URU Trajectory Prediction Using Drivable Area Exit Points
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in predicting the trajectories of uncertain road users in urban environments due to the complexity of understanding their behavior, which is influenced by demographics, traffic dynamics, and environmental conditions, leading to difficulties in identifying meaningful entry and exit points within drivable areas.
Innovation Solution
The system generates trajectories for uncertain road users by identifying a plurality of goal points within a drivable area, receiving perception information, and selecting a target exit point based on a computed score using a loss function, allowing the autonomous vehicle to navigate and avoid collisions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If the autonomous vehicle uses simplified drivable area representation to identify entry and exit points, then the navigation decision process is facilitated, but the ability to infer meaningful information about smaller discrete target locations is lost
Solution Approach 1:
The drivable area is segmented into multiple discrete target locations along the boundary, transforming the continuous boundary into discrete inferable points. This allows the system to maintain simplified representation while recovering the ability to identify specific target locations for trajectory prediction
Solution Approach 2:
Different regions of the drivable area boundary are assigned different qualities based on their inferability. The system identifies specific segments of the boundary where target location information can be meaningfully inferred, applying local refinement to the otherwise simplified representation
2Measurement precision
If the autonomous vehicle considers multiple goal points for URU trajectory prediction, then the prediction accuracy is improved, but the computational complexity increases
Solution Approach 1:
The set of goal points is segmented into discrete target locations along the drivable area boundary. This segmentation allows the system to consider multiple potential destinations without overwhelming computational complexity, as each segment represents a manageable discrete option
Solution Approach 2:
The system considers a subset of goal points that are most relevant to the current situation rather than all possible boundary points. This partial action approach provides sufficient prediction accuracy while reducing computational burden by focusing on the most probable exit locations
Data Source
AI summary
Methods and systems for controlling navigation of a vehicle are disclosed. The system will first identify a plurality of goal points corresponding to a drivable area that a vehicle is traversing or will traverse, where the plurality of goal points are potential targets that an uncertain road user (URU) within the drivable area can use to exit the drivable area. The system will then receive perception information relating to the URU within the drivable area, and identify a target exit point from the plurality goal points based on a score. The score is computed based on the received perception information and a loss function. The system will generate a trajectory of the URU from a current position of the URU to the target exit point, and control navigation of the vehicle to avoid collision with the URU.