Edge Intelligence for Object Detection in Blockchain-Based Internet of Vehicles: Convergence of Symbolic and Connectionist AI

Abstract

Reliable detection of objects is a crucial requirement to improve the safety of the visual Internet of Vehicles (V-IoVs). The resemblance of objects to each other or the background makes the detection of objects difficult. The traditional connectionist artificial intelligence (All-based object detection model is a potential approach to increase detection performance, but it has poor interpretability and high computational complexity. Edge intelligence has demonstrated a considerably good balance between efficiency and computation complexity, integrating multi-access edge computing and AI. In this article, an edge AI framework is designed to perform the object detection task, and a novel abductive learning algorithm is proposed to realize the interpretability and robustness of AI in the V-IoV system. Based on the you only look once (YOLO) classifier, the abductive model is used to learn from the data, which combines symbolic and connectionist AI. Moreover, blockchain is developed for model sharing. Compared to the state of the art, simulation results show the high accuracy of the proposed algorithm. Moreover, the proposed approach has interpretability and strong robustness.