Object Trajectory Prediction With Lane-Aware Maneuver Scoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing self-driving car systems face challenges in safely maneuvering around dynamic objects without considering road lane boundaries, increasing the risk of collisions.
Innovation Solution
Predicting object trajectories without considering road lane boundaries and mapping these trajectories onto road lanes, allowing for additional maneuvering freedom to avoid collisions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the system predicts object trajectories without considering road lane boundaries, then the maneuvering freedom increases and collision avoidance capability improves, but the system may allow trajectories that violate road lane rules
Solution Approach 1:
The system segments the trajectory evaluation process into two independent stages: first generating trajectories without lane boundary constraints to maximize maneuvering freedom, then separately evaluating each trajectory against road lane rules. This segmentation allows the system to explore a broader solution space while maintaining regulatory compliance through the second evaluation stage.
Solution Approach 2:
The system performs preliminary trajectory generation without lane boundary constraints before conducting the final compliance check. By removing constraints during the creative generation phase and applying them only in the evaluation phase, the system discovers more maneuvering options that would be missed if constraints were applied from the beginning.
2Reliability
If the system considers road lane boundaries during trajectory prediction, then road lane rule compliance is maintained, but the maneuvering freedom is reduced and collision avoidance capability deteriorates
Solution Approach 1:
The system dynamically adjusts the application of lane boundary constraints based on the evaluation stage. During trajectory generation, constraints are relaxed to allow maximum freedom; during evaluation, constraints are applied to ensure compliance. This dynamic approach allows the system to optimize both maneuvering freedom and rule compliance at different phases of the process.
3Reliability
If the system generates multiple predicted trajectories and maps them onto road lanes, then the collision risk is reduced through comprehensive analysis, but the computational complexity increases
Solution Approach 1:
The system segments the computational process into distinct modules: trajectory generation, road lane mapping, and compliance evaluation. Each module handles a specific aspect of the analysis independently, which organizes the computational complexity into manageable segments while maintaining comprehensive collision risk assessment through the combination of multiple trajectories.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Methods (400) and devices (210) for generating data for controlling a Self-Driving Car (SDC) (220) are disclosed. The method (400) includes: i) receiving a section of a road map (350) corresponding to surroundings of the SDC (220) and at least one object, ii) generating a plurality of predicted trajectories including a potential future location points of the at least one object, iii) mapping the potential future location points on the section of the road map, iv) computing a score for each of the potential future location points, the score representing an association of a given potential future location point with the plurality of road lanes at a future instance of time, v) computing an aggregated score from the scores corresponding to potential future location points, and vi) based on the aggregated score, determining a predicted location of the at least one object at the future instance of time.