Abnormality Detection Device for Automatic Driving Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automatic driving systems face challenges in accurately detecting abnormalities, such as hydroplaning on wet roads, which can lead to erroneous determination of vehicle malfunctions, as they do not adequately consider the external environment when assessing the vehicle's state.
Innovation Solution
An abnormality detection device that includes sensors like LIDAR and cameras to detect the external environment and vehicle state, determining if the environment is suitable for automatic driving control by comparing the detected road surface shape and vehicle state with predetermined thresholds, and switching to manual control when abnormalities are detected.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If abnormality detection is performed based only on vehicle traveling state without considering external environment, then detection simplicity is maintained, but false abnormality detection occurs in adverse conditions such as hydroplaning
Solution Approach 1:
The abnormality detection function is segmented into two independent determination processes: one for vehicle traveling state abnormality and another for external environment suitability. This modular approach allows each determination to be performed separately using appropriate sensors and algorithms, improving detection accuracy while maintaining manageable system complexity through functional decomposition.
Solution Approach 2:
The external environment determination acts as an intermediary condition that mediates between the traveling state detection and the final abnormality conclusion. By introducing this intermediate assessment layer that evaluates road conditions, weather, and other environmental factors, the system avoids false positives without requiring complete redesign of the detection architecture.
2Reliability
If external environment sensing and evaluation is added to the detection system, then false abnormality detection is reduced, but system complexity and sensor requirements increase
Solution Approach 1:
The sensor system is designed with multi-functionality where sensors serve multiple purposes: LIDAR and cameras not only detect external environment characteristics for suitability determination but also provide data for vehicle positioning and obstacle detection. This universal approach enhances system reliability without proportionally increasing complexity, as the same hardware infrastructure supports multiple detection functions.
Solution Approach 2:
The system evaluates external environment suitability by analyzing changes in environmental parameters such as road surface friction coefficient, visibility conditions, and weather factors. By monitoring these parameter changes and comparing them against predetermined thresholds, the system reliably determines whether current conditions are suitable for automatic driving without requiring overly complex sensor arrays.
3Measurement precision
If the system continuously monitors both traveling state and external environment, then detection accuracy is improved, but processing time and computational load increase
Solution Approach 1:
The system implements periodic determination cycles where traveling state abnormality detection and external environment suitability evaluation are performed at regular intervals rather than continuously. This periodic action maintains high detection precision by frequently updating assessments while reducing computational load and processing time by allowing brief intervals between determination cycles, optimizing the balance between accuracy and efficiency.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This solution enables accurate detection of abnormalities in automatic driving systems by considering both the vehicle's state and the external environment, preventing false alarms and ensuring safe operation by switching to manual control when necessary.
Implementation Method 1
a LIDAR configured to irradiate surroundings of the vehicle with light and configured to detect reflected light of the irradiated light
Data Source
AI summary
An abnormality detection device includes a sensor configured to detect an external environment of a vehicle and an electronic control unit configured to: detect a traveling state of the vehicle; acquire a control command value for the vehicle in automatic driving control, the vehicle being caused to travel automatically in the automatic driving control; determine, based on a difference between the traveling state and the control command value, whether the traveling state is abnormal; determine, based on a detection result from the sensor, whether the external environment is suitable for execution of the automatic driving control; and determine that an abnormality has occurred in an automatic driving system when it is determined that the traveling state is abnormal and it is determined that the external environment is suitable for the execution of the automatic driving control, the automatic driving system performing the automatic driving control.