A generative design pipeline for urban district and community planning
Through the geometry and evaluation engine of urban design pipelines, design options that meet urban design projects are automatically generated, solving the difficulties of designers in meeting multiple criteria and goals, achieving efficient and data-driven design generation, and reducing design time.
Patent Information
- Application Number
- CN201880085475.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Priority Date
- 2018-11-05
- Filing Date
- 2018-11-09
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2039-03-17
AI Technical Summary
In urban design projects, it is difficult for designers to effectively track and meet a large number of design guidelines and goals, resulting in poor design and lack of data support decision-making and design fixation, and the traditional design process lacks repeatability, resulting in long design time.
The urban design pipeline adopts computer-aided design, combined with a geometry engine and an evaluation engine, automatically generates design options that meet design criteria and optimize design goals, and generates final design options through an iterative process, providing quantifiable metrics and repeatable design processes.
Generate design options that meet design criteria and objectives, reduce the risk of poor performance designs, provide data-driven decision-making capabilities, and significantly accelerate the design generation process.
Smart Images

Figure CN111557005B_ABST
Abstract
Description
[0001] CROSS-REFERENCE TO RELATED APPLICATIONS
[0002] This application claims the benefit of priority to U.S. Provisional Patent Application Serial No. 62 / 584,711, filed on November 10, 2017, entitled “Generative Design Techniques for Urban and Neighborhood Planning,” and claims the benefit of priority to U.S. Patent Application Serial No. 16 / 181,224, filed on November 5, 2018, entitled “Generative Design Pipeline For Urban And Neighborhood Planning.” The subject matter of these related applications is hereby incorporated by reference herein.
[0003] background
[0004] Fields of various embodiments
[0005] Embodiments of the present invention relate generally to computer-aided design techniques, and more particularly, to a generative design pipeline for urban and neighborhood planning.
[0006] Description of Related Technology
[0007] In a typical urban design project, a designer generates a design for developing a property. For example, a designer may plan to develop and build a number of houses in a housing subdivision. Urban design projects are typically subject to numerous design criteria (including both design constraints and design requirements) and numerous design goals. For example, a design constraint may be that construction of a given urban design project should not occur outside of a particular property boundary. A design requirement may be that a given urban design project should include at least a minimum number of apartment units. A design goal may be that a given urban design project should maximize population density.
[0008] When generating designs for urban design projects, designers typically implement a traditional design process in which the designer uses both their hands and their brains to make many design choices. In this regard, for most urban design projects, the designer must determine where different buildings should be placed on the property based on various design criteria and design goals. The designer must also determine how various roads should traverse the property based on various design criteria and design goals. When making these and other design choices based on the design criteria and design goals, the designer typically relies on intuition and experience rather than implementing a more objective and more deterministic approach. This traditional design process has at least three specific disadvantages.
[0009] First, when making design choices, designers often have difficulty keeping track of the large number of design criteria and design goals that are typically associated with urban design projects. As a result, designers often produce designs that do not meet the design criteria very well or do not adequately address all design goals. In fact, designers sometimes completely forget to consider certain design criteria or design goals in their designs.
[0010] Second, designers cannot deterministically quantify the extent to which a given design meets specific design criteria or design goals. As a result, there is often little or no hard data available to validate various design choices. As a result, designers are unable to provide data-informed recommendations to stakeholders in urban design projects about the best performing designs. Furthermore, in practice, designers often rely on intuition and experience when recommending designs. However, doing so can bias designers toward familiar designs, leading to a phenomenon known in the art as “design fixation,” in which designers habitually generate similar designs.
[0011] Third, designers are often unable to make design decisions and determinations quickly due to the large number of design constraints and design goals to consider. Often, traditional design processes lack repeatable components, requiring designers to start from scratch for each new urban design project. For these reasons, generating designs for urban design projects can take a long time.
[0012] As previously stated, what is needed in the art are more efficient techniques for generating designs for urban design projects. Summary of the invention
[0013] Various embodiments include a computer-implemented method for generating design options for an urban area design project, comprising: generating a first geometric grid for a first candidate design based on a first design criterion associated with a first area of land; subdividing the first geometric grid to generate a first plurality of communities; populating the first plurality of communities with a first set of dwelling units; generating a first metric for a 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.
[0014] At least one technical advantage of the disclosed urban design pipeline is that design options that satisfy design criteria and achieve design goals associated with an urban design project are automatically generated. Therefore, regardless of the number of design criteria and design goals involved, designers can use the urban design pipeline to generate designs with minimal risk of generating poorly performing designs.
[0015] BRIEF DESCRIPTION OF THE DRAWINGS
[0016] In order that the manner in which the above features of the various embodiments may be understood in detail, the inventive concept briefly outlined above may be described in more detail by reference to various embodiments, some of which are shown in the accompanying drawings. However, it should be noted that the drawings only show typical embodiments of the inventive concept and are therefore not to be construed as limiting the scope in any way, and that other equally effective embodiments exist.
[0017] Figure 1 A system configured to implement one or more aspects of the present invention is shown;
[0018] Figure 2 According to various embodiments of the present invention Figure 1 A more detailed illustration of the urban design pipeline;
[0019] Figure 3 is a flow chart of method steps for generating a set of design options for an urban area design project according to various embodiments of the present invention;
[0020] Figure 4 The present invention shows various embodiments of the Figure 2 How the geometry engine generates geometric meshes for candidate designs;
[0021] Figure 5 The present invention shows various embodiments of the Figure 2 How the geometry engine generates community segments for candidate designs;
[0022] Figure 6 The present invention shows various embodiments of the Figure 2 How the geometry engine places housing units within a candidate design;
[0023] Figure 7 The present invention shows various embodiments of the Figure 2 How the geometry engine places apartment units within candidate designs;
[0024] Figure 8 The present invention shows various embodiments of the Figure 2 How the geometry engine assigns program types to house units and apartment units in candidate designs;
[0025] Fig. 9 is a flow chart of method steps for generating candidate designs for an urban area design project according to various embodiments of the present invention;
[0026] Fig.10 The present invention shows various embodiments of the Figure 2 How the evaluation engine generates solar metrics for candidate designs;
[0027] Fig.11 The present invention shows various embodiments of the Figure 2 How the evaluation engine generates horizon metrics for candidate designs;
[0028] Fig.12 The present invention shows various embodiments of the Figure 2 How the evaluation engine generates yard size metrics for candidate designs;
[0029] Fig.13 The present invention shows various embodiments of the Figure 2 How the evaluation engine generates diversity metrics for candidate designs;
[0030] Fig.14 The present invention shows various embodiments of the Figure 2 How the evaluation engine generates program metrics for candidate designs;
[0031] Fig.15 The present invention shows various embodiments of the Figure 2 How the evaluation engine generates cost metrics for candidate designs;
[0032] Fig.16 The present invention shows various embodiments of the Figure 2 How the evaluation engine generates profit metrics for candidate designs;
[0033] Fig.17 The present invention shows various embodiments of the Figure 2 how the evaluation engine generates combined metrics for candidate designs; and
[0034] Fig.18 is a flow chart of method steps for evaluating candidate designs for an urban area design project according to various embodiments of the present invention. DETAILED DESCRIPTION
[0035] In the following description, numerous specific details are set forth to provide a more thorough understanding of various embodiments. However, it will be apparent to one skilled in the art that the inventive concept may be practiced without one or more of these specific details.
