- News
- Announcing the RobotPerf™ benchmarks beta release: An industry standard for benchmarking robotic brains
- Yocto, ROS 2, and hardware acceleration: A production-grade trio for robotics
- Intel adds cost-optimized FPGAs with RISC-V option
- AMD accelerates innovation at the edge with Kria K24 SOM and starter kit for industrial and commercial applications
- From sanctions to silicon: China’s semiconductor breakthrough
- 2 technologies that will be huge for robotic surgery
- Unlocking efficiency: The power of IP blocks in silicon chip design
- U.S. investment in semiconductor manufacturing: Building the talent pipeline
- Papers
News
Announcing the RobotPerf™ benchmarks beta release: An industry standard for benchmarking robotic brains
Source
: Acceleration Robotics, September 15, 2023 [1]
AMD, Intel, Ford, Harvard, Klagenfurt University, Georgia Institute of Technology, Boston University, Johannes Kepler University Linz, Barnard College, Columbia University, and Carnegie Mellon University announce the beta release of RobotPerf™ Benchmarks. An advanced benchmarking suite crafted specifically to evaluate robotics computing performance using ROS 2 as its baseline.
Yocto, ROS 2, and hardware acceleration: A production-grade trio for robotics
Source
: Acceleration Robotics, September 14, 2023 [2]
Building a production-grade operating system for robots requires a perfect mix of customization, performance, and security. With Yocto and ROS 2, this becomes achievable. In this post, we're diving deep into the integration of ROS 2 Humble into Yocto and PetaLinux, and why hardware acceleration plays a vital role in this process.
Intel adds cost-optimized FPGAs with RISC-V option
Source
: The Register, September 15, 2023 [3]
Intel has expanded its Agilex FPGA portfolio to meet demand for customized workloads, including AI processing, and provide a more comprehensive line-up. The Agilex 3 device family offers power and cost-optimized FPGAs in compact form factors, offering a more comprehensive solution than the Agilex 5, 7, and 9 lines.
AMD accelerates innovation at the edge with Kria K24 SOM and starter kit for industrial and commercial applications
Source
: AMD, September 19, 2023 [4]
AMD has announced the AMD Kria K24 System-on-Module (SOM) and KD240 Drives Starter Kit, which offer power-efficient compute in a small form factor for cost-sensitive industrial and commercial edge applications. The K24 SOM is half the size of a credit card and uses half the power of the larger Kria K26 SOM.
From sanctions to silicon: China’s semiconductor breakthrough
Source
: Power Technology, September 18, 2023 [5]
This could enable China to bridge the technological gap that the US is determined to maintain, and position China as a world leader in chip production.
2 technologies that will be huge for robotic surgery
Source
: The Robot Report, September 20, 2023 [6]
Intuitive Surgical President Dave Rosa is excited about two technological opportunities advancing surgical robotics and minimally invasive surgery: improved visualization for surgeons and focal therapy. He believes these advancements will help surgeons better understand their work.
Unlocking efficiency: The power of IP blocks in silicon chip design
Source
: Semiconductor Engineering, September 14, 2023 [7]
Document the IP selection process and establish procedures for effective IP management.
U.S. investment in semiconductor manufacturing: Building the talent pipeline
Source
: Council on Foreign Relations, September 18, 2023 [8]
To reverse the three decade long decline in the United States' share of semiconductor manufacturing, a concerted effort is required.
Papers
RobotPerf: An open-source, vendor-agnostic, benchmarking suite for evaluating robotics computing system performance
Source
: Acceleration Robotics , September 15, 2023 [9]
RobotPerf is a vendor-agnostic benchmarking suite for robotics computing performance across various hardware platforms, using ROS 2 as its common baseline. It uses black-box testing and grey-box testing to evaluate performance. The suite is adaptable for custom ROS 2 computational graphs and is an open-source initiative committed to community input.
Multi-axis Current Loop Control Based on FPGA
Source
: iopscience, 2023 [10]
This paper uses a three-loop control structure with a FPGA as the control chip, enabling parallel control of multi-axis motors. The code is written in Verilog HDL and simulation results are provided by SignalTap. The FPGA's rich logic resources and parallel processing ability significantly reduce the calculation time of the servo system.
