- News
- China overtakes USA in robot density
- 3 ways semiconductors enhance automation and efficiency
- 10 industries China is focusing on automating
- Semiconductor world in for a rough ride as chip bubble bursts at the high end
- Could RISC-V become a force in high performance computing?
- A Century of Moore’s Law
- Our future could be full of undying, self-repairing robots – here’s how
- Micro FPGAs and embedded FPGAs
- Emulating an NVIDIA Jetson Orin NX using the NVIDIA Jetson AGX Orin developer kit
- Papers
News
China overtakes USA in robot density
Source
: Robotics & Automation News, February 3, 2023 [1]
China’s massive investment in industrial robotics has put the country in the top ranking of robot density, surpassing the United States for the first time, according to a report by the International Federation of Robotics.
3 ways semiconductors enhance automation and efficiency
Source
: Newsroom Texas Instruments, June 28, 2022 [2]
Semiconductor technology is helping maximize productivity across a range of industrial systems, from robotics to factory automation, grid, home automation and more.
10 industries China is focusing on automating
Source
: The Robot Report, February 3, 2023 [3]
China has created the "Robot + Application Action Plan" to accelerate the use of robotics in manufacturing, agriculture, architecture, logistics, energy, healthcare, education, elderly services, commercial community service, and emergency and extreme environment applications.
Semiconductor world in for a rough ride as chip bubble bursts at the high end
Source
: The Register, February 4, 2023 [4]
The semiconductor gold rush is over at the high end, with Samsung and SK Hynix reporting dismal earnings due to macroeconomic forces. Intel, AMD, and Qualcomm, whose top-end chips depend on DRAM and NAND flash, saw declines across key markets. Micron was among the first semis to succumb to market forces, laying off 4,800 after its Q1, 2023 earnings tumbled 88% from the year prior on a nearly $200 million loss.
Could RISC-V become a force in high performance computing?
Source
: The Register, February 8, 2023 [5]
RISC-V is becoming increasingly popular in the high performance computing (HPC) sector, with plans to deploy future exascale and post-exascale supercomputers based on it. It is free to use and can be extended by adding custom instructions to the standard set.
A Century of Moore’s Law
Source
: SemiAnalysis, February 4, 2023 [6]
Moore's Law has become a cornerstone of the semiconductor industry, despite skeptics predicting its end. The semiconductor industry and those who follow it are likely to be familiar with Moore’s Law (Sidebar 1), which describes semiconductor technology improvements in terms of a clocklike cadence of doublings in the number of transistors in an integrated circuit over time.
Our future could be full of undying, self-repairing robots – here’s how
Source
: Robohub, February 1, 2023 [7]
AI systems such as ChatGPT and StableDiffusion are advancing rapidly, but the rate of advancement in robotics is slow, raising the possibility that future AI systems will need robotic "bodies" to interact with the world.
Micro FPGAs and embedded FPGAs
Source
: Semiconductor Engineering, February 2, 2023 [8]
Renesas has announced their Forge FPGA family, which are tiny, draw standby current measured in micro-amps, and are expected to sell in volume at prices less than 50 cents. They come with a complete tool kit and programming environment, and can be programmed in Verilog or using Renesas' graphical user interface.
Emulating an NVIDIA Jetson Orin NX using the NVIDIA Jetson AGX Orin developer kit
Source
: NVIDIA Technical Blog, February 6, 2023 [9]
The Jetson AGX Orin Developer Kit enables developers to emulate natively any of the NVIDIA Jetson Orin family modules, allowing them to quickly and cost-effectively evaluate the minimal hardware requirements for a project. It emulates the hardware specifications of the chosen module, and replicates its performance. This post shows how to emulate different Jetson modules with just one developer kit and summarizes the performance obtained through emulation. Jetson Nano can also be emulated, but it does not include hardware units for video encoding, so performance measurements would not be under the same conditions.
Papers
PiDRAM: A holistic end-to-end FPGA-based framework for processing-in-DRAM
Source
: ACM Transactions on Architecture and Code Optimization, November 17, 2022 [10]
Commodity DRAM-based processing-using-memory (PuM) techniques are an opportunity for alleviating the data movement bottleneck at low cost. However, system integration of these techniques requires appropriate tools to develop hardware and software components. PiDRAM is the first flexible end-to-end framework that enables system integration studies and evaluation of these techniques. We implement PiDRAM on an FPGA-based RISC-V system and demonstrate the flexibility and ease of use of two state-of-the-art PuM techniques: RowClone and D-RaNGe. We solve key integration challenges to make these techniques work and be effective on a real-system prototype, including memory allocation, alignment, and coherence.
FPGA-based object detection acceleration architecture design
Source
: iopscience, December 1, 2022 [11]
A multi-strategy optimization hardware accelerator based on the YOLOv2 model improves parallelism and real-time performance while reducing power consumption and resource consumption.