[0036] As mentioned above, urban design projects are often subject to numerous design criteria and design goals, which complicate the numerous design decisions that designers must make when generating designs. As a result, designers often generate designs that do not meet the design criteria well, do not fully achieve the design goals, or completely ignore specific design criteria and / or design goals. In addition, designers lack any technology for quantifying the extent to which the design criteria and / or design goals are met, and therefore cannot make data-informed decisions about which design is better than any other design. Finally, the traditional design process lacks repeatability, and therefore must start over in each new design project.
[0037] To address these issues, embodiments of the present invention include an urban design pipeline that 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 goals associated with the urban design project, and then generates a plurality of candidate designs that meet the design criteria and optimize the design goals. Each candidate design includes a specific layout of house units, apartment units, and roads that are configured in a manner that meets the design criteria and achieves the design goals to a certain extent.
[0038] The evaluation engine evaluates each candidate design across a set of metrics to generate a combined metric. The combined metric for a given candidate design indicates how well the candidate design satisfies the design criteria and optimizes the design goals. The geometry engine modifies the candidate design based on the corresponding metric to generate a candidate design that better satisfies the design criteria and more effectively achieves the design goals. The geometry engine and the evaluation engine iteratively operate in this manner until convergence criteria are met and a final set of design options are generated. These design options may better satisfy the design criteria and optimize the design goals relative to previously generated candidate designs.
[0039] At least one technical advantage of the disclosed urban area design pipeline is the automatic generation of design options that meet design criteria and achieve design goals associated with an urban area design project. Therefore, regardless of the number of design criteria and design goals involved, designers can use the urban area design pipeline to generate designs with minimal risk of generating poorly performing designs. Another technical advantage is that the urban area design pipeline can generate quantifiable metrics that indicate the extent to which design criteria and design goals are met, thereby enabling data-informed decisions and recommendations to be made. Yet another technical advantage is that the disclosed urban area design pipeline includes repeatable stages that can be easily adapted to other urban area design projects with different design criteria and different design goals. Therefore, the process of generating designs can be greatly accelerated compared to traditional manual techniques. These technical advantages represent a number of technical advances over prior art methods.
[0040] System Overview
[0041] Figure 1 A system configured to implement one or more aspects of the present invention is shown. As shown, the system 100 includes one or more clients 110 and one or more servers 130, which are configured to interact to generate a set of design options 140 for an urban area design project. A given client 110 or a given server 130 can be any technically feasible type of computer system, including a desktop computer, a laptop computer, a mobile device, a virtualized instance of a computing device, a distributed and / or cloud-based computer system, etc. The client 110 and the server 130 are coupled together via a network 150. The network 150 can be any technically feasible set of interconnected communication links, including a local area network (LAN), a wide area network (WAN), the World Wide Web or the Internet, etc.
[0042] As further shown, the client 110 includes a processor 112, an input / output (I / O) device 114, and a memory 116 coupled together. The processor 112 includes any technically feasible set of hardware units configured to process data and execute software applications. For example, the processor 112 may include one or more central processing units (CPUs). The I / O device 114 includes any technically feasible set of devices configured to perform input and / or output operations, including, for example, a display device, a keyboard, and a touch screen, etc.
[0043] Memory 116 includes any technically feasible storage medium configured to store data and software applications, such as, for example, a hard disk, a random access memory (RAM) module, and a read-only memory (ROM). Memory 116 includes client-side urban design pipeline 120(0). Client-side urban design pipeline 120(0) is a software application that, when executed by processor 112, causes processor 112 to participate in generating design options 140. In doing so, client-side urban design pipeline 120(0) interoperates with a corresponding client-side urban design pipeline 120(1) residing within server 130, as described in more detail below.
[0044] The server 130 includes a processor 132, an I / O device 134, and a memory 136 coupled together. The processor 132 includes any technically feasible set of hardware units configured to process data and execute software applications, such as one or more CPUs. The I / O device 134 includes any technically feasible set of devices configured to perform input and / or output operations, such as a display device, a keyboard, or a touch screen, etc.
[0045] Memory 136 includes any technically feasible storage medium configured to store data and software applications, such as, for example, a hard disk, a RAM module, and a ROM. Memory 136 includes server-side urban design pipeline 120(1). Server-side urban design pipeline 120(1) is a software application that, when executed by processor 132, causes processor 132 to participate in generating design options 140. In doing so, server-side urban design pipeline 120(1) interoperates with client-side urban design pipeline 120(0), as described above.
[0046] In operation, one or more instances of the client-side urban design pipeline 120(0) and one or more instances of the server-side urban design pipeline 120(1) interact to generate a plurality of design options 140(0)-140(N). Each design option 140 describes a different development plan for developing a physical property with various structures, roads, and other fixtures as part of an urban design project, which will be discussed below in conjunction with Figure 2-Figure 18 Generally, one or more client-side urban design pipelines 120(0) and one or more server-side urban design pipelines 120(1) together represent different parts of a distributed software entity. Therefore, for simplicity, the client-side urban design pipeline 120(0) and the server-side urban design pipeline 120(1) will be collectively referred to as the urban design pipeline 120 in this document. Figure 2 The urban design pipeline 120 is described in more detail.
[0047] Figure 2 According to various embodiments of the present invention Figure 1 As shown, the urban design pipeline 120 includes a geometry engine 200 and an evaluation engine 210. The geometry engine 200 and the evaluation engine 210 are configured to perform an iterative process to generate design options 140 based on design criteria 202 and design goals 204.
