News

PRESS RELEASE: Acceleration Robotics announce and open sources ROBOTCORE®, the first Robotic Processing Unit – specialized in ROS computations

Source: Acceleration Robotics, Septemeber 29, 2022 [1]
ROBOTCORE® is a processing unit for the robotics architect that maps robotics computations efficiently to its CPUs, GPU and FPGA to obtain faster robots and with additional real-time capabilities.

Acceleration Robotics, AMD partner to design robotic compute architectures with ROS

Source: The Robot Report, Septemeber 23, 2022 [2]
Acceleration Robotics and AMD are working together to develop new robotic capabilities. The collaboration will be led by Victor Mayoral-Vilches, a former Systems Architect at Xilinx. About 55% of the total commercial robots to be shipped in 2024 will use ROS, according to ABI Research.

Acceleration robotics partners with PlanV for a robotics-specific open source RISC-V Microcontroller

Source: Hackster.io, Septemeber 26, 2022 [3]
Acceleration Robotics has announced a partnership with Germany's PlanV. The pair will build a microcontroller specifically for Robot Operating System (ROS) 2 robotics projects. Most microcontrollers are generally accepted as programmable specialized devices, but not much is robotics-specific.

SiFive RISC-V cores picked for Google AI compute nodes

Source: The Register, Septemeber 23, 2022 [4]
SiFive says its processors are being used to manage AI workloads in Google datacenters. Multi-core RISC-V design with vector extensions, optimized for AI/ML applications. SiFive and Google were a little coy about exactly how this is packaged and used.

Arm is the new RISC/Unix, RISC-V is the new arm

Source: The Next Platform, Septemeber 22, 2022 [5]
Arm Ltd and its platoons of licensees have finally stormed the glass house - well, more of a data warehouse (literally) than a cathedral. They are firmly encamped on the no longer tiled, but concrete, floors of the old mainframe datacenters.

How semiconductor makers can turn a talent challenge into a competitive advantage

Source: McKinsey & Company, Septemeber 7, 2022 [6]
Semiconductor companies are on the cusp of a decade of opportunity, but success will be predicated on the ability to attract and retain the best and brightest.

India can contribute to chip making in a big way

Source: thehindubusinessline, Septemeber 25, 2022 [7]
Legislation provides for a $52 billion package to boost semiconductor manufacturing in the US. No country has an absolute monopoly over the troika of equipment, materials and services which power the ecosystem. The supply chains are the proverbial Achilles Heel for any entity since there is no absolute control over them.

Intel to broaden FPGA lineup and make them at home

Source: The Next Platform, Septemeber 27, 2022 [8]
Intel bought Altera for $16.7 billion in 2015 because of concerns about FPGAs storming the datacenter. In June 2015, Intel thought as much as a third of servers in hyperscaler and cloud datacenters would have an FPGA accelerator.

Study improves agricultural robotics with 2D LiDAR technology

Source: ZoOptics, Septemeber 27, 2022 [9]
A 2D LiDAR laser-scanner-based navigation approach was used for crop row tracking in 3D. It was possible to define a reference trajectory followed by two different control strategies. A backstepping approach-based strategy and an independently considered regulation of the front and rear steering axle positions were examined.

Is Nvidia blunting intuitive surgical's edge in robotic surgery?

Source: The Motley Fool, Septemeber 25, 2022 [10]
Intuitive Surgical is one of many medical device companies using Nvidia's Orin IGX technology. The company hauled in $6 billion in revenue over the 12 months ended in June. Other big-name peers that were mentioned include Siemens Healthineers, and Stryker.

Nvidia shuts out RISC-V software support for GPUs

Source: HPCwire, Septemeber 23, 2022 [11]
Nvidia has no plans to add RISC-V support for CUDA. CUDA is crucial to the company's pivot to becoming a software company. The company is moving its software stack heavily in the direction of Arm, which is behind its own homegrown CPUs. Nvidia is pairing its Hopper-based GPUs with Grace CPUs.

Nvidia drive Thor is a “centralized computer” for autonomous vehicles

Source: allaboutcircuits, Septemeber 27, 2022 [12]
At NVIDIA's most recent GTC, the company announced a new SoC to centralize the disparate computing requirements of modern vehicles.

Develop for all six NVIDIA Jetson Orin modules with the power of one developer kit

Source: NVIDIA Technical Blog, Septemeber 22, 2022 [13]
Jetson Orin Nano modules have up to 40 TOPS of AI performance. Jetson AGX Orin is already redefining robotics and other autonomous edge use cases. The developer kit's ability to natively emulate performance for any of the modules lets you start now.

