Adaptive Traffic Simulation Model for Unexpected Scenarios
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional traffic simulation models are not sufficiently predictive or adaptive to accommodate unexpected scenarios, requiring the creation of new models for each new behavior, which is computationally arduous and time-consuming.
Innovation Solution
A computer-implemented method for predicting the evolution of traffic simulations that accepts traffic data, executes a traffic simulation, and allows for the modeling and simulation of interventions to adapt to abnormal or forecasted scenarios, enabling predictive and adaptive simulations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional traffic simulation models are used, then the simulation structure is simple and fixed, but the simulation is not sufficiently predictive or adaptive to accommodate unexpected scenarios
Solution Approach 1:
The patent implements dynamic adaptation by allowing the simulation model to automatically adjust its parameters and structure in response to unexpected scenarios. The system uses machine learning techniques to dynamically modify simulation behavior without requiring complete model recreation, enabling adaptability while maintaining reasonable complexity levels.
Solution Approach 2:
The system changes simulation parameters dynamically based on detected scenarios. When unexpected events are identified, the model adjusts relevant parameters and behaviors to accommodate new conditions, rather than requiring a completely new model structure.
2Adaptability or versatility
If new simulation models are created to simulate new behaviors, then the simulation can accommodate new scenarios, but it is computationally arduous and time-consuming
Solution Approach 1:
The system performs preliminary preparation by maintaining a library of pre-configured simulation models for various scenario types. When a new scenario is detected, the system selects and adapts from existing pre-prepared models rather than creating from scratch, significantly reducing preparation time.
Solution Approach 2:
The patent uses copying by replicating and adapting existing simulation models to new scenarios. Instead of creating entirely new models, the system copies relevant components from existing models and modifies them to fit new behavioral requirements, reducing computational effort.
3Adaptability or versatility
If deep learning simulation modelling is used, then the simulation becomes adaptive, but it is reliant on well-constructed training datasets which are laborious to prepare and computationally expensive
Solution Approach 1:
The patent implements a universal simulation framework that can handle multiple scenario types with a single adaptable model structure. This multi-functional approach reduces the need for separate specialized training datasets for each scenario type, as the system can adapt one model to serve multiple purposes.
Solution Approach 2:
The system performs self-service by automatically generating or selecting training data from existing simulation runs and real-world data sources. The adaptive model self-trains on relevant data without requiring extensive manual dataset construction, reducing preparation time and labor.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A computer-implemented method for predicting evolution of a traffic simulation, the method comprising: accepting input of traffic data comprising data obtained from sensors in a geographic region; executing a traffic simulation using the traffic data for the geographic region; responsive to a decision to model the effects of a modification to the traffic simulation, selecting an intervention from a plurality of potential interventions; modifying parameters of the traffic simulation using the intervention to obtain modified simulation parameters; and executing a modified traffic simulation using the modified simulation parameters, the modified traffic simulation being configured to reflect the effect of the intervention on traffic.