Expanded Object Tracking With Center-Truncated Radar Measurements
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current automotive object tracking systems face challenges in accurately capturing real-world automotive radar measurements, which are complex due to multiple reflections from objects, leading to inaccurate kinematic and extended state estimation, especially when dealing with noise and complex spatial distributions.
Innovation Solution
The system employs a centre-truncated distribution and underlying untruncated Gaussian distribution pair to estimate both kinematic and extended states, using a probabilistic filter to remove noise and update truncation intervals, enabling accurate tracking of object dimensions and orientation while simplifying computation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If contour model is used to capture measurement distribution along object contour, then measurement precision is improved, but device complexity increases due to requiring much more degrees of freedom and complex data association
Solution Approach 1:
The patent transforms the complex contour model parameters into a simplified set of parameters representing the minimal enclosing rectangle (length, width, orientation, and position). This parameter transformation maintains the ability to capture measurement distribution while dramatically reducing model complexity and degrees of freedom required.
Solution Approach 2:
The patent extracts only the essential geometric features (bounding rectangle characteristics) from the full contour model, discarding unnecessary complexity while retaining the core functionality of describing object shape and orientation for radar measurement interpretation.
2Productivity
If surface model is used to assume radar measurements are generated from inner surface, then computational simplicity is improved, but measurement precision deteriorates because the model is away from real world automotive radar measurements
Solution Approach 1:
The patent changes the measurement model from an inner-surface assumption to an external bounding rectangle model that better reflects real-world radar measurements. By transforming the parameters to represent the minimal enclosing rectangle rather than internal surface geometry, the model achieves both computational efficiency and accuracy in capturing actual radar measurement distributions.
3Reliability
If fixed set of points on rigid body is used for extended object tracking, then object tracking capability is improved, but ease of operation deteriorates due to non-scalable data association requirements
Solution Approach 1:
The patent creates a universal data association framework based on the minimal enclosing rectangle that can handle any number of objects and measurement configurations. This approach replaces the fixed-point-to-fixed-point association with a flexible rectangle-to-measurement association, making the system scalable and adaptable to different tracking scenarios without requiring complex one-to-one mapping rules.
Data Source
Figure 1A
Figure 1B
Figure 1C
AI summary
A system and a method for tracking an expanded state of an object including a kinematic state indicative of a position of the object and an extended state indicative of one or combination of a dimension and an orientation of the object is provided herein. The system comprises at least one sensor configured to probe a scene including a moving object with one or multiple signal transmissions to produce one or multiple measurements of the object per the transmission, and a processor configured to execute a probabilistic filter tracking a joint probability of the expanded state of the object estimated by a motion model of the object and a measurement model of the object, wherein the measurement model includes a center-truncated distribution having truncation intervals. The system further comprises an output interface configured to output the expanded state of the object.