Vehicle Trajectory Prediction Using Multi-Sensor Model Fitting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for predicting a vehicle's trajectory are inadequate in accurately determining future positions, accelerations, velocities, and yaw rates, especially when limited by the absence of historical data, and fail to effectively integrate data from multiple surrounding vehicles.
Innovation Solution
A method utilizing sensors from a first vehicle to capture data on multiple vehicles, including positions, accelerations, velocities, and yaw rates, and applying a vehicle model like CYRA to predict trajectories by determining parameters through least squares or quadratic programming, which improves curve fitting with data from multiple sources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If data from multiple sensors and multiple vehicles is integrated using a vehicle model, then trajectory prediction accuracy is improved, but device complexity and computational requirements increase
Solution Approach 1:
The system segments the trajectory prediction task by processing data from different sensors (first sensor and second sensor) independently to determine separate lists of points, then combines these segmented results through parameter fitting to achieve accurate predictions without overwhelming system complexity
Solution Approach 2:
The vehicle model serves as a universal framework that processes data from multiple sources (first sensor data, second sensor data, historical data) and applies the same mathematical model (CYRA model with parameters a, b, c, d) to predict trajectories of multiple vehicles simultaneously
2Measurement precision
If historical data is used to improve curve fitting, then prediction accuracy is enhanced, but reliability decreases when historical data is unavailable
Solution Approach 1:
The system is designed to be self-sufficient by using real-time sensor data from the first sensor and second sensor to independently determine trajectory parameters without relying on external historical data, ensuring reliable operation in all conditions while optionally improving accuracy when historical data is available
3Duration of action of moving object
If prediction is made for longer time periods, then future position accuracy is reduced, but the useful prediction range is extended
Solution Approach 1:
The system dynamically adjusts the prediction approach by using a physics-based vehicle model that accounts for changing vehicle states (position, acceleration, velocity, yaw rate) over time, allowing accurate predictions to be made for extended periods by continuously modeling the vehicle's dynamic behavior rather than using static extrapolation
Data Source
AI summary
A method for predicting a trajectory (108) of a vehicle (102) uses first data captured by a first sensor of a first vehicle (101) to determine a first position, a first acceleration, a first velocity and a first yaw rate of a second vehicle (102) and uses second data captured by a second sensor of the first vehicle (101) to determine a second position, a second acceleration, a second velocity and a second yaw rate of the second vehicle (102). The method uses these first and second sets of information with a vehicle model to determine first and second lists of points for predicting the trajectory. One or more parameters of a model for the prediction of the trajectory (108) are determined depending on the first and second lists of points, and the prediction of the trajectory (108) is determined depending on the model defined by these parameters.