Edge computing global leader ADLINK Technology has unveiled its ROScube-X Series real-time ROS 2 robot controller for advanced robotics applications.
Powered by the NVIDIA Jetson AGX Xavier module which features an integrated NVIDIA Volta GPU, dual deep learning accelerators and a wide variety of interfaces – including GMSL2 camera connectors for advanced robotics system integration - the ADLINK ROScube-X Series supports the full complement of resources provided by the NVIDIA JetPack SDK.
It’s specifically suited for robotics applications demanding high-performance AI computing capabilities with minimal power consumption.
The ROScube-X’s list of features includes powerful AI computing for intelligent robotics development, excellent performance per watt with power consumption as low as 20W, ruggedised, secure connectivity with locking USB ports, a comprehensive I/O for connecting a wide range of devices, and time synchronisation with GMSL2 camera and IMU.
“ADLINK is working closely with NVIDIA to empower high-performance AI computing at the edge, and our new ROScube-X enables integrators to develop and deploy advanced robotics applications faster and easier than ever,” says Dr Ryan Chen, director of ADLINK’s Advanced Robotic Platform Group.
“This allows our industrial and commercial customers to take their business operations to the next level and create new value in their product lines.”
Robotic systems based on the ROScube-X are supported by ADLINK’s Neuron SDK, a platform specifically designed for professional robotic applications such as autonomous mobile robots (AMR).
Dr Chen says the ROScube-X was designed to provide users with optimised AI.
“The ROScube-X is an integrated hardware and software solution which acts as a vantage point from which users can optimise AI value by enabling powerful and sustainable deployment of their models,” he says.
“This gives our customers a competitive edge by providing them with a platform to immediately develop robotics solutions and allowing them to choose their hardware solution at deployment time.”
With the newly released ROS 2 Foxy Fitzroy, Neuron SDK customers can enjoy the benefits of long-term support as well as ADLINK’s quality-guaranteed services.
The NVIDIA Jetson embedded AI computing platform provides high-performance, low-power computing for deep learning and computer vision to make it possible to build software-defined autonomous machines.
The platform, which now features cloud-native support, includes small form-factor Jetson modules with GPU-accelerated parallel processing, the JetPack SDK with developer tools, and comprehensive libraries for building AI applications along with an ecosystem of partners with services and products that accelerate development.
“Customers can get advanced robotics products to market more quickly with ADLINK’s expertise in edge computing and deep knowledge of the Jetson platform,” says Murali Gopalakrishna, head of product management of autonomous machines at NVIDIA.
“Moreover, with support for cloud-native technologies now available across the NVIDIA Jetson lineup, manufacturers of intelligent machines and developers of AI applications can build and deploy high-quality, software-defined features on embedded and edge devices targeting robotics, industrial IoT and more.”
The ROScube-X is available now from ADLINK Technology.