Autonomous Driving Sensor Fault Self-Diagnosis via Environmental Model Cross-Checks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Advanced driver assistance systems (ADAS) and autonomous driving systems face faults due to faulty sensors or aberrant sensor data processing, leading to incorrect object detection and implementation of safety and driving functionalities.
Innovation Solution
A computing system that populates sensor measurement data into an environmental model, performs safety cross-checks, and identifies faults by comparing data models, analyzing motion, detecting missing data, divergent classifications, or operational sensor characteristics, enabling a control system to adjust vehicle operations accordingly.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple sensors are used to detect objects and implement automated driving functionality, then the system's measurement precision and reliability are improved, but the complexity of detecting and measuring sensor faults increases
Solution Approach 1:
The patent introduces an environmental model as an intermediary representation that integrates data from multiple sensors (cameras, LIDAR, RADAR, ultrasonic sensors) into a unified spatial framework. This environmental model serves as a mediator that allows the system to cross-validate sensor readings and detect faults by comparing expected environmental states with actual sensor measurements, thereby resolving the contradiction between improved measurement precision and increased fault detection difficulty
Solution Approach 2:
The system implements feedback mechanisms where the environmental model continuously compares sensor measurements against expected patterns and provides feedback on sensor performance. When discrepancies are detected between multiple sensor readings or between sensor readings and the environmental model, the system generates fault indicators that trigger diagnostic routines, enabling automated detection of sensor faults while maintaining high measurement precision through multi-sensor fusion
2Reliability
If safety cross-checks are performed to identify sensor faults, then the system's reliability is improved, but the computational time and processing duration increase
Solution Approach 1:
The patent implements preliminary action by continuously maintaining an environmental model that pre-processes and organizes sensor data in real-time, even before fault conditions occur. The system pre-establishes the spatial and temporal relationships between objects and sensor readings, so that when fault detection is needed, the comparison can be performed rapidly against the pre-computed environmental model rather than processing raw sensor data from scratch, thus improving reliability while minimizing additional processing time
Solution Approach 2:
The system applies partial action by performing safety cross-checks selectively rather than continuously analyzing all sensor data at full depth. The environmental model enables the system to focus cross-checks only on specific sensors or detection events where faults are suspected or where critical safety decisions are required, thereby maintaining high system reliability while reducing overall computational time and processing duration
3Measurement precision
If the system performs comprehensive fault diagnosis including comparing environmental models with data models and analyzing motion patterns, then the fault detection precision is improved, but the device complexity increases
Solution Approach 1:
The environmental model serves as a universal data structure that handles multiple sensor types (cameras, LIDAR, RADAR, ultrasonic sensors) and multiple detection functions (object detection, fault detection, motion analysis) within a single unified framework. This multi-functional approach allows the system to perform comprehensive fault diagnosis including environmental model comparison, motion pattern analysis, and sensor cross-validation without requiring separate complex systems for each function, thereby improving fault detection precision while managing device complexity through consolidation
Data Source
AI summary
This application discloses a computing system to self-diagnosis of faults for an assisted or automated driving system of a vehicle. The computing system can populate measurement data collected by sensors mounted in the vehicle into an environmental model, and detect an object proximate to the vehicle based on the measurement data in the environmental model. The computing system can identify a fault in at least one of the sensors by performing one or more safety cross-checks including one or more of comparing the environmental modal against one or more data models populated with sensor measurements or objects detected by different sensors, analyzing estimated motion of the vehicle or the object for aberrant movement, identifying missing measurement data, identifying divergent object classifications, or identifying operational sensor characteristics. A control system for the vehicle can configured to control operation of the vehicle based, at least in part, on the identified fault.