Corpus ID: 208527097

Quantized deep learning models on low-power edge devices for robotic systems

@article{Sinha2019QuantizedDL,
  title={Quantized deep learning models on low-power edge devices for robotic systems},
  author={Anugraha Sinha and Naveen Kumar and Murukesh Mohanan and M. D. Muhaimin Rahman and Yves Quemener and Amina Mim and Suzana Ilic},
  journal={ArXiv},
  year={2019},
  volume={abs/1912.00186}
}
  • Anugraha Sinha, Naveen Kumar, +4 authors Suzana Ilic
  • Published 2019
  • Engineering, Computer Science
  • ArXiv
  • In this work, we present a quantized deep neural network deployed on a low-power edge device, inferring learned motor-movements of a suspended robot in a defined space. This serves as the fundamental building block for the original setup, a robotic system for farms or greenhouses aimed at a wide range of agricultural tasks. Deep learning on edge devices and its implications could have a substantial impact on farming systems in the developing world, leading not only to sustainable food… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Citations

    Publications citing this paper.

    A Data and Compute Efficient Design for Limited-Resources Deep Learning

    VIEW 1 EXCERPT
    CITES BACKGROUND

    References

    Publications referenced by this paper.
    SHOWING 1-9 OF 9 REFERENCES

    Efficient Deep Learning Inference on Edge Devices

    VIEW 1 EXCERPT

    Toward an Intelligent Edge: Wireless Communication Meets Machine Learning

    VIEW 1 EXCERPT

    Resource-conserving agriculture increases yields in developing countries.

    VIEW 1 EXCERPT