Predictive SoC Cooling Control for Autonomous Driving Vehicles

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Heat generation in systems on chip (SoC) for autonomous driving poses challenges during advanced arithmetic processing, leading to difficulties in maintaining optimal operating temperatures for reliable vehicle control.

Innovation Solution

A cooling execution device that predicts the operation of the SoC based on sensor data and initiates cooling measures, utilizing machine learning models to anticipate temperature changes and adjust cooling methods accordingly, including air, water, and liquid nitrogen cooling.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If advanced arithmetic processing is performed in the SoC for autonomous driving, then the autonomous driving function is improved, but heat generation increases causing temperature to rise

Engineering Contradiction:
Improveautonomous driving processing capabilityVSAvoidSoC operating temperature
Core Design Contradiction:
ProductivityVSTemperature

Solution Approach 1:

The cooling execution device predicts future operation status of the SoC based on current detection results and initiates cooling measures in advance before the temperature actually rises. The prediction unit uses machine learning models to forecast temperature changes, and the execution unit starts cooling operations proactively, preventing overheating before it occurs during intensive autonomous driving processing.

Inventive Principle:
Principle #10Preliminary action

2Temperature

If cooling measures are continuously applied to the SoC, then temperature control is improved, but energy consumption increases

Engineering Contradiction:
ImproveSoC temperature controlVSAvoidcooling system energy consumption
Core Design Contradiction:
TemperatureVSUse of energy by moving object

Solution Approach 1:

The cooling execution device applies cooling measures periodically rather than continuously. The execution unit activates cooling based on predicted temperature changes and deactivates it when temperature stabilizes or the vehicle stops. This periodic cooling approach maintains effective temperature control while significantly reducing energy consumption compared to continuous cooling operation.

Inventive Principle:
Principle #19Periodic action

3Temperature

If multiple cooling methods (air, water, liquid nitrogen) are available, then temperature control flexibility is improved, but device complexity increases

Engineering Contradiction:
Improvetemperature control flexibilityVSAvoidcooling system complexity
Core Design Contradiction:
TemperatureVSDevice complexity

Solution Approach 1:

The cooling execution device dynamically selects and switches between different cooling methods based on real-time temperature conditions and processing load. The execution unit chooses from air cooling, water cooling, or liquid nitrogen cooling depending on the situation, making the cooling system adaptable to varying thermal demands without requiring all cooling components to operate simultaneously, thus managing complexity through dynamic rather than static configuration.

Inventive Principle:
Principle #15Dynamics

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

The solution effectively maintains optimal operating temperatures for the SoC, enabling advanced arithmetic operations and ensuring reliable autonomous driving by preventing overheating.

Implementation Method 1

a cooling unit that cools the SoC

Methodology Applied
Scientific EffectHeat transfer: Conduction (thermal)

Data Source

PatentEP4610138A1Cooling execution device, cooling execution method, cooling execution program, and vehicle
Publication Date: 2025.09.03 SOFTBANK GROUP CORP
  • EP4610138A1 patent drawingFigure 1
  • EP4610138A1 patent drawingFigure 2
  • EP4610138A1 patent drawingFigure 3

AI summary

The cooling execution device includes: an acquisition unit that acquires a detection result of detecting an object related to operation of a control device mounted on a vehicle, the control device controlling autonomous driving of the vehicle; and an execution unit that performs cooling of the control device based on the detection result.