Monday, November 28, 2022
HomeScienceBio-inspired localization system slashes power consumption

Bio-inspired localization system slashes power consumption


Credit: Krasula, Shutterstock

Impressed by barn owls, researchers have developed an revolutionary localization system that mixes state-of-the-art sensors with a neuromorphic computational map primarily based on resistive random-access reminiscence (RRAM).

As we enter the period of pervasive computing, increasingly of our on a regular basis objects are being embedded with microprocessors to assist our lives run easily. To attain this, these techniques must function repeatedly and waste minimal vitality, all whereas extracting helpful and compact info from noisy and sometimes incomplete knowledge captured from a number of sensors in actual time. Due to their in-memory, event-driven computing capabilities, hybrid memristive complementary metal-oxide semiconductor (CMOS) neuromorphic architectures present a great {hardware} substrate for such duties.

Researchers supported partially by the MeM-Scales venture got down to show the complete potential of such a system. To this finish, they developed a bio-inspired, event-driven object localization system that {couples} superior piezoelectric micro-machined ultrasound transducer (PMUT) sensors with a neuromorphic computational map primarily based on RRAM. Their paper printed within the journal Nature Communications describes how the proposed neuromorphic strategy has made it attainable to scale back power consumption by 5 orders of magnitude in contrast with standard localization techniques primarily based on microcontrollers.

Impressed by nature

Inspiration for the system was drawn from the barn owl’s neuroanatomy. “Our proposed solution represents a first step in demonstrating the concept of a biologically inspired system to improve efficiency in computation,” notes research senior writer Dr. Elisa Vianello in a information merchandise posted on EE Times. “It paves the best way towards extra complex systems that carry out much more subtle duties to unravel actual–world issues by combining info extracted from totally different sensors.

“We envision that such an approach to conceive a bio–inspired system will be key to build the next generation of edge AI devices, in which information is processed locally and with minimal resources. In particular, we believe that small animals and insects are a great source of inspiration for an efficient combination of sensory information processing and computation. Thanks to the latest advancements in technology, we can couple innovative sensors with advanced RRAM–based computation to build ultra–low–power systems,” states Dr. Vianello, who’s a senior scientist at electronics and knowledge know-how laboratory CEA-Leti of MeM-Scales venture coordinator French Various Energies and Atomic Vitality Fee in France.

The analysis group performed measurements of the system consisting of RRAM-based coincidence detectors, delay-line circuits and a full-custom ultrasound sensor. They used the experimental outcomes to calibrate the system-level simulations. These simulations have been then used to estimate the item localization mannequin’s angular decision and energy efficiency. The outcomes confirmed a lot higher vitality effectivity than a microcontroller performing the identical process. “The goal is, as always, to get the best power efficiency for the level of performance needed by a specific application. Further improvements in energy efficiency are certainly possible with our system,” observes Dr. Vianello.

The research demonstrates that combining visible sensors akin to dynamic imaginative and prescient sensor cameras with a PMUT-based listening to sensor ought to be explored to develop future client robots. The MeM-Scales (Reminiscence applied sciences with multi-scale time constants for neuromorphic architectures) venture ends in June 2023.


A computing in-memory system based on stacked 3D resistive memories


Extra info:
Filippo Moro et al, Neuromorphic object localization utilizing resistive recollections and ultrasonic transducers, Nature Communications (2022). DOI: 10.1038/s41467-022-31157-y

Quotation:
Bio-inspired localization system slashes energy consumption (2022, September 27)
retrieved 27 September 2022
from https://techxplore.com/information/2022-09-bio-inspired-localization-slashes-power-consumption.html

This doc is topic to copyright. Other than any honest dealing for the aim of personal research or analysis, no
half could also be reproduced with out the written permission. The content material is supplied for info functions solely.



Click Here To Join Our Telegram Channel



Source link

If in case you have any considerations or complaints relating to this text, please tell us and the article can be eliminated quickly. 

Raise A Concern

RELATED ARTICLES
- Advertisment -

Most Popular