NightSight: Passive Computation for Navigation in Dark Using Events

2026-05-25

AI Summary

This work addresses the challenge of autonomous navigation for small aerial robots in complete darkness under stringent constraints on payload, power consumption, and computational resources. The authors propose a lightweight perception system that integrates a monocular event camera, a coded aperture lens, and an infrared speckle projector. By leveraging depth-dependent blur patterns generated when structured light passes through the coded aperture, a convolutional neural network is trained solely on synthetic data featuring planar walls to estimate dense depth. Remarkably, the model demonstrates zero-shot generalization to complex real-world environments. Implemented on a Jetson Orin Nano embedded platform, the system achieves real-time performance at 20 Hz, with an L1 depth estimation error of 7.0 cm (2.80% relative error) within a 2.5-meter range, confirming its effectiveness and practicality under resource-limited conditions.

Abstract

Small aerial robots are particularly well-suited for search and rescue in confined and hazardous environments due to their agility, low cost, and ability to traverse through cluttered spaces that are inaccessible to larger platforms. However, enabling autonomous navigation in complete darkness remains a significant challenge, because small aerial robots cannot easily accommodate perception systems that demand substantial payload, power, or computation. In this work, we present a lightweight perception approach that combines a monocular event camera, a coded aperture lens, and an infrared dot projector to enable navigation in such conditions. The projected pattern, when imaged through the coded aperture, produces depth dependent blur signatures that implicitly encode scene geometry. We train a convolutional neural network to decode these signatures into dense depth maps using only synthetic data generated from a simple planar wall setup. Despite this minimal training regime, the model generalizes zero-shot to complex real-world scenes. Our system operates in real time at 20 Hz on a NVIDIA Jetson Orin Nano, demonstrating suitability for resource-constrained platforms. We further analyze the impact of different coded aperture designs on depth estimation performance. Our approach gives high accuracy (l1 error 7.0cm) upto 2.5m range (2.80% error). These results highlight the potential of combining structured illumination, coded optics, and event-based sensing for enabling robust perception and navigation in complete darkness.

Problem

• autonomous navigation
• darkness
• small aerial robots
• perception
• resource-constrained

Innovation

• event-based vision
• coded aperture
• structured illumination
• zero-shot depth estimation
• autonomous navigation in darkness