Ghost Trip Detection via Driver Login and Vehicle Motion Correlation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In fleet operations, drivers sometimes engage in unauthorized 'ghost trips' by deactivating their on-board recorder devices, allowing unauthorized use of vehicles for personal activities or third-party tasks, which are not tracked or monitored effectively.
Innovation Solution
A system and method that utilize movement detectors and electronic on-board recorders to detect unauthorized vehicle movements and assign a likelihood of responsibility to drivers by analyzing their logged-in and logged-out durations, using a processor and non-transient computer media to identify candidates for ghost trips.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If drivers deactivate or log out of on-board recorder devices to engage in unauthorized activities, then drivers gain freedom to use vehicles for personal or third-party purposes, but fleet management loses tracking and oversight capability
Solution Approach 1:
The system performs preliminary actions by continuously recording driver login/logout events and vehicle movement data before unauthorized activities occur. This pre-recorded data enables post-event analysis to identify ghost trips by matching periods when drivers were logged out with periods when vehicles were in motion, thereby recovering tracking information that would otherwise be lost.
Solution Approach 2:
The system establishes feedback loops by continuously monitoring and correlating driver status data with vehicle movement data. This feedback mechanism enables the system to detect discrepancies between driver login state and vehicle motion state, automatically identifying potential ghost trips and providing ongoing oversight despite driver deactivation attempts.
2Reliability
If the system monitors all vehicle movements and driver login/logout events continuously, then fleet management gains comprehensive oversight capability, but system complexity and data processing requirements increase
Solution Approach 1:
The system extracts and isolates only the critical data elements needed for ghost trip detection: driver login/logout events and vehicle movement status. By focusing on these specific extracted data points rather than processing all possible vehicle telemetry, the system achieves reliable oversight capability while minimizing system complexity and data processing requirements.
Solution Approach 2:
The monitoring system is segmented into distinct functional components: one component records driver login/logout events, another records vehicle movement data, and a third component analyzes the correlation between these data streams. This segmentation allows each component to operate independently with focused functionality, reducing overall system complexity while maintaining comprehensive oversight capability.
3Measurement precision
If the system analyzes driver durations and assigns likelihood scores to identify ghost trip candidates, then fleet management can identify unauthorized use, but processing time and computational resources increase
Solution Approach 1:
The system applies partial action by assigning likelihood scores only to drivers who meet specific criteria: those whose logged-out duration overlaps with vehicle movement periods. Rather than calculating scores for all drivers in the fleet, the system focuses computational resources on the subset of drivers who are potential candidates for ghost trips, thereby maintaining identification accuracy while reducing processing time and computational resource requirements.
Data Source
AI summary
Unauthorized use of fleet vehicles is detected by matching drivers' logged out times with vehicle movements for which there is no logged in driver. Allowance is made for vehicles that may be moved within permitted areas without a logged in driver. A likelihood value is assigned to each candidate driver whose logged out time corresponds to the duration of unauthorized movement of the vehicle. The likelihood value is increased if the candidate driver is the next driver to log into the vehicle after its unauthorized usage.