Lane-Keeping Trajectory Planning Under Boundary Confidence Limits
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current autonomous driving systems face limitations in lane keeping due to increasing uncertainty of lane boundary detection with distance, leading to restricted top speeds and increased hardware and software requirements, which negatively impact user experience and practicality.
Innovation Solution
Introducing a predefined availability criterion for the nominal trajectory, allowing a reduced frequency of back-up stops and shifting reliability requirements to other system components, enabling higher top speeds while maintaining safety integrity levels without stricter hardware or software demands.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the vehicle requires full stop capability within available lane description, then safety is improved, but top speed is drastically limited
Solution Approach 1:
The system dynamically adjusts the stopping distance requirement based on the confidence level of lane trace estimation. When confidence is high, shorter stopping distances are acceptable, enabling higher speeds. When confidence decreases, longer stopping distances are required, reducing speed accordingly. This dynamic adaptation resolves the contradiction by making safety requirements flexible rather than fixed.
Solution Approach 2:
The patent changes the parameter of stopping distance from a fixed strict requirement to a variable parameter that depends on confidence levels. By allowing the stopping distance parameter to increase when confidence decreases, the system maintains safety while enabling higher top speeds during high-confidence periods, thus resolving the speed-limiting contradiction.
2Reliability
If strict safety requirements are imposed on in-vehicle systems, then reliability is improved, but device complexity increases
Solution Approach 1:
The patent transforms fixed strict safety parameters into dynamic parameters based on confidence levels. Instead of requiring complex hardware and software to maintain constant high safety levels, the system adjusts safety parameters (stopping distance, speed limits) dynamically, achieving comparable or superior safety with simpler systems.
Solution Approach 2:
The system implements dynamic safety requirements that adapt to real-time confidence levels rather than maintaining static strict requirements. This dynamic approach reduces the need for overly complex safety systems while maintaining or improving actual safety performance through context-appropriate parameter adjustment.
3Measurement precision
If lane trace projection confidence is maintained high, then measurement precision is improved, but available stopping distance is reduced
Solution Approach 1:
The system dynamically adjusts stopping distance based on measured confidence levels. When lane trace confidence is high, shorter stopping distances are permitted. When confidence decreases, the system automatically increases the required stopping distance, maintaining the appropriate balance between precision and safety distance.
Solution Approach 2:
The patent makes stopping distance a variable parameter that changes with confidence levels. High confidence allows reduced stopping distance, while low confidence triggers increased stopping distance requirements, resolving the contradiction between maintaining high precision and ensuring adequate stopping distance.
Data Source
Figure 1(a)~1(b)
Figure 2(a)~2(b)
Figure 3
AI summary
A system for a lane keeping feature of a vehicle is provided. The lane keeping feature has a predefined safety requirement criterion for keeping the vehicle within bounds while the lane keeping feature is active. The system comprises a road estimation module and a trajectory planning module. The road estimation module is configured to receive sensor data comprising information about a surrounding environment of the vehicle, and to determine a drivable area based on the sensor data. The drivable area comprises a left boundary and a right boundary extending along a direction of travel of the vehicle, wherein each boundary comprises a plurality of points distributed along each boundary, each point being associated with a confidence level. The trajectory planning module is configured to receive the determined drivable area, and to determine a nominal trajectory for the vehicle based on the received drivable area. The nominal trajectory is determined based on the predefined safety requirement criterion and a predefined availability criterion. The trajectory planning module is further configured to determine a back-up stop trajectory for the vehicle based on the received drivable area, where the back-up stop trajectory is determined based on a predefined confidence criterion. The predefined confidence criterion is dependent on a predefined value of frequency of back-up stops that is based on the predefined availability criterion for the nominal trajectory.