Road User Trajectory End-Point Evaluation With Confidence Scoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing trajectory prediction methods for autonomous vehicles face challenges in efficiently generating and ranking multiple feasible trajectories for road users, requiring high computational effort and lacking reliable assessment of trajectory reliability.
Innovation Solution
A method that determines trajectory end points for road users using extracted characteristics, evaluates these end points with a classification to provide confidence scores, and utilizes a generative adversarial network for training to improve trajectory prediction efficiency and reliability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple future trajectories are generated for road users, then trajectory prediction completeness is improved, but computational effort increases
Solution Approach 1:
The patent segments the trajectory prediction task into two parts: generating multiple future trajectories and then ranking/evaluating them. This segmentation allows the system to maintain comprehensive trajectory coverage while managing computational effort through efficient evaluation metrics and confidence scoring mechanisms.
Solution Approach 2:
The patent replaces complex mechanical simulation of all possible trajectories with machine learning-based confidence scoring and evaluation. The system uses trained models to assess trajectory likelihood and reliability, substituting computationally intensive simulation with faster probabilistic evaluation.
2Measurement precision
If entity-based models are used to encode road users and environment, then trajectory prediction accuracy is improved, but processing time increases with number of road users
Solution Approach 1:
The patent applies preliminary action by pre-processing and encoding road user and environment data into structured representations before trajectory generation. This preliminary encoding organizes data in a way that enables faster processing during actual trajectory prediction, reducing real-time computational burden.
Solution Approach 2:
The patent changes parameters by transforming detailed entity data into compressed feature representations and confidence scores. This parameter transformation maintains essential information for accurate prediction while reducing data dimensionality and processing requirements.
3Reliability
If grid maps with detailed environment information are used, then trajectory prediction reliability is improved, but memory requirements increase
Solution Approach 1:
The patent extracts only the essential features and characteristics from detailed grid map representations that are necessary for trajectory prediction. By taking out and retaining only critical environmental information, the system maintains prediction reliability while reducing memory consumption.
Solution Approach 2:
The patent applies partial action by using a simplified representation of the environment that captures sufficient information for reliable trajectory prediction without storing complete detailed grid maps. The system processes only the necessary portion of environmental data required for the prediction task.
Data Source
AI summary
A computer implemented method for determining and evaluating a trajectory of a road user is provided. Input data associated with a state of movement and with an environment of the road user is received. Characteristics related to the road user are extracted from the input data. One or more trajectory end points are determined for the road user by using extracted characteristics. For each of the trajectory end points, a respective trajectory associated with one of the trajectory end points is determined by using the associated trajectory end point and the extracted characteristics, and the respective trajectory of the road user is evaluated by using a classification which relies on the extracted characteristics to provide a confidence score for each trajectory associated with one of the trajectory end points.