Radar Misalignment Monitoring Using 3D Velocity Self-Check
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for detecting radar sensor misalignment in autonomous vehicles require multiple sensor modalities, dedicated infrastructure, and significant computation, which is not always feasible due to limited resources and availability of high-definition maps.
Innovation Solution
A method using only radar sensor data to estimate 3D radar velocity and compare it to the vehicle's longitudinal axis to detect misalignment, reducing computational load and reliance on additional sensors or infrastructure.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple sensor modalities and dedicated infrastructure are used for radar misalignment detection, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent extracts the misalignment detection function from a complex multi-sensor system and implements it using only radar sensor data. By taking out the essential detection capability and removing dependencies on additional sensors and infrastructure, the system achieves misalignment detection while reducing device complexity.
Solution Approach 2:
The radar sensor performs self-diagnosis by using its own data to detect misalignment. The system compares the radar velocity vector with the vehicle longitudinal axis to identify misalignment, allowing the sensor to monitor its own alignment status without external assistance or additional sensor modalities.
2Measurement precision
If multiple sensor modalities and high-definition maps are used for misalignment detection, then measurement precision is improved, but use of energy increases
Solution Approach 1:
The patent extracts the core detection function from energy-intensive multi-sensor processing and implements it using only radar data. By removing the need for sensor fusion, high-definition map processing, and complex data alignment, the system significantly reduces computing resource consumption while maintaining detection accuracy.
Solution Approach 2:
Instead of processing all available sensor data and high-definition maps, the system performs partial processing using only the necessary radar velocity data and vehicle orientation information. This selective approach reduces energy consumption while achieving the required detection precision.
3Measurement precision
If multiple sensor modalities are integrated for radar misalignment detection, then measurement precision is improved, but ease of operation deteriorates
Solution Approach 1:
The patent extracts the detection function from complex multi-sensor integration and implements it using only radar sensor data. This eliminates the need for coordinating multiple sensors, synchronizing data streams, and managing complex calibration procedures, thereby improving ease of operation.
Solution Approach 2:
The system uses the radar sensor's own data to perform self-diagnosis and misalignment detection. This self-service approach eliminates the need for external calibration equipment, dedicated infrastructure, and complex operational procedures, making the system easier to implement and operate.
Data Source
AI summary
A system for monitoring radar misalignment on an autonomous vehicle is provided. The system includes a radar sensor configured to capture sensor data. The radar sensor is disposed on an autonomous vehicle traveling along a trajectory. The system also includes an autonomy computing system comprising a processor and a memory storing computer executable instructions. The processor, upon executing the computer executable instructions, configured to: generate a radar coordinate system from the sensor data, identify a static object from the sensor data, compute a vehicle coordinate system based on the static object. The system further includes computing a misalignment between the radar coordinate system and the vehicle coordinate system based on a comparison of an orientation of the radar coordinate system and an orientation of the vehicle coordinate system, and generate a sensor data transformation to align the sensor data to the vehicle coordinate system.