Robust Trajectory Generation for Robotic Control on the Neuromorphic Research Chip Loihi

Abstract

Neuromorphic hardware has several promising advantages compared to von Neumann architectures and is highly interesting for robot control. However, despite the high speed and energy efficiency of neuromorphic computing, algorithms utilizing this hardware in control scenarios are still rare. One problem is the transition from fast spiking activity on the hardware, which acts on a timescale of a few milliseconds, to a control-relevant timescale on the order of hundreds of milliseconds. Another problem is the execution of complex trajectories, which requires spiking activity to contain sufficient variability, while at the same time, for reliable performance, network dynamics must be adequately robust against noise. In this study we exploit a recently developed biologically-inspired spiking neural network model, the so-called anisotropic network. We identified and transferred the core principles of the anisotropic network to neuromorphic hardware using Intel's neuromorphic research chip Loihi and validated the system on trajectories from a motor-control task performed by a robot arm. We developed a network architecture including the anisotropic network and a pooling layer which allows fast spike read-out from the chip and performs an inherent regularization. With this, we show that the anisotropic network on Loihi reliably encodes sequential patterns of neural activity, each representing a robotic action, and that the patterns allow the generation of multidimensional trajectories on control-relevant timescales. Taken together, our study presents a new algorithm that allows the generation of complex robotic movements as a building block for robotic control using state of the art neuromorphic hardware.

Ag2Se Nanowire Network as an Effective In-Materio Reservoir Computing Device

“…Recently, several hardware AI implementations have been suggested for ANNs. [1][2][3][4] Our previous work demonstrated reservoir computing (RC), in a recurrent neural network (RNN), [5][6][7] as a suitable candidate to replace the AI software system with a random network of nonlinear nanojunctions. [8] Thus, we focused on RC hardware for in-materio computing, which is expected to operate with a significantly lower power consumption than traditional AI software.…”

MEMSORN: Self-organization of an inhomogeneous memristive hardware for sequence learning

“…Neuromorphic technologies with online learning capabilities can support the hardware implementation of such self-organizing SRNNs 6,7 . For example, a recent study has successfully mapped a self-organizing network on Loihi digital neuromorphic hardware for the generation of robust trajectories 8 .…”

Brian2Loihi: An emulator for the neuromorphic chip Loihi using the spiking neural network simulator Brian

“…These can be connected up to one another, stimulated with inputs, and the resulting activity patterns can be read out from the chip as output. A variety of algorithms and applications have been developed in recent years, including robotic control (DeWolf et al, 2020;DeWolf et al, 2016;Michaelis et al, 2020;Stagsted et al, 2020), spiking variants of deep learning algorithms, attractor networks, nearest-neighbor or graph search algorithms (reviewed by Davies et al, 2021). Moreover, neuromorphic hardware may provide a suitable substrate for performing large scale simulations of the brain (S. Furber, 2016;Thakur et al, 2018).…”