Mantis: Enabling Energy-Efficient Autonomous Mobile Agents with Spiking Neural Networks

Rachmad Vidya Wicaksana Putra, Muhammad Shafique

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Autonomous mobile agents such as unmanned aerial vehicles (UAVs) and mobile robots have shown huge potential for improving human productivity. These mobile agents require low power/energy consumption to have a long lifespan since they are usually powered by batteries. These agents also need to adapt to changing/dynamic environments, especially when deployed in far or dangerous locations, thus requiring efficient online learning capabilities. These requirements can be fulfilled by employing Spiking Neural Networks (SNNs) since SNNs offer low power/energy consumption due to sparse computations and efficient online learning due to bio-inspired learning mechanisms. However, a methodology is still required to employ appropriate SNN models on autonomous mobile agents. Towards this, we propose a Mantis methodology to systematically employ SNNs on autonomous mobile agents to enable energy-efficient processing and adaptive capabilities in dynamic environments. The key ideas of our Mantis include the optimization of SNN operations, the employment of a bio-plausible online learning mechanism, and the SNN model selection. The experimental results demonstrate that our methodology maintains high accuracy with a significantly smaller memory footprint and energy consumption (i.e., 3.32x memory reduction and 2.9x energy saving for an SNN model with 8-bit weights) compared to the baseline network with 32-bit weights. In this manner, our Mantis enables the employment of SNNs for resource- and energy-constrained mobile agents.

Original languageEnglish (US)
Title of host publication2023 9th International Conference on Automation, Robotics and Applications, ICARA 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages197-201
Number of pages5
ISBN (Electronic)9781665489218
DOIs
StatePublished - 2023
Event9th International Conference on Automation, Robotics and Applications, ICARA 2023 - Abu Dhabi, United Arab Emirates
Duration: Feb 10 2023Feb 12 2023

Publication series

Name2023 9th International Conference on Automation, Robotics and Applications, ICARA 2023

Conference

Conference9th International Conference on Automation, Robotics and Applications, ICARA 2023
Country/TerritoryUnited Arab Emirates
CityAbu Dhabi
Period2/10/232/12/23

Keywords

  • Autonomous mobile agents
  • energy efficiency
  • online learning
  • robots
  • spiking neural networks
  • UAVs

ASJC Scopus subject areas

  • Computer Science Applications
  • Mechanical Engineering
  • Control and Optimization
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Mantis: Enabling Energy-Efficient Autonomous Mobile Agents with Spiking Neural Networks'. Together they form a unique fingerprint.

Cite this