Previous Hardware Acceleration in Robotics
Newsletters
- Hardware Acceleration in Robotics #45 - ROS 2 HAWG - meeting #14, What slowdown? - December 2022 robotics investments reaches $1.14B and more
- Hardware Acceleration in Robotics #44 - ROS developers meet-up organised by acceleration robotics, China unveils new plan for wider robot use from manufacturing to agriculture and more
- Hardware Acceleration in Robotics #43 - ROS 2 HAWG#14, Acceleration robotics joins AESEMI to lead new processor architectures, ROS 2 HAWG in 2022 and more
- Hardware Acceleration in Robotics #42 - Can the U.S. bring chip manufacturing home?, The best tech of CES 2023, Teaching old robots new tricks and more
- Hardware Acceleration in Robotics #41 - ROS Meetup, Does 2+2=4? Microchip announces PolarFire 2; You do the math, Robots at CES 2023 and more
- Hardware Acceleration in Robotics #40 - Robot sales on track to hit a new high in 2022, Where all the semiconductor investments are going and more
- Hardware Acceleration in Robotics #39 - May the best robot win, Auto chips seen as biggest revenue producer in ‘23: KPMG survey and more
- Hardware Acceleration in Robotics #38 - ROS 2 HAWG - meeting #13, Intrinsic acquires OSRC and OSRC-SG, Mobile robot shipments increased by 53% in 2022 and more
- Hardware Acceleration in Robotics #37 - China surpasses U.S. in robot density, India in the Era of ‘Silicon Diplomacy’ and more
- Hardware Acceleration in Robotics #36 - Acceleration Robotics collaborating with Microchip to fasten robot computations with ROS 2 and RISC-V FPGA SoCs and more
Past ROS 2 Hardware Acceleration Working Group
meetings
- 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
Tao, M. (2023, February 3). China overtakes USA in robot density. Robotics & Automation News. https://roboticsandautomationnews.com/2023/02/03/china-overtakes-usa-in-robot-density/59868/ ↩︎
Ron, A. (2022, June 28). 3 ways semiconductors enhance automation and efficiency. Newsroom | news.ti.com. https://news.ti.com/blog/2022/06/28/3-ways-semiconductors-enhance-automation-and-efficiency?HQS=null-null-rob-rob_gen-enslt-blog-aac_315x220-eu_awr&DCM=yes&dclid=COvDvJ2-hf0CFckqBgAdmQ4L5Q ↩︎
Wessling, B. (2023, February 3). 10 industries China is focusing on automating. The Robot Report. https://www.therobotreport.com/china-plans-to-put-more-robots-into-these-10-industries/ ↩︎
Mann, T. (2023, February 4). Semis are in for a rough ride as high-end chip bubble bursts. The Register: Enterprise Technology News and Analysis. https://www.theregister.com/2023/02/04/semiconductor_market_bubble/?utm_source=daily&utm_medium=newsletter&utm_content=article ↩︎
Robinson, D. (2023, February 8). Could RISC-V become a force in HPC? We talk to the experts. The Register: Enterprise Technology News and Analysis. https://www.theregister.com/2023/02/08/riscv_hpc/ ↩︎
Herz, D. (2023, February 4). A century of Moore’s law. SemiAnalysis | Dylan Patel | Substack. https://www.semianalysis.com/p/a-century-of-moores-law?utm_source=substack&utm_medium=email ↩︎
Our future could be full of undying, self-repairing robots – here’s how. (2023, February 1). Robohub - Connecting the robotics community to the world. https://robohub.org/our-future-could-be-full-of-undying-self-repairing-robots-heres-how/ ↩︎
Tate, G. (2023, February 2). Micro FPGAs and embedded FPGAs. Semiconductor Engineering. https://semiengineering.com/micro-fpgas-and-embedded-fpgas/?cmid=dab065b1-0170-4214-9b52-25847ca6019b ↩︎
Sanchez, M. (2023, February 6). Emulating an NVIDIA Jetson Orin NX using the NVIDIA Jetson AGX Orin developer kit. NVIDIA Technical Blog. https://developer.nvidia.com/blog/emulating-an-nvidia-jetson-orin-nx-using-the-nvidia-jetson-agx-orin-developer-kit/ ↩︎
Olgun, A., Luna, J. G., Kanellopoulos, K., Salami, B., Hassan, H., Ergin, O., & Mutlu, O. (2022, November 17). PiDRAM: A holistic end-to-end FPGA-based framework for processing-in-DRAM. ACM Transactions on Architecture and Code Optimization. https://dl.acm.org/doi/full/10.1145/3563697 ↩︎
Wenhao, L., & Huaixiang, H. (2022, December 1). FPGA-based object detection acceleration architecture design. iopscience. https://iopscience.iop.org/article/10.1088/1742-6596/2405/1/012011 ↩︎