Abstract: A method and system provide the ability to generate and use synthetic data to extract elements from a floor plan drawing. A room layout is generated. Room descriptions are used to generate and place synthetic instances of symbol elements in each room. A floor plan drawing is obtained and pre-processed to determine a drawing area. Based on the synthetic data symbols in the floor plan drawing are detected. Orientations of the detected symbols are also detected. Based on the detected symbols and orientations, building information model (BIM) elements are fetched and placed in the floor plan drawing.

Abstract: Methods, systems, and apparatus, including medium-encoded computer program products, for computer aided design of physical structures using generative design processes, where the 3D models of the physical structures are produced so as to facilitate manufacturing of the physical structures using 2.5-axis subtractive manufacturing systems and techniques, include: obtaining a design space, design criteria, and in-use case(s); iteratively modifying a generatively designed shape in the design space in accordance with the design criteria and the in-use case(s) using a density-based representation of the generatively designed shape and including adjusting the density-based representation of the generatively designed three dimensional shape in accordance with a milling direction of a 2.

Abstract: A simulation suggestion system comprising a server connected with a plurality of clients via a network. The server executes a design engine for generating designs, a simulation suggestion engine for identifying suggested simulations for the designs, and a simulation engine for performing the suggested simulations on the designs. The simulation engine includes one or more simulation tools for performing one or more suggested simulations on a design. A user completes a design of an object via the design engine. The simulation suggestion engine automatically identifies one or more simulation tools that are appropriate for the completed design based on at least one characteristic of the design. The simulation suggestion engine automatically identifies and loads simulation parameters (boundary conditions) for the suggested simulation tools. The suggested simulation tools are then performed on the completed design via the simulation engine.

Abstract: A design engine is configured to interact with potential occupants of a structure in order to generate data that defines the usage preferences of those occupants. The design engine generates multiple candidate designs for the structure via a generative design process, and then evaluates each candidate design using a set of metrics determined relative to the usage preferences. Based on these evaluations, the design engine selects at least one candidate design that optimizes the set of metrics across all potential occupants.

Abstract: A method and system provide the ability to design a terrain surface. A triangular surface mesh representative of an existing surface is obtained and consists of triangles that are connected by vertices and edges. A drain intention is specified for the terrain surface through a geometry that is a point or line. The drain intention defines a drainage flow that influences a shape of the terrain surface. The mesh is modified using a Voronoi diagram that prevents a drain conflict between mesh triangles. A drain direction is autonomously determined a for each of the mesh triangles based on the drain intention. The determination generates a drain pattern that is used to shape the terrain surface.

Abstract: In various embodiments, a training application generates a trained encoder that automatically generates shape embeddings having a first size and representing three-dimensional (3D) geometry shapes. First, the training application generates a different view activation for each of multiple views associated with a first 3D geometry based on a first convolutional neural network (CNN) block. The training application then aggregates the view activations to generate a tiled activation. Subsequently, the training application generates a first shape embedding having the first size based on the tiled activation and a second CNN block. The training application then generates multiple re-constructed views based on the first shape embedding. The training application performs training operation(s) on at least one of the first CNN block and the second CNN block based on the views and the re-constructed views to generate the trained encoder.

Abstract: A method and system provide the ability to manage data. Property sets consisting of property set objects are created based on a schema that defines a type and a version of the objects. The property sets are organized hierarchically to form a property tree. A commit graph stores the property set objects via an append only data structure. The commit graph provides a topology of changes between states of the objects as commit nodes organized as parent commit nodes and child commit nodes. Change sets represent a change between two commit nodes. Each change set tracks changes made on the objects, and the changes specify permitted basic operations including insert, remove, or modify operations that are applied on each state to get to a next state of the objects.

Abstract: Design process that performs geometry synthesis on a 3D model of a product based on a design problem statement and manufacturing constraints associated with a manufacturing machine intended to manufacture the product. The manufacturing constraints may include dimensions for a tool bit, dimensions for a tool head, a set of machining directions of the manufacturing machine, or any combination thereof. For a 5-axis manufacturing machine, the set of machining directions may be determined by a “NormalSearch” algorithm and/or a “HeatSearch” algorithm. The geometry synthesis produces a design solution comprising a final 3D model of the product, whereby each point on the boundary of the final 3D model is determined to be accessible by a tool bit and/or tool head in at least one machining direction of the manufacturing machine. Thus, the design solution for the product is more easily and directly manufacturable by the manufacturing machine.

