Autonomous Driving using Spiking Neural Networks on Dynamic Vision Sensor Data: A Case Study of Traffic Light Change Detection

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chen, Xuelei, Spanogianopoulos, Sotirios
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912227179626496
author Chen, Xuelei
Spanogianopoulos, Sotirios
author_facet Chen, Xuelei
Spanogianopoulos, Sotirios
contents Autonomous driving is a challenging task that has gained broad attention from both academia and industry. Current solutions using convolutional neural networks require large amounts of computational resources, leading to high power consumption. Spiking neural networks (SNNs) provide an alternative computational model to process information and make decisions. This biologically plausible model has the advantage of low latency and energy efficiency. Recent work using SNNs for autonomous driving mostly focused on simple tasks like lane keeping in simplified simulation environments. This paper studies SNNs on photo-realistic driving scenes in the CARLA simulator, which is an important step toward using SNNs on real vehicles. The efficacy and generalizability of the method will be investigated.
format Preprint
id arxiv_https___arxiv_org_abs_2311_09225
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Autonomous Driving using Spiking Neural Networks on Dynamic Vision Sensor Data: A Case Study of Traffic Light Change Detection
Chen, Xuelei
Spanogianopoulos, Sotirios
Computer Vision and Pattern Recognition
Neural and Evolutionary Computing
Robotics
Image and Video Processing
Autonomous driving is a challenging task that has gained broad attention from both academia and industry. Current solutions using convolutional neural networks require large amounts of computational resources, leading to high power consumption. Spiking neural networks (SNNs) provide an alternative computational model to process information and make decisions. This biologically plausible model has the advantage of low latency and energy efficiency. Recent work using SNNs for autonomous driving mostly focused on simple tasks like lane keeping in simplified simulation environments. This paper studies SNNs on photo-realistic driving scenes in the CARLA simulator, which is an important step toward using SNNs on real vehicles. The efficacy and generalizability of the method will be investigated.
title Autonomous Driving using Spiking Neural Networks on Dynamic Vision Sensor Data: A Case Study of Traffic Light Change Detection
topic Computer Vision and Pattern Recognition
Neural and Evolutionary Computing
Robotics
Image and Video Processing
url https://arxiv.org/abs/2311.09225