Vehicle Driving Evaluation Architecture for Traceable Sensor Causality

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing vehicle driving systems face challenges in tracing the causal relationship between sensor data and strategic guidelines, particularly when using artificial intelligence, leading to difficulties in verifying the planned driving actions.

Innovation Solution

A processing system that includes multiple individual evaluation units, an integration evaluation unit, and a driving planning unit, which evaluates sensor data from different sources individually and integrates the results to plan driving actions, enhancing traceability.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If sensor data from multiple sensors is evaluated together in a single integrated evaluation, then the driving action planning is simplified, but the traceability of causal relationships between sensor data and strategic guidelines deteriorates

Engineering Contradiction:

Improveevaluation system structureVSAvoidtraceability of causal relationship

Core Design Contradiction:

Device complexityVSLoss of information

Solution Approach 1:

The evaluation system is segmented into multiple individual evaluation units, each responsible for evaluating sensor data from a specific sensor against strategic guidelines. This segmentation preserves traceability by maintaining distinct evaluation paths for each sensor while still contributing to the overall driving action planning process.

Inventive Principle:

Principle #1Segmentation

2Loss of information

If individual evaluation units process sensor data separately, then traceability of causal relationships is improved, but the integration complexity and processing time increase

Engineering Contradiction:

Improvetraceability of causal relationshipVSAvoidprocessing time

Core Design Contradiction:

Loss of informationVSLoss of time

Solution Approach 1:

Individual evaluation units perform preliminary evaluations of sensor data against strategic guidelines in parallel, generating intermediate evaluation results before integration. This preliminary action allows traceability to be maintained at the individual sensor level while enabling efficient parallel processing that reduces overall computation time.

Inventive Principle:

Principle #10Preliminary action

3Measurement precision

If artificial intelligence is used for strategic guideline evaluation, then the driving action planning accuracy is improved, but the verifiability and traceability of the evaluation process deteriorates

Engineering Contradiction:

Improvedriving action planning accuracyVSAvoidverifiability of evaluation process

Core Design Contradiction:

Measurement precisionVSLoss of information

Solution Approach 1:

The system introduces intermediate evaluation results as a mediator between the AI-based individual evaluation units and the final integrated evaluation. These intermediate results provide verifiable traceable information about how each sensor's data contributes to the overall driving action planning, making the AI process transparent and checkable.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS20250282380A1Processing system and method

Publication Date: 2025.09.11 DENSO CORP

AI summary

A processing system that executes a process related to driving of a vehicle is provided. The processing system includes: a plurality of individual evaluation units that output individual evaluation results related to a strategic guideline based on sensor data, in which at least some of output sources of the sensor data are different from each other; an integration evaluation unit that integrates each of the individual evaluation results and outputs an evaluation result after integration; and a driving planning unit that plans a driving action based on the evaluation result after integration.