AI Route Stacking for Proximal Fleet Route Reassignment

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current fleet logistics systems are inefficient and wasteful, leading to increased costs, emissions, and time inefficiencies due to underutilized vehicles and redundant routes, particularly in school bus operations.

Innovation Solution

A system utilizing an artificial intelligence engine to reassign routes from one vehicle to another within a fleet, optimizing vehicle utilization by identifying proximally available route groups based on location and time, and providing a graphical representation with color-coded indicators for efficient route reassignment.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If routes are assigned to multiple vehicles in a fleet, then service coverage is improved, but vehicle utilization efficiency deteriorates due to redundant routes and underutilized vehicles

Engineering Contradiction:
Improveservice coverageVSAvoidvehicle utilization efficiency
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The system merges routes from multiple vehicles by identifying proximal routes that can be consolidated. The AI engine analyzes spatial and temporal proximity of routes across different vehicles and combines them into unified route groups, allowing a single vehicle to service multiple previously separate routes, thereby eliminating redundancy and improving utilization efficiency while maintaining service coverage

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The system dynamically reassigns routes between vehicles based on real-time proximity analysis. The AI engine continuously evaluates route proximity metrics and adjusts route assignments adaptively, allowing routes to be moved between vehicles as conditions change, optimizing utilization without compromising service reliability

Inventive Principle:
Principle #15Dynamics

2Productivity

If more vehicles are deployed to handle all routes, then service capacity is improved, but operational costs increase due to increased maintenance and fuel consumption

Engineering Contradiction:
Improveservice capacityVSAvoidfuel consumption and maintenance costs
Core Design Contradiction:
ProductivityVSLoss of energy

Solution Approach 1:

The system consolidates service capacity by merging multiple vehicle routes into route groups that can be serviced by fewer vehicles. The AI engine identifies proximal routes that can be combined, reducing the total number of vehicles needed while maintaining service capacity through optimized route consolidation

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The system changes the parameter of route assignment from one-to-one to many-to-one relationships. By modifying how routes are distributed across vehicles (using proximity-based grouping), the system reduces the number of active vehicles required while maintaining service capacity, thereby reducing fuel consumption and maintenance costs

Inventive Principle:
Principle #35Parameter changes

3Device complexity

If traditional routing systems are used without AI optimization, then system complexity is low, but route optimization efficiency deteriorates leading to wasted time and resources

Engineering Contradiction:
Improvesystem complexityVSAvoidtime inefficiency in route management
Core Design Contradiction:
Device complexityVSLoss of time

Solution Approach 1:

The system implements self-service optimization where the AI engine automatically analyzes route proximity, identifies consolidation opportunities, and reassigns routes without requiring manual intervention. The system serves itself by autonomously optimizing fleet operations, reducing time inefficiency while the complexity is managed through automated algorithms rather than manual processes

Inventive Principle:
Principle #25Self-service

Data Source

PatentUS20250315756A1Route stacking in a fleet routing system
Publication Date: 2025.10.09 ZUM SERVICES INC
  • US20250315756A1 patent drawing
  • US20250315756A1 patent drawing
  • US20250315756A1 patent drawing

AI summary

A system and method include a device associated with a user. The device may identify to a server computer a route to be reassigned from a first vehicle to a second vehicle among a fleet of vehicles. The server device may include an artificial intelligence engine which compares the route to be reassigned to a plurality of route groups associated with one of the administrator and the ride requestor. The server device may further identify one or more route groups which are able to service the route to be reassigned based on the artificial intelligence engine. The server device may transmit a graphical representation of one or more of the plurality of route groups which is proximally available in terms of location and time, as determined by the artificial intelligence engine to service the route to be reassigned with a color coded indicator. The server device reassigns the route.