[0048] The design criteria 202 may include design constraints, which generally describe design features and / or design attributes that should be avoided when generating the design options 140. A given design constraint may indicate, for example, a physical property area in which construction of a structure cannot occur, a maximum number of floors of a structure that cannot be exceeded, an unallowable placement pattern of roads, etc. The design constraints may be derived from local development regulations and / or building codes as well as guidelines received from one or more stakeholders in the urban design project.
[0049] The design criteria 202 may also include design requirements that generally describe features and / or attributes of the designs that should be included in the design options 140. A given design requirement may indicate, for example, one or more desired orientations of structures, the number of parking lots required for each structure, a target configuration of road intersections, etc. The design requirements may be derived from local development regulations and / or building codes as well as guidelines received from one or more stakeholders in an urban design project.
[0050] The design goals 204 include a set of objective functions to be maximized or minimized when generating the design options 140. A given objective function quantifies a particular property of a given design. In practice, the design goals 204 include objective functions that quantify solar energy collection, available sight lines associated with windows in a structure, the size of a yard associated with a structure, neighborhood diversity, program distribution, total project cost, and total project profit.
[0051] In operation, the geometry engine 200 receives the design criteria 202 and the design goals 204 and generates candidate designs 206 for the urban design project. Each candidate design 206 describes a different development plan for developing a physical property with various structures, roads, and other fixtures associated with the urban design project. A given candidate design 206 satisfies some or all of the design criteria 202 and is therefore generally considered a feasible design. The candidate designs 206 also achieve the design goals 204 to varying degrees. The evaluation engine 210 evaluates each candidate design 206 based on the objective function included in the design goals 204 to generate design metrics 212. The design metrics 212 generated for a given candidate design 206 quantify the degree to which the design goals 204 are met by the given candidate design 206. In particular, the design metrics 212 quantify the solar energy collection, available sight lines, yard size, community diversity, project distribution, total project cost, and total project profit of the given candidate design 206.
[0052] The geometry engine 200 analyzes the design metrics 212 in conjunction with the candidate designs 206, and then regenerates and / or modifies the candidate designs 206 to generate improved versions of the candidate designs 206 that better achieve the design goals 204 while still satisfying the design criteria 202. In the manner described, the geometry engine 200 and the evaluation engine 210 complete one iteration of the urban district design pipeline 120. In subsequent iterations, the evaluation engine 210 generates design metrics 212 for these improved versions of the candidate designs 206, and the geometry engine 200 again regenerates and / or modifies the candidate designs 206. The geometry engine 200 and the evaluation engine 210 iterate in this manner until one or more convergence criteria are met. When the convergence criteria are met, the urban district design pipeline 120 outputs a final set of candidate designs 206 as design options 140. In one embodiment, the geometry engine 200 and the evaluation engine 210 execute a multi-objective solver to generate and / or update the candidate designs 206 until the design metrics 212 reach a certain threshold specified in the convergence criteria. Further details will be provided below in conjunction with the invention. Figure 3 The process performed by urban area design pipeline 120 in generating design options 140 is described.
[0053] Figure 3 is a flow chart of method steps for generating a set of design options for an urban design project according to various embodiments of the present invention. Figure 1-Figure 2 The method steps are described herein with reference to a system, but those skilled in the art will understand that any system configured to perform the method steps in any order falls within the scope of the present invention.
[0054] As shown, the method 300 begins at step 302, where the geometry engine 200 obtains the design criteria 202 and the design goals 204. The design criteria 202 may include design constraints that describe design features and / or design attributes that should be avoided when generating the design options 140. The design criteria 202 may also include design requirements that describe design features and / or design attributes that should be included in the design options 140. The design goals 204 include a set of objective functions that should be maximized or minimized when generating the design options 140.
[0055] At step 304, the geometry engine 200 generates or updates candidate designs 206 based on the design criteria 202 and the design goals 204. A given candidate design 206 describes different development plans for developing a physical property. Each candidate design 206 generated by the geometry engine 210 satisfies the design criteria 202 and is therefore considered a feasible design and also achieves the design goals 204 to some extent. Figure 4-Figure 9 The geometry engine 200 is described in more detail.
[0056] At step 306, evaluation engine 210 evaluates candidate designs 206 across multiple dimensions to generate design metrics 212. In practice, evaluation engine 210 generates design metrics 212 that quantify solar energy collection, available sight lines, yard size, community diversity, project distribution, total project cost, and total project profit for each candidate design 206. Figure 10-Figure 18 The evaluation engine 210 is described in more detail.
[0057] At step 308, geometry engine 200 and / or evaluation engine 210 determines whether one or more convergence criteria are met. In one embodiment, geometry engine 200 and / or evaluation engine 210 determines whether design metrics 212 generated for candidate design 206 meet or exceed a minimum threshold level. If the convergence criteria are not met, method 300 returns to step 304 and performs another iteration. Otherwise, method 300 proceeds to step 310.
[0058] In step 310, the urban design pipeline 120 outputs design options 140. Each design option 140 satisfies the design criteria 202 and also achieves the design goals 204 to the best degree compared to the candidate designs 206 generated and evaluated during the previous iteration. A given design option 140 describes a specific development plan for developing a physical property with various structures, roads, and other fixtures associated with the urban design project, which will also be discussed below in conjunction with the present invention. Figure 4-Figure 9 A more detailed description is given.
[0059] Through the above-described method 300, the urban design pipeline 120 automatically generates feasible design options for an urban design project that meet the provided design criteria and optimize the provided design goals. Therefore, the designer does not need to manually or mentally track these design criteria and design goals when generating a design. In addition, the urban design pipeline 120 can quantify the degree to which the design goals are achieved, thereby providing hard data based on which specific design options can be selected. Finally, by updating the design criteria and design goals, the urban design pipeline 120 can be repeatedly applied to different urban design projects, thereby greatly speeding up the process of generating designs for urban design projects.
[0060] Geometry Engine
[0061] As above combined Figure 1-Figure 3 As discussed, the urban design pipeline 120 implements a geometry engine 200 to generate geometry associated with candidate designs 206. As described herein, the "geometry" associated with a given design generally refers to the topological layout of various elements associated with an urban design project, including housing units, roads, parklands, and the like. In one embodiment, the geometry engine 200 generates the geometry of a given candidate design 206 based on a set of construction parameters that may vary between different candidate designs 206. The geometry engine 200 performs a multi-step process to generate geometry for each candidate design 206, as described below in conjunction with Figure 4-Figure 8 Described by example.
