Autonomous Vehicle Fleet Servicing Around Predicted Ride Demand
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Managing the maintenance and service needs of autonomous vehicles in a fleet is challenging due to fluctuating demand, as they lack human oversight, complicating the balance between vehicle maintenance and service availability to meet ride requests efficiently.
Innovation Solution
A transportation management system generates demand predictions based on historical data, current conditions, and future events to schedule autonomous vehicle maintenance during periods of low demand, optimizing service readiness during peak demand using machine learning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If autonomous vehicles are scheduled for maintenance frequently to ensure reliability, then vehicle reliability improves, but service availability deteriorates due to vehicles being unavailable during maintenance
Solution Approach 1:
The system performs preliminary scheduling of maintenance activities by predicting future demand patterns and proactively scheduling maintenance during anticipated low-demand periods. This allows maintenance to be completed before vehicles are needed during peak demand, ensuring both reliability and service availability.
Solution Approach 2:
The maintenance schedule is made dynamic by continuously adjusting it based on real-time demand fluctuations and predictive analytics. The system can reschedule maintenance activities respond to changing demand patterns, optimizing the balance between vehicle reliability and service availability throughout the fleet operation cycle.
2Productivity
If demand prediction accuracy is improved using machine learning, then service availability improves, but system complexity increases
Solution Approach 1:
The machine learning system operates autonomously to generate demand predictions and schedule maintenance activities without requiring complex manual intervention. The system self-adjusts and learns from historical data automatically, reducing the operational complexity despite the advanced algorithms employed.
Solution Approach 2:
Traditional manual scheduling methods are replaced with automated machine learning-based predictive analytics. This substitution of mechanical/manual processes with intelligent algorithms improves prediction accuracy and service availability while the automation actually reduces operational complexity by eliminating manual coordination requirements.
3Productivity
If maintenance is performed during high-demand periods to ensure vehicle readiness, then service availability improves, but loss of time increases due to vehicles being taken offline when most needed
Solution Approach 1:
The system schedules maintenance activities in advance during predicted low-demand periods, ensuring vehicles are serviced before peak demand occurs. This preliminary scheduling prevents vehicle unavailability during high-demand periods, eliminating the trade-off between service availability and loss of time.
Solution Approach 2:
The system continuously monitors actual demand patterns and compares them with predictions, using this feedback to refine future maintenance scheduling. This feedback loop ensures that maintenance is consistently scheduled during appropriate low-demand periods, optimizing both service availability and minimizing vehicle unavailability time.
Data Source
AI summary
In particular embodiments, a computing system may determine a predicted amount of ride requests for a plurality of collectively-managed vehicles and determine an availability of the collectively-managed vehicles to satisfy the predicted amount of ride requests. Subsequent to determining that the availability fails to satisfy one or more predetermined criteria for servicing the predicted amount of ride requests, the system may determine status information associated with the collectively-managed vehicles and determine, based on at least the status information, one or more minimum services for servicing one or more vehicles among the plurality of collectively-managed vehicles at one or more service centers such that the availability satisfies the one or more predetermined criteria. The system may instruct the one or more vehicles that are to receive the one or more minimum services to travel to the one or more service centers to be serviced.