Traffic Simulation Using Vehicle Dynamics Model
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current traffic flow simulation methods, such as those using intelligent driver models and deep learning, lack authenticity in simulating vehicle motion, especially during lane changes and turns, due to insufficient physical constraints, and require significant resources for training and sample acquisition.
Innovation Solution
A method and apparatus that acquire road network structure and vehicle information, using a vehicle dynamics model to determine a reference speed for a target vehicle, which updates vehicle information based on safe distance, brake reaction distance, and lane change conditions, constrained by the road network structure.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If intelligent driver model or deep learning method is used for traffic flow simulation, then the simulation can be performed, but the authenticity of vehicle motion simulation is insufficient especially during lane changes and turns
Solution Approach 1:
The patent replaces complex intelligent driver models and deep learning methods with a simplified vehicle dynamics model based on fundamental physics principles (Newton's laws, friction, centrifugal force). This substitution maintains simulation authenticity for lane changes and turns while significantly reducing model complexity and computational requirements.
Solution Approach 2:
The patent changes the approach from using complex behavioral parameters in intelligent driver models to using fundamental physical parameters (mass, friction coefficient, centrifugal force, braking distance) in the vehicle dynamics model. This parameter transformation improves authenticity while simplifying the simulation framework.
2Productivity
If intelligent driver model or deep learning method is used for traffic flow simulation, then the simulation can be performed, but significant resources are required for training and sample acquisition
Solution Approach 1:
The patent replaces resource-intensive deep learning and intelligent driver models with a computationally efficient vehicle dynamics model based on fundamental physics. This substitution dramatically reduces computational resources and training requirements while maintaining simulation accuracy for vehicle motion.
Solution Approach 2:
The patent uses simple, computationally inexpensive physics-based calculations instead of expensive deep learning models that require extensive training data and computational power. The vehicle dynamics model provides adequate accuracy at a fraction of the computational cost.
3Reliability
If traditional traffic simulation methods are used, then the simulation can be performed quickly, but the physical constraints during lane changes and turns are not properly modeled
Solution Approach 1:
The patent transforms the simulation approach from complex behavioral models to physics-based parameter calculations. By using fundamental physical parameters (friction, centrifugal force, braking distance) the model achieves accurate physical constraint modeling while maintaining computational efficiency.
Solution Approach 2:
The patent applies detailed physics-based modeling specifically to critical motion scenarios (lane changes and turns) where physical constraints are most important, while using simpler models for other aspects of traffic simulation. This localized application of complex physics ensures authenticity where needed without overall computational overhead.
Data Source
AI summary
Embodiments of the present disclosure relate to a method and apparatus for updating information. The method may include: acquiring road network structure information of a target road network and vehicle information of a target number of vehicles in the target road network, the vehicle information including initial state information, perception information and positioning information, and the vehicle information being constrained by the road network structure information; selecting a target vehicle from the target number of vehicles; determining, based on a vehicle dynamics model, a reference speed at which the target vehicle passes a preset time step; and updating vehicle information of a vehicle in the target road network based on the reference speed of the target vehicle.