Dual Sensor Fusion for Autonomous Vehicle Diagnostics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current automated driving systems face challenges in independently validating sensor readings, which can lead to diagnostic difficulties and reduced robustness, affecting customer satisfaction and safety.
Innovation Solution
The implementation of a dual sensor fusion system with distinct algorithms and controllers allows for independent validation of sensor data, generating a diagnostic signal when discrepancies are detected, enabling the vehicle to execute fallback commands and maintain safety.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a single sensor fusion algorithm is used in automated driving systems, then the system complexity is reduced, but the ability to independently validate sensor readings and detect diagnostic issues deteriorates
Solution Approach 1:
The patent divides the single sensor fusion system into multiple independent sensor fusion algorithms (first sensor fusion algorithm and second sensor fusion algorithm). Each algorithm processes sensor data independently to produce separate outputs, enabling cross-validation of sensor readings without requiring a single complex validation system.
2Reliability
If multiple sensor fusion algorithms and controllers are implemented, then independent validation of sensor readings is improved, but the device complexity increases
Solution Approach 1:
The patent implements a feedback mechanism where the sensor fusion arbitration algorithm continuously monitors and compares outputs from multiple sensor fusion algorithms. When discrepancies are detected between the first and second sensor fusion outputs, the system generates a diagnostic signal that triggers fallback commands, creating a closed-loop validation system that improves reliability through structured comparison.
3Difficulty of detecting and measuring
If sensor fusion arbitration with diagnostic signals is added, then the diagnosis of software or hardware issues is improved, but the computational processing requirements increase
Solution Approach 1:
The patent applies partial action by implementing selective validation - the arbitration algorithm only performs full comparison and diagnostic analysis when necessary conditions are met (discrepancies between sensor fusion outputs). During normal operation, the system relies on the redundancy of multiple algorithms without requiring constant intensive arbitration processing, reducing overall computational burden while maintaining diagnostic capability.
Data Source
AI summary
A control system for an autonomous vehicle includes at least one controller. The controller is programmed to receive first sensor readings from a first group of sensors, provide a first sensor fusion output based on the first sensor readings, the first sensor fusion output including a first detected state of a detected object, receive second sensor readings from a second group of sensors, and provide a second sensor fusion output based on the second sensor readings, the second sensor fusion output including a second detected state of the detected object. The controller is additionally programmed to, in response to the first detected state being outside a predetermined range of the second detected state, generate a diagnostic signal.