Vehicle Motion Planning With Simultaneous Abort Trajectories
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for planning vehicle motion in autonomous or advanced driver assistance systems often fail to balance efficient maneuvers with safety, leading to frequent forced abortions of maneuvers due to worst-case predictions of other traffic participants' behavior.
Innovation Solution
A computer-implemented method that determines both a nominal trajectory for a desired maneuver and an abort trajectory simultaneously using a single optimization process, where the abort trajectory ensures safety even under adverse conditions, reducing the frequency of forced abortions by shaping the nominal trajectory to be easily abortable.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If trajectories are determined based on a worst case prediction of the behavior of other traffic participants, then safety is improved, but maneuver efficiency deteriorates and certain maneuvers can't be carried out
Solution Approach 1:
The trajectory planning is segmented into two distinct components: a nominal trajectory that enables efficient maneuver execution based on plausible behavior predictions, and a fallback trajectory that ensures safety based on worst-case predictions. This segmentation allows the system to optimize for efficiency in normal conditions while maintaining safety guarantees through the separate fallback plan.
Solution Approach 2:
The fallback trajectory is pre-calculated and prepared in advance alongside the nominal trajectory. By having the safety trajectory ready beforehand, the system can quickly switch to it when needed without compromising maneuver efficiency during normal operation. The fallback trajectory is continuously adapted but always available as a pre-prepared safety net.
2Reliability
If a fallback trajectory is continuously adapted and switched to when nominal trajectory becomes unsafe, then safety is maintained, but the frequency of forced abortions increases
Solution Approach 1:
The system continuously monitors the actual behavior of other traffic participants and compares it against the worst-case assumptions used in fallback trajectory calculation. When the actual behavior deviates from the worst-case scenario and confirms safety, the system provides feedback to continue with the nominal trajectory, avoiding unnecessary abortions. This feedback mechanism reduces false positives in safety assessments.
Solution Approach 2:
The system dynamically adjusts the weighting and parameters of trajectory selection based on real-time observations. When traffic participants exhibit predictable and safe behavior, the nominal trajectory parameters are maintained. When uncertainty increases or actual behavior approaches worst-case scenarios, the system transitions to fallback trajectory parameters, optimizing the balance between maneuver completion and safety.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method for planning the motion of a vehicle includes: determining a nominal trajectory for the vehicle based on a desired maneuver to be carried out in a traffic space, on a current state of movement of the vehicle and on a detected state of a surrounding of the vehicle, and determining an abort trajectory branching off from the nominal trajectory and guiding the vehicle to a safe condition regardless of the desired maneuver, wherein the nominal trajectory and the abort trajectory are determined simultaneously using a single optimization process.