EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SNN4Agents: a framework for developing energy-efficient embodied spiking neural networks for autonomous agents

Rachmad Vidya Wicaksana Putra, Alberto Marchisio, Muhammad Shafique

Frontiers in Robotics and AI · 26.07.2024 · 11

DOI: 10.3389/frobt.2024.1401677 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Robotics and AI, online erschienen am 26.07.2024. Verfasst von Rachmad Vidya Wicaksana Putra und 2 weiteren Autor:innen. Beteiligte Einrichtung: eBrain Lab, Division of Engineering, New York University (NYU) Abu Dhabi, Abu Dhabi, United Arab Emirates. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent trends have shown that autonomous agents, such as Autonomous Ground Vehicles (AGVs), Unmanned Aerial Vehicles (UAVs), and mobile robots, effectively improve human productivity in solving diverse tasks. However, since these agents are typically powered by portable batteries, they require extremely low power/energy consumption to operate in a long lifespan. To solve this challenge, neuromorphic computing has emerged as a promising solution, where bio-inspired Spiking Neural Networks (SNNs) use spikes from event-based cameras or data conversion pre-processing to perform sparse computations efficiently. However, the studies of SNN deployments for autonomous agents are still at an early stage. Hence, the optimization stages for enabling efficient embodied SNN deployments for autonomous agents have not been defined systematically. Toward this, we propose a novel framework called SNN4Agents that consists of a set of optimization techniques for designing energy-efficient embodied SNNs targeting autonomous agent applications. Our SNN4Agents employs weight quantization, timestep reduction, and attention window reduction to jointly improve the energy efficiency, reduce the memory footprint, optimize the processing latency, while maintaining high accuracy. In the evaluation, we investigate use cases of event-based car recognition, and explore the trade-offs among accuracy, latency, memory, and energy consumption. The experimental results show that our proposed framework can maintain high accuracy (i.e., 84.12% accuracy) with 68.75% memory saving, 3.58x speed-up, and 4.03x energy efficiency improvement as compared to the state-of-the-art work for the NCARS dataset. In this manner, our SNN4Agents framework paves the way toward enabling energy-efficient embodied SNN deployments for autonomous agents.

Schlagwörter

Stichwörter der Autor:innen

automotive dataautonomous agentsenergy efficiencyneuromorphic computingneuromorphic processorspiking neural networks

Autor:innen und Institutionen

  • eBrain Lab, Division of Engineering, New York University (NYU) Abu Dhabi, Abu Dhabi, United Arab Emirates.

Zitieren

APA

Putra, R. V. W., Marchisio, A., & Shafique, M. (2024). SNN4Agents: a framework for developing energy-efficient embodied spiking neural networks for autonomous agents. Frontiers in Robotics and AI, 11. https://doi.org/10.3389/frobt.2024.1401677

Vancouver

Putra RVW, Marchisio A, Shafique M. SNN4Agents: a framework for developing energy-efficient embodied spiking neural networks for autonomous agents. Frontiers in Robotics and AI. 2024;11. doi:10.3389/frobt.2024.1401677

BibTeX
@article{Putra2024,
  author = {Putra, Rachmad Vidya Wicaksana and Marchisio, Alberto and Shafique, Muhammad},
  title = {SNN4Agents: a framework for developing energy-efficient embodied spiking neural networks for autonomous agents},
  journal = {Frontiers in Robotics and AI},
  year = {2024},
  volume = {11},
  doi = {10.3389/frobt.2024.1401677}
}
Kostenlos starten →