Object Relevance Screening for Vehicle Path Conflict Planning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicle planning systems face high computational costs when simulating the impact of numerous objects in the environment, making it impractical with onboard computing capabilities, especially in environments with many objects.
Innovation Solution
Implementing an object relevance determination system that identifies and omits irrelevant objects from computations by determining if they will intersect with the vehicle's path or share a road segment, using sensor data and map information to assess relevance based on trajectory predictions and height relative to the vehicle.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If simulations are performed including each detected object, then accuracy of action determination is improved, but computational cost increases beyond onboard capabilities
Solution Approach 1:
The patent extracts and removes irrelevant objects from the simulation process by determining object relevance based on trajectory predictions and spatial relationships. Only relevant objects that may intersect with the vehicle's path are included in simulations, while irrelevant objects are excluded, thereby reducing computational cost while maintaining accuracy for important objects.
Solution Approach 2:
The patent applies different processing quality levels to different objects based on their relevance. Relevant objects receive full simulation processing with detailed impact analysis, while irrelevant objects are quickly identified and excluded from simulations. This localized quality approach ensures high accuracy for critical objects while reducing overall computational burden.
2Reliability
If all detected objects are included in planning computations, then completeness of safety assessment is improved, but processing time increases
Solution Approach 1:
The patent performs preliminary relevance determination before including objects in full planning computations. By predicting object trajectories and assessing potential intersections with the vehicle's path in advance, the system pre-filters the object set to include only those that require detailed safety assessment, thereby reducing processing time while maintaining completeness for relevant objects.
Solution Approach 2:
The patent segments the object processing into two distinct stages: (1) relevance determination stage where objects are quickly filtered based on trajectory predictions and spatial relationships, and (2) detailed simulation stage where only relevant objects undergo comprehensive safety assessment. This segmentation reduces overall processing time while ensuring complete assessment of relevant objects.
3Measurement precision
If computational resources are allocated to simulate all objects, then detection precision of relevant objects is improved, but overall system efficiency decreases
Solution Approach 1:
The patent extracts irrelevant objects from the computational process through relevance determination based on trajectory predictions and spatial filtering. By removing these objects from simulations, computational resources are concentrated on relevant objects, improving detection precision for critical objects while increasing overall system efficiency through reduced processing load.
Solution Approach 2:
The patent changes the parameter of object inclusion from binary (all objects included) to conditional (only relevant objects included) based on trajectory predictions and spatial relationships. This parameter change optimizes resource allocation by directing computational precision toward relevant objects while maintaining system efficiency through exclusion of irrelevant objects.
Data Source
AI summary
A vehicle computing system may implement techniques to determine relevance of objects detected in an environment to a vehicle operating in the environment (e.g., whether an object could potentially impact the vehicle's ability to safely travel). The techniques may include determining an initial location and trajectory associated with a detected object and determining whether the detected object may intersect a path polygon (e.g., planned path with a safety buffer) of the vehicle. A path intersection may include the detected object intersecting the path polygon or sharing a road segment with the vehicle at a substantially similar height as the vehicle (e.g., on a similar plane). Based on a determination that the detected object does not intersect the planned path of the vehicle, the vehicle computing system may determine that the detected object is irrelevant to the vehicle and may disregard the detected object in vehicle control planning considerations.