[0062] Figure 4 The present invention shows various embodiments of the Figure 2 200 generates a geometric mesh for a candidate design. As shown, the geometry engine 200 generates an initial mesh 400 based on a perimeter 410. The perimeter 410 corresponds to a property line and resides near a buffer zone 420 where the geometry engine 200 cannot generate geometric shapes. The perimeter 410 is defined as a design constraint in the design criteria 202, which constrains the geometry engine 200 to generate geometric shapes only within the boundaries of the perimeter 410. The geometry engine 200 generates the initial mesh 400 by projecting a plurality of longitudinal lines longitudinally between the top and bottom edges of the perimeter 410 and a plurality of transverse lines transversely between the left and right edges of the perimeter 410, thereby forming a polygonal mesh.
[0063] Figure 5 It shows various embodiments according to the present invention. Figure 2, how the geometry engine 200 generates community subdivisions for candidate designs. As shown, the geometry engine 200 subdivides the initial grid 400 by selecting one or more longitudinal lines 500 and one or more transverse lines 510 to produce community subdivisions 520. The longitudinal lines 500 selected in this manner provide roads that pass through the initial grid 400 in the longitudinal direction, referred to herein as "avenues". The transverse lines 510 selected in this manner provide roads that pass through the initial grid 400 in the transverse direction, referred to herein as "streets". In one embodiment, the geometry engine 200 can select one or more longitudinal lines 500 and one or more transverse lines 510 based on a set of construction parameters.
[0064] Figure 6 It shows various embodiments according to the present invention. Figure 2 As shown, the geometry engine 200 fills in the neighborhood subdivision 520 by placing center lines 600 that traverse the neighborhood subdivision 520 longitudinally and then placing the house units 610 along those center lines. Figure 5 In the example shown, the geometry engine 200 excludes the community 520(5) from the process because that particular community subdivision is too small to include a house unit. In one embodiment, the geometry engine 200 can determine the placement and orientation of the house unit 610 based on a set of construction parameters.
[0065] Figure 7 It shows various embodiments according to the present invention. Figure 2 The geometry engine 200 fills in the candidate design by placing a center line 700 that longitudinally traverses the portion of a particular neighborhood subdivision 520 that does not include a housing unit 610. Figure 5 The geometry engine 200 then places the apartment units 710 along these center lines 700. In one embodiment, the geometry engine 200 may determine the placement and orientation of the apartment units 710 based on a set of construction parameters.
[0066] Figure 8 It shows various embodiments according to the present invention. Figure 2206 . The geometry engine 200 of FIG. 206 illustrates how the geometry engine 200 assigns engineering types to house units and apartment units in candidate designs. As shown, the geometry engine assigns house type 800 to an exemplary house unit and apartment type 810 to an exemplary apartment unit. The available house types and apartment types are generally referred to herein as "engineering" types. The available engineering types are specified in the design criteria 202. For example, a given engineering type may be a "3-story house" or a "5-story apartment building," etc. The design criteria 202 may also indicate the minimum number of each engineering type to be included in any given candidate design 206. In one embodiment, the geometry engine 200 determines the distribution of engineering types based on a set of construction parameters. The geometry engine 210 incorporates vegetation 820 into the remaining areas that are not populated with roads, houses, apartments, or other elements.
[0067] General reference Figure 4-Figure 8 , geometry engine 200 performs the above operations to generate a given candidate design included in candidate designs 206. Geometry engine 200 is configured to perform similar operations multiple times using different sets of input parameters to generate a spectrum of different candidate designs 206. The input parameters control the placement of roads, house units, apartment units, and other attributes, which can vary between different candidate designs 206. Fig. 9 The various operations performed by geometry engine 200 are described in more detail.
[0068] Fig. 9 is a flow chart of method steps for generating candidate designs for an urban design project according to various embodiments of the present invention. Figure 1-Figure 8 The method steps are described herein with reference to a system, but those skilled in the art will understand that any system configured to perform the method steps in any order falls within the scope of the present invention.
[0069] As shown, method 900 begins at step 902, where geometry engine 200 generates an initial design grid based on a site perimeter. The site perimeter may correspond to a property line. Geometry engine 200 generates initial grid 400 by projecting a plurality of longitudinal lines in a longitudinal direction between edges of the perimeter and projecting a plurality of transverse lines in a transverse direction between edges of the perimeter, as described above in conjunction with Figure 4 described.
[0070] At step 904, the geometry engine 200 intersects the initial design grid generated at step 902 with roads to generate communities. To do so, the geometry engine 200 selects one or more longitudinal lines and one or more transverse lines generated at step 902 as roads that traverse the initial grid, as described above in conjunction with Figure 5 described.
[0071] In step 906, the geometry engine 200 places the housing units within the community subdivisions generated in step 904. The geometry engine 200 generates center lines within some or all of the community subdivisions and then places one or more housing units along each center line, as described above in conjunction with Figure 6 In one embodiment, the geometry engine 200 may not place housing units in community subdivisions unless those subdivisions are of at least a minimum size.
[0072] At step 908, the geometry engine 200 places the apartment units within the unoccupied areas of the community subdivision previously generated at step 904 and at least partially populated with housing units at step 906. The geometry engine 200 performs step 908 with respect to the remaining space within the community subdivision that has not yet been occupied by housing units. Figure 7 An example of how geometry engine 200 performs step 908 is described.
[0073] At step 910, the geometry engine 200 assigns project types to the house units generated and placed at step 906 and the apartment units generated and placed at step 908. The geometry engine 200 performs step 910 based on the design criteria 202, which indicate the available house types and apartment types, and the minimum number of each type that should be included in any given candidate design 206.
[0074] At step 912, geometry engine 200 fills the remaining area of the neighborhood subdivision with vegetation and / or parkland. Figure 8 An example of how geometry engine 200 performs steps 910 and 912 is described.
[0075] The geometry engine 200 repeats the method 900 to generate each candidate design 206. In one embodiment, the geometry engine 200 may perform the method 900 with many different sets of construction parameters to generate many different candidate designs 206, thereby performing a generative design process. The evaluation engine 210 analyzes each candidate design 206 to generate a design metric 212, as described below in conjunction with Figure 10-Figure 18 Described in more detail.
