Adaptive Semi-Automated Driving Activation via Sensor Prediction Quality
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle operation systems lack effective methods to ensure safety by accurately assessing and adapting to changing object states in the vehicle's surroundings, particularly in situations where the semi-automated driving functions may not maintain a certain safety level due to limitations in sensor capabilities.
Innovation Solution
A method utilizing a surroundings sensor system to detect and predict object states at different points in time, adapting the activation state of semi-automated driving functions based on these predictions, and deactivating the function if prediction quality falls below a threshold to prevent unsafe operations, ensuring safety by limiting the driving function's capabilities when accuracy is insufficient.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If semi-automated driving functions are activated to improve productivity and reduce manual operation, then ease of operation increases, but reliability decreases when object state prediction quality is insufficient
Solution Approach 1:
The system continuously monitors prediction quality by comparing predicted object states with actually detected states and uses this feedback to dynamically adapt the activation state of driving functions. When prediction quality falls below thresholds, the system automatically deactivates or limits driving functions, ensuring reliability while maintaining ease of operation under suitable conditions.
Solution Approach 2:
The activation state of driving functions is made dynamic rather than static. The system adapts the degree of automation in real-time based on current prediction quality, transitioning between fully active, limited, and deactivated states. This dynamic adaptation resolves the contradiction by adjusting reliability according to operational conditions while preserving ease of operation when safe.
2Productivity
If the degree of automation is increased to improve productivity, then productivity increases, but measurement precision requirements increase leading to potential safety risks
Solution Approach 1:
The system changes the parameter of automation level based on prediction quality metrics. When measurement precision is sufficient, high-level automation is permitted to maximize productivity. When precision degrades below thresholds, the system automatically reduces automation level or deactivates functions, preventing safety risks while allowing productivity benefits under suitable conditions.
3Productivity
If driving functions are kept continuously active to maintain productivity, then productivity is maintained, but safety risks increase when prediction quality deteriorates
Solution Approach 1:
The system takes preliminary anti-action by continuously monitoring prediction quality and proactively deactivating or limiting driving functions before safety risks can materialize. By detecting degradation in measurement precision in advance and automatically adapting the activation state, the system prevents harmful outcomes while minimizing disruption to productivity.
4Measurement precision
If more sensors and detection systems are added to improve measurement precision, then measurement precision improves, but device complexity increases
Solution Approach 1:
Instead of continuously using all available sensors and computational resources at full capacity, the system applies partial action by activating higher levels of automation and using more sophisticated prediction algorithms only when prediction quality thresholds are met. When quality is sufficient, the system can afford to use complex models and multiple sensors; when quality degrades, it simplifies operations, reducing device complexity requirements while maintaining adequate measurement precision.
Data Source
AI summary
A method for operating a vehicle includes detecting an object state using a surroundings sensor system of the vehicle at a first point in time, detecting an object state using the surroundings sensor system at a later second point in time, and adapting an activation state of a semi-automated or fully-automated driving function of the vehicle based on the detected object states.