Neuromorphic control of a simulated 7-DOF arm using Loihi

Abstract

In this paper, we present a fully spiking neural network running on Intel’s Loihi chip for operational space control of a simulated 7-DOF arm. Our approach uniquely combines neural engineering and deep learning methods to successfully implement position and orientation control of the end effector. The development process involved 4 stages: 1) Designing a node-based network architecture implementing an analytical solution; 2) developing rate neuron networks to replace the nodes; 3) retraining the network to handle spiking neurons and temporal dynamics; and finally 4) adapting the network for the specific hardware constraints of the Loihi. We benchmark the controller on a center-out reaching task, using the deviation of the end effector from the ideal trajectory as our evaluation metric. The RMSE of the final neuromorphic controller running on Loihi is only slightly worse than the analytic solution, with 4.13% more deviation from the ideal trajectory, and uses two orders of magnitude less energy per inference than standard hardware solutions. While qualitative discrepancies remain, we find these results support both our approach and the potential of neuromorphic controllers. To the best of our knowledge, this work represents the most advanced neuromorphic implementation of neurorobotics developed to date.

Bioinspired smooth neuromorphic control for robotic arms

“…The continuous, high-precision and synchronized computations that these methods rely on hinder their compatibility with modern neuromorphic processors. This incompatibility prevents them from exploiting the energy efficiency, low latency, and robustness provided by neuromorphic computing [16].…”

An organic brain-inspired platform with neurotransmitter closed-loop control, actuation and reinforcement learning

“…Indeed, state-of-the-art neuromorphic controllers may either leverage on neuromorphic models to determine a control law, 26,27 or they can rely on spiking neural networks (SNNs) to implement long-standing control laws, such as proportional, integral and derivative (PID) controllers on silicon neuromorphic chips. 28,29 Crucially, such approaches still fail in recapitulating the autonomous adaptation that characterizes neural processing. As a result, while neuromorphic sensing and motion control in organic neuromorphic architectures were demonstrated, 7,30 a neuromorphic control-loop controlled system is still missing.…”

CBMC: A Biomimetic Approach for Control of a 7-Degree of Freedom Robotic Arm

“…In [ 10 , 11 ], a 4-DoF robotic arm is controlled by a single-layer SNN network that is trained with spiking timing-dependent plasticity (STDP). Recently, DeWolf et al [ 12 ] combined SNN and a neuromorphic chip to present a neurorobotic controller.…”