Layered Simulation Variables for Deterministic AV Scenario Testing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing simulation systems for autonomous vehicles lack expressiveness and efficiency in testing various scenarios without compromising accuracy, speed, and determinism, and require user intervention to change simulation parameters.
Innovation Solution
A variable system that allows for the encoding of simulation variables in different layers, enabling override and refinement at runtime without altering underlying software components, facilitating deterministic sampling and noise injection for more exhaustive testing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If simulation parameters are changed to test various scenarios, then testing coverage and expressiveness are improved, but system complexity and user intervention requirements increase
Solution Approach 1:
The simulation system is segmented into multiple layers (base layer, override layer, refinement layer) that can be independently managed. Each layer handles specific parameters, allowing complex simulations to be broken down into manageable segments without increasing overall system complexity.
Solution Approach 2:
Parameter specifications are predetermined and organized in layered structures before simulation execution. The base layer establishes default parameters, while override and refinement layers pre-define modifications, eliminating the need for user intervention during runtime and reducing operational complexity.
2Adaptability or versatility
If simulation parameters are changed at runtime, then testing flexibility is improved, but software component modification requirements increase
Solution Approach 1:
The system adds a temporal dimension to parameter management by organizing parameters across multiple layers that are resolved at different stages of simulation execution. This layered temporal structure allows runtime parameter changes without modifying software components, as parameters are injected through the layered system rather than hard-coded.
Solution Approach 2:
The layered parameter system acts as an intermediary between the software components and the simulation parameters. Software components query parameters through the layered system, which resolves the appropriate values from base, override, or refinement layers, eliminating the need to modify software components when parameters change.
3Measurement precision
If deterministic sampling is implemented, then simulation accuracy is improved, but processing time and computational resources increase
Solution Approach 1:
Parameter specifications including deterministic sampling rules are predetermined and organized in the layered structure before simulation execution. The system pre-establishes which parameters should be sampled deterministically and with what precision, allowing accurate simulations without real-time computational overhead during execution.
Data Source
AI summary
Embodiments of a variable system for simulating the operation of an autonomous system, such as an autonomous vehicle, are disclosed. A layered approach for defining variables can allow changing the specification of those variables under the rules of override and refinement, while leaving the software components that query those variables at runtime unaffected. The variable system can facilitate, among others, deterministic sampling of variables, simulation variations, noise injection, and realistic message timing. These applications can make the simulator more expressive and more powerful by virtue of being able to test the same scenario under many different conditions. As a result, more exhaustive testing can be performed without requiring user intervention and without having to change the individual software components of the simulator.