Generative design pipeline for urban and neighborhood planning

Patent metadata

Field	Value
Publication number	US-2019147116-A1
Application number	US-201816181224-A
Country	US
Kind code	A1
Filing date	Nov 5, 2018
Priority date	Nov 10, 2017
Publication date	May 16, 2019
Grant date	—

Abstract

An urban design pipeline automatically generates design options for an urban design project. The urban design pipeline includes a geometry engine and an evaluation engine. The geometry engine analyzes design criteria and design objectives associated with the urban design project and then generates numerous candidate designs that meet the design criteria and optimize the design objectives to varying degrees. The evaluation engine evaluates each candidate design to generate a set of metrics. The geometry engine modifies the candidate designs based on corresponding metrics to generate candidate designs that better meet the design criteria and more effectively achieve the design objectives.

First claim

What is claimed is:

1 . A computer-implemented method for generating design options for an urban design project, the method comprising:
generating a first geometrical mesh for a first candidate design based on a first design criterion associated with a first region of land; subdividing the first geometrical mesh to generate a first plurality of neighborhoods; populating the first plurality of neighborhoods with a first set of dwelling units; generating a first metric for the first candidate design based on a first objective function; modifying the first candidate design based on the first metric to generate a first design option; and determining that a second metric generated for the first design option based on the first objective function exceeds the first metric, indicating that the first design option is a higher ranked design than the first candidate design.

2 . The computer-implemented method of claim 1 , wherein subdividing the first geometrical mesh comprises projecting at least one line segment across the first geometrical mesh to generate a first neighborhood included in the first plurality of neighborhoods and a second neighborhood included in the first plurality of neighborhoods, and further comprising designating the at least one line segment as a roadway for accessing both the first neighborhood and the second neighborhood.

3 . The computer-implemented method of claim 1 , wherein populating the first plurality of neighborhoods comprises:
determining that a first neighborhood included in the first plurality of neighborhoods has an area that is greater than a minimum area; identifying a first subregion within the first neighborhood; assigning the first subregion to a first dwelling unit included in the first set of dwelling units; and assigning a first dwelling unit type to the first dwelling unit.

4 . The computer-implemented method of claim 1 , wherein generating the first metric comprises determining an estimated amount of solar energy collected by the first set of dwelling units.

5 . The computer-implemented method of claim 1 , wherein generating the first metric comprises:
determining a first length associated with a first line of sight emanating from a first dwelling unit included in the first set of dwelling units; determining a second length associated with a second line of sight emanating from a second dwelling unit included in the first set of dwelling units; combining the first line of sight length with the second line of sight length to generate at least a portion of the first metric.

6 . The computer-implemented method of claim 1 , wherein generating the first metric comprises:
determining a first yard size associated with a first dwelling unit included in the first set of dwelling units; determining a second yard size associated with a second dwelling unit included in the first set of dwelling units; and combining the first yard size with the second yard size to generate at least a portion of the first metric.

7 . The computer-implemented method of claim 1 , wherein generating the first metric comprises:
determining that a first neighborhood included in the first plurality of neighborhoods includes more dwelling units than a second neighborhood included in the first plurality of neighborhoods; and computing a number of dwelling units included in the first neighborhood to generate at least a portion of the first metric, wherein the number of dwelling units included in the first neighborhood indicates a degree of variability in neighborhoods included in the first candidate design.

8 . The computer-implemented method of claim 1 , wherein generating the first metric comprises:
determining that a first number of dwelling units included in the first set of dwelling units are assigned a first dwelling unit type; and determining a difference between the first number of dwelling units and a recommended number of dwelling units that should be assigned the first dwelling unit type to generate at least a portion of the first metric, wherein the difference between the first number of dwelling units and a recommended number of dwelling units indicates a degree to which the first candidate design meets a second design criterion.

9 . The computer-implemented method of claim 1 , wherein generating the first metric comprises:
determining a first construction cost associated with a first dwelling unit included in the first set of dwelling units; determining a second construction cost associated with a second dwelling unit included in the first set of dwelling units; and combining the first construction cost with the second construction cost to generate at least a portion of the first metric.

10 . The computer-implemented method of claim 1 , wherein generating the first metric comprises:
determining a first estimated revenue associated with a first dwelling unit included in the first set of dwelling units; determining a first estimated profit associated with the first dwelling unit based on the first estimated revenue and a first construction cost associated with the first dwelling unit; determining a second estimated revenue associated with a second dwelling unit included in the first set of dwelling units; determining a second estimated profit associated with the second dwelling unit based on the second estimated revenue and a second construction cost associated with the second dwelling unit; combining the first estimated profit with the second estimated profit to generate at least a portion of the first metric.

11 . A non-transitory computer-readable medium storing program instructions that, when executed by one or more processors, causes the one or more processors to generate design options for an urban design project by performing the steps of:
generating a first geometrical mesh for a first candidate design based on a first design criterion associated with a first region of land; subdividing the first geometrical mesh to generate a first plurality of neighborhoods; populating the first plurality of neighborhoods with a first set of dwelling units; generating a first metric for the first candidate design based on a first objective function; modifying the first candidate design based on the first metric to generate a first design option; and determining that a second metric generated for the first design option based on the first objective function exceeds the first metric, indicating that the first design option is a higher ranked design than the first candidate design.

12 . The non-transitory computer-readable medium of claim 11 , wherein the first design criterion defines a property boundary associated with the first region of land, and the first geometrical mesh is generated within an area that is defined by the property boundary.

13 . The non-transitory computer-readable medium of claim 11 , wherein the step of populating the first plurality of neighborhoods comprises:
determining that a first neighborhood included in the first plurality of neighborhoods has an area that is greater than a minimum area; identifying a first subregion within the first neighborhood; assigning the first subregion to a first dwelling unit included in the first set of dwelling units, wherein the first dwelling unit has a first dwelling unit type; determining that a second neighborhood included in the first plurality of neighborhoods has an area that is less than the minimum area; identifying a second subregion within the second neighborhood; and assigning the second subregion to a second dwelling unit included in the first set of dwelling units, wherein the second dwelling unit has

Assignees

• Autodesk Inc

Inventors

• Benjamin David
• Stoddart James
• Villaggi Lorenzo
• Nagy Danil

Classifications

• G06F2111/04

  Constraint-based CAD · CPC title

• G06F2111/02

  CAD in a network environment, e.g. collaborative CAD or distributed simulation · CPC title

• G06N3/126 Primary

  Evolutionary algorithms, e.g. genetic algorithms or genetic programming · CPC title

• G06F2111/20

  Configuration CAD, e.g. designing by assembling or positioning modules selected from libraries of predesigned modules · CPC title

• G06F30/13 Primary

  Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads · CPC title