Low-latency neuromorphic air hockey player

Brains process sensory information to guide behaviour, enabling organisms to adapt to dynamic and unpredictable conditions. Neuromorphic engineering seeks to emulate these neurobiological principles to develop compact, low-power systems capable of real-time sensory-motor integration. This approach a...

Full description

Saved in:
Bibliographic Details
Main Authors: Juan P Romero B, Dimitrios Korakovounis, Jens E Pedersen, Jorg Conradt
Format: Article
Language:English
Published: IOP Publishing 2025-01-01
Series:Neuromorphic Computing and Engineering
Subjects:
Online Access:https://doi.org/10.1088/2634-4386/addc15
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850239637438595072
author Juan P Romero B
Dimitrios Korakovounis
Jens E Pedersen
Jorg Conradt
author_facet Juan P Romero B
Dimitrios Korakovounis
Jens E Pedersen
Jorg Conradt
author_sort Juan P Romero B
collection DOAJ
description Brains process sensory information to guide behaviour, enabling organisms to adapt to dynamic and unpredictable conditions. Neuromorphic engineering seeks to emulate these neurobiological principles to develop compact, low-power systems capable of real-time sensory-motor integration. This approach addresses some limitations of traditional AI and holds promise for autonomous systems that can interact robustly with the real world. However, most of today’s widely used neuromorphic benchmarks focus primarily on improving accuracy metrics using pre-recorded datasets, often overlooking critical factors such as latency and power consumption. This underscores the need for benchmarks to evaluate real-time performance under noisy, dynamic conditions. To address this need, we developed a system that uses spiking neural networks (SNNs) to control a robotic manipulator in an air-hockey game. In this setup, the automated opponent uses SNNs to process data from an event-based camera, enabling it to track the puck’s movements and respond to the actions of a human player. Our study demonstrates the potential of SNNs to accomplish fast real-time tasks while running on massively parallel hardware. We believe our air-hockey platform provides a versatile testbed for evaluating neuromorphic systems and invites further exploration of advanced algorithms, such as those incorporating trajectory prediction or adaptive learning, which could significantly enhance real-time decision-making and control.
format Article
id doaj-art-ef30e8f4e42743a39a63afb74a850236
institution OA Journals
issn 2634-4386
language English
publishDate 2025-01-01
publisher IOP Publishing
record_format Article
series Neuromorphic Computing and Engineering
spelling doaj-art-ef30e8f4e42743a39a63afb74a8502362025-08-20T02:01:05ZengIOP PublishingNeuromorphic Computing and Engineering2634-43862025-01-015202401410.1088/2634-4386/addc15Low-latency neuromorphic air hockey playerJuan P Romero B0https://orcid.org/0009-0004-1644-2740Dimitrios Korakovounis1https://orcid.org/0009-0006-2490-3206Jens E Pedersen2https://orcid.org/0000-0001-6012-7415Jorg Conradt3https://orcid.org/0000-0001-5998-9640NCS Lab. Royal Institute of Technology , Stockholm, SwedenNCS Lab. Royal Institute of Technology , Stockholm, SwedenNCS Lab. Royal Institute of Technology , Stockholm, SwedenNCS Lab. Royal Institute of Technology , Stockholm, SwedenBrains process sensory information to guide behaviour, enabling organisms to adapt to dynamic and unpredictable conditions. Neuromorphic engineering seeks to emulate these neurobiological principles to develop compact, low-power systems capable of real-time sensory-motor integration. This approach addresses some limitations of traditional AI and holds promise for autonomous systems that can interact robustly with the real world. However, most of today’s widely used neuromorphic benchmarks focus primarily on improving accuracy metrics using pre-recorded datasets, often overlooking critical factors such as latency and power consumption. This underscores the need for benchmarks to evaluate real-time performance under noisy, dynamic conditions. To address this need, we developed a system that uses spiking neural networks (SNNs) to control a robotic manipulator in an air-hockey game. In this setup, the automated opponent uses SNNs to process data from an event-based camera, enabling it to track the puck’s movements and respond to the actions of a human player. Our study demonstrates the potential of SNNs to accomplish fast real-time tasks while running on massively parallel hardware. We believe our air-hockey platform provides a versatile testbed for evaluating neuromorphic systems and invites further exploration of advanced algorithms, such as those incorporating trajectory prediction or adaptive learning, which could significantly enhance real-time decision-making and control.https://doi.org/10.1088/2634-4386/addc15event-based visionSpiNNakerLow latencyreal-time
spellingShingle Juan P Romero B
Dimitrios Korakovounis
Jens E Pedersen
Jorg Conradt
Low-latency neuromorphic air hockey player
Neuromorphic Computing and Engineering
event-based vision
SpiNNaker
Low latency
real-time
title Low-latency neuromorphic air hockey player
title_full Low-latency neuromorphic air hockey player
title_fullStr Low-latency neuromorphic air hockey player
title_full_unstemmed Low-latency neuromorphic air hockey player
title_short Low-latency neuromorphic air hockey player
title_sort low latency neuromorphic air hockey player
topic event-based vision
SpiNNaker
Low latency
real-time
url https://doi.org/10.1088/2634-4386/addc15
work_keys_str_mv AT juanpromerob lowlatencyneuromorphicairhockeyplayer
AT dimitrioskorakovounis lowlatencyneuromorphicairhockeyplayer
AT jensepedersen lowlatencyneuromorphicairhockeyplayer
AT jorgconradt lowlatencyneuromorphicairhockeyplayer