Simulation Run Change Proposals for Error-Aware Validation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Simulating complex traffic scenarios in a resource-efficient and cost-effective manner, particularly in the context of validating driver assistance systems and autonomous driving algorithms, is challenging due to the need for numerous simulation runs and the high computational intensity.

Innovation Solution

A computer-implemented method generates change proposals for simulation runs based on error descriptions from previous simulations, identifying and adjusting parameter sets in not yet completed simulations to avoid errors, thereby reducing the number of necessary runs.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If numerous simulation runs are performed to cover the parameter space of complex traffic scenarios, then the validation completeness and reliability improve, but the computational resources and time required increase significantly

Engineering Contradiction:
Improvevalidation completenessVSAvoidcomputational resources
Core Design Contradiction:
ReliabilityVSUse of energy by moving object

Solution Approach 1:

The system performs preliminary analysis of simulation parameters and error patterns before executing full simulation runs. By identifying critical parameter combinations and potential error sources in advance, the system can prioritize which simulations to run and which to skip, reducing computational resources while maintaining validation completeness.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system continuously monitors simulation results and error descriptions, using this feedback to dynamically adjust the simulation strategy. When errors are detected in certain parameter ranges, the system adapts by focusing subsequent simulations on affected areas, avoiding redundant runs in already-validated regions, thus optimizing resource utilization.

Inventive Principle:
Principle #23Feedback

2Reliability

If the number of simulation runs is increased to cover all parameter variations, then the detection of errors improves, but the time required for validation increases

Engineering Contradiction:
Improveerror detection capabilityVSAvoidvalidation time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary error analysis by examining parameter sets and identifying those likely to produce errors based on historical data and parameter sensitivity analysis. This allows the system to focus validation efforts on high-risk parameter combinations, achieving effective error detection with fewer simulation runs.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system dynamically adjusts simulation parameters based on detected error patterns. When specific parameter combinations are identified as error-prone, the system modifies subsequent simulation parameter selections to target these areas, improving error detection efficiency without requiring exhaustive parameter space coverage.

Inventive Principle:
Principle #35Parameter changes

3Loss of information

If simulation runs are performed with comprehensive parameter coverage, then the insight gained from simulations improves, but the cost and resource intensity increase

Engineering Contradiction:
Improveinsight qualityVSAvoidresource intensity
Core Design Contradiction:
Loss of informationVSLoss of energy

Solution Approach 1:

The system performs preliminary analysis to identify critical parameter combinations that provide the most insight into system behavior and potential errors. By focusing simulations on these high-value parameter sets, the system maintains high insight quality while reducing the overall number of simulations required.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system applies different simulation strategies to different parameter regions based on their importance and error-risk characteristics. High-priority parameter regions receive more detailed simulation coverage, while low-priority regions use reduced sampling, optimizing the balance between insight quality and resource consumption.

Inventive Principle:
Principle #3Local quality

Data Source

PatentEP4607398A1Computer-implemented method for generating a modification suggestion for a simulation run and corresponding device for data processing
Publication Date: 2025.08.27 DSPACE SE & CO KG
  • EP4607398A1 patent drawingFigure 1
  • EP4607398A1 patent drawing
  • EP4607398A1 patent drawing

AI summary

The invention relates to a computer-implemented method for generating a change proposal for at least one simulation run of a simulation comprising a plurality of simulation runs, with the steps: - receiving an error description of a simulation run of a first simulation, wherein the simulation run whose error description is received is based on a first parameter set comprising a plurality of parameter values, - identifying not yet completed simulation runs of the first simulation or of a second simulation with a parameter set that matches the first parameter set in at least one parameter value, - generating the change proposal for the identified simulation runs taking into account the received error description.Furthermore, the invention relates to a device for data processing comprising means for carrying out the above method, a computer program product and a corresponding computer-readable data carrier.