Aetina Highlights DeviceEdge AIB-AT78/68 for Humanoid Robots at NVIDIA GTC 2026
March 18, 2026
News
Aetina Corporation is attending NVIDIA GTC 2026 to showcase its high-precision 3D vision technology and enterprise-grade Generative AI agents moving robots and automation systems toward end-to-end autonomy. Highlighted will be the DeviceEdge AIB-AT78/68 series edge supercomputing platform powered by NVIDIA Jetson Thor, and modular NVIDIA MGX Edge Servers with NVIDIA NIM microservices support.
“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,” said 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.”
DeviceEdge AIB-AT78/68
The DeviceEdge AIB-AT78/68 series is powered by NVIDIA Jetson T5000 and NVIDIA Jetson T4000 modules and ideal for humanoid robots and advanced robotic systems. The platform is currently utilized in onboard computing for humanoid robots as it delivers enhanced computing, real-time perception, and decision capabilities that facilitate comprehensive robot protocols and AI skills.
With up to 2070 FP4 TFLOPS of AI performance and I/O including QSFP28 (100 Gbps), EtherCAT, and dual 10 GbE industrial-grade connectivity, the solution is designed for sensor fusion and high-speed motion control. It combines NVIDIA Isaac, NVIDIA Isaac GR00T, and Vision AI workflows for scalable physical AI.
Demonstrated will be the Humanoid Surround Vision Solution, a collaboration between Stereolabs and Aetina that is built on the AIB-AT78/68 platform. The GMSL2 solution integrates two ZED X stereo cameras for frontal depth sensing and two ZED X One cameras for peripheral awareness. With GMSL2’s high bandwidth and low latency, the platform enables sub-millisecond 3D perception processing, equipping robots with human-like environmental navigation capabilities.
SuperEdge AEX-2UA1 2U
The SuperEdge AEX-2UA1 2U is a short-depth edge server designed on NVIDIA MGX architecture that is accelerated by NVIDIA RTX PRO 6000 Blackwell Server Edition GPUs. Combining NVIDIA NIM microservices to run Large Language Models (LLMs) at the edge aids in quick adoption of agentic AI capable of executing on-premises reasoning, analyzation of operational data, and generation of real-time insights.
“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,” said 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.”
For more information, visit aetina.com and Application Highlight: How Physical AI Hardware Platforms, AI SDKs, and Strategic Partnerships are Overcoming Old Pain Points.
Chad Cox. Production Editor, Embedded Computing Design, has responsibilities that include handling the news cycle, newsletters, social media, and advertising. Chad graduated from the University of Cincinnati with a B.A. in Cultural and Analytical Literature.
