Multistage Sensor Fusion for Mixed-ASIL Environmental Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for fusing measurement data from on-board sensors to support driving assistance and emergency braking functions face challenges in managing different functional safety ratings, leading to increased development and validation efforts and resource requirements, particularly in achieving the necessary ASIL-B ratings for safety-critical applications.
Innovation Solution
A two-stage measurement data fusion method is implemented, where the first environmental model is created with a higher functional safety rating (e.g., ASIL-B) and the second with a lower rating (e.g., QM), allowing for separate processing and reducing power demand by reusing processed data from the first model in the second stage, enabling the generation of environmental models with different safety ratings.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If all sensor data are processed with the highest functional safety rating (ASIL-B), then safety-critical functions meet the required safety standard, but development and validation effort and resource requirements increase
Solution Approach 1:
The patent segments the sensor system into multiple groups (first group with ASIL-B rating, second group with lower ratings) and processes their measurement data separately through different environmental models. This allows each group to be processed according to its actual safety requirements rather than forcing all sensors to meet the highest rating, thereby reducing development and validation effort while maintaining necessary safety standards for critical functions.
2Adaptability or versatility
If multiple environmental models with different safety ratings are calculated in parallel, then functions with different ASIL ratings can be implemented, but resource requirements of the controller increase
Solution Approach 1:
The patent applies preliminary action by having the first environmental model (ASIL-B) process measurement data from the first sensor group in advance. The results of this preliminary processing are then reused by the second environmental model, which only needs to process additional measurement data from the second sensor group. This sequential approach with data reuse reduces the overall computational load and power demand compared to running multiple independent parallel models.
3Measurement precision
If central fusion of all sensor data takes place in one controller, then comprehensive environmental models are created, but computational load and processing time increase
Solution Approach 1:
The patent segments the central fusion process into multiple stages, with the first environmental model processing critical ASIL-B sensor data separately and independently. This segmentation allows the safety-critical processing path to operate with minimal latency while non-critical sensors are processed in subsequent stages. The segmented approach maintains comprehensive environmental modeling accuracy while reducing processing time for critical functions.
Data Source
AI summary
A method for the fusion of measurement data from a plurality of on-board sensors. Measurement data ascertained by a first group of sensors are received by a first controller or by a first module, and are fused to form a first environmental model. The measurement data are used with a first functional safety rating by the first environmental model, or the first environmental model is created based on the measurement data. Measurement data ascertained by at least one second group of sensors are received by at least one second controller or by at least one second module, and are fused to form at least one second environmental model. The measurement data of the second group are used with a second functional safety rating by the second environmental model, or the at least one second environmental model is created based on the measurement data of the second group.