Intelligent machines work in unstructured environments by differential neuromorphic computing

TL;DR

This paper introduces a memristor-based differential neuromorphic computing method that enables intelligent machines to better understand and adapt to unstructured environments, demonstrating rapid learning and high accuracy in tasks like object grasping and autonomous driving.

Contribution

The paper presents a novel memristor-based neuromorphic approach that mimics human perception, offering scalable, adaptive, and real-time processing for unstructured environments.

Findings

Fast learning (~1 ms) of object features with a single memristor

94% accuracy in decision-making for autonomous driving scenarios

Effective amplification and adaptation of mechanical stimuli in memristors

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.