[0076] Evaluation Engine
[0077] The urban area design pipeline 120 implements an evaluation engine 210 to analyze the candidate designs 206 across several different metrics. These metrics quantify the solar energy collection, available sight lines, yard size, community diversity, engineering distribution, total project cost, and total project profit for any given candidate design 206. The evaluation engine 210 calculates the value of each of these different metrics for each candidate design 206 to generate design metrics 212. Figure 10-Figure 16How evaluation engine 210 generates design metrics 212 for exemplary candidate design 206 is illustrated.
[0078] Fig.10 It shows various embodiments according to the present invention. Figure 2 206. As shown, the evaluation engine 210 estimates the solar gain on the roof surfaces of all house units included in the candidate design 206. Solar gain generally refers to the amount of solar energy collected at a given roof surface. Some roof surfaces provide greater solar gain than other roof surfaces. For example, the roof surface of house unit 1000 provides high solar gain, the roof surface of house unit 1010 provides medium solar gain, and the roof surface of house unit 1020 provides low solar gain. In one embodiment, the evaluation engine 210 generates an estimate of the solar gain for a given roof surface based on the ratio between the number of unobstructed sampled solar rays and the number of available sampled solar rays. The evaluation engine 210 calculates the total solar gain of the candidate design 206 to generate the solar metric.
[0079] Fig.11 It shows various embodiments according to the present invention. Figure 2 How the evaluation engine 210 generates view metrics for candidate designs. As shown, the evaluation engine 210 generates multiple sight lines emanating from the house units and apartment units included in the candidate design 206. Some sight lines intersect with nearby obstacles and are considered obstructed sight lines. Obstructed sight lines are generally shorter. Other sight lines do not intersect with nearby obstacles and are considered unobstructed sight lines. Unobstructed sight lines are relatively longer than obstructed sight lines. For a given house or apartment unit, the evaluation engine 210 determines a normalized sight line length. The evaluation engine 210 averages the normalized sight line lengths to generate a sight line metric.
[0080] Fig.12 It shows various embodiments according to the present invention. Figure 2 206. As shown, the evaluation engine 210 determines the yard size of each house unit in the candidate design. Some house units have larger yards, while other house units have smaller yards. For example, house unit 1200 has a very large yard, while house unit 1210 has a very small yard. The evaluation engine 210 calculates the average yard size of all house units in the candidate design 206 to generate the yard metric.
[0081] Fig.13 It shows various embodiments according to the present invention. Figure 2206. As shown, the evaluation engine 210 generates a diversity metric for a candidate design. As shown, the evaluation engine 210 generates a grouping of housing units for each community and then determines the community 1300, including the housing unit 1310, which includes the most housing units. The number of housing units within the largest community is generally indicative of the level of diversity expected in the community layouts included in the candidate design 206. In particular, candidate designs with many smaller communities tend to have more varied community layouts than candidate designs with a few very large communities (which typically have long rows of housing units). Long rows of houses are generally undesirable in candidate designs. The evaluation engine 210 generates a diversity metric based on the number of houses included in the largest community.
[0082] Fig.14 It shows various embodiments according to the present invention. Figure 2 206. As shown, the evaluation engine 210 tabulates different types of project types, including house types and apartment types, to determine how well the number of project types matches the distribution of project types specified in the design criteria 202. The candidate design 206 includes several different project types, including house types 1400, 1410, 1420, and 1430, and apartment type 1440. As described above, the design criteria 202 includes the available project types and the minimum number of units of each type to be included in the candidate design 206. The evaluation engine 206 generates engineering metrics to reflect how well the candidate design 206 matches the distribution of project types specified in the design criteria 202. In one embodiment, the engineering metrics indicate the difference between the number of project types specified in the design criteria 202 and the actual number of corresponding project types included in the candidate design 206.
[0083] Fig.15 It shows various embodiments according to the present invention. Figure 2 206. As shown, the evaluation engine 210 determines various costs associated with the development of various fixtures included in the candidate design 206, including road costs 1500, lot costs 1510, and park costs 1520. For a given type of fixture, the evaluation engine 210 calculates the total number of units, total area, or total linear metrics for each instance of the fixture type. The evaluation engine 210 also determines the cost per unit, per area, or per linear unit for building a given type of fixture. Based on this information, the evaluation engine 210 determines the total cost of building each instance of the fixture. For example, the evaluation engine 210 can measure the total area of a park site and then multiply that area by the cost per unit area of building the park site to generate a park cost 1520. Based on the total cost aggregated over all fixtures, the evaluation engine 210 generates a cost metric.
[0084] Fig.16 It shows various embodiments according to the present invention. Figure 2 206. As shown, the evaluation engine 210 determines various revenue sources associated with the sale of portions of the candidate design 206. These revenue sources are represented by various sales prices associated with the fixtures included in the candidate design 206, including a house sales price 1600, an apartment sales price 1610, and a yard sales price 1620. For a given type of fixture, the evaluation engine 210 calculates the sales price of the type of fixture, and then multiplies that number by the number of instances of the type of fixture to determine the total revenue that can be generated by selling those instances. For example, the evaluation engine 210 can multiply the house sales price 1600 by the number of houses included in the candidate design 206 to derive the total revenue obtained by selling each house included in the candidate design 206. The evaluation engine 210 sums the total revenue on all fixtures, and then subtracts the various costs calculated when generating the cost metric to generate the profit metric. In one embodiment, the sales price of a given fixture can quantify the extent to which the sales price of the fixture is increased compared to another fixture. For example, yard sale price 1620 may indicate the extent to which the sale price of a corresponding home is increased by the associated yard.
[0085] General reference Figure 10-Figure 16 , the evaluation engine 210 calculates the different metrics discussed herein and then combines these metrics to produce an overall combined metric for the candidate design 206, such as Fig.17 shown.
[0086] Fig.17 It shows various embodiments according to the present invention. Figure 2 1700 is derived from solar metric 1710, view metric 1720, yard metric 1730, diversity metric 1740, engineering metric 1750, cost metric 1760, and profit metric 1770. Combined metric 1700 describes how well candidate design 206 achieves design goal 204. Design metrics 212 include combined metric 1700 and / or individual metrics associated with combined metric 1700. Fig.18 Describing in more detail the various operations performed by the evaluation engine 210 in calculating these metrics,
[0087] Fig.18 is a flow chart of method steps for evaluating candidate designs for an urban design project according to various embodiments of the present invention. Figures 1 to 17 The method steps are described using a system configured to perform the method steps in any order, but those skilled in the art will understand that any system configured to perform the method steps in any order falls within the scope of the present invention.
