Evasive Steering Assist With Driver-Specific Intent Thresholds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional vehicle ADAS systems for evasive steering are generic and not driver-specific, leading to insufficient performance and potential collisions due to inadequate steering torque application.
Innovation Solution
A self-learning-based system that determines driver-specific parameter thresholds for evasive steering assistance using steering angular rate, torque, lateral acceleration, and jerk, calibrated through a highway overtake maneuver, and enhances engagement with vehicle perception sensors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional generic ADAS systems are used for evasive steering, then system complexity is reduced, but performance is insufficient leading to collisions
Solution Approach 1:
The system performs preliminary calibration during highway overtake maneuvers to establish driver-specific thresholds before actual evasive situations occur. This advance preparation enables the system to achieve high reliability without increasing operational complexity, as the personalized parameters are pre-determined during routine driving.
Solution Approach 2:
The system automatically learns and adapts to individual driver characteristics through self-calibration during normal highway overtaking. This self-service approach eliminates the need for manual configuration or complex setup procedures, maintaining ease of operation while achieving driver-specific performance optimization.
2Ease of operation
If driver-specific calibration is implemented, then driver acceptance and safety improve, but system complexity increases
Solution Approach 1:
The system uses highway overtake maneuvers, which are routine driving actions, for dual purposes: normal driving and calibration of evasive steering parameters. This multi-functionality allows driver-specific adaptation without requiring separate calibration procedures, maintaining ease of operation while achieving personalized performance.
Solution Approach 2:
The system automatically performs calibration during normal driving operations without requiring driver intervention or complex setup procedures. This self-service approach improves driver acceptance by eliminating burden while the underlying complexity is managed automatically by the control system.
3Reliability
If generic threshold values are used, then system simplicity is maintained, but performance is insufficient in certain scenarios
Solution Approach 1:
The system pre-determines driver-specific thresholds during highway overtake calibration before actual evasive maneuvers are needed. This preliminary action enables the system to adapt to individual driver characteristics and maintain high reliability across different driving styles and scenarios without requiring complex real-time adjustments.
Solution Approach 2:
The system changes the threshold parameters from generic fixed values to driver-specific calibrated values. By adjusting these parameters based on individual driver behavior during highway overtaking, the system achieves both high reliability and adaptability to different driving styles and scenarios.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Evasive steering assist (ESA) systems and methods for a vehicle utilize a set of vehicle perception systems configured to detect an object in a path of the vehicle, a driver interface configured to receive steering input from a driver of the vehicle via a steering system of the vehicle, a set of steering sensors configured to measure a set of steering parameters, and a controller configured to determine a set of driver-specific threshold values for the set of steering parameters, compare the measured set of steering parameters and the set of driver-specific threshold values to determine whether to engage/enable an ESA feature of the vehicle, and in response to engaging/enabling the ESA feature of the vehicle, command the steering system to assist the driver in avoiding a collision with the detected object.