DriCon: On-device Just-in-Time Context Characterization for Unexpected Driving Events

TL;DR

DriCon is an on-device system that characterizes unexpected driving events in real-time by analyzing spatial and behavioral data, providing interpretable explanations and improving understanding of driving behavior.

Contribution

The paper introduces DriCon, a novel on-device system that performs just-in-time context characterization of driving events using live data and large datasets, with improved interpretability.

Findings

Achieves 80% similarity in driving behavior characterization

Uses live data to generate human-interpretable explanations

Operates effectively on a dashboard-mounted edge device

Abstract

Driving is a complex task carried out under the influence of diverse spatial objects and their temporal interactions. Therefore, a sudden fluctuation in driving behavior can be due to either a lack of driving skill or the effect of various on-road spatial factors such as pedestrian movements, peer vehicles' actions, etc. Therefore, understanding the context behind a degraded driving behavior just-in-time is necessary to ensure on-road safety. In this paper, we develop a system called \ourmethod{} that exploits the information acquired from a dashboard-mounted edge-device to understand the context in terms of micro-events from a diverse set of on-road spatial factors and in-vehicle driving maneuvers taken. \ourmethod{} uses the live in-house testbed and the largest publicly available driving dataset to generate human interpretable explanations against the unexpected driving events. Also, it provides a better insight with an improved similarity of $80$\% over $50$ hours of driving data than the existing driving behavior characterization techniques.