Vehicle Path Planning for Safer Fallback Stops in Oncoming Traffic
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current autonomous vehicle path planning systems fail to adequately address the risk of collisions during unexpected stops, particularly when navigating through lanes with oncoming traffic, which poses a safety concern for both the vehicle and passengers.
Innovation Solution
A method for operating autonomous vehicles with a fallback stop feature that uses sensor and localization data to determine candidate paths, calculates an overlap cost parameter for potential collisions, and selects a path to minimize time spent in lanes with oncoming traffic, thereby reducing the risk of collisions by influencing the weighting factors of candidate paths to penalize unsafe stopping conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If the vehicle follows a conventional path planning approach focusing on avoidance of objects and comfort, then the path following capability is improved, but the safety risk in case of unexpected stops increases
Solution Approach 1:
The system preemptively identifies stop positions along candidate paths where the vehicle would be vulnerable to oncoming traffic, and adjusts path selection to avoid these dangerous stopping locations before any actual stop event occurs. This prevents the harmful situation of stopping in an unsafe position rather than reacting after the danger arises
Solution Approach 2:
The system performs preliminary assessment of stop positions and overlap costs for each candidate path before final path selection. By evaluating the overlap between expected trajectories of other vehicles and potential stop positions in advance, the system selects paths that minimize exposure to collision risks before the vehicle actually needs to stop
2Productivity
If the vehicle spends more time in lanes with oncoming traffic to reach destination faster, then the productivity is improved, but the safety risk of collision increases
Solution Approach 1:
The system changes the cost function parameters for path selection by introducing an overlap cost parameter that quantifies the danger of stopping in lanes with oncoming traffic. This modifies the optimization criteria to balance travel time against safety, selecting paths that achieve acceptable productivity while minimizing exposure to oncoming traffic during potential stop events
3Reliability
If the vehicle executes fallback stop feature in any drivable area, then the reliability is improved, but the harmful effect of potential collision with oncoming traffic increases
Solution Approach 1:
The system preemptively identifies and avoids selecting candidate paths that would result in stopping positions overlapping with the expected trajectories of other vehicles. By adjusting the path cost before execution, it prevents the fallback stop from creating a harmful collision scenario rather than mitigating it after the fact
Data Source
AI summary
There is provided a method for operating a vehicle having an automated driving system (ADS) and a fallback stop feature. The method includes obtaining sensor data and localization data including information about a surrounding environment of the vehicle, and determining a plurality of candidate paths for a prediction time horizon within a drivable area in the surrounding environment of the vehicle based on the sensor data and the localization data. Further, the method includes determining an expected trajectory of a target vehicle located in the surrounding environment of the vehicle for the prediction time horizon based on the obtained sensor data and localization data, and determining, for each candidate path, an overlap cost parameter for an overlap between the target vehicle's expected trajectory and a set of stop positions of the vehicle based on predicted executions of the fallback stop feature within the prediction time horizon.