Volinski A, Zaidel Y, Shalumov A, DeWolf T, Supic L, Ezra Tsur E. Data-driven artificial and spiking neural networks for inverse kinematics in neurorobotics.
PATTERNS (NEW YORK, N.Y.) 2022;
3:100391. [PMID:
35079712 PMCID:
PMC8767299 DOI:
10.1016/j.patter.2021.100391]
[Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 08/10/2021] [Revised: 09/06/2021] [Accepted: 10/21/2021] [Indexed: 11/26/2022]
Abstract
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.
Collapse