AI Event Detection for MaaS Vehicle and Occupant Trip Assignment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current fleet management systems for mobility providers in Mobility-as-a-Service (MaaS) platforms do not adequately consider passenger preferences, safety concerns, privacy, and regulatory compliance when assigning trips, leading to inefficient, insecure, and unprofitable operations.
Innovation Solution
A system and method that utilize a trained artificial intelligence model to analyze on-board diagnostic (OBD) data and occupant data from sensors like imaging, audio, and LIDAR sensors to determine events related to vehicles and occupants, generating driver and passenger profiles, and storing them on a distributed ledger for secure, customized trip assignments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If traditional fleet management systems assign trips based only on current location and source location, then assignment speed is improved, but passenger satisfaction and safety are worsened
Solution Approach 1:
The system performs preliminary actions by collecting and analyzing passenger preferences, safety concerns, privacy requirements, and regulatory compliance factors before trip assignment. This allows the system to pre-evaluate multiple vehicles and their suitability for each passenger, so that when assignment is needed, the decision can be made quickly with comprehensive information already processed.
Solution Approach 2:
The patent introduces an intermediary system that acts as a mediator between the simple location-based matching and the complex passenger requirements. This intermediary layer processes multiple factors including passenger preferences, safety concerns, privacy requirements, and regulatory compliance, then provides refined assignment recommendations that balance speed with comprehensive passenger needs.
2Reliability
If comprehensive factors like passenger preferences, safety, privacy, and compliance are considered in trip assignment, then passenger satisfaction and safety are improved, but system complexity increases
Solution Approach 1:
The system segments the complex assignment problem into distinct modules: one module handles passenger preferences, another handles safety concerns, a third handles privacy requirements, and a fourth handles regulatory compliance. Each module processes its specific factor independently and provides output to the overall assignment system, making the complexity manageable and maintainable while still considering all factors comprehensively.
3Measurement precision
If real-time data from multiple sensors is collected and analyzed, then event determination accuracy is improved, but data processing time and computational resources increase
Solution Approach 1:
The system extracts and focuses only on the most relevant parameters from the comprehensive sensor data for each specific event type. Rather than processing all possible sensor inputs uniformly, the system identifies and extracts only the critical parameters needed for determining each event, reducing computational overhead while maintaining high accuracy for each specific detection task.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A mobility player system including memory and a processor is provided. The memory stores a trained AI model. The processor receives on-board diagnostic (OBD) data associated with a first vehicle registered with a first mobility provider. The processor receives occupant data, different from the OBD data, from plurality of sensors associated with the first vehicle. The processor determines a plurality of parameters based on the received OBD data and the received occupant data. The processor applies the trained Al model on the plurality of parameters. The processor determines one or more events related to the first vehicle, or related to an occupant of the first vehicle, based on the application of the trained AI model on the plurality of parameters. The processor transmits information about the determined one or more events to one or more nodes of a distributed ledger associated with a Mobility-as-a-Service (MaaS) network.