Obstacle Avoidance and Target Acquisition for Robot Navigation Using a Mixed Signal Analog/Digital Neuromorphic Processing System

TLDR

Neuromorphic hardware emulates biological neural networks, providing low‑power, parallel, event‑driven computing, but device variability remains a key challenge. The study builds an autonomous neuromorphic agent that performs obstacle avoidance and target acquisition by interfacing the mixed‑signal ROLLS processor with a dynamic vision sensor on a robotic vehicle. A neural‑network architecture that compensates for device variability was developed and validated across diverse environments, and a Dynamic Neural Field for target acquisition was implemented in spiking neuromorphic hardware. The integrated system successfully demonstrated obstacle avoidance and target acquisition, showing that the network and DVS enable biologically inspired obstacle‑avoidance dynamics and functional navigation.

Abstract

Neuromorphic hardware emulates dynamics of biological neural networks in electronic circuits offering an alternative to the von Neumann computing architecture that is low-power, inherently parallel, and event-driven. This hardware allows to implement neural-network based robotic controllers in an energy-efficient way with low latency, but requires solving the problem of device variability, characteristic for analog electronic circuits. In this work, we interfaced a mixed-signal analog-digital neuromorphic processor ROLLS to a neuromorphic dynamic vision sensor (DVS) mounted on a robotic vehicle and developed an autonomous neuromorphic agent that is able to perform neurally inspired obstacle-avoidance and target acquisition. We developed a neural network architecture that can cope with device variability and verified its robustness in different environmental situations, e.g., moving obstacles, moving target, clutter, and poor light conditions. We demonstrate how this network, combined with the properties of the DVS, allows the robot to avoid obstacles using a simple biologically-inspired dynamics. We also show how a Dynamic Neural Field for target acquisition can be implemented in spiking neuromorphic hardware. This work demonstrates an implementation of working obstacle avoidance and target acquisition using mixed signal analog/digital neuromorphic hardware.