ROS 2 Hardware Acceleration Working Group

ROS 2 Hardware Acceleration Working Group - meeting #10

Source: ROS Discourse, June 30, 2022 [1]
We discussed new reference hardware platform and ROS 2 hardware acceleration stack. We also covered a collaboration between researchers from Acceleration Robotics and Harvard University on systems architecture and ROS with RobotCore: An Open Architecture for Hardware Acceleration in ROS 2.

News

Siemens and NVIDIA to enable industrial metaverse

Source: Siemens, June 29, 2022 [2]
Siemens and NVIDIA announced an expansion of their partnership to enable the industrial metaverse and increase use of AI-driven digital twin technology that will help bring industrial automation to a new level.

Simplifying hardware acceleration for robots with ROS 2

Source: TechTalks, July ,3 2022 [3]
Robot developers are increasingly focusing on developing software to run on existing hardware. There is a critical relationship between the hardware and the software capabilities in a robot. Retaining design control over the computing hardware is needed to create more specialized, power-efficient, secure, and high-performing robots.

Reducing software complexity is crucial to speeding up the shift to autonomous driving

Source: Automotive News Europe, July 1, 2022 [4]
The current chip generation is probably not able to fully deliver what complete autonomous driving requires. Autonomous vehicles are part of a larger paradigm shift toward software-defined vehicles. Reducing the complexity of architectures, chips and software is one of the central challenges to reaching autonomous driving faster.

Toward standard tests for automotive lidar systems

Source: SPIE, July 1, 2022 [5]
SPIE sponsored the first large-scale, open, and noncompetitive lidar benchmarking study. A multidisciplinary team evaluated 10 lidar systems in this pilot project. The field test was not designed to be a competition, but rather an experiment to quantify lidar performance.

The latest release of Isaac ROS is available now with ROS 2 Humble hardware-acceleration features

Source: NVIDIA Developer, July 5, 2022 [6]
Latest Humble ROS 2 release improves performance on compute platforms that offer hardware accelerators. Humble enables hardware-acceleration features for type adaptation and type negotiation eliminating software/CPU overhead and improving performance of hardware acceleration.

Intel and Google Cloud announce Cloud HPC toolkit

Source: HPCwire, July 6, 2022 [7]
Intel and Google are working together to drive high performance computing (HPC) forward on Google Cloud. Intel oneAPI Base and HPC Toolkits can be used to optimize performance. Tools improve compile times, speed of results and offer multi-vendor acceleration in SYCL.

Upcoming RISC-V laptop promises free silicon upgrades

Source: Ars Technica, July 5, 2022 [8]
World's first laptop to use the RISC-V instruction set architecture will reportedly start shipping in September. Roma laptop is available for preorder on Xcalibyte's website without much detail or pricing. The clamshell computer should bring the open ISA to a new form.

Brian Gerkey on the success of Open Robotics and ROS

Source: The Robot Report, July 5, 2022 [9]
The CEO and co-founder of Open Robotics, Brian Gerkey, talks about the development and evolution of the Robot Operating System (ROS) Gerkey on why open source software has played such a pivotal role in the growth of the robotics industry.

Using cloud-based, GPU-accelerated AI for algorithmic trading

Source: HPCwire, July 6, 2022 [10]
Microsoft and NVIDIA have a long history of working together to support algorithmic trading. The partnership makes NVIDIA's powerful GPU acceleration available to financial institutions. Microsoft Azure cloud, NVIDIA GPUs and NVIDIA AI provide scalable, accelerated resources for automating quantitative analysis and stock trading.

Pony.ai to mass produce autonomous driving controller built on Nvidia Drive Orin

Source: Robotics & Automation News, July 6, 2022 [11]
Pony.ai's Autonomous Driving Controller (ADC) powered by the Nvidia Drive Hyperion compute architecture (Drive Orin) has been sampled to customers with plans to mass produce the ADC starting in Q4 2022. The ADC enables vehicles to intelligently and comfortably maneuver on busy city streets, highways, and expressways.

Speed up machine learning models with accelerated WEKA

Source: NVIDIA Technical Blog, July 1, 2022 [12]
WekaDeeplearning4j and wekaRAPIDS provide enhanced functionality and performance inside the WEKA workbench. Accelerated WEKA improves communication between the JVM and Python interpreter. It also provides integration with the RAPIDS cuML library, which implements machine learning algorithms that are accelerated on NVIDIA GPUs.

Papers

Agilicious: Open-source and open-hardware agile quadrotor for vision-based flight

Source: Science, June 22, 2022 [13]
Agilicious is a codesigned hardware and software framework tailored to autonomous, agile quadrotor flight. It is completely open source and open hardware and supports both model-based and neural network–based controllers. Agilicious offers a unique combination of flexible software stack and high-performance hardware.

