NFT-Based Intelligence Networking for Connected and Autonomous Vehicles: A Quantum Reinforcement Learning Approach
Yuzheng Ren, Renchao Xie, F. Richard Yu, Tao Huang, Yunjie Liu
Abstract
Recently, the Internet of vehicles (IoV) and connected and autonomous vehicles (CAVs) have become research hotspots. The accuracy and efficiency of artificial intelligence (AI) models are crucial for CAVs to make decisions automatically. Intelligence networking enables each CAV to train appropriate models locally with the help of other CAVs' intelligence and make up for the lack of experience and computing power of a single-vehicle. However, intelligence is distributed across diverse geo-locations in the intelligence networking paradigm, which calls for accurate, efficient, and lightweight intelligence discovery mechanisms. In this article, we propose a non-fungible token (NFT)-based distributed intelligence networking scheme (NDIN) for CAVs. We use NFT to tokenize intelligence and efficiently describe intelligence from multiple aspects through meta-data, facilitating applications to better understand and search for intelligence in complex and trust-lacking IoV. We present the architecture, modules, and core mechanism of NDIN. Then, we formulate the essential problem as a discrete Markov decision process (MDP) and adopt the quantum-inspired reinforcement learning (QRL) algorithm to find the optimal policy. Also, the convergence rate and performance compared with existing schemes are evaluated. Finally, we discuss several related challenges and opportunities.