Autonomous Vehicle Shoulder Stop Position Scoring for MRM
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
During autonomous driving, abnormal situations may arise that require a vehicle to perform a minimum risk maneuver (MRM), particularly a shoulder stop, to ensure safety and minimize risk.
Innovation Solution
The vehicle is equipped with sensors to detect the surrounding environment and a processor to generate vehicle state information. When an MRM is required, the processor determines the MRM type, such as a shoulder stop, and generates stop position candidate groups by partitioning the shoulder area into virtual areas, calculating scores based on vehicle speed, free space, and distance, and selecting the optimal stop position.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the shoulder area is partitioned into multiple virtual areas and scored based on multiple parameters, then the accuracy of stop position selection is improved, but the computational complexity increases
Solution Approach 1:
The shoulder area is divided into multiple virtual areas (first virtual area, second virtual area, third virtual area) along the vehicle traveling direction. Each virtual area is independently scored based on multiple parameters including free space, distance from current position, and vehicle speed. This segmentation allows systematic evaluation of different stop position candidates while maintaining manageable computational complexity through structured processing.
Solution Approach 2:
The system evaluates multiple parameters (free space, distance, vehicle speed) and converts them into scores for each virtual area. By changing physical parameters into comparable score values, the system enables accurate comparison and selection of stop positions while simplifying the decision-making process through standardized evaluation metrics.
2Reliability
If multiple stop position candidate groups are generated and evaluated, then the reliability of the shoulder stop maneuver is improved, but the time required for position selection increases
Solution Approach 1:
The system pre-generates multiple stop position candidate groups (first candidate group, second candidate group) before executing the shoulder stop maneuver. Each candidate group contains multiple stop position candidates that are pre-evaluated and scored. This preliminary preparation ensures reliable stop position selection while reducing real-time computational burden by performing evaluations in advance.
Solution Approach 2:
The system dynamically selects from multiple pre-generated candidate groups based on current vehicle conditions and environmental factors. The candidate groups can be adjusted and re-evaluated as vehicle speed, distance, and free space parameters change, allowing the system to maintain reliability while adapting to dynamic conditions without excessive computational overhead.
Data Source
AI summary
An autonomous vehicle is provided which includes: at least one sensor configured to detect surrounding environment of the vehicle and to generate surrounding environment information; a processor, during autonomous driving of the vehicle, configured to generate vehicle state information by monitoring a state of the vehicle, and to determine whether a minimum risk maneuver (MRM) is required based on at least one of the surrounding environment information and the vehicle state information; and a controller configured to control operations of the vehicle under the control of the processor, wherein, based on a determination that the MRM is required, the processor is configured to determine an MRM type, and when the determined MRM type is a shoulder stop, the processor is configured to generate at least one stop position candidate group.