Autonomous Vehicle Trip Pre-Assignment to Cut Empty Miles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current autonomous vehicle dispatching systems lack efficient trip planning and vehicle assignment methods, leading to increased 'empty miles' and reduced ridership, as they rely on user-initiated requests rather than proactive trip suggestions.
Innovation Solution
A method for advanced trip planning that uses server computing devices to determine potential pickup and destination locations, assign vehicles, and provide trip information to users, including estimated times of arrival and costs, while considering historical user scores and current demand to pre-assign vehicles and reduce 'empty miles'.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the system waits for user-initiated requests to assign vehicles, then the system complexity remains low, but empty miles increase and ridership decreases
Solution Approach 1:
The system performs preliminary trip planning and vehicle assignment before users actually request rides. The server determines potential pickup locations, destination locations, and assigns vehicles in advance based on predicted demand, thereby reducing empty miles and improving ridership without requiring complex real-time decision-making systems
2Ease of operation
If the system provides detailed trip information and options to users, then user satisfaction increases, but the time required for trip planning and confirmation increases
Solution Approach 1:
The system pre-determines multiple potential trips with associated trip information including estimated costs and times before users need to make decisions. This allows users to review pre-calculated options and make quick selections without experiencing long wait times for trip planning and confirmation
Solution Approach 2:
The system provides a limited set of pre-determined trip options (e.g., top 3 potential trips) rather than all possible trips. This gives users sufficient information to make informed decisions while keeping the presentation time short and manageable
3Loss of energy
If the system pre-assigns vehicles to potential trips, then empty miles are reduced, but the risk of assigning vehicles to unwanted trips increases
Solution Approach 1:
The system assigns vehicles to potential trips in advance but maintains the ability to reassign or cancel assignments based on user feedback. Users can confirm or cancel trips within a grace period, ensuring that pre-assignments do not result in forced unwanted trips while still capturing the efficiency benefits of early vehicle positioning
Solution Approach 2:
The system incorporates user feedback loops where users can confirm or cancel pre-assigned trips. This feedback mechanism allows the system to adjust assignments based on actual user preferences, maintaining reliability while preserving the efficiency gains from pre-assignment
4Productivity
If the system calculates multiple potential trips with rankings and scores, then trip optimization improves, but the computational complexity increases
Solution Approach 1:
The system calculates rankings and scores for potential trips but only presents a limited number of top-ranked options to users (e.g., top 3 trips). This partial presentation approach maintains computational optimization benefits while avoiding the complexity of processing and displaying all possible trip combinations
Solution Approach 2:
The system uses historical trip data and user behavior patterns to automatically generate trip recommendations and rankings without requiring manual intervention. The model self-optimizes by learning from past trip data, reducing the need for complex real-time computational algorithms
Data Source
AI summary
Aspects of the disclosure provide for advanced trip planning for an autonomous vehicle service. For instance, an example method may include determining a potential pickup location for a user, determining a set of potential destination locations for a user, and determining a set of potential trips. For each potential trip a vehicle of a fleet of autonomous vehicles of the service may be assigned and trip information, including an estimated time of arrival for the assigned vehicle of the potential trip to reach the destination location of the potential trip, may be determined. The trip information for each potential trip may be provided for display to the user. Thereafter, confirmation information identifying one of the set of potential trips may be received, and the assigned vehicle for one first of the set of potential trips may be dispatched to pick up the user.