Self-Driving Car Trajectory Filtering for Improbable Vehicle Maneuvers
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current self-driving car systems face inefficiencies in determining trajectories of surrounding vehicles, particularly when dealing with unpredictable road users, as existing methods are resource-intensive and include improbable maneuvers, which can increase the risk of collisions.
Innovation Solution
The system generates trajectories for self-driving cars by determining the presence and motion characteristics of third-party objects, calculating braking profiles, and eliminating improbable maneuvers from predicted trajectories to refine the SDC's path and reduce collision risks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the system generates multiple predicted trajectories for third-party objects including improbable maneuvers, then the trajectory prediction comprehensiveness is improved, but the computational resource consumption increases and collision risk increases
Solution Approach 1:
The system performs preliminary filtering of improbable maneuvers before full trajectory processing. By calculating braking profiles and identifying physically impossible maneuvers in advance, the system eliminates unrealistic trajectories early in the processing pipeline, reducing computational load on subsequent modules while maintaining comprehensive analysis of feasible trajectories.
Solution Approach 2:
The system applies different processing quality levels to different trajectory candidates. High-probability, physically feasible trajectories receive detailed processing, while improbable maneuvers are quickly filtered using braking profile calculations. This local differentiation of processing intensity optimizes resource allocation based on trajectory likelihood and physical feasibility.
2Adaptability or versatility
If the system includes improbable maneuvers in predicted trajectories, then the coverage of possible paths is improved, but the safety decreases due to increased collision risk
Solution Approach 1:
The system extracts and separates improbable maneuvers from the set of predicted trajectories through braking profile analysis. By identifying trajectories that require physically impossible braking patterns, the system removes these hazardous candidates from further processing, ensuring that only feasible trajectories influence the SDC's navigation decisions while maintaining coverage of all potentially relevant paths.
3Measurement precision
If the system processes all predicted trajectories without filtering, then the accuracy of trajectory prediction is improved, but the processing time increases
Solution Approach 1:
The system performs preliminary filtering of improbable maneuvers before full trajectory processing. By calculating braking profiles and identifying physically impossible maneuvers in advance, the system eliminates unrealistic trajectories early in the processing pipeline, reducing computational load on subsequent modules while maintaining comprehensive analysis of feasible trajectories.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method and an electronic device for generating a trajectory of a Self-Driving Car (SDC) are provided. The method comprises: determining a presence of at least one third-party object around the SDC; generating a plurality of predicted trajectories for the third-party object, where at least one of the plurality of trajectories includes a maneuver executable, by the third-party object, at a future third-party object location; calculating, for the at least one of the plurality of trajectories including the a respective braking profile associated with the third-party object; in response to the respective braking profile being above a pre-determined threshold, eliminating an associated one of the at least one of the plurality of trajectories from future processing; determining an SDC trajectory based on remaining ones of the plurality of predicted trajectories for the third-party