Papers

High-performance computing for SKA transient search: use of FPGA based accelerators - a brief review

Source: arXiv, July 14, 2022 [14]
High-Performance computing efforts with FPGA for the accelerated pulsar/transient search for the SKA. Case studies are presented from within SKA and pathfinder telescopes highlighting future opportunities. It reviews the scenario that has shifted from offline processing of the radio telescope data to digitizing several hundreds of thousands of antenna output over huge bandwidths.

LPYOLO: low precision YOLO for face detection on FPGA

Source: arXiv, July 28, 2022 [15]
In this work, TinyYolov3 architecture is redesigned and deployed for face detection. It is a CNN based object detection method and developed for embedded systems. PYNQ-Z2 is selected as a target board which has low-end Xilinx Zynq 7020 System-on-Chip (SoC).

Previous Hardware Acceleration in Robotics Newsletters

Past ROS 2 Hardware Acceleration Working Group meetings

  1. https://news.accelerationrobotics.com/robotcore-first-robotic-processing-unit-specialized-ros/ ↩︎

  2. Wessling, B. (2022, September 23). Acceleration robotics, AMD partner to design robotic compute architectures with ROS. The Robot Report. https://www.therobotreport.com/acceleration-robotics-amd-partner-to-design-robotic-compute-architectures-with-ros/ ↩︎

  3. Halfacree, G. (2022, September 26). Acceleration robotics partners with PlanV for a robotics-specific open source RISC-V Microcontroller. Hackster.io. https://www.hackster.io/news/acceleration-robotics-partners-with-planv-for-a-robotics-specific-open-source-risc-v-microcontroller-cf13cdd01e9a ↩︎

  4. Robinson, D. (2022, September 23). Google uses SiFive RISC-V cores in AI compute nodes. The Register: Enterprise Technology News and Analysis. https://www.theregister.com/2022/09/23/google_using_sifive_riscv_cores/?utm_source=daily&utm_medium=newsletter&utm_content=article ↩︎

  5. Morgan, T. P. (2022, September 22). The Next Platform. https://www-nextplatform-com.cdn.ampproject.org/c/s/www.nextplatform.com/2022/09/22/arm-is-the-new-risc-unix-risc-v-is-the-new-arm/amp/ ↩︎

  6. How semiconductor makers can turn a talent challenge into a competitive advantage. (2022, September 7). McKinsey & Company. https://www.mckinsey.com/industries/semiconductors/our-insights/how-semiconductor-makers-can-turn-a-talent-challenge-into-a-competitive-advantage ↩︎

  7. Awasthi, A. (2022, September 25). India can contribute to chip making in a big way. thehindubusinessline. https://www-thehindubusinessline-com.cdn.ampproject.org/c/s/www.thehindubusinessline.com/opinion/india-can-contribute-to-chip-making-in-a-big-way/article65935233.ece/amp/ ↩︎

  8. Morgan, T. P. (2022, September 27). Intel to broaden FPGA lineup and make them at home. The Next Platform. https://www.nextplatform.com/2022/09/27/intel-to-broaden-fpga-lineup-and-make-them-at-home/ ↩︎

  9. Roy, P. (2022, September 27). Study improves agricultural robotics with 2D LiDAR technology. AZoOptics.com. https://www.azooptics.com/News.aspx?newsID=27954 ↩︎

  10. Rossolillo, N. (2022, September 25). Is Nvidia blunting intuitive surgical's edge in robotic surgery? The Motley Fool. https://www.fool.com/investing/2022/09/25/is-nvidia-blunting-intuitive-surgicals-edge-in-rob/ ↩︎

  11. Shah, A. (2022, September 23). Nvidia shuts out RISC-V software support for GPUs. HPCwire. https://www.hpcwire.com/2022/09/23/nvidia-shuts-out-risc-v-software-support-for-gpus/ ↩︎

  12. Hertz, J. (2022, October 27). NVIDIA DRIVE Thor is a “centralized computer” for autonomous vehicles. allaboutcircuits. https://www.allaboutcircuits.com/news/nvidia-drive-thor-centralized-computer-autonomous-vehicles/ ↩︎

  13. Sheshadri, S. H. (2022, September 22). Develop for all six NVIDIA Jetson Orin modules with the power of one developer kit. NVIDIA Technical Blog. https://developer.nvidia.com/blog/develop-for-all-six-nvidia-jetson-orin-modules-with-the-power-of-one-developer-kit/ ↩︎

  14. High-performance computing for SKA transient search: use of FPGA based accelerators - a brief review. (2022, July 14). arXiv.org e-Print archive. https://arxiv.org/pdf/2207.07054.pdf ↩︎

  15. Gunay, B., Ocku, s. B., & Bilge, H. S. (2022, July 28). LPYOLO: low precision YOLO for face detection on FPGA. arXiv.org e-Print archive. https://arxiv.org/pdf/2207.10482.pdf ↩︎