Vehicle Path Planning for Fallback Stop Collision Risk
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing path planning systems for autonomous vehicles focus primarily on object avoidance and comfort, neglecting the risk of collisions due to unexpected stops, which can pose a safety hazard for both the ego-vehicle and oncoming traffic.
Innovation Solution
A method for operating autonomous vehicles with a fallback stop feature that involves determining candidate paths based on sensor and localization data, considering an overlap cost parameter to minimize the duration of time spent in lanes with potential oncoming traffic, thereby reducing the risk of collisions during unexpected stops.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If conventional path planning systems focus on object avoidance and comfort, then path smoothness and comfort are improved, but safety risk during unexpected stops worsens
Solution Approach 1:
The system performs preliminary action by predicting potential stop positions along each candidate path before the vehicle actually stops. The overlap cost parameter is calculated in advance by determining where the vehicle would stop if a fallback stop were executed at various points along the path, and comparing these predicted stop positions with expected trajectories of surrounding vehicles. This allows the path planning system to evaluate safety risks beforehand and select paths that minimize collision risk during unexpected stops.
2Adaptability or versatility
If the vehicle spends more time in lanes with potential oncoming traffic, then path flexibility is improved, but collision risk during unexpected stops worsens
Solution Approach 1:
The overlap cost parameter serves as an intermediary that bridges path flexibility and collision risk evaluation. Instead of directly restricting the vehicle from spending time in lanes with potential oncoming traffic, the system introduces this intermediate metric that quantifies the risk by comparing predicted stop positions with expected trajectories of surrounding vehicles. The cost function uses this intermediary parameter to indirectly control the vehicle's path selection, allowing flexible path planning while automatically penalizing paths that pose higher collision risks during unexpected stops.
3Reliability
If the vehicle minimizes time in unsafe conditions, then safety is improved, but path selection complexity worsens
Solution Approach 1:
The system applies parameter changes by introducing the overlap cost parameter as an additional factor in the existing cost function. Rather than fundamentally changing the path selection mechanism, the patent modifies the cost function by adding this new parameter that quantifies safety risk. The overlap cost parameter is calculated by comparing predicted stop positions with expected trajectories of surrounding vehicles, and this single parameter modification allows the system to minimize time in unsafe conditions while integrating seamlessly with existing path planning algorithms, thus avoiding excessive complexity.
Data Source
Figure 1
Figure 2
Figure 3a~3b
AI summary
There is provided a method for operating a vehicle having an ADS and a fall back stop feature by determining a plurality of candidate paths for a prediction time horizon within a drivable area in the surrounding environment of the vehicle based on sensor data and localization data. Each candidate path is associated with a nominal cost functional value based on at least one cost parameter. Further, the method comprises determining an expected trajectory of a target vehicle located in the surrounding environment of the vehicle for the prediction time horizon 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.