Vehicle Driving Control Using Deep Learning for Friction Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional autonomous driving vehicles struggle to accurately analyze the influence of factors such as air resistance and friction during travel, which hinders effective control and safety.

Innovation Solution

An information processing device utilizing deep learning for multivariate analysis to infer control variables from various vehicle-related information, enabling precise driving control and strategy updates in real-time.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If conventional autonomous driving vehicles use traditional control methods, then the device complexity is low, but the measurement precision of factors such as air resistance and friction is insufficient

Engineering Contradiction:
Improveanalysis accuracy of air resistance and frictionVSAvoidcontrol system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces traditional mechanical control methods with an information processing device that uses deep learning algorithms. The inference unit performs multivariate analysis on sensor data to calculate control variables, substituting physical measurement methods with computational analysis to achieve higher precision in analyzing air resistance and friction factors.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent changes the parameters of the control system by introducing multiple sensor types (acceleration sensor, angular acceleration sensor, gyro sensor) and using deep learning to process these parameters. The inference unit calculates control variables based on multiple input parameters simultaneously, enabling precise analysis of complex factors like air resistance and friction that cannot be measured by single parameters.

Inventive Principle:
Principle #35Parameter changes

2Productivity

If the information acquisition unit acquires information in units of prescribed cycles, then the processing speed is improved, but the response time to rapid changes may be delayed

Engineering Contradiction:
Improveprocessing speedVSAvoidresponse delay
Core Design Contradiction:
ProductivityVSLoss of time

Solution Approach 1:

The patent implements periodic action by acquiring information in units of prescribed cycles through the information acquisition unit. The inference unit processes data at regular intervals to calculate control variables, balancing processing speed with system stability. This periodic processing ensures high productivity while maintaining acceptable response times for normal operating conditions.

Inventive Principle:
Principle #19Periodic action

3Measurement precision

If deep learning multivariate analysis is used to infer control variables, then the control precision is improved, but the use of energy increases

Engineering Contradiction:
Improvecontrol variable accuracyVSAvoidenergy consumption of information processing device
Core Design Contradiction:
Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent applies partial action by using deep learning multivariate analysis selectively for inferring control variables that require high precision (such as those affecting air resistance and friction), rather than applying it to all control parameters. This selective approach achieves necessary control precision while reducing overall energy consumption compared to universal deep learning application.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentEP4610128A1Information processing device, vehicle, information processing method, and program
Publication Date: 2025.09.03 SOFTBANK GROUP CORP
  • EP4610128A1 patent drawingFigure 1
  • EP4610128A1 patent drawingFigure 2
  • EP4610128A1 patent drawingFigure 3

AI summary

An information processing device of the disclosure includes an information acquisition unit that is capable of acquiring plurality information related to a vehicle, an inference unit that calculates index values from the plurality information acquired by the information acquisition unit, and uses deep learning to infer plural control variables from the index values, and a driving control unit that executes driving control of the vehicle on the basis of the plural control variables.