Driver Assistance Learning for Reliable Familiar-Route Automation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing driver assistance systems for motor vehicles face challenges in providing quick and reliable environment-dependent support, particularly in familiar environments, as the learning process can be lengthy and may not account for driver preferences and habits, leading to delayed availability of automated functions.
Innovation Solution
A method involving continuous learning by detecting the vehicle's environment and driver actions, with a quality measure to assess correlation reliability, allowing adaptive automation levels based on environment familiarity and action confirmation, enabling rapid deployment of automated functions while ensuring safety through categorization levels.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a learning mode is used to create a sufficient database for automating driving tasks, then the automated function becomes available, but the learning process takes a relatively long time
Solution Approach 1:
The system performs preliminary learning actions by continuously detecting surroundings and driver actions, storing them as training data in advance. This allows the automated function to become available more quickly without compromising the quality of the learned correlation, as the learning process occurs progressively rather than requiring a complete upfront learning phase.
2Loss of time
If automated functions are deployed quickly in familiar environments, then driver assistance is provided rapidly, but the reliability of learned correlations may be insufficient
Solution Approach 1:
The system applies partial automation based on the quality measure of learned correlations. When correlation reliability is insufficient, the system provides partial assistance (e.g., warnings or suggestions) rather than full automation. This allows rapid deployment of assistance functions while maintaining safety through proportional automation levels matched to the confidence in learned patterns.
Solution Approach 2:
The system changes the parameter of automation level dynamically based on the quality measure of learned correlations. As the quality measure improves with more training data, the system transitions from lower automation levels (warnings, suggestions) to higher automation levels (partial or full automation). This allows rapid adaptation to familiar environments while ensuring reliability through progressive parameter adjustment.
3Reliability
If the driver assistance system waits for high-quality learned correlations before providing automated functions, then reliability is ensured, but the assistance is delayed even in familiar environments
Solution Approach 1:
The system dynamically adjusts the level of automated assistance provided based on the real-time quality measure of learned correlations. Rather than waiting for a fixed threshold to be met, the system continuously adapts the automation level to the current state of learning, providing appropriate assistance immediately while improving reliability over time as more data is collected and processed.
Data Source
AI summary
The invention relates to a method for operating a driver assistance device of a motor vehicle, comprising detecting of an environment of the motor vehicle by an associated sensor device of the motor vehicle for the driver assistance device, detecting of at least one action of a driver of the motor vehicle, which action correlates with a driving movement of the motor vehicle, by an associated additional sensor device of the motor vehicle for the driver assistance device, learning of a correlation between the detected environment and the detected action by the driver assistance device via repeated detecting of the environment and the action, evaluating of a reliability of the learned correlation by means of a quality criterion by the driver assistance device, and carrying out of at least one automated function which correlates with a driving movement of the motor vehicle by the driver assistance device according to the instantaneous environment of the motor vehicle and/or a value of quality criterion, in order to provide a driver of the motor vehicle, as quickly as possible, with an environment-related assistance via a driver assistance device.