Autonomous Vehicle Trajectory Evaluation via Reference Comparison
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for generating longitudinal trajectories for autonomous driving vehicles (ADVs) lack efficiency in considering safety, comfort, and traffic rules, leading to suboptimal navigation.
Innovation Solution
A system generates multiple trajectory candidates by comparing each candidate with a reference trajectory, calculating objective, safety, and comfort costs, and selecting the target trajectory based on total costs, ensuring safe, comfortable, and rule-following paths.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple trajectory candidates are generated and evaluated considering safety, comfort, and traffic rules, then the navigation reliability is improved, but the computational complexity increases
Solution Approach 1:
The trajectory evaluation process is segmented into three distinct cost components: safety cost, comfort cost, and traffic rule cost. Each component is calculated independently and then combined to form the total cost, allowing for modular and efficient computation while comprehensively evaluating multiple trajectory candidates
Solution Approach 2:
The patent transforms the qualitative evaluation criteria (safety, comfort, rule-following) into quantitative cost parameters. By defining specific mathematical formulations for each cost type and combining them with weighted coefficients, the system efficiently compares multiple trajectory candidates through numerical optimization
2Reliability
If trajectory evaluation considers multiple factors (safety, comfort, traffic rules), then the navigation safety is improved, but the processing time increases
Solution Approach 1:
The evaluation process is divided into separate computational modules for safety cost, comfort cost, and traffic rule cost. This segmentation allows parallel computation of different cost components and enables efficient optimization by focusing on the most critical factors first
Solution Approach 2:
The patent pre-defines cost functions and evaluation criteria before trajectory generation. By establishing the safety, comfort, and rule-following cost models in advance, the system avoids complex real-time calculations during trajectory selection, reducing processing time while maintaining comprehensive evaluation
Data Source
AI summary
In one embodiment, a system generates a plurality of trajectory candidates for an autonomous driving vehicle (ADV) from a starting point to an end point of a particular driving scenario. The system generates a reference trajectory corresponding to the driving scenario based on a current state of the ADV associated with the starting point and an end state of the ADV associated with the end point, where the reference trajectory is associated with an objective. For each of the trajectory candidates, the system compares the trajectory candidate with the reference trajectory to generate an objective cost representing a similarity between the trajectory candidate and the reference trajectory. The system selects one of the trajectory candidates as a target trajectory for driving the ADV based on objective costs of the trajectory candidates.