Vehicle Path Fusion Control Under Sensor Reliability Changes
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle control systems face challenges in accurately and stably determining driving paths, especially when sensors deteriorate or environmental conditions change, leading to unreliable lane recognition and vehicle behavior instability.
Innovation Solution
A vehicle control method and device that utilize multiple estimated driving paths from various sensors and algorithms, evaluate their reliability, and fuse them to produce a stable and optimal driving path, thereby minimizing function deterioration and ensuring smooth vehicle behavior.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple driving path estimation algorithms are used, then the reliability and accuracy of driving path determination is improved, but the device complexity and computational burden increase
Solution Approach 1:
The system segments the driving path estimation task by employing multiple specialized algorithms (lane recognition, curvature-based estimation, map matching) that each handle specific aspects of path determination. This segmentation allows the system to improve overall reliability through algorithm diversity while managing complexity by organizing each algorithm's processing independently with dedicated evaluation and fusion stages.
Solution Approach 2:
The system merges the outputs of multiple driving path estimation algorithms through a weighted fusion process. The driving path evaluation unit combines estimates from lane recognition, curvature-based, and map matching algorithms, assigning weights based on their respective reliability assessments. This merging approach consolidates the benefits of multiple algorithms into a single robust driving path determination, improving reliability while managing complexity through systematic integration.
2Measurement precision
If multiple sensors and algorithms are integrated, then the accuracy of driving path estimation is improved, but the processing time and computational resources increase
Solution Approach 1:
The system performs preliminary actions by pre-configuring multiple driving path estimation algorithms and their corresponding evaluation criteria before actual driving path determination is needed. The weighting schemes and reliability assessment mechanisms are established in advance, allowing the system to quickly fuse sensor data and algorithm outputs during real-time operation without extensive computational deliberation, thus improving accuracy while minimizing processing time.
Solution Approach 2:
The system dynamically adjusts parameters such as algorithm weights and reliability thresholds based on current driving conditions and sensor performance. By changing these parameters adaptively, the system optimizes the balance between processing multiple algorithms for accuracy and minimizing computation time, allowing faster processing when conditions permit and more thorough analysis when time allows.
3Reliability
If sensor data from multiple sources is used, then the robustness against sensor deterioration is improved, but the difficulty of detecting and measuring reliable data increases
Solution Approach 1:
The system implements feedback mechanisms where the driving path evaluation unit continuously assesses the reliability of each sensor and algorithm output, comparing expected patterns with actual measurements. This feedback loop identifies sensor deterioration or environmental interference by detecting deviations from normal operation, allowing the system to adjust weights or switch to alternative algorithms, thereby maintaining robustness while managing the complexity of reliability assessment through systematic monitoring.
4Device complexity
If a single driving path algorithm is used, then the device complexity is reduced, but the stability of vehicle behavior deteriorates under changing environmental conditions
Solution Approach 1:
The system achieves universality by designing a multi-functional driving path estimation framework that can adapt to various environmental conditions using multiple algorithms. Rather than relying on a single specialized algorithm, the system employs lane recognition, curvature-based estimation, and map matching methods that collectively cover diverse driving scenarios. This multi-functionality ensures stable vehicle behavior across changing conditions while managing complexity through a unified evaluation and fusion architecture.
Data Source
AI summary
Provided are a method and a device for controlling the behavior of a vehicle. The method comprising a sensing information receiver receiving sensing information, a driving path estimator estimating a driving path for each preconfigured driving path estimation algorithm, a driving path evaluator evaluating a reliability of the driving path for each driving path estimation algorithm, a driving path fuser producing a fused driving path, a defect detector determining whether a defect occurs by comparing the fused driving path with the driving path for each driving path estimation algorithm, and a control signal outputter outputting a control signal for controlling a behavior of the vehicle according to a final fused driving path reproduced.