Vehicle Sensor Data Prioritization for Unknown Sensor Faults
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods fail to account for previously unknown sensor insufficiencies that can arise during vehicle operation due to mechanical, thermal, or electrical influences, leading to false measurements and increased accident risk in autonomous systems.
Innovation Solution
A method and system that utilizes an expert system to evaluate sensor data, recognize unknown insufficiencies, and adjust processing parameters to compensate for these issues, including a dynamic assignment of priorities based on current conditions and sensor reliability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If an expert system is developed in the design phase for the entire fleet, then known insufficiencies can be accounted for, but previously unknown insufficiencies occurring during vehicle operation cannot be recognized
Solution Approach 1:
The system dynamically adapts the assignment rule during vehicle operation based on recognized insufficiencies. The priority assignments for output data are not fixed but can be updated when new insufficiencies are detected, allowing the system to transition from static design-phase configurations to dynamic operational adaptation.
Solution Approach 2:
The system implements a feedback mechanism where sensor data is continuously evaluated, insufficiencies are recognized from the evaluation results, and the assignment rule is updated based on this feedback. This closed-loop approach enables the system to learn from operational experience and improve its sensor evaluation over time.
2Measurement precision
If the assignment rule is updated based on recognized insufficiencies, then false measurements can be reduced, but the system complexity increases
Solution Approach 1:
The control device performs self-diagnosis and self-adjustment by automatically recognizing insufficiencies from sensor data and updating its own assignment rule without external intervention. This self-service capability reduces the need for manual calibration and external system complexity while improving measurement accuracy.
Solution Approach 2:
The assignment rule acts as an intermediary mechanism that mediates between raw sensor data and the environment model. By updating this intermediary rule based on recognized insufficiencies, the system can improve measurement accuracy without fundamentally changing the complex sensor evaluation architecture.
3Reliability
If dynamic priority assignment is implemented, then vehicle-specific insufficiencies can be compensated, but the processing time increases
Solution Approach 1:
The system changes the priority parameters of output data dynamically based on recognized insufficiencies and current sensor conditions. By adjusting these parameters rather than reprocessing entire data streams, the system can adapt to varying conditions with minimal additional processing time.
Solution Approach 2:
The system applies partial updates to the assignment rule, modifying only the priority assignments for affected sensors or evaluation functions rather than recalculating all priorities. This selective approach reduces processing overhead while still compensating for vehicle-specific insufficiencies.
Data Source
AI summary
A method for processing sensor data in a control device of a vehicle. The method includes: evaluating sensor data generated by different sensors of the vehicle for detecting its environment, via different evaluation functions which convert at least part of the sensor data as input data into output data, wherein the output data are assigned a priority using an assignment rule based on known insufficiencies of the sensors and/or the evaluation functions and the output data are used according to their priority in order to update an environment model that stores information about objects in the environment of the vehicle; recognizing an insufficiency that differs from the known insufficiencies using at least a part of the sensor data and/or at least a part of the output data; updating the assignment rule based on the recognized insufficiency.