A Privacy-Preserving and Edge-Collaborating Architecture for Personalized Mobility

Driven by technologies and demands, the modern transportation system has developed from intelligent systems (ITS) to autonomous (ATS) resolve intertwined demands supplies with few human interventions. In ATS, personal mobility service (PMS) is that can sense real-time traffic conditions comprehensively, learn travelers’ preferences accurately, recommend multimodal travel options appropriately, provide responses timely elevate level of personalization intelligence in smart services. Since current PMS widely employs centralized approaches (CPMS) process massive sensitive data individuals support diverse edge devices, resulting high pressure privacy protection performance balancing, this paper presents a federated (FPMS) its design architecture logical physical views adopting learning multimodal, dynamic, personalized system-saving safety efficiency guaranteed. Moreover, through an extensive evaluation, performances CPMS FPMS are compared reveal merits reducing costs latency.