News

RTI boosts performance of ROS2 in software-defined vehicles

Source: eenewseurope, June 29, 2022 [1]
Real-Time Innovations (RTI) has launched the latest version of its Connext Drive for software defined vehicles with custom middleware to cut the latency of designs using the Robotics Operating System (ROS2) Connext Drive 2.0, based on a DDS publish-subscribe framework, now adds direct integrations into AUTOSAR Classic and ROS 2.

Intel is running rings around AMD and Arm at the edge

Source: The Register, June 27, 2022 [2]
Supermicro launched a wave of edge appliances using Intel's newly refreshed Xeon-D processors. Supermicro was the only one of the five vendors that even offered an AMD-based edge appliance. Just one appliance from Inspur used an Arm-based chip from Nvidia.

First working silicon of a DSP with embedded FPGA

Source: New Electronics, June 28, 2022 [3]
Flex Logix Technologies, a supplier of reconfigurable computing solutions, architecture and software, and CEVA, a licensor of wireless, sensing and integrated IP solutions, have announced the first successful silicon implementation that uses Flex Logix’s EFLX embedded FPGA (eFPGA) connected to a CEVA-X2 DSP instruction extension interface.

Using cloud-based, GPU-accelerated AI to track identity Fraud

Source: HPCwire, June 27, 2022 [4]
Microsoft and NVIDIA have a long history of working together to support financial institutions in detecting and preventing fraud. Using Microsoft Azure cloud and NVIDIA AI provides scalable, accelerated resources needed for AI/ML/DL algorithms, routines, and libraries. The partnership makes NVIDIA's powerful GPU acceleration available to financial institutions.

MIT CSAIL releases open-source simulator for autonomous vehicles

Source: The Robot Report, June 22, 2022 [5]
MIT researchers have released an open-source simulation engine that can construct photorealistic environments to train and test autonomous vehicles. VISTA 2.0 is an updated version of the team's previous model VISTA. It's able to simulate complex sensor types and interactive scenarios and intersections at scale.

Autonomous mobility for everyone

Source: Engineering, June 28, 2022 [6]
Autonomous vehicles are starting to become a key player in many people's day-to-day lives. The industry's ongoing challenge is the fragmented development environment for autonomous driving applications. Apex.AI has developed Apex.OS as an end-of-end software development kit (SDK).

Into the GPU Chiplet era: an interview with AMD's Sam Naffziger

Source: Tom's Hardware, June 23, 2022 [7]
Sam Naffziger is AMD's Senior Vice President, Corporate Fellow, and Product Technology Architect. AMD recently provided some tantalizing details on its upcoming RDNA 3 GPU architecture. The company is slated to launch before the end of the year with a chiplet-based design.

An Abu Dhabi center is developing ways to stop autonomous systems from getting hacked

Source: WIRED Middle East, April 29, 2022 [8]
A zero-trust architecture can be used to strengthen the security and reliance of mission-critical enterprise applications and autonomous systems, says a chief researcher at TII’s Secure Systems Research Center.

Research Institute creates framework and AI tools for autonomous industrial robots

Source: Vision Systems Design, June 29, 2022 [9]
The Southwest Research Institute has introduced an image reconstruction framework and AI-based classification tools. It allows industrial robots to visually scan and reconstruct an object and then perform tasks on it. The approach can be applied to grinding, polishing, cleaning, welding, sealing, and other industrial processes.

Papers

Data-driven offline optimization for architecting hardware accelerators

Source: arXiv.org, February 3, 2022 [10]
Develop a data-driven offline optimization method for designing hardware accelerators, dubbed PRIME, that enjoys all of these properties. Our approach learns a conservative, robust estimate of the desired cost function, utilizes infeasible points, and optimizes the design against this estimate without any additional simulator queries during optimization. PRIME architects accelerators -- tailored towards both single and multiple applications -- improving performance upon state-of-the-art simulation-driven methods by about 1.54x and 1.20x, while considerably reducing the required total simulation time by 93% and 99%, respectively. In addition, PRIME also architects effective accelerators for unseen applications in a zero-shot setting, outperforming simulation-based methods by 1.26x.

CFU Playground: full-stack open-source framework for tiny machine learning (tinyML) acceleration on FPGAs

Source: arXiv.org, Jaunary 5, 2022 [11]
Open-source framework CFU Playground enables rapid and iterative design of machine learning (ML) accelerators. It tightly integrates open-source software, RTL generators, and FPGA tools for synthesis, place, and route. The rapid, deploy-profile-optimization feedback loop lets ML hardware and software developers achieve significant returns.

Previous Hardware Acceleration in Robotics Newsletters

Past ROS 2 Hardware Acceleration Working Group meetings

  1. Flaherty, N. (2022, June 29). RTI boosts performance of ROS2 in software-defined vehicles. eenewseurope. https://www.eenewseurope.com/en/rti-boosts-performance-of-ros2-in-software-defined-vehicles/ ↩︎

  2. Mann, T. (2022, June 27). Intel is running rings around AMD and arm at the edge. The Register: Enterprise Technology News and Analysis. https://www.theregister.com/2022/06/27/intel_edge_amd_arm/ ↩︎

  3. Tyler, N. (2022, June 28). First working silicon of a DSP with embedded FPGA. New Electronics. https://www.newelectronics.co.uk/content/news/first-working-silicon-of-a-dsp-with-embedded-fpga ↩︎

  4. Using cloud-based, GPU-accelerated AI to track identity fraud. (2022, June 24). HPCwire. https://www.hpcwire.com/solution_content/microsoft-nvidia/using-cloud-based-gpu-accelerated-ai-to-track-identity-fraud/ ↩︎

  5. Wessling, B. (2022, June 22). MIT CSAIL releases open-source simulator for autonomous vehicles. The Robot Report. https://www.therobotreport.com/mit-csail-releases-open-source-simulator-for-autonomous-vehicles/ ↩︎

  6. MacAlpine, J. (2022, June 28). Autonomous mobility for everyone. Engineering.com. https://www.engineering.com/story/autonomous-mobility-for-everyone ↩︎

  7. Waltron, J., & Alcorn, P. (2022, June 23). Into the GPU Chiplet era: An interview with AMD's Sam Naffziger. Tom's Hardware. https://www.tomshardware.com/features/gpu-chiplet-era-interview-amd-sam-naffziger?&es_id=3e579176c8 ↩︎

  8. This Abu Dhabi center is stopping autonomous systems from getting hacked. (2022, April 29). WIRED Middle East. https://wired.me/technology/an-abu-dhabi-center-is-developing-ways-to-stop-autonomous-systems-from-getting-hacked/ ↩︎

  9. Wilson, L. (2022, June 29). Research institute creates framework and AI tools for autonomous industrial robots. Vision Systems Design. https://www.vision-systems.com/factory/robotics/article/14278878/research-institute-creates-framework-and-ai-tools-for-autonomous-industrial-robots ↩︎

  10. Kumar, A., Yazdanbakhsh, A., Hashemi, M., Swersky, K., & Levine, S. (2022, February 3). Data-driven offline optimization for architecting hardware accelerators. arXiv.org e-Print archive. https://arxiv.org/pdf/2110.11346.pdf ↩︎

  11. Prakash, S., Callahan, T., Bushagour, J., Banbury, C., Green, A. V., Warden, P., Ansell, T., & R, V. J. (2022, January 5). CFU Playground: full-stack open-source framework for tiny machine learning (tinyML) acceleration on FPGAs. arXiv.org e-Print archive. https://arxiv.org/pdf/2201.01863.pdf ↩︎