Artificial Intelligence & Machine Learning Open Access (CC-BY 4.0) Featured Paper Identifier: IEEE-RH-2026-0003

Neuromorphic Event-Driven Spike Routing for Low-Latency Visual Odometry

(1) Dr. Elena Rostova — MIT CSAIL

Date of Publication: June 10, 2026

Digital Object Identifier (DOI): 10.1109/IRH.2026.1001431

Volume & Issue: Vol. 14, Issue 2 (pp. 88-101)

Conference & Proceedings: IEEE Direct Journal Submission

Abstract

Conventional frame-based sensors exhibit high motion blur and prohibitive energy consumption in high-velocity drone flight. Here, we present a spiking neural network (SNN) topology integrated with neuromorphic silicon event cameras. By executing temporal spike contrast backpropagation on an asynchronous crossbar array, our model tracks 6-DOF trajectory poses at 10,000 frames-per-second equivalent temporal resolution with only 14mW power consumption.

Index Terms / Keywords

Neuromorphic Vision Spiking Neural Networks Visual Odometry Asynchronous Circuits Low-Power Robotics

Full-Text Manuscript Access

Published under Creative Commons Attribution 4.0 International (CC BY 4.0)

412 Downloads

Download Official PDF (Open Access)

Citation Information

IEEE Standard Format:

Dr. Elena Rostova, "Neuromorphic Event-Driven Spike Routing for Low-Latency Visual Odometry," International Conference Summit (ICS), vol. 14, no. 2, pp. 88-101, Jun 2026, doi: 10.1109/IRH.2026.1001431.

View BibTeX Record ↓

@article{rostova2026IEEERH20260003,
  title={Neuromorphic Event-Driven Spike Routing for Low-Latency Visual Odometry},
  author={Dr. Elena Rostova},
  journal={International Conference Summit (ICS) Open Transactions},
  volume={14},
  number={2},
  pages={88-101},
  year={2026},
  doi={10.1109/IRH.2026.1001431},
  publisher={International Conference Summit (ICS)}
}