Data-driven artificial and spiking neural networks for inverse kinematics in neurorobotics.

Autor:	Volinski A; Neuro-Biomorphic Engineering Lab, The Open University of Israel, Ra'anana, Israel., Zaidel Y; Neuro-Biomorphic Engineering Lab, The Open University of Israel, Ra'anana, Israel., Shalumov A; Neuro-Biomorphic Engineering Lab, The Open University of Israel, Ra'anana, Israel., DeWolf T; Applied Brain Research, Waterloo, Canada., Supic L; Accenture Labs, San Francisco, USA., Ezra Tsur E; Neuro-Biomorphic Engineering Lab, The Open University of Israel, Ra'anana, Israel.
Jazyk:	angličtina
Zdroj:	Patterns (New York, N.Y.) [Patterns (N Y)] 2021 Nov 18; Vol. 3 (1), pp. 100391. Date of Electronic Publication: 2021 Nov 18 (Print Publication: 2022).
DOI:	10.1016/j.patter.2021.100391
Abstrakt:	Inverse kinematics is fundamental for computational motion planning. It is used to derive an appropriate state in a robot's configuration space, given a target position in task space. In this work, we investigate the performance of fully connected and residual artificial neural networks as well as recurrent, learning-based, and deep spiking neural networks for conventional and geometrically constrained inverse kinematics. We show that while highly parameterized data-driven neural networks with tens to hundreds of thousands of parameters exhibit sub-ms inference time and sub-mm accuracy, learning-based spiking architectures can provide reasonably good results with merely a few thousand neurons. Moreover, we show that spiking neural networks can perform well in geometrically constrained task space, even when configured to an energy-conserved spiking rate, demonstrating their robustness. Neural networks were evaluated on NVIDIA's Xavier and Intel's neuromorphic Loihi chip. Competing Interests: The authors declare no competing interests. (© 2021 The Author(s).)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu