News8Plus-Realtime Updates On Breaking News & Headlines

Realtime Updates On Breaking News & Headlines

Neuromorphic chip dramatically reduces power requirements for rolling robot


Credit: Science Robotics (2022). DOI: 10.1126/scirobotics.abk2948

A crew of researchers at Tsinghua University’s Heart for Mind-Impressed Computing Research in Beijing, China, has developed a neuromorphic chip that may scale back the facility consumption of a cat-and-mouse-type rolling robotic by roughly half, in comparison with a traditional NVIDIA chip designed for AI purposes. Of their paper revealed within the journal Science Robotics, the group describes design ideas they used to construct the chip and the way effectively it labored when examined.

As AI purposes mature, they turn into extra advanced and require extra energy to run, which generally is a drawback for autonomous robots working within the subject. Most of those methods are based mostly on the usage of neural networks. On this new effort, the researchers believed that constructing a chip with comparable skills however based mostly on neuromorphic computing expertise would use far much less energy. They constructed a neuromorphic chip referred to as TianjicX and put it in a small rolling robot referred to as Tianjicat.

Credit: Science Robotics (2022). DOI: 10.1126/scirobotics.abk2948

The chip was imbued with spatiotemporal elasticity that allowed for adaptive allocation of its assets and likewise the scheduling of a number of duties (the robotic had to have the ability to preserve observe of the mouse and chase it, whereas on the similar time processing and responding to details about obstacles). It additionally had a high-level module that bridged the hole between the necessities given and the bodily structure of the robotic.

Tianjicat was then programmed to comply with a goal and keep away from operating into obstacles utilizing information from onboard sensors. The goal on this case was a rolling, remote-controlled toy with a cartoon mouse affixed to its high. The researchers referred to it as a cat-and-mouse problem.

The researchers discovered the mechanical cat fairly able to chasing the mouse whereas avoiding obstacles. It additionally was in a position to catch the mouse. Tianjicat used simply over 50% much less energy than an equivalent NVIDIA chip-based robotic. They usually additionally discovered that their neuromorphic chip-based robotic had markedly decreased latency—79 occasions lower than the NVIDIA based mostly system, permitting the robotic to make choices a lot quicker.


A neuromorphic computing architecture that can run some deep neural networks more efficiently


Extra data:
Songchen Ma et al, Neuromorphic computing chip with spatiotemporal elasticity for multi-intelligent-tasking robots, Science Robotics (2022). DOI: 10.1126/scirobotics.abk2948

© 2022 Science X Community

Quotation:
Neuromorphic chip dramatically reduces energy necessities for rolling robotic (2022, June 16)
retrieved 16 June 2022
from https://techxplore.com/information/2022-06-neuromorphic-chip-power-requirements-robot.html

This doc is topic to copyright. Aside from 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 data functions solely.



Click Here To Join Our Telegram Channel



Source link

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

Raise A Concern