Who wants to be a self-driving car?

Abstract

Self-driving cars and autonomous transportation systems are projected to create radical societal changes, yet public understanding and trust of self-driving cars and autonomous systems is limited. The authors present a new mixed-reality experience designed to provide its users with insights into the ways that self-driving cars operate. A single-person vehicle equipped with sensors provides its users with data driven visual feedback in a virtual reality headset to navigate in physical space. The authors explore how immersive experiences might provide ‘conceptual affordances’ that lower the entry barrier for diverse audiences to discuss complex topics.

FedMon: A Federated Learning Monitoring Toolkit

“…In a similar fashion, Meng et al [41] introduced VADAF, an FL service providing users with monitoring insights at a client level for the model loss, accuracy, and data heterogeneity, so that anomaly detection can be performed to finding abnormal client behavior. Taejoon et al [42] introduced CARLA-FLMon, a monitoring and graphical plotting tool for FL that can be used to visually assess the results of an FL experiment run and users can also extract information about client utilization to detect performance degradation. However, as the name denotes, this tool is limited to the application of FL on the CARLA autonomous car driving simulator.…”