Acceleration Robotics launches ROBOT CORE ROS 2 hardware

Robotics startup Acceleration Robotics has released networking products enabling 62-1000X faster communication for autonomous systems via new time-sensitive networking (TSN) capabilities. TSN's determinism facilitates modular designs using standard ethernet infrastructure - a paradigm shift promising more interoperable robot components.

Previously, engineering complex robots required customized cabling imposing deployment constraints. TSN's precise transmissions leverage widespread ethernet while guaranteeing real-time response critical for nimble control loops. This unified connectivity between sensors, compute and motion units simplifies swapping modules from various vendors.

Enriched ethernet standardization supports rapidly evolving autonomy, learning and safety needs inaccessible via legacy fieldbuses. Acceleration's extreme low-latency "Robot Core" offerings demonstrate TSN's aptitude managing torrents of tactile, visual and positional datasets underlying responsive mobility and dexterity.

The bandwidth explosion also expands prospects for wireless tactile gloves steering humanoid motion, dense sensor skins enabling delicate manipulation, and light-speed simulations training robots safely. System architects gain flexibility harnessing off-the-shelf TSN advancements over proprietary continuity necessitating brittle interfaces.

Founder Victor Mayoral Vilches stated, "Our research shows TSN will eventually subsume many real-time industry protocols. The result should be a unified landscape of physically collaborative robots and components."

By graduating time-sensitive networking to microseconds, Acceleration Robotics clears a path to simpler but more adaptive automatons. Their timely tools promise to unshackle developers as innovative applications command increasingly synchronized orchestration between networked computing, actuation and perception modules.

The team completely rewrote the network stack of robots, including ROS 2, and implemented it in hardware. The resulting design was prototyped and implemented in FPGAs.

Wilches and a group of scientists and industry leaders set out to create a methodology for measuring the performance of robotics and control systems. Acceleration Robotics published the RobotPerf documentation earlier this year.

ROBOTCORE ROS 2 hardware implements the ROS 2 robotics framework for unprecedented network interface speed and efficiency. This robot core (IP core) uses FPGA technology to increase the ROS 2 communication speed. This speeds up data processing, reduces latency, and improves synchronization of robotic systems. ROBOTCORE ROS 2 provides the future of accelerated robotics networks by sending or receiving packets in less than 2.5 microseconds, which is 62 times faster than CPU-based software.

ROBOTCORE ROS 2 is versatile and widely compatible, making it a viable solution for scenarios where speed and reliability are non-negotiable. These applications include:

Industrial automation: Simplifies communication on production and assembly lines to improve operational efficiency.
Remote Control: Provides smooth and responsive control in remote control systems, which is crucial for performing precise tasks.
Autonomous vehicles: Provides fast data exchange necessary for real-time decision-making in autonomous driving systems.
Research and development: Provides a reliable platform for the development and testing of next-generation robotic technologies.

Share with friends:

Write and read comments can only authorized users