Object Sensing Fusion System Sensor Health Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Object sensing fusion systems in vehicles face accuracy issues due to faulty or obscured sensors, which can lead to diminished state of health and potential collisions, as existing systems lack effective methods to assess and identify faulty sensors in real-time.
Innovation Solution
A method and system that analyze target data from vision and radar systems using a context queue to compute matching scores within individual frames and across a sequence of frames, allowing for the assessment of the state of health of the object sensing fusion system and identification of faulty sensors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If object sensing fusion systems use multiple sensors (vision and radar) to improve detection accuracy, then the system's ability to detect objects improves, but the complexity of assessing sensor health and detecting faulty sensors increases
Solution Approach 1:
The system implements a feedback mechanism by continuously computing matching scores between vision and radar targets and using these scores to assess sensor health. The state of health estimation is fed back to identify potentially faulty sensors, creating a closed-loop system that automatically monitors and evaluates sensor performance without adding manual complexity
Solution Approach 2:
The sensing fusion system performs self-diagnosis by comparing target data from multiple sensors and automatically identifying potentially faulty sensors through matching score computations. The system serves its own health assessment needs by using its existing target data and processing capabilities to evaluate sensor performance, eliminating the need for separate external monitoring systems
2Measurement precision
If the system computes matching scores across multiple frames to improve sensor health assessment accuracy, then the reliability of fault detection improves, but the processing time and computational load increase
Solution Approach 1:
The system computes matching scores across multiple frames but only to the extent necessary for reliable fault detection. By using a sequence of frames rather than excessive computation, the system achieves sufficient measurement precision for identifying faulty sensors while avoiding unnecessary processing time and computational waste
3Reliability
If the system continuously monitors sensor health by analyzing target data from multiple sensors, then the ability to identify faulty sensors improves, but the computational resources required increase
Solution Approach 1:
The system uses its existing target data and processing infrastructure to perform sensor health monitoring, turning existing computational resources toward the dual purpose of object detection and sensor fault identification. This self-service approach enables reliable fault detection without requiring additional dedicated computational energy or separate monitoring hardware
Data Source
AI summary
A method and system for estimating the state of health of an object sensing fusion system. Target data from a vision system and a radar system, which are used by an object sensing fusion system, are also stored in a context queue. The context queue maintains the vision and radar target data for a sequence of many frames covering a sliding window of time. The target data from the context queue are used to compute matching scores, which are indicative of how well vision targets correlate with radar targets, and vice versa. The matching scores are computed within individual frames of vision and radar data, and across a sequence of multiple frames. The matching scores are used to assess the state of health of the object sensing fusion system. If the fusion system state of health is below a certain threshold, one or more faulty sensors are identified.