Energy-Efficient Autonomous Aerial Navigation with Dynamic Vision Sensors: A Physics-Guided Neuromorphic Approach

TL;DR

This paper introduces a neuromorphic, energy-efficient drone navigation system using event cameras and physics-guided neural networks to detect moving objects and plan optimal, low-energy paths in real-time.

Contribution

It combines event-based vision processing with physics-guided neural networks for autonomous drone navigation, emphasizing energy efficiency and robustness.

Findings

Successful detection of moving objects with shallow SNN architecture

Effective energy-aware path planning using physics-guided neural networks

Implementation validated in Gazebo simulation environment

Abstract

Vision-based object tracking is a critical component for achieving autonomous aerial navigation, particularly for obstacle avoidance. Neuromorphic Dynamic Vision Sensors (DVS) or event cameras, inspired by biological vision, offer a promising alternative to conventional frame-based cameras. These cameras can detect changes in intensity asynchronously, even in challenging lighting conditions, with a high dynamic range and resistance to motion blur. Spiking neural networks (SNNs) are increasingly used to process these event-based signals efficiently and asynchronously. Meanwhile, physics-based artificial intelligence (AI) provides a means to incorporate system-level knowledge into neural networks via physical modeling. This enhances robustness, energy efficiency, and provides symbolic explainability. In this work, we present a neuromorphic navigation framework for autonomous drone navigation. The focus is on detecting and navigating through moving gates while avoiding collisions. We use event cameras for detecting moving objects through a shallow SNN architecture in an unsupervised manner. This is combined with a lightweight energy-aware physics-guided neural network (PgNN) trained with depth inputs to predict optimal flight times, generating near-minimum energy paths. The system is implemented in the Gazebo simulator and integrates a sensor-fused vision-to-planning neuro-symbolic framework built with the Robot Operating System (ROS) middleware. This work highlights the future potential of integrating event-based vision with physics-guided planning for energy-efficient autonomous navigation, particularly for low-latency decision-making.