Digital Retina for IoV Towards 6G: Architecture, Opportunities, and Challenges

TL;DR

The paper addresses the limitations of single-vehicle perception in dynamic IoV environments by proposing Vehicular Digital Retina (VDR), a cloud-edge-end architecture with multi-stream learning. It introduces three data/knowledge/model streams (data, knowledge, model) and leverages V2X communications to enable end-edge-cloud collaboration for collaborative perception and learning. A detailed framework is provided, including secure collaboration mechanisms (role authentication, encryption, content security) and a case study demonstrating noticeable perception gains from knowledge sharing at the edge. The work highlights the potential of VDR to enhance safe, scalable intelligent driving and outlines future directions such as VoK evaluation, DRL-based optimization, and blockchain-assisted security for 6G IoV applications.

Abstract

Vehicles are no longer isolated entities in traffic environments, thanks to the development of IoV powered by 5G networks and their evolution into 6G. However, it is not enough for vehicles in a highly dynamic and complex traffic environment to make reliable and efficient decisions. As a result, this paper proposes a cloud-edge-end computing system with multi-streams for IoV, referred to as Vehicular Digital Retina (VDR). Local computing and edge computing are effectively integrated in the VDR system through the aid of vehicle-to-everything (V2X) networks, resulting in a heterogeneous computing environment that improves vehicles' perception and decision-making abilities with collaborative strategies. Once the system framework is presented, various important functions in the VDR system are explained in detail, including V2X-aided collaborative perception, V2X-aided stream sharing for collaborative learning, and V2X-aided secured collaboration. All of them enable the development of efficient mechanisms of data sharing and information interaction with high security for collaborative intelligent driving. We also present a case study with simulation results to demonstrate the effectiveness of the proposed VDR system.

Figures (4)

• Figure 1: Illustration of the VDR System.
• Figure 2: Illustration of stream sharing for collaborative learning in VDR.
• Figure 3: Illustration of Secure Collaboration for VDR.
• Figure 4: Illustration of a VDR-based collaborative perception scheme.