Autonomous Passenger Route Scoring for Preference-Based Trip Planning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing autonomous passenger vehicle (APV) systems lack the ability to account for diverse customer preferences, leading to suboptimal trip planning and reduced customer satisfaction.
Innovation Solution
A system that includes a device configured to receive customer preferences, determine route scores based on these preferences, and select a planned route accordingly, while also considering historical data and real-time conditions to optimize the trip.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a single standardized route is used for all customers, then route planning is simple and fast, but customer satisfaction decreases due to inability to accommodate individual preferences
Solution Approach 1:
The system changes parameters by assigning preference scores to different route characteristics (scenic views, travel time, cost, comfort) and dynamically adjusts route selection based on these scored parameters. This allows customized routing without requiring completely different planning systems for each customer type.
Solution Approach 2:
The route planning process is segmented into separate evaluation criteria (scenic value, time efficiency, cost effectiveness, comfort level), each scored independently. This segmentation allows the complex customization task to be broken down into manageable scoring components that can be processed systematically.
2Adaptability or versatility
If multiple potential routes are evaluated based on customer preferences, then customer satisfaction improves, but route determination time increases
Solution Approach 1:
The system performs preliminary actions by pre-calculating and storing preference scores for various route characteristics before actual trip planning. Historical data about customer preferences and route qualities is analyzed in advance to establish scoring frameworks, enabling faster real-time route selection without重新calculating everything from scratch.
Solution Approach 2:
The system uses feedback loops where historical data from past trips and customer preferences is continuously analyzed to refine and update preference scores. This feedback mechanism allows the system to learn from previous experiences and improve future route selections, making the evaluation process more efficient over time.
3Reliability
If route selection considers multiple factors such as scenic views, travel time, and cost, then trip quality improves, but computational complexity increases
Solution Approach 1:
The system transforms complex qualitative factors (scenic beauty, comfort, cost) into quantitative preference scores through parameter changes. By converting these diverse factors into comparable numerical values, the system can reliably evaluate and compare routes using consistent scoring criteria without getting bogged down in the complexity of evaluating each factor separately.
Data Source
AI summary
A first device includes one or more processors configured to receive, from a second device associated with a customer, a service request for a trip from a first location to a second location via an autonomous vehicle. The one or more processors are configured to access preferences for the trip, where one or more of the preferences include one or more preference scores. The one or more processors are configured to determine a route score associated with each of one or more potential routes for the trip based at least in part on the one or more preference scores. The one or more processors are configured to select a planned route from the one or more potential routes based on the route scores. The one or more processors are also configured to provide information associated with the planned route to the second device.