[0088] As shown, method 1800 begins at step 1802, where evaluation engine 210 obtains candidate design 206 generated by geometry engine 210. Candidate design 206 describes the layout of various fixtures associated with an urban design project, including various housing units, apartment units, roads, and the like.
[0089] At step 1804, the evaluation engine 210 determines the total solar energy collected in the candidate design 206 to generate a solar energy metric. In one embodiment, the evaluation engine 210 determines the ratio between the potential solar energy that can be collected (based on the number of unobstructed sunlight rays) and the total number of available sunlight rays to generate the solar energy metric. Some cells within the candidate design 206 generate more solar energy than other cells. The solar energy metric represents the sum of the solar energy generated by all cells within the candidate design 206. Fig.10 An example of how the assessment engine 210 generates solar energy metrics is described.
[0090] In step 1806, the evaluation engine 210 determines the average length of sight lines across all house units and apartment units in the candidate design 206 to generate a sight line metric. Some sight lines intersect obstacles and therefore may be shorter than sight lines that do not intersect obstacles. Therefore, some house units or apartment units may have longer sight lines than other units. The evaluation engine 210 totals the length of the lot lines across all house units and apartment units and divides by the total number of units to generate a sight line metric. Fig.11 An example of how the evaluation engine 210 generates a view metric is described.
[0091] In step 1808, the evaluation engine 210 determines the average yard area of all house units to generate a yard metric. Due to the uncertain nature of the generative design process, some house units have larger yards than others. The evaluation engine 210 adds the areas of all yards associated with the house units in the candidate design 206 and divides by the number of house units to generate the yard metric. Fig.12 An example of how the assessment engine 210 generates yard metrics is described.
[0092] At step 1810, the evaluation engine 210 determines the number of units in the largest community to generate a diversity metric. The number of housing units within the largest community generally indicates the level of diversity expected in the community layouts included in the candidate design 206. In particular, candidate designs with many smaller communities tend to have more varied community layouts than candidate designs with a few very large communities (which typically have long rows of housing units). Fig.13 An example of how the evaluation engine 210 generates a diversity metric is described.
[0093] At step 1812, the assessment engine 210 determines a distribution of projects, including types of house units and types of apartment units, relative to the project requirements indicated in the design criteria 202. The design criteria 202 include the types of projects available and the minimum number of units of each type to be included in the candidate design 206. The assessment engine 206 generates a project metric based on how well the candidate design 206 matches the distribution of project types specified in the design criteria 202.
[0094] At step 1814, the evaluation engine 210 determines the construction cost of the candidate design 206 to generate a cost metric. The evaluation engine 210 calculates individual costs for generating each type of fixture to generate the cost metric. In doing so, the evaluation engine 210 calculates the costs for building different types of fixtures based on a unit cost of an instance of the fixture, a cost per unit area associated with the fixture, or a cost per linear unit associated with the fixture, and so on.
[0095] At step 1816, the evaluation engine 210 determines the revenue generated by the candidate design in conjunction with the cost metric generated at step 1814 to generate a profit metric. The evaluation engine 210 calculates the revenue for any given fixture based on the estimated selling price of the fixture. Any given estimated selling price can be generated based on current market conditions, comparisons to similar fixtures, or any other technically feasible valuation method.
[0096] In step 1818, the evaluation engine 210 generates a combined metric based on the previously generated solar metrics, view metrics, yard metrics, diversity metrics, engineering metrics, cost metrics, and profit metrics. The combined metric indicates the overall degree to which the candidate design achieves the design goals 204. In one embodiment, the combined metric indicates the degree to which the design candidate 206 optimizes the objective function specified in the design goals 204. In another embodiment, the combined metric is a weighted sum of the individually generated metrics.
[0097] Once the evaluation engine 210 has generated the various metrics described above for each candidate design 206, the geometry engine 200 analyzes these metrics in conjunction with the corresponding candidate designs 206 and then modifies those candidate designs 206 to improve the associated metrics. In one embodiment, the geometry engine 200 implements a genetic algorithm or an evolutionary algorithm based on the associated metrics to improve the candidate designs. When the candidate designs 206 are sufficiently improved, the geometry engine 200 determines that one or more convergence criteria have been met and the urban area design pipeline 120 outputs design options 140 based on these candidate designs 206. In one embodiment, the design options 140 include each candidate design 206 having a metric that exceeds a given threshold. The metrics generated via the above process can be used to rank the candidate designs 206 relative to each other. Therefore, these metrics represent hard data based on which high-performance candidate designs can be selected.
[0098] In summary, the 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 the design criteria and design goals associated with the urban design project and then generates a number of candidate designs that meet the design criteria and optimize the design goals. Each candidate design includes a specific layout of housing units, apartment units, and roads that are configured in a way that meets the design criteria and achieves the design goals to a certain extent.
[0099] The evaluation engine evaluates each candidate design across a set of metrics to generate a combined metric. The combined metric for a given candidate design indicates the extent to which the candidate design satisfies the design criteria and optimizes the design goals. The geometry engine modifies the candidate design based on the corresponding metric to generate a candidate design that better satisfies the design criteria and more effectively achieves the design goals. The geometry engine and the evaluation engine operate iteratively in this manner until convergence criteria are met and a final set of design options are generated. These design options may better satisfy the design criteria and optimize the design goals relative to previously generated candidate designs.
[0100] At least one technical advantage of the disclosed urban design pipeline over the prior art is the automatic generation of design options that satisfy all design criteria and achieve all design goals associated with an urban design project. Thus, regardless of the number of design criteria and design goals involved, a designer can use the urban design pipeline to generate designs with minimal risk of generating poorly performing designs. Another technical advantage is that the urban design pipeline generates quantifiable metrics that indicate the extent to which the design goals are met, thereby enabling data-informed decisions about different designs. Yet another technical advantage is that the disclosed urban design pipeline includes repeatable stages that can be easily adapted to other urban design projects with different design criteria and design goals. Thus, the process of generating designs can be greatly accelerated compared to traditional manual techniques. These technical advantages represent one or more technical advances over prior art methods.
[0101] 1. Some embodiments include a computer-implemented method for generating design options for an urban area design project, the method comprising: generating a first geometric grid for a first candidate design based on a first design criterion associated with a first area of land; subdividing the first geometric grid to generate a first plurality of communities; populating the first plurality of communities 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.
[0102] 2. A computer-implemented method according to clause 1, wherein subdividing the first geometric grid includes: projecting at least one line segment on the first geometric grid to generate a first community included in the first plurality of communities and a second community included in the first plurality of communities, and also includes: designating the at least one line segment as a road for accessing both the first community and the second community.
