Intelligent machines work in unstructured environments by differential neuromorphic computing

Author:

Occhipinti Luigi1ORCID,Wang Shengbo2,Gao Shuo2,Tang Chenyu3,Occhipinti Edoardo4,Li Cong2,Wang Shurui2,Wang Jiaqi2,Zhao Hubin5,Hu Guohua6ORCID,Nathan Arokia7,Dahiya Ravinder8ORCID

Affiliation:

1. University of Cambridge

2. School of Instrumentation and Optoelectronic Engineering, Beihang University

3. University of Cambridge, Department of Engineering

4. Imperial College London, Department of Computing

5. University College London, HUB of Intelligent Neuro-engineering (HUBIN), CREATe, Division of Surgery and Interventional Science

6. The Chinese University of Hong Kong

7. University of Cambridge, Darwin College

8. Northeastern University

Abstract

Abstract Efficient operation of intelligent machines in the real world requires methods that allow them to understand and predict the uncertainties presented by the unstructured environments with good accuracy, scalability and generalization, similar to humans. Current methods rely on pretrained networks instead of continuously learning from the dynamic signal properties of working environments and suffer inherent limitations, such as data-hungry procedures, and limited generalization capabilities. Herein, we present a memristor-based differential neuromorphic computing, perceptual signal processing and learning method for intelligent machines. The main features of environmental information such as amplification (> 720%) and adaptation (< 50%) of mechanical stimuli encoded in memristors, are extracted to obtain human-like processing in unstructured environments. The developed method takes advantage of the intrinsic multi-state property of memristors and exhibits good scalability and generalization, as confirmed by validation in two different application scenarios: object grasping and autonomous driving. In the former, a robot hand experimentally realizes safe and stable grasping through fast learning (in ~ 1 ms) the unknown object features (e.g., sharp corner and smooth surface) with a single memristor. In the latter, the decision-making information of 10 unstructured environments in autonomous driving (e.g., overtaking cars, pedestrians) is accurately (94%) extracted with a 40×25 memristor array. By mimicking the intrinsic nature of human low-level perception mechanisms, the electronic memristive neuromorphic circuit-based method, presented here shows the potential for adapting to diverse sensing technologies and helping intelligent machines generate smart high-level decisions in the real world.

Publisher

Research Square Platform LLC

Reference57 articles.

1. Toward next-generation learned robot manipulation;Cui J;Sci Robot,2021

2. Neuro-Inspired electronic skin for robots;Liu F;Sci Robot,2022

3. Davies M, Wild A, Orchard G, Sandamirskaya Y, Guerra GAF, Joshi P, Plank P, Risbud SR (2021) Advancing neuromorphic computing with loihi: a survey of results and outlook. Proc. IEEE 109, 911–934

4. The mechanosensory neurons of touch and their mechanisms of activation;Handler A;Nat Rev Neurosci,2021

5. The structural basis of odorant recognition in insect olfactory receptors;Mármol J;Nature,2021

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3