Simulated Driving Test Parameter Tuning for Critical Interactions

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing simulated driving tests for autonomous vehicles often fail to capture critical interactions due to inappropriate parameter settings, leading to inefficient and resource-intensive trial-and-error processes, and lack of objective evaluation of AV software performance.

Innovation Solution

A parameter tuning system that uses criticality scores and optimization algorithms to identify optimal parameter values for generating simulated driving tests, ensuring they capture intended scenarios and critical interactions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional simulated driving tests are generated with fixed parameter settings, then the simulation process is simple to implement, but the tests fail to capture critical interactions and AV software performance cannot be properly evaluated

Engineering Contradiction:

Improveability to capture critical interactionsVSAvoidparameter tuning system complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system dynamically adjusts simulation parameters based on criticality scores and optimization algorithms. Parameters such as scenario frequency, severity, and AV response characteristics are modified to maximize the capture of critical interactions while maintaining system manageability through automated tuning.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The system implements feedback loops where simulation results are analyzed to generate criticality scores, which then feed back into parameter adjustment. This closed-loop approach allows the system to learn from previous simulations and continuously improve its ability to capture critical interactions without manual intervention.

Inventive Principle:

Principle #23Feedback

2Measurement precision

If multiple parameter variations are tested through trial-and-error, then optimal parameters may be found, but the process is resource-intensive and time-consuming

Engineering Contradiction:

Improveparameter optimization accuracyVSAvoidparameter tuning time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary analysis by establishing parameter ranges and criticality criteria before running simulations. Optimization algorithms pre-process the parameter space to identify promising regions, allowing the system to achieve high measurement precision without exhaustive trial-and-error testing.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent replaces manual trial-and-error parameter tuning with automated optimization algorithms. These algorithms systematically explore the parameter space using computational methods, achieving precise parameter identification much faster than human operators could through repeated testing and adjustment.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Reliability

If comprehensive simulated driving tests are generated to cover all scenarios, then AV software can be thoroughly evaluated, but computational resources are excessively consumed

Engineering Contradiction:

Improvesoftware evaluation completenessVSAvoidcomputational resource consumption

Core Design Contradiction:

ReliabilityVSUse of energy by moving object

Solution Approach 1:

The system applies different levels of simulation detail and resource allocation to different scenario types based on their criticality. High-criticality scenarios receive more comprehensive testing resources, while low-criticality scenarios use simplified models, optimizing the overall balance between evaluation completeness and computational efficiency.

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The optimization algorithms identify and focus computational resources on the most critical parameter combinations and scenario variations. Rather than exhaustively testing all possible scenarios, the system performs partial action on high-priority areas, achieving reliable software evaluation with reduced computational overhead.

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS12509116B2Tuning parameters used for generating simulated driving tests

Publication Date: 2025.12.30 GM CRUISE HOLDINGS LLC

AI summary

Tools can generate simulated driving tests that allow a same driving scenario to be tested at different geographical locations and with different arrangements of simulated road user(s) and/or simulated road objects. Numerous parameters used by these tools for creating the simulated driving tests can impact the usefulness of the simulated driving tests. If the parameters are not set appropriately, the simulated driving tests may not result in critical interactions that would enable accurate assessment of vehicle software. To alleviate some of these concerns, a parameter tuning system can find optimal value ranges of parameters based on criticality scores of generated simulated driving tests, so that better simulated driving tests can be obtained.