Home /Research /Using neuro-accelerators on FPGAs in collaborative robotics tasks
LEARNING

Using neuro-accelerators on FPGAs in collaborative robotics tasks

Aleksandr Zelensky, Evgeny A. Semenishchev, Andrey Alepko, Tagir Abdullin, Yurii Ilyukhin, V. L Voronin

Year
2021
Citations
5

Abstract

The article discusses the implementation of a hardware neuroaccelerator based on FPGAs of the Cyclone IV series with 115,000 logical elements. An assessment of the requirements for the hardware resources of the computing platform is given. The features of the implementation of the neural network in the tasks of cognitive robotics and industrial production have been investigated in order to improve safety in the interaction of a robot and a person.

Keywords

Field-programmable gate arrayRoboticsComputer scienceArtificial intelligenceRobotArtificial neural networkComputer architectureEmbedded systemHuman–computer interaction

Related papers

Browse all LEARNING papers