Watch eYs3D's Improved Robot Vision at CES 2023

By Chad Cox

Production Editor

Embedded Computing Design

January 05, 2023


At CES 2023, eYs3D is revealing its modular platform-as-a-service (PaaS) XINK Development kit for future autonomous robotic environments including AIoT, smart city, indoor cleaning robots, and outdoor agricultural robots. Robotics as a Service (RaaS) will be influenced by both, the industrial and retail markets, and improved robot vision from eYs3D will ease some of the development pain.

The system provides AI inference tools such as TensorFlow, TensorFlow Lite, PyTorch, Caffe, and TVM and is powered by eYs3D’s new eCV1 AI chip integrating four Core ARM 64-Bit CPUs and a 4.6 TOPS neural processor unit (NPU).

James Wang, Chief Strategy Officer of eYs3D believes, “Mobile autonomy must be accompanied by advances in computer vision to enable new areas of robotic deployment, including accurate picking and packing; moving, sorting and efficiently storing items; autonomous navigation; and other markets.”

XINK delivers high-performance computing, AI acceleration, smart power management, machine vision subsystems, I/O controls and Flexi-bus communication peripherals with support for H.264 compression and Imaging Signal Processing (ISP). Image data is inputted from an external ISP (eYs3D's separate eSP87x series stereo video and depth processor) or the ISP soft code within the module.  Wang continues, “Our XINK platform will allow rapid, one-stop development of vision capabilities for these applications, and we expect to host a community of developers who will both provide and benefit from contributed building blocks.”

eYs3D's environment is a cost-effective solution for design of safe, vision-capable mobile AI products equipped with field analysis, object recognition, obstacle detection, object tracking and following, and route planning functions.

XINK offers multiple benefits:

  •  Industry 4.0 application readiness, via high-speed communications and conformance to IEEE 1588 standards
  • Effective power management, including with sleep and deep sleep modes for unused blocks, supporting always-on capability
  • Superior computing performance through the quad-core Cortex A55 and the 4.6 TOPS NPU in the eCV1 chip, which provides dedicated machine learning instructions, a patented neural network engine, and Tensor Processing Fabric
  • Highly flexible image and computer vision processing for domain-specific applications

The XINK platform demonstrations will be showcased at CES 2023 at two booth locations, one at the LVCC, Booth #15769, Central Hall and the other in the Venetian at Eureka Park, Booth 62500, AT1, Hall G.

For further information, visit

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.

More from Chad