Lateral Gap Budgeting for Autonomous Driving Disengagement Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In autonomous driving scenarios, determining a safe minimum lateral gap between a vehicle and surrounding objects is challenging due to uncertainties in perception, cross-track errors, and behavior prediction, making it difficult for drivers to take control effectively, especially in complex driving conditions.
Innovation Solution
A method and system that calculate a budgeted lateral gap by combining potential uncertainties, such as perception errors and cross-track errors, with a speed-based buffer, and provide notifications to drivers through audible, visual, or haptic means to ensure safe manual control takeover.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If the vehicle operates in autonomous driving mode with control system handling driving operations, then the automation level is improved, but the driver's ability to take control effectively deteriorates due to uncertainties in perception and cross-track errors
Solution Approach 1:
The system calculates the minimum lateral gap in advance before driver takeover is needed, using perception errors, cross-track errors, and behavior prediction uncertainties. This preliminary calculation ensures that when the driver needs to take control, the vehicle is already positioned at a safe distance from surrounding objects, enabling effective driver intervention without compromising safety
Solution Approach 2:
The system incorporates a speed-based buffer and combines multiple uncertainty factors (perception error, cross-track error, behavior prediction uncertainty) to create a safety cushion. This cushioning effect ensures that even when drivers take control in challenging conditions, there is sufficient lateral space to prevent collisions while the driver adjusts to the vehicle state
2Reliability
If the minimum lateral gap is calculated based on multiple uncertainties including perception error and cross-track error, then the safety is improved, but the complexity of the system increases
Solution Approach 1:
The system merges multiple uncertainty factors (perception error, cross-track error, behavior prediction uncertainty) into a single minimum lateral gap calculation. By combining these factors through a unified computational framework that includes a speed-based buffer, the system achieves comprehensive safety coverage while maintaining a manageable computational structure
Solution Approach 2:
The system dynamically adjusts the minimum lateral gap based on changing parameters such as vehicle speed, perception error margins, and cross-track error variations. This parameter-based approach allows the safety calculation to adapt to real-time conditions without requiring a completely complex system architecture, as the same computational framework handles varying input parameters
3Ease of operation
If the driver is notified to take control based on determined minimum lateral gap, then the driver comfort is improved, but the loss of time occurs during the transition from autonomous to manual control
Solution Approach 1:
The system performs preliminary calculation of the minimum lateral gap and monitors when conditions require driver takeover. By having the safety parameters pre-calculated and ready, the system can notify the driver immediately when takeover is needed, reducing the transition time while ensuring the driver has sufficient information to take control comfortably and safely
Data Source
AI summary
The technology involves determining a minimum lateral gap distance between a vehicle configured for autonomous driving and one or more other objects in the vehicle's environment. The minimum lateral gap is used when determining whether to have a driver take over control of certain driving operations. This provides a measure of safety during disengagements or other change of control events. Determining the minimum lateral gap includes calculating a budgeted distance based on a cross-track error for a lateral position of the vehicle, an allowed actual gap distance to an object in the vehicle's environment, and a perception error associated with a location of the object in the vehicle's environment. This determination can be done for a set of possible operating speeds and steering rate limit combinations. The vehicle's control system may notify the driver to take control, for instance with audible, visual and/or haptic notifications.