Aetina Launches Edge AI Systems for Robotics
Aetina Corp. has introduced its DeviceEdge AIE-KT78 and AIE-KT68 flagship edge AI systems for robotics and autonomous machines. The edge AI systems, powered by Nvidia Jetson Thor, integrate the Nvidia Blackwell architecture's high-performance AI compute, high-bandwidth sensor connectivity, and deterministic industrial control. These edge systems help developers design collaborative robots (cobots), humanoid robots, and autonomous machines that "perceive, reason, decide, and act" in real-world environments.
The AIE-KT78 and AIE-KT68 edge AI systems support on-device multimodal generative AI, large language models (LLM), vision language models (VLM), and vision language action (VLA) model execution. They connect high-resolution sensors with motors, joints, and actuators through high-bandwidth interfaces and EtherCAT control. A dedicated RJ45 1-GbE EtherCAT port is used as an independent EtherCAT Master, leveraging microsecond-level synchronization to connect high-level AI inference with motors, joints, sensors, and actuators.
This consolidates perception, decision-making, and deterministic control within a single system, Aetina said. It improves the flexibility and safety of cobots working alongside people, enabling fast switching between tasks, and supports more complex spatial awareness and continuous motion decision-making for humanoid robots, according to the company.
This architecture also reduces the need for additional control hardware and cross-platform integration, which simplifies the system design for applications such as cobots, humanoid robots, industrial robotic arms, and advanced autonomous machines.
The AIE-KT78 is powered by the Nvidia Jetson T5000 module with 128 GB of 256-bit LPDDR5X memory, delivering up to 2,070 FP4 TFLOPS of AI performance, and the AIE-KT68 is powered by the Nvidia Jetson T4000 module with 64 GB of 256-bit LPDDR5X memory, delivering up to 1,200 FP4 TFLOPS.
In addition, to handle data-intensive perception workloads, the AIE-KT Series simultaneously integrates QSFP28 connectivity (delivering up to 4 × 25 Gbits/s of bandwidth depending on configuration) and dual RJ45 10GbE ports, enabling high-speed processing of massive real-time data streams from high-resolution cameras, 3D LiDAR, radar, depth cameras, inertial measurement units, and a variety of other industrial sensors. The edge AI systems also support up to eight GMSL2camera inputs for multi-view environmental perception and spatial understanding.
The AIE-KT78/68 edge systems, housed in a 220 × 143 × 80-mm footprint, support a wide 9 to 48-VDC input range over an operating temperature of −25°C to 55°C. They also feature USB 3.2, isolated digital I/O, and M.2 expansion slots.
The AIE-KT78 and AIE-KT68 run Linux with the full Nvidia AI software stack, including JetPack 7, CUDA, TensorRT, DeepStream, Holoscan, and Isaac ROS. They are available now.
Related articles
Aetina Adds Jetson T3000 and T2000 Support to Edge AI Systems
Aetina Introduces Palm-Sized In-Vehicle Edge AI Platforms
Aetina Unveils Next-Gen MXM AI Modules
The post Aetina Launches Edge AI Systems for Robotics appeared first on Embedded.