Autonomous Vehicle Lateral Error Disengagement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for disengaging autonomous vehicle mode, such as applying torque to the steering wheel, are ineffective when the input torque is below a predefined threshold, leading to cognitive problems and safety risks for drivers.
Innovation Solution
The system calculates lateral deviation from a planned path using sensor data and disengages autonomous mode when the deviation exceeds a predefined threshold, regardless of the torque applied, ensuring safe driver intervention.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If torque threshold is increased to ensure intentional disengagement, then false disengagement is reduced, but legitimate driver intervention is blocked
Solution Approach 1:
The patent introduces lateral deviation as an intermediary parameter to mediate between torque input and disengagement decision. Instead of directly using torque threshold, the system first measures lateral deviation caused by driver steering input, then uses this deviation as the basis for disengagement determination. This intermediary approach allows detection of genuine driver intent without requiring excessive torque that could block legitimate intervention.
Solution Approach 2:
The patent replaces the mechanical torque-based disengagement system with a lateral deviation-based system. Instead of relying on mechanical torque sensors and fixed threshold comparisons, the system uses lateral deviation measurements (which can be derived from sensor data or steering angle sensors) to determine driver intent. This substitution allows for more nuanced detection of driver intervention while maintaining safety.
2Reliability
If lateral deviation threshold is set low for safety, then driver intervention is detected early, but normal lane adjustments cause false disengagement
Solution Approach 1:
The patent applies dynamics by making the disengagement threshold adaptive rather than fixed. The lateral deviation threshold is adjusted based on vehicle operating conditions, allowing the system to tolerate larger deviations during normal operations (such as lane changes or curve driving) while maintaining high sensitivity for detecting genuine driver intervention. This dynamic adjustment prevents false disengagement while ensuring safety.
Solution Approach 2:
The system performs preliminary assessment of driving context before triggering disengagement. By evaluating whether the current driving situation normalizes lateral deviation (such as upcoming curves or lane changes), the system can preemptively adjust thresholds or suppress disengagement signals that would otherwise be triggered by expected positional variations. This preliminary action prevents false disengagement while maintaining readiness for genuine intervention.
Data Source
AI summary
In one or more embodiments, a method comprises receiving, at a processor, sensor data from a sensor at a vehicle that is moving while in an autonomous mode. A position and an orientation of the vehicle based on the sensor data is determined at the processor. A lateral deviation of the vehicle from a planned path based on the position and the orientation of the vehicle while the vehicle is moving in the autonomous mode is calculated at the processor. In response to the lateral deviation exceeding a predefined lateral deviation threshold, the autonomous mode is disengaged.