Vehicle Sensor Prioritization for Forward Object Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current automotive perception sensor processing systems face high computational demands due to noisy and uncertain sensor data, particularly with RADAR and LIDAR systems, and existing methods prioritize object detections based solely on proximity, which is inefficient for advanced driver assistance and autonomous driving applications.
Innovation Solution
A method and processing unit that assign priority values to sensor detections based on a pre-selected prioritization scheme, weighting objects ahead of the vehicle more heavily, optimizing processing resources for ADAS and autonomous driving systems by using an asymmetric prioritization scheme that considers driving conditions and vehicle parameters.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If object detections are prioritized based on proximity to the vehicle, then processing resources are focused on nearby objects, but objects ahead of the vehicle that are further away receive insufficient processing attention
Solution Approach 1:
The patent applies asymmetry by implementing a directional prioritization scheme where objects ahead of the vehicle (positive y-axis region) are assigned higher priority weights compared to objects in other directions. This asymmetric weighting ensures that ADAS-relevant objects receive preferential processing attention while maintaining overall system productivity through efficient resource allocation.
2Reliability
If all sensor detections are processed equally, then comprehensive object tracking is achieved, but computational demands become excessively high for embedded systems
Solution Approach 1:
The patent applies local quality by assigning different priority weights to different spatial regions in the coordinate system. Objects in the ADAS-relevant region (ahead of the vehicle) receive higher priority weights, while objects in other regions receive lower weights. This localized differentiation allows the system to process detections with varying levels of detail according to their operational importance, reducing overall computational complexity while maintaining reliability for critical functions.
3Measurement precision
If sensor sensitivity is increased to detect more objects, then detection coverage is improved, but the number of detections to process increases significantly
Solution Approach 1:
The patent applies partial action by implementing a prioritization scheme that processes detections in order of their assigned priority weights. Rather than processing all detections equally, the system focuses computational resources on high-priority detections (those ahead of the vehicle) while reducing or skipping lower-priority detections. This allows the system to maintain high detection sensitivity while managing processing throughput by performing partial processing on the detection set.
Data Source
AI summary
Disclosed is a method for processing perception sensor data in an ego vehicle. The method includes receiving sensor data associated with locations of detections in a coordinate system having a y-axis and an x-axis. The method includes assigning a priority value to the detections based on their location in the coordinate system. The method includes generating output data based on the detections and the assigned priority values. The assigned priority values are assigned based on the location of the detections in the coordinate system according to a pre-selected prioritization scheme.