Genetic Algorithm for Automated Room Object Distribution

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current room and surface planning processes are inefficient and time-consuming, involving multiple technicians and lengthy meetings to optimize space utilization, especially in dynamic environments like factories and offices, where sudden changes require rapid solutions.

Innovation Solution

An automated system using a genetic algorithm processes data on rooms, surfaces, and objects to generate and refine solutions for optimal object distribution, incorporating AI and neural networks to evaluate and recombine solutions based on multiple parameters, facilitating real-time optimization and implementation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If multiple technicians are involved in room planning to consider various aspects (aesthetic, process sequence, supply lines, ventilation, etc.), then the quality and comprehensiveness of the planning solution is improved, but the time required and complexity of the planning process increases significantly

Engineering Contradiction:
Improvecomprehensiveness of planning solutionVSAvoidplanning time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The planning system segments the complex room planning task into distinct modules: data input modules for room/surface characteristics, object requirements, and boundary conditions; a genetic algorithm module for generating and evaluating layouts; and an output module for presenting optimized solutions. Each module handles specific aspects independently, allowing parallel processing and reducing overall planning time while maintaining comprehensive consideration of all requirements.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent replaces the mechanical system of human technicians deliberating in meetings with an automated computer-based genetic algorithm system. The algorithm automatically generates, evaluates, and optimizes room layouts by processing boundary conditions and object requirements, eliminating the need for lengthy human discussions while producing comprehensive solutions that consider all specified constraints.

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

2Reliability

If traditional manual planning methods are used with multiple technicians discussing in meetings, then various aspects can be thoroughly reviewed, but the ability to provide rapid solutions when boundary conditions change suddenly is reduced

Engineering Contradiction:
Improvethoroughness of aspect reviewVSAvoidadaptability to sudden changes
Core Design Contradiction:
ReliabilityVSAdaptability or versatility

Solution Approach 1:

The planning system is designed to be dynamic and adaptable. When boundary conditions change suddenly (e.g., during a pandemic), users can input new conditions into the data input modules, and the genetic algorithm rapidly generates new optimized layouts. The system continuously evaluates layouts against updated constraints and can provide multiple alternative solutions, enabling quick adaptation to changing requirements while maintaining thorough review of all aspects through automated evaluation criteria.

Inventive Principle:
Principle #15Dynamics

3Productivity

If detailed planning is performed to optimize space utilization in enclosed spaces, then the efficiency of space use is improved, but the complexity of the planning process and number of parameters to consider increases

Engineering Contradiction:
Improvespace utilization efficiencyVSAvoidplanning process complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The genetic algorithm system performs self-service optimization by automatically generating and evaluating numerous layout configurations without requiring manual intervention for each evaluation. The algorithm independently processes boundary conditions, evaluates space utilization efficiency for each generated layout, and identifies optimal solutions, thereby achieving detailed optimization of space usage while keeping the user interface simple and the planning process straightforward.

Inventive Principle:
Principle #25Self-service

Data Source

PatentUS20240169106A1System for Planning a Room and/or Surface, and Use of a Genetic Algorithm
Publication Date: 2024.05.23 SIEMENS AG

AI summary

Various embodiments of the teachings herein include a system for automated distribution of a number of predetermined objects in a room and/or on a surface. The system may include: a module for inputting and/or generating data; a module for outputting and/or presenting solutions; and interfaces for transmitting the data to a storage unit connected to a processor configured to carry out a genetic algorithm. The genetic algorithm uses the data and initially provides a generation of solutions. The processor evaluates and selects among the solutions based on their progressiveness then recombines the selected solutions. The procedure repeats and provides the most progressive solutions to an artificial intelligence and/or to a neural network which uses the solutions to generate new rules and transfers the most progressive solutions to the processor for refinement of the algorithm.