Autonomous Driving Scenario Editing for Relative Vehicle Actions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current autonomous driving simulation systems lack the ability to define the relative actions of non-ego vehicles in relation to ego vehicles, making it difficult to accurately simulate scenarios such as collisions and rotations, which hinders the testing and verification of autonomous vehicle software.
Innovation Solution
A method and apparatus that allow users to set the location and actions of non-ego vehicles relative to ego vehicles at specific time points, including user-defined velocities and rotations, and trigger conditions to define target actions based on these relationships, enabling more precise simulation scenarios.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If individual actor actions are defined separately in related art scenario editors, then the scenario creation process is simple, but the relative timing and positioning accuracy between actors deteriorates
Solution Approach 1:
The scenario definition is segmented into multiple time points (first time point, second time point, third time point) with distinct parameters for each. This allows precise control of relative timing and positioning by defining actor locations and actions at discrete temporal segments rather than continuously, resolving the contradiction between measurement precision and complexity.
Solution Approach 2:
The patent introduces a temporal dimension by defining scenario parameters at multiple discrete time points rather than as static definitions. This dimensional approach enables accurate representation of relative timing and positioning changes over time, transforming the scenario from a spatial-only definition to a spatio-temporal definition.
2Manufacturing precision
If relative definitions between actors are not supported, then the scenario editor remains simple to operate, but the simulation accuracy of relative collision timing and distance deteriorates
Solution Approach 1:
The patent introduces an intermediary processing layer that automatically calculates relative parameters (relative collision timing, relative distance, relative rotation) between actors based on their individual definitions at multiple time points. This intermediary computation layer maintains ease of operation by allowing simple individual actor definitions while achieving high simulation accuracy through automated relative parameter calculation.
Solution Approach 2:
The system performs preliminary calculations of relative parameters between actors during the scenario definition phase. By pre-computing relative collision timing, relative distance, and relative rotation at multiple time points, the system ensures simulation accuracy is built into the scenario definition itself, eliminating the need for complex manual relative definitions while maintaining operational simplicity.
3Adaptability or versatility
If only start and end points are defined for actors, then the scenario definition is straightforward, but the ability to represent complex relative movements deteriorates
Solution Approach 1:
The actor movement is segmented into discrete time points (first, second, and third time points) with specific location and action parameters defined at each segment. This segmentation enables representation of complex relative movements by breaking down continuous motion into controllable temporal segments, allowing precise definition of cut-in maneuvers, collision timing, and positioning changes.
Solution Approach 2:
The patent transforms static start-end point definitions into dynamic multi-time-point definitions. By allowing actor locations and actions to be defined at multiple discrete time points with temporal relationships, the system enables dynamic representation of complex relative movements such as cut-in maneuvers and collision scenarios, adapting the definition structure to match the temporal dynamics of the scenario.
Data Source
AI summary
A method and apparatus for creating a scenario for an autonomous driving simulation. The method includes setting, based on a first user input, a location of a first target object at each of a first plurality time points on a map for a simulation scenario, the first plurality of time points comprising a first time point and a third time point; and defining, based on a second user input, an action of a second target object that is different from the first target object in relation to at least one of the set locations of the first target object.