[0103] 3. A computer-implemented method according to any one of clauses 1-2, wherein populating the first plurality of communities includes: determining that an area of a first community included in the first plurality of communities is greater than a minimum area; identifying a first sub-area within the first community; assigning the first sub-area to a first dwelling unit included in the first dwelling unit set; and assigning a first dwelling unit type to the first dwelling unit.
[0104] 4. The computer-implemented method of any of clauses 1-3, wherein generating the first metric comprises determining an estimated amount of solar energy collected by the first set of dwelling units.
[0105] 5. A computer-implemented method according to any one of clauses 1-4, wherein generating the first metric includes: determining a first length associated with a first line of sight from a first dwelling unit included in the first set of dwelling units; determining a second length associated with a second line of sight from a second dwelling unit included in the first set of dwelling units; and combining the length of the first line of sight with the length of the second line of sight to generate at least a portion of the first metric.
[0106] 6. A computer-implemented method according to any of clauses 1-5, wherein generating the first metric includes: 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.
[0107] 7. A computer-implemented method according to any one of clauses 1-6, wherein generating the first metric includes: determining that a first community included in the first plurality of communities includes more residential units than a second community included in the first plurality of communities; and calculating the number of residential units included in the first community to generate at least a portion of the first metric, wherein the number of residential units included in the first community indicates a degree of variability of the communities included in the first candidate design.
[0108] 8. A computer-implemented method according to any of clauses 1-7, wherein generating the first metric includes: determining to assign a first dwelling unit type to a first number of dwelling units included in the first dwelling unit set; 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 the recommended number of dwelling units indicates the extent to which the first candidate design satisfies a second design criterion.
[0109] 9. A computer-implemented method according to any of clauses 1-8, wherein generating the first metric includes: 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.
[0110] 10. A computer-implemented method according to any one of clauses 1-9, wherein generating the first metric includes: determining a first estimated income 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 income and a first construction cost associated with the first dwelling unit; determining a second estimated income 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 income and a second construction cost associated with the second dwelling unit; and combining the first estimated profit with the second estimated profit to generate at least a portion of the first metric.
[0111] 11. Some embodiments include a non-transitory computer-readable medium storing program instructions that, when executed by one or more processors, cause the one or more processors to generate design options for an urban design project by performing the following steps: generating a first geometric grid for a first candidate design based on a first design criterion associated with a first area of land; subdividing the first geometric grid to generate a first plurality of communities; populating the first plurality of communities 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.
[0112] 12. The non-transitory computer-readable medium of clause 11, wherein the first design criteria defines a property boundary associated with a first area of the land, and the first geometric mesh is generated within an area defined by the property boundary.
[0113] 13. A non-transitory computer-readable medium according to any one of clauses 11-12, wherein the step of filling the first plurality of communities includes: determining that an area of a first community included in the first plurality of communities is greater than a minimum area; identifying a first sub-area within the first community; assigning the first sub-area to a first dwelling unit included in the first dwelling unit set, wherein the first dwelling unit has a first dwelling unit type; determining that an area of a second community included in the first plurality of communities is less than the minimum area; identifying a second sub-area within the second community; and assigning the second sub-area to a second dwelling unit included in the first dwelling unit set, wherein the second dwelling unit has a second dwelling unit type.
[0114] 14. A non-transitory computer-readable medium according to any one of clauses 11-13, wherein the step of generating the first metric includes: determining a first length associated with a first line of sight from a first dwelling unit included in the first set of dwelling units; determining a second length associated with a second line of sight from a second dwelling unit included in the first set of dwelling units; and combining the length of the first line of sight with the length of the second line of sight to generate at least a portion of the first metric.
[0115] 15. A non-transitory computer-readable medium as described in any of clauses 11-14, wherein the step of generating the first metric includes: 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.
[0116] 16. A non-transitory computer-readable medium as described in any of clauses 11-15, wherein the step of generating the first metric includes: determining that a first community included in the first plurality of communities includes more residential units than a second community included in the first plurality of communities; and calculating the number of residential units included in the first community to generate at least a portion of the first metric, wherein the number of residential units included in the first community indicates a degree of variability of the communities included in the first candidate design.
[0117] 17. A non-transitory computer-readable medium according to any one of clauses 11-16, wherein the step of generating the first metric includes: determining to assign a first dwelling unit type to a first number of dwelling units included in the first dwelling unit set; 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 the recommended number of dwelling units indicates the extent to which the first candidate design satisfies a second design criterion.
[0118] 18. A non-transitory computer-readable medium as described in any of clauses 11-17, wherein the step of generating the first metric includes: 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.
[0119] 19. A non-transitory computer-readable medium according to any one of clauses 11-18, wherein the step of generating the first metric includes: determining a first estimated income 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 income and a first construction cost associated with the first dwelling unit; determining a second estimated income 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 income and a second construction cost associated with the second dwelling unit; and combining the first estimated profit with the second estimated profit to generate at least a portion of the first metric.
[0120] 20. Some embodiments include a system comprising: a memory for storing an urban area design pipeline; and a processor, which, when executing the urban area design pipeline, is configured to perform the following steps: generating a first geometric grid for a first candidate design based on a first design criterion associated with a first area of land; subdividing the first geometric grid to generate a first plurality of communities; populating the first plurality of communities 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.
[0121] Any and all combinations of any claim elements recited in any claim and / or any elements described in this application, in any manner, are within the intended scope of the invention and protection.
[0122] The description of the various embodiments has been presented for purposes of illustration, but is not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments.
[0123] The various aspects of the present embodiment may be embodied as a system, method or computer program product. Therefore, the various aspects of the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment (including firmware, resident software, microcode, etc.) or a combination of software and hardware embodiments that are generally all referred to as "modules" or "systems" herein. In addition, the various aspects of the present disclosure may take the form of a computer program product contained in one or more computer-readable media having computer-readable program code contained thereon.
[0124] Any combination of one or more computer-readable media may be utilized. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or apparatus, or any suitable combination of the foregoing. More specific examples (non-exhaustive list) of computer-readable storage media would include the following: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer-readable storage medium may be any tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or apparatus.
[0125] Aspects of the present disclosure are described above with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiments of the present disclosure. It will be understood that each frame in the flowchart and / or block diagram and the combination of frames in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine. The instructions, when executed via the processor of a computer or other programmable data processing device, enable the function / action specified in one or more frames of the flowchart and / or block diagram to be implemented. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, an application-specific processor or a field programmable gate array.
