Driving Pattern Profiles for Predicting ADAS Disengagement Causes
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Changes in available driver assistance features in vehicles, such as enabling or disabling autonomous driving modes, can disrupt the driving experience and reduce safety due to unexpected transitions, often caused by factors like weather, sensor misalignment, road conditions, and wireless network performance.
Innovation Solution
A system that collects probe data from vehicles, matches it to path segments, and determines the cause of changes in driver assistance capabilities, allowing for geographic database updates to avoid problematic areas and improve route planning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If driver assistance features are enabled based on sensor and map data, then driving automation capability is improved, but unexpected disengagements occur due to environmental factors like weather and road conditions
Solution Approach 1:
The system performs preliminary routing analysis to identify path segments with historical driver assistance disengagements before the driver travels them. By pre-identifying problematic segments and providing advance warning, the system allows the driver to take preventive action (manual control or route change) before automated features are likely to disengage, thus maintaining reliability while preserving automation capability.
Solution Approach 2:
The system collects and analyzes probe data from multiple vehicles to build a historical database of driver assistance disengagements associated with specific path segments. This feedback loop enables the system to learn from real-world performance and continuously improve its ability to predict and warn about problematic segments, enhancing reliability without reducing automation extent.
2Reliability
If driver assistance features are disabled due to environmental concerns, then safety is improved by preventing unexpected behavior, but the driving experience is interrupted and productivity decreases
Solution Approach 1:
The system provides advance warning of problematic path segments before the driver encounters them, enabling proactive decision-making. Drivers can prepare to take manual control gradually or select alternative routes, avoiding abrupt disengagements and maintaining trip continuity while preserving safety.
Solution Approach 2:
By warning drivers in advance of segments likely to cause disengagements, the system enables drivers to take counter-actions (maintain manual control or change route) before the harmful effect (unexpected feature disablement) occurs. This prevents the interruption while maintaining safety through informed driver decision-making.
3Reliability
If driver assistance features are disabled to avoid problematic areas, then reliability is improved, but adaptability decreases as drivers cannot use features in challenging conditions
Solution Approach 1:
The system introduces an intermediary information layer (warnings and route recommendations) between the driver and the driver assistance system. This mediator provides context about environmental challenges ahead, enabling drivers to make informed decisions about when to use manual control or alternative routes, rather than forcing blanket disabling of features. This maintains adaptability while improving predictability through informed driver choice.
Data Source
AI summary
Systems and methods for determining a cause of a change in driver assistance capability may be based on probe data generated by a mobile device or vehicle. The probe data is matched to a path segment. A cause of the change in driver assistance capability for the path segment is determined based on the probe data matched to the path segment. A geographic database record including the cause of the change in the driver assistance capability is output.