Efficient Edge-AI application deployment for FPGAs

Source: MDPI, May 28, 2022 [14]
This paper explores the efficacy and the dynamic deployment of hardware accelerated applications on the Kria KV260 development platform based on the Xilinx Kria K26 system-on-module (SoM), which includes a Zynq multiprocessor system-on-chip (MPSoC). The platform supports the Python-based PYNQ framework and maintains a high level of versatility with the support of custom bitstreams (overlays). The demonstration proved the reconfigurabibilty and the overall ease of implementation with low-footprint machine learning (ML)

Previous Hardware Acceleration in Robotics Newsletters

Past ROS 2 Hardware Acceleration Working Group meetings

  1. Hardware Acceleration WG, meeting #10. https://discourse.ros.org/t/hardware-acceleration-wg-meeting-10/25852 ↩︎

  2. Siemens and NVIDIA to enable industrial metaverse. (2022, June 29). Siemens Digital Industries Software. https://www.plm.automation.siemens.com/global/en/our-story/newsroom/siemens-xcelerator-nvidia-omniverse-industrial-metaverse/108414 ↩︎

  3. Dickson, D. (2022, July 3). Simplifying hardware acceleration for robots with ROS 2. TechTalks. https://bdtechtalks.com/2022/07/03/simplifying-hardware-acceleration-for-robots-with-ros-2/ ↩︎

  4. Sarkkinen, T. (2022, July 1). Reducing software complexity is crucial to speeding up the shift to autonomous driving. Automotive News Europe. https://europe.autonews.com/guest-columnist/reducing-software-complexity-crucial-speeding-shift-autonomous-driving ↩︎

  5. Hallett, P. (2022, July 1). Toward standard tests for automotive LiDAR systems. SPIE. https://amp-spie-org.cdn.ampproject.org/c/s/amp.spie.org/news/photonics-focus/julyaug-2022/benchmarking-automotive-lidar-systems ↩︎

  6. NVIDIA Isaac ROS. (2022, July 5). NVIDIA Developer. https://developer.nvidia.com/isaac-ros?ncid=so-link-738333&=&linkId=100000133685302#cid=em22_so-link_en-us ↩︎

  7. Hampton, J. (2022, July 6). Intel and Google cloud announce cloud HPC toolkit. HPCwire. https://www.hpcwire.com/off-the-wire/intel-and-google-cloud-announce-cloud-hpc-toolkit/ ↩︎

  8. Harding, S. (2022, July 5). Upcoming RISC-V laptop promises free silicon upgrades. Ars Technica. https://arstechnica.com/gadgets/2022/07/first-risc-v-laptop-expected-to-ship-in-september/ ↩︎

  9. Crowe, S. (2022, July 5). Brian Gerkey on the success of open robotics and ROS. The Robot Report. https://www.therobotreport.com/brian-gerkey-on-the-success-of-open-robotics-and-ros/?spMailingID=71423&puid=2502618&E=2502618&utm_source=newsletter&utm_medium=email&utm_campaign=71423 ↩︎

  10. Ware, A. (2022, July 6). Using cloud-based, GPU-accelerated AI for algorithmic trading. HPCwire. https://www.hpcwire.com/solution_content/microsoft-nvidia/using-cloud-based-gpu-accelerated-ai-for-algorithmic-trading/ ↩︎

  11. Edwards, D. (2022, July 6). Pony.ai to mass produce autonomous driving controller built on Nvidia drive Orin. Robotics & Automation News. https://roboticsandautomationnews.com/2022/07/06/pony-ai-to-mass-produce-autonomous-driving-controller-built-on-nvidia-drive-orin/51871/ ↩︎

  12. Bifet, A., Cassale, G. W., & Liu, J. (2022, July 5). Speed up machine learning models with accelerated WEKA. NVIDIA Technical Blog. https://developer.nvidia.com/blog/speed-up-machine-learning-models-with-accelerated-weka/ ↩︎

  13. Foehn, P., Kaufmann, E., Romero, A., Penicka, R., Sun, S., Bauersfeld, L., Laengle, T., Cioffi, G., Song, Y., Loquercio, A., & Scaramuzza, D. (2022, June 22). Agilicious: Open-source and open-hardware agile quadrotor for vision-based flight. Science . https://www.science.org/doi/10.1126/scirobotics.abl6259 ↩︎

  14. Kalapothas, S., Flamis, F., & Kitsos, P. (2022, May 28). Efficient Edge-AI application deployment for FPGAs. MDPI. https://www.mdpi.com/2078-2489/13/6/279 ↩︎