 FP4 TFLOPS of AI efficiency with in depth 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 may also help shut the hole between simulation and real-world deployment, driving scalable bodily AI adoption.
As well as, by a collaboration with Stereolabs, Aetina plans to display 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 assist.
“Aetina is deeply integrating GMSL2 3D visible notion expertise with the NVIDIA Jetson Thor platform, whereas leveraging the excellent inference capabilities of NVIDIA MGX modular edge servers to construct diversified, deployable infrastructure for the bodily AI period,” stated Joe Lo, president of Aetina. “Along with empowering next-generation robots with complete environmental notion, we’re serving to assemble an autonomous ‘mind’ that connects sharp sensing to clever decision-making—accelerating the journey from lab prototypes to real-world, multi-scenario deployments.”
Past robotics, Aetina can 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 situations akin to 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 allows seamless edge-side integration of high-fidelity notion and workflow reasoning, propelling AI purposes to a brand new stage of autonomy,” the corporate stated.
Aetina invited world companions and media to go to Sales space 139 to see its dwell demonstrations. It stated it expects the AIB-AT78/68 sequence to be commercially out there in late March.
The submit Aetina exhibits 3D imaginative and prescient and enterprise generative AI at GTC 2026 appeared first on The Robotic Report.
