AV Fleet Charging Scheduling via Predictive Maintenance Windows
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The periodic downtime for maintenance of autonomous vehicles (AVs) complicates meeting ride demand and matching available vehicles to riders, especially during high demand periods, leading to potential inefficiencies and increased resource costs.
Innovation Solution
A service facility with multiple service regions for concurrent maintenance tasks and a mobile charging platform that allows AVs to recharge and perform other services in the field, minimizing downtime and optimizing resource utilization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If AVs are taken offline for routine servicing at regular intervals, then maintenance reliability is improved, but productivity and availability for servicing ride requestors deteriorate
Solution Approach 1:
The system performs preliminary scheduling of maintenance tasks by predicting future maintenance needs and scheduling them during periods of low ride demand. The transportation management system analyzes historical data, ride patterns, and maintenance requirements to proactively plan maintenance windows that minimize impact on service availability, rather than reacting to maintenance needs when they arise.
Solution Approach 2:
The maintenance scheduling system dynamically adjusts maintenance timing and duration based on real-time conditions including current ride demand, vehicle location, battery charge levels, and predicted future demand. The system can reschedule maintenance tasks, extend or compress maintenance windows, and adapt the fleet composition for maintenance based on changing operational conditions to optimize the balance between reliability and productivity.
2Reliability
If more AVs are purchased to compensate for downtime, then service level is improved, but resource costs and fleet size requirements worsen
Solution Approach 1:
The system implements continuous feedback loops where the transportation management system monitors actual maintenance durations, vehicle utilization patterns, and service level performance. This feedback informs dynamic adjustments to maintenance scheduling strategies, allowing the system to learn from past performance and optimize fleet size requirements over time by refining when and how vehicles are taken offline for maintenance.
Solution Approach 2:
The system changes operational parameters such as maintenance timing, duration, and vehicle routing to minimize the impact on service levels. By adjusting these parameters dynamically based on demand patterns and vehicle states, the system can maintain high service levels with a smaller fleet size compared to static maintenance schedules that require larger buffers for downtime.
3Reliability
If maintenance frequency is increased to ensure vehicle availability, then reliability is improved, but loss of time and operational efficiency worsen
Solution Approach 1:
The system performs preliminary scheduling of maintenance tasks by predicting future maintenance needs and scheduling them during periods of low ride demand. The transportation management system analyzes historical data, ride patterns, and maintenance requirements to proactively plan maintenance windows that minimize impact on service availability, rather than reacting to maintenance needs when they arise.
Solution Approach 2:
The system minimizes interruptions to useful action by scheduling maintenance during natural low-demand periods and optimizing vehicle routing to reduce travel time to maintenance facilities. The system also enables parallel maintenance activities where multiple vehicles are serviced simultaneously at distributed locations, maintaining continuous operational flow while ensuring regular maintenance is performed.
Data Source
AI summary
In one embodiment, a system includes one or more processors and one or more computer-readable non-transitory storage media coupled to one or more of the processors. The one or more computer-readable non-transitory storage media include instructions operable when executed by one or more of the processors to cause the system to perform operations including receiving service-facility data associated with a service facility that includes one or more service regions for servicing autonomous vehicles. Each of the one or more service regions is configured to charge an autonomous vehicle. The service facility data includes location information indicating a location of each of the one or more service regions; and availability information indicating an availability of each of the one or more service regions. The operations also include receiving vehicle data associated with a number of autonomous vehicles. The vehicle data includes a charge level of a respective autonomous vehicle.