[0126] The flow charts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the system, method and computer program product according to the various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, segment or part of the code, which includes one or more executable instructions for realizing one or more specified logical functions. It should also be noted that in some alternative implementations, the functions indicated in the box may not occur in the order indicated in the figure. For example, the two boxes shown in succession can actually be executed substantially simultaneously, or sometimes these boxes can be executed in reverse order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart and the combination of boxes in the block diagram and / or flow chart can be realized by a combination of a system based on special-purpose hardware or special-purpose hardware and computer instructions that performs a specified function or action.
[0127] While the foregoing is directed to embodiments of the present disclosure, other and further embodiments of the disclosure may be devised without departing from the basic scope thereof, and the scope of the disclosure is determined by the claims that follow.
Claims
1. A computer-implemented method for generating design options for an urban district design project, the urban district design project comprising the development and construction of a plurality of dwelling units to be constructed, the method comprising: generating a first geometric mesh for a first candidate design based on first design criteria associated with a first area of land; For the first candidate design, subdividing the first geometric grid to generate a first plurality of communities; For the first candidate design, populating the first plurality of communities with a first set of dwelling units; generating a first value of a metric for the first candidate design based on a first objective function; modifying the first candidate design based on the first value to generate a first design option; as well as determining that a second value of the metric generated for the first design option based on the first objective function exceeds the first value, indicating that the first design option is a higher ranked design than the first candidate design, determining whether the second value of the metric satisfies one or more convergence criteria; outputting the first design option when the second value of the metric satisfies the one or more convergence criteria, wherein subdividing the first geometric grid comprises: projecting at least one line segment on the first geometric grid to generate a first community included in the first plurality of communities and a second community included in the first plurality of communities, and further comprising: designating the at least one line segment as a road for entering both the first community and the second community, and Wherein the metrics include a solar energy metric indicating a sum of solar energy generated in all cells of the candidate design.
2. The computer-implemented method of claim 1 , wherein: Populating the first plurality of communities includes: determining that an area of a first community included in the first plurality of communities is greater than a minimum area; identifying a first sub-region within the first community; allocating the first sub-area to a first dwelling unit included in the first set of dwelling units; and A first dwelling unit type is assigned to the first dwelling unit.
3. The computer-implemented method of claim 1 , wherein: Generating the first value includes determining an estimated amount of solar energy collected by the first set of dwelling units.
4. The computer-implemented method of claim 1 , wherein: Generating the first value includes: determining a first length associated with a first line of sight from a first dwelling unit included in the first set of dwelling units; determining a second length associated with a second line of sight from a second dwelling unit included in the first set of dwelling units; The length of the first line of sight is combined with the length of the second line of sight to generate at least a portion of the first value.
5. The computer-implemented method of claim 1 , wherein: Generating the first value includes: 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 The first yard dimension is combined with the second yard dimension to generate at least a portion of the first value.
6. The computer-implemented method of claim 1 , wherein: Generating the first value includes: determining that a first community included in the first plurality of communities includes more dwelling units than a second community included in the first plurality of communities; and calculating a number of dwelling units included in the first neighborhood to generate at least a portion of the first value, The number of dwelling units included in the first community indicates a degree of variability of the community included in the first candidate design.
7. The computer-implemented method of claim 1 , wherein: Generating the first value includes: Determining to assign a first dwelling unit type to a first number of dwelling units included in the first set of dwelling units; 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 value, Wherein a difference between the first number of living units and the recommended number of living units indicates the extent to which the first candidate design satisfies a second design criterion.
8. The computer-implemented method of claim 1 , wherein: Generating the first value includes: 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 The first construction cost is combined with the second construction cost to generate at least a portion of the first value.
9. The computer-implemented method of claim 1 , wherein: Generating the first value includes: determining a first estimated income 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 income 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; The first estimated profit is combined with the second estimated profit to generate at least a portion of the first value.
10. A non-transitory computer-readable medium storing program instructions, which, when executed by one or more processors, causes the one or more processors to perform the computer-implemented method of claim 1 by performing the following steps.
11. The non-transitory computer readable medium of claim 10, wherein: The first design criteria defines a property boundary associated with a first area of the land, and the first geometric mesh is generated within the area defined by the property boundary.
12. The non-transitory computer readable medium of claim 10, wherein: The steps of populating the first plurality of communities include: determining that an area of a first community included in the first plurality of communities is greater than a minimum area; identifying a first sub-region within the first community; assigning the first sub-area 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 an area of a second community included in the first plurality of communities is smaller than the minimum area; identifying a second sub-region within the second community; and The second sub-area is assigned to a second dwelling unit included in the first set of dwelling units, wherein the second dwelling unit has a second dwelling unit type.
13. The non-transitory computer readable medium of claim 10, wherein: The step of generating the first value comprises: determining a first length associated with a first line of sight from a first dwelling unit included in the first set of dwelling units; determining a second length associated with a second line of sight from a second dwelling unit included in the first set of dwelling units; The length of the first line of sight is combined with the length of the second line of sight to generate at least a portion of the first value.
14. The non-transitory computer readable medium of claim 10, wherein: The step of generating the first value 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 The first yard dimension is combined with the second yard dimension to generate at least a portion of the first value.
15. The non-transitory computer readable medium of claim 10, wherein: The step of generating the first value comprises: determining that a first community included in the first plurality of communities includes more dwelling units than a second community included in the first plurality of communities; and calculating a number of dwelling units included in the first neighborhood to generate at least a portion of the first value, The number of dwelling units included in the first community indicates a degree of variability of the community included in the first candidate design.
16. The non-transitory computer readable medium of claim 10, wherein: The step of generating the first value comprises: Determining to assign a first dwelling unit type to a first number of dwelling units included in the first set of dwelling units; 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 value, Wherein a difference between the first number of living units and the recommended number of living units indicates the extent to which the first candidate design satisfies a second design criterion.
17. The non-transitory computer readable medium of claim 10, wherein: The step of generating the first value 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 The first construction cost is combined with the second construction cost to generate at least a portion of the first value.
18. The non-transitory computer readable medium of claim 10, wherein: The step of generating the first value comprises: determining a first estimated income 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 income 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; and The first estimated profit is combined with the second estimated profit to generate at least a portion of the first value.
19. A system comprising: A memory device for storing the designed pipelines in the urban area; as well as A processor, which when executing the urban area design pipeline is configured to perform the computer-implemented method of claim 1.
