Simulated Driving Scenario Evaluation for Accurate Operator Assessment

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing systems lack an effective method to assess driving performance of vehicle operators, particularly in simulated driving scenarios, which are crucial for training and evaluating both human and autonomous driving algorithms.

Innovation Solution

A system is developed that utilizes a simulation engine to simulate real-life and hypothetical driving situations, incorporating vehicle events detected by individual vehicles within a fleet, and processes data through sensors and processors to evaluate operator performance, using simulation scenarios to determine metrics and provide feedback.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If real-life driving situations are simulated to assess operator performance, then measurement precision is improved, but device complexity increases

Engineering Contradiction:
Improvedriving performance assessment accuracyVSAvoidsimulation system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent creates virtual copies of real driving scenarios by capturing actual driving data (sensor readings, vehicle states, environmental conditions) and reconstructing them in a simulation environment. This allows realistic performance assessment without requiring physical test tracks or real-world testing, thus improving measurement precision while managing system complexity through digital replication.

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The system performs preliminary data collection and scenario reconstruction before actual performance assessment. By pre-processing real driving situations into structured simulation scenarios with defined ground truth, the system establishes a ready-to-use test bed that simplifies the assessment process and improves measurement accuracy without requiring complex real-time processing during evaluation.

Inventive Principle:
Principle #10Preliminary action

2Measurement precision

If comprehensive simulation scenarios are created based on vehicle events, then measurement precision is improved, but loss of time increases

Engineering Contradiction:
Improveperformance metric accuracyVSAvoidsimulation execution time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent divides comprehensive driving scenarios into discrete, manageable segments based on specific vehicle events (e.g., braking events, lane changes, intersections). Each segment can be independently simulated and evaluated, allowing the system to assess performance across multiple focused scenarios rather than requiring one exhaustive simulation, thus improving measurement precision while reducing total execution time.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system focuses simulation resources on critical driving events and key performance metrics rather than attempting to simulate every aspect of driving behavior. By concentrating computational effort on the most important scenarios and metrics, the system achieves high measurement precision for essential performance indicators without the prohibitive time cost of comprehensive full-fidelity simulation.

Inventive Principle:
Principle #16Partial or excessive action

3Adaptability or versatility

If multiple vehicle operators are evaluated using the same simulation framework, then adaptability is improved, but device complexity increases

Engineering Contradiction:
Improvemulti-operator evaluation capabilityVSAvoidevaluation system complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent designs a universal simulation framework that can evaluate multiple types of vehicle operators (human drivers, autonomous vehicle algorithms, semi-autonomous systems) using the same core infrastructure. The system accommodates different operator models and performance metrics through configurable parameters and interfaces, enabling multi-operator assessment without requiring separate evaluation systems for each operator type, thus improving adaptability while managing complexity through standardized architecture.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentEP3818422B1Systems and methods for comparing driving performance for simulated driving
Publication Date: 2025.08.13 SMARTDRIVE SYSTEMS INC
  • EP3818422B1 patent drawingFigure 1
  • EP3818422B1 patent drawingFigure 2
  • EP3818422B1 patent drawingFigure 3

AI summary

This disclosure relates to a system that determines driving performance by a vehicle operator for simulated driving of a simulated vehicle in a simulation engine. Individual vehicle event scenarios correspond to vehicle events. Individual simulation scenarios correspond to individual vehicle event scenarios. A vehicle operator, e.g., an autonomous driving algorithm, operates the simulated vehicle in the simulation engine for a set of simulation scenarios. One or more metrics quantify the performance of the vehicle operator based on simulated results.