Summary of Real-time Spacecraft Pose Estimation Using Mixed-precision Quantized Neural Network on Cots Reconfigurable Mpsoc, by Julien Posso et al.
Real-Time Spacecraft Pose Estimation Using Mixed-Precision Quantized Neural Network on COTS Reconfigurable MPSoC
by Julien Posso, Guy Bois, Yvon Savaria
First submitted to arxiv on: 6 Jun 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Hardware Architecture (cs.AR)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary A pioneering approach to real-time spacecraft pose estimation utilizes a mixed-precision quantized neural network implemented on the FPGA components of a commercially available Xilinx MPSoC, renowned for its suitability in space applications. A novel evaluation technique assesses layer-wise neural network sensitivity to quantization, facilitating an optimal balance between accuracy, latency, and FPGA resource utilization. The implementation is 7.7 times faster and 19.5 times more energy-efficient than the best-reported values in the existing spacecraft pose estimation literature. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A new way of quickly and accurately determining where a spacecraft is in space uses special computer chips called FPGAs. These chips are good for space applications because they can handle complex calculations quickly and use little power. The researchers developed a way to make sure their calculations were accurate while also being fast and efficient. Their method was 7.7 times faster and used 19.5 times less energy than other methods that have been tried before. |
Keywords
» Artificial intelligence » Neural network » Pose estimation » Precision » Quantization
