Autonomous Vehicle Fleet Parking Assignment Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The complexity of distributing a fleet of autonomous vehicles to parking locations efficiently, considering factors like available spaces, travel time, traffic congestion, and service needs, becomes challenging as the number of vehicles and locations increases, especially in emergency situations where vehicles need to be grounded or serviced.
Innovation Solution
A method and system using processors to identify vehicle locations, available spaces, and assign vehicles to parking locations based on multiple factors such as travel time, space availability, and service needs, determining a total cost for each assignment and selecting the most efficient route to minimize overall costs, while also considering traffic congestion and sending navigation instructions to vehicles.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a fleet of autonomous vehicles is distributed to multiple parking locations, then service coverage and responsiveness are improved, but the complexity of fleet management and assignment optimization increases
Solution Approach 1:
The fleet management system segments the fleet into multiple groups assigned to different parking locations, with each location having dedicated vehicles. This segmentation allows independent management of each location's fleet while maintaining overall system coordination, reducing the complexity of managing the entire fleet as a single unit.
Solution Approach 2:
The system performs preliminary assignment of vehicles to parking locations based on predicted demand patterns, historical data, and service requirements. By pre-positioning vehicles at optimal locations before demand arises, the system improves service coverage and responsiveness while simplifying real-time management decisions.
2Productivity
If vehicles are assigned to parking locations based on multiple factors (travel time, space availability, traffic congestion), then assignment efficiency is improved, but the computational complexity and processing time increase
Solution Approach 1:
The system applies different weighting factors to various assignment criteria based on local conditions at each parking location and time period. For example, during peak hours, travel time may be weighted more heavily, while during off-peak hours, space availability may be prioritized. This localized optimization improves assignment efficiency without requiring complex global optimization for all scenarios.
Solution Approach 2:
The system dynamically adjusts the parameters and weights of assignment factors based on real-time conditions, historical patterns, and service priorities. By changing parameters such as traffic congestion levels, space availability thresholds, and travel time constraints, the system optimizes assignment efficiency for varying operational contexts without increasing fundamental computational complexity.
3Loss of time
If the system optimizes vehicle distribution considering traffic congestion and route planning, then travel time and fuel efficiency are improved, but the real-time processing requirements and system complexity increase
Solution Approach 1:
The system pre-calculates and stores optimal routes between parking locations and service areas, considering historical traffic patterns and congestion data. By having route information prepared in advance, the system reduces real-time processing requirements while still providing optimized travel time and fuel efficiency when vehicles need to be dispatched.
Solution Approach 2:
The system creates simplified models or copies of the physical vehicle fleet and their locations for computational optimization purposes. These virtual representations allow the system to perform complex route optimization and congestion analysis without requiring real-time processing of actual vehicle data, reducing computational burden while maintaining optimization quality.
Data Source
AI summary
Aspects of the disclosure relate to assigning a fleet of driverless vehicles to a plurality of parking locations for parking vehicles of the fleet. For instance, locations of the vehicles of the fleet as well as a number of available spaces at each of the plurality of parking location locations may be tracked. A subset of the fleet not already located at one of the plurality of parking locations is identified. At least one assignment assigning each vehicle of the subset to a respective parking location of the plurality of parking locations is determined according to the numbers of available spaces and the identified locations of the subset. For the at least one assignment, a total cost is determined by determining a cost value for each of a plurality of factors. The given assignment is sent to the fleet based on the total cost and the cost value.