From Vision to Decision: Neuromorphic Control for Autonomous Navigation and Tracking

TL;DR

This paper introduces a neuromorphic control framework for autonomous vision-guided navigation that efficiently resolves indecision and integrates seamlessly with visual processing, demonstrated through simulations and quadrotor experiments.

Contribution

A novel neuromorphic control system that directly transforms visual inputs into motion commands and resolves indecision via a dynamic bifurcation mechanism, enabling real-time autonomous navigation.

Findings

Effective in simulation environments

Validated on a quadrotor platform

Minimal computational and parameter requirements

Abstract

Robotic navigation has historically struggled to reconcile reactive, sensor-based control with the decisive capabilities of model-based planners. This duality becomes critical when the absence of a predominant option among goals leads to indecision, challenging reactive systems to break symmetries without computationally-intense planners. We propose a parsimonious neuromorphic control framework that bridges this gap for vision-guided navigation and tracking. Image pixels from an onboard camera are encoded as inputs to dynamic neuronal populations that directly transform visual target excitation into egocentric motion commands. A dynamic bifurcation mechanism resolves indecision by delaying commitment until a critical point induced by the environmental geometry. Inspired by recently proposed mechanistic models of animal cognition and opinion dynamics, the neuromorphic controller provides real-time autonomy with a minimal computational burden, a small number of interpretable parameters, and can be seamlessly integrated with application-specific image processing pipelines. We validate our approach in simulation environments as well as on an experimental quadrotor platform.