Previous Hardware Acceleration in Robotics
Newsletters
- Hardware Acceleration in Robotics #77 - Modi wants to make India a chip-making superpower. Can he?, What's new in China's robotics market? and more
- Hardware Acceleration in Robotics #76 - July 2023 robotics investments total US $2.1 billion, North American robot orders drop for 2nd quarter in a row and more
- Hardware Acceleration in Robotics #75 - How to simplify robotics research with a native, ROS-based system, Predicting the future for semiconductors and more
- Hardware Acceleration in Robotics #74 - Autoware accelerators, application-specific system-on-chip (Soc) and software platform for autonomous vehicles (robots), How Intel, Samsung and TSMC are changing the world and more
- Hardware Acceleration in Robotics #73 - ROSCon 2023 comes to INDIA, Turnaround in semiconductor market, TIER IV and Axell unveil Autoware Accelerator prototypes: Building energy-efficient autonomous vehicles and more
- Hardware Acceleration in Robotics #72 - The rise of FPGA technology in high-performance computing, A stable heartbeat for the world of electronics, Why people are still key to tech transformation and more
- Hardware Acceleration in Robotics #71 - June 2023 robotics investments total US $2.1 billion, Chip experts see talent shortage as main growth hurdle and more
- Hardware Acceleration in Robotics #70 - Europe’s strategy to boost its computer chip industry and compete with Asia gets final approval, Robot operating system advances left up to industry and more
- Hardware Acceleration in Robotics #69 - Industrial robot components market worth more than $18B by 2027, How India is working to become the semiconductor hub globally in the next 10 years? and more
- Hardware Acceleration in Robotics #68 - Acceleration Robotics leads RobotPerf™ Benchmarks to its first "alpha" release, Broadcom to invest in a $1 billion EU-funded chip programme in Spain and more
Past ROS 2 Hardware Acceleration Working Group
meetings
- Hardware Acceleration WG, meeting #22
- Hardware Acceleration WG, meeting #21
- Hardware Acceleration WG, meeting #20
- Hardware Acceleration WG, meeting #19
- Hardware Acceleration WG, meeting #18
- Hardware Acceleration WG, meeting #17
- Hardware Acceleration WG, meeting #16
- Hardware Acceleration WG, meeting #15
- Hardware Acceleration WG, meeting #14
- Hardware Acceleration WG, meeting #13
- Hardware Acceleration WG, meeting #12
- Hardware Acceleration WG, meeting #11
- Hardware Acceleration WG, meeting #10
- Hardware Acceleration WG, meeting #9
- Hardware Acceleration WG, meeting #8
- Hardware Acceleration WG, meeting #7
- Hardware Acceleration WG, meeting #6
- Hardware Acceleration WG, meeting #5
- Hardware Acceleration WG, meeting #4
- Hardware Acceleration WG, meeting #3
- Hardware Acceleration WG, meeting #2
- Hardware Acceleration WG, meeting #1
Mayoral-Vilches, V. (2023, September 15). Announcing the RobotPerf™ benchmarks beta release: An industry standard for benchmarking robotic brains. Acceleration Robotics. https://news.accelerationrobotics.com/robotperf-beta/ ↩︎
Yocto, ROS 2, and hardware acceleration: A production-grade trio for robotics. (2023, September 14). Acceleration Robotics. https://news.accelerationrobotics.com/yocto-ros2-hardware-acceleration/ ↩︎
Robinson, D. (2023, September 15). Intel adds cost-optimized FPGAs with RISC-V option. The Register. https://www.theregister.com/2023/09/15/intel_fpga_updates/ ↩︎
AMD accelerates innovation at the edge with Kria K24 SOM and starter kit for industrial and commercial applications. (2023, September 19). AMD. https://www.amd.com/en/newsroom/press-releases/2023-9-19-amd-accelerates-innovation-at-the-edge-with-kria-k.html ↩︎
From sanctions to silicon: China’s semiconductor breakthrough. (2023, September 18). Power Technology. https://www.power-technology.com/comment/from-sanctions-to-silicon-chinas-semiconductor-breakthrough/ ↩︎
Hammerand, J. (2023, September 12). 2 technologies that will be huge for robotic surgery. The Robot Report. https://www.therobotreport.com/two-technologies-that-will-be-huge-for-robotic-surgery-per-intuitives-dave-rosa/?spMailingID=98260&puid=2502618&E=2502618&utm_source=newsletter&utm_medium=email&utm_campaign=98260 ↩︎
Varde, A. (2023, September 14). Unlocking efficiency: The power of IP blocks in silicon chip design. Semiconductor Engineering. https://semiengineering.com/unlocking-efficiency-the-power-of-ip-blocks-in-silicon-chip-design/ ↩︎
Sloun, S. V. (2023, September 18). U.S. investment in semiconductor manufacturing: Building the talent pipeline. Council on Foreign Relations. https://www.cfr.org/blog/us-investment-semiconductor-manufacturing-building-talent-pipeline ↩︎
Mayoral-Vilches, V., Jabbour, J., Yu-Shun, H., Zishen, W., Martínez-Farina, A., Crespo-Álvarez, M., Stewart, M., Reina-Muñoz, J. M., Nagras, P., Vikhe, G., Bakhshalipour, M., Pinzger, M., Rass, S., Panigrahi, S., Corradi, G., Roy, N., Gibbons, P. B., Neuman, S. M., Plancher, B., & Reddi, V. J. (2023, September 15). RobotPerf: An open-source, vendor-agnostic, benchmarking suite for evaluating robotics computing system performance. Acceleration Robotics . https://accelerationrobotics.com/pdf/robotperf.pdf ↩︎
Hu, J., Chen, Y., Zhao, J., Wu, S., & Zou, J. (2023). Multi-axis Current Loop Control Based on FPGA. iopscience. https://iopscience.iop.org/article/10.1088/1742-6596/2564/1/012009/pdf ↩︎