Vehicle Object Tracking During Impact Using Dual Motion Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle tracking systems fail to reliably determine object trajectories during and after a collision due to excessive acceleration exceeding standard motion model limits, leading to poor or incomplete tracking post-accident.
Innovation Solution
The method involves using a first movement model for normal conditions and switching to a second movement model during a collision, which allows higher acceleration values, enabling continuous object tracking by utilizing detection data from both phases for improved plausibility checks and post-collision analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a standard motion model is used for tracking during normal vehicle operation, then tracking accuracy is maintained under normal conditions, but tracking fails during collision when accelerations exceed model limits
Solution Approach 1:
The system dynamically switches between a first motion model for normal operation and a second motion model for collision conditions. The processing unit detects collision events and activates the second motion model temporarily during the collision phase, allowing the tracking system to adapt its parameters (maximum acceleration, speed, yaw rate) to match the extreme conditions of impact while maintaining reliability throughout the event.
2Reliability
If the driver assistance system is deactivated immediately during collision, then system safety is protected, but object tracking is lost and cannot be re-established quickly
Solution Approach 1:
The collision event is segmented into distinct phases (first phase before collision, second phase during collision, third phase after collision). The system maintains different motion models for each phase, allowing continuous tracking throughout the collision event rather than deactivating. This segmentation enables the system to preserve tracking functionality while adapting to the extreme conditions of each phase.
3Measurement precision
If plausibility checks require data collection over several seconds or minutes, then trajectory validation is thorough, but tracking cannot be maintained during the brief collision event
Solution Approach 1:
The system changes the parameters of the motion model during the collision phase, specifically allowing significantly higher acceleration values, speed limits, and yaw rates in the second motion model compared to the first. This parameter adjustment enables the plausibility check to validate trajectories during the brief collision event rather than requiring extended data collection periods, matching the validation timescale to the collision duration.
Data Source
Figure 1
Figure 2a~2d
Figure 3
AI summary
The invention relates to a method comprising steps of detecting an object in an environment of a motor vehicle, tracking the object in relation to the motor vehicle by means of a first motion model of the motor vehicle in a first phase, detecting an impact of the motor vehicle with an obstacle, and tracking the object in relation to the motor vehicle by means of a second motion model of the motor vehicle in a second phase.