Route-Guided Autonomous Driving Software Training for Faster Updates

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Autonomous driving systems face challenges in efficiently processing massive and complex data and software due to the lack of standardized driving situations and environments, leading to difficulties in providing appropriate software and data updates.

Innovation Solution

A method and apparatus for controlling autonomous driving by searching and training software linked with route guidance, which includes generating route information, searching and selecting driving information, training driving software, and distributing it to the moving object, thereby optimizing the interworking with route control.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If autonomous driving systems process massive and complex data and software through conventional methods, then comprehensive driving coverage is achieved, but time and computing resources required for updates increase significantly

Engineering Contradiction:

Improvecomprehensive driving coverageVSAvoidupdate time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The patent segments the autonomous driving software update process into multiple independent modules: route guidance module, driving data module, software training module, and distribution module. Each module processes specific aspects of driving information independently, allowing parallel processing and reducing overall update time while maintaining comprehensive coverage.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system performs preliminary actions by pre-processing and pre-training driving software in advance using historical driving data and simulation environments. This prepares the software updates before they are needed, so that when actual updates are required, the processing time is significantly reduced while maintaining reliability.

Inventive Principle:

Principle #10Preliminary action

2Reliability

If autonomous driving systems process massive and complex data and software through conventional methods, then comprehensive driving coverage is achieved, but computing resources required for updates increase significantly

Engineering Contradiction:

Improvecomprehensive driving coverageVSAvoidcomputing resources

Core Design Contradiction:

ReliabilityVSUse of energy by moving object

Solution Approach 1:

The patent divides computing tasks into segmented modules that can be processed independently and distributed across different computing resources. This segmentation allows for optimized resource allocation, reducing overall computing resource consumption while maintaining comprehensive driving coverage through coordinated module execution.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces intermediary components such as data preprocessing layers and simulation environments that act as mediators between raw driving data and the core processing systems. These intermediaries reduce the computational burden on main processing systems by filtering, transforming, and preparing data in advance, thereby reducing computing resource requirements.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Adaptability or versatility

If autonomous driving systems lack standardized processing methods, then flexibility in handling diverse driving scenarios is maintained, but efficiency in processing massive data and software decreases

Engineering Contradiction:

Improvehandling diverse driving scenariosVSAvoidprocessing efficiency

Core Design Contradiction:

Adaptability or versatilityVSProductivity

Solution Approach 1:

The patent implements universal processing modules that can handle multiple types of driving scenarios through standardized interfaces and data structures. These multi-functional modules maintain adaptability to diverse scenarios while improving processing efficiency through consistent, reusable code patterns and standardized workflows.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system uses parameter changes to maintain adaptability while improving efficiency. By adjusting processing parameters such as data sampling rates, training iteration counts, and simulation complexity levels based on the specific driving scenario, the system optimizes processing efficiency for each scenario type while maintaining the flexibility to handle diverse situations.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS12516947B2Method and system for controlling autonomous driving by search and train of autonomous driving software linked with route guidance

Publication Date: 2026.01.06 KAKAO MOBILITY CORP

AI summary

Disclosed herein a method and system for controlling autonomous driving by search and train of autonomous driving software linked with route guidance.The method includes: generating route information based on a route request of a moving object and associated information according to the route request, searching and selecting, based on the route information and the associated information, driving information including driving data and driving software, the driving data being associated with recognition, determination and control of autonomous driving for a route and driving control, training the driving software by using the route request, the associated information and the driving data, and distributing the driving information to the moving object and executing driving control of the moving object based on the driving information.