Abstract: A system and method for generating a submittal register for various construction projects or other items is disclosed. Among other things, the system and method include inputting the construction project specifications in a file format, such as PDF, into a web application interface to convert the specification to a text file, applying an algorithm to the text file based on a set of rules, that are iteratively revised using machine learning, to identify all required submittals, generating a final submittal register, and delivering the final submittal register.

Abstract: A design analysis engine analyzes a CAD assembly to generate a topological model. The topological model is a graph of nodes coupled together via a set of edges. Each node represents a different CAD model in the CAD assembly and each edge represents a different connection between two such CAD models. The design analysis engine also analyzes the CAD assembly to generate a data model corresponding to the topological model. The data model is a structured dataset that includes component entries and connection entries. A component entry includes design data associated with a CAD model in the CAD assembly and a connection entry includes design data associated with a physical or logical connection between two or more such CAD models. A user interacts with the topological model to navigate the CAD assembly, obtain CAD model data, and initiate automatically-performed design tasks.

Abstract: A design engine implements a probabilistic approach to generating designs that exposes automatically-generated design knowledge to the user during operation. The design engine interactively generates successive populations of designs based on a problem definition associated with a design problem and/or a previously-generated population of designs. During the above design process, the design engine generates a design knowledge graphical user interface (GUI) that graphically exposes various types of design knowledge to the user. In particular, the design engine generates a design variable dependency GUI that visualizes various dependencies between designs variables. The design engine also generates a design evolution GUI that animates the evolution of designs across the successive design populations. Additionally, the design engine generates a design exploration GUI that facilitates the user exploring various statistical properties of automatically-generated designs.

Abstract: Methods, systems, and apparatus, including medium-encoded computer program products, for designing three dimensional lattice structures include, in one aspect, a method including: obtaining a mechanical problem definition including a 3D model of an object; generating a numerical simulation model for the 3D model of the object using one or more loading cases and one or more isotropic solid materials identified as a baseline material model for a design space; predicting performance of different lattice settings in different orientations in the design space using a lattice structural behavior model in place of the baseline material model in the numerical simulation model; and presenting a set of lattice proposals for the design space based on the predicted performance of the different lattice settings in the different orientations; wherein the lattice structural behavior model has been precomputed for the different lattice settings, which are generable by the 3D modeling program.

Abstract: In one embodiment of the present invention, a method for multiple device interaction includes detecting an orientation of a first device relative to a second device. The method also includes detecting a first gesture performed with either the first device or the second device, wherein the first gesture causes a first action that is based at least in part on the orientation of the first device relative to the second device.

Abstract: A method and system provide the ability to propagate object connections. A three-dimensional (3D) model (that has 3D object components) is acquired. Two or more of the 3D object components are selected as input elements. A connection between the input elements is defined and selected. Data is autonomously collected from the selected connection. The data includes a number of the input elements, a section type of the input elements, and a relative geometrical position between the input elements. A rule autonomously created based on the data. The 3D model is autonomously searched based on the rule to identify other instances of other 3D object components that are consistent with the data. The connection is then autonomously propagated to the identified other 3D object components.

Abstract: In various embodiments, a training application trains a machine learning model to modify portions of shapes when designing 3D objects. The training application converts first structural analysis data having a first resolution to first coarse structural analysis data having a second resolution that is lower than the first resolution. Subsequently, the training application generates one or more training sets based on a first shape, the first coarse structural analysis data, and a second shape that is derived from the first shape. Each training set is associated with a different portion of the first shape. The training application then performs one or more machine learning operations on the machine learning model using the training set(s) to generate a trained machine learning model. The trained machine learning model modifies at least a portion of a shape having the first resolution based on coarse structural analysis data having the second resolution.

Abstract: A control mechanism scheduler for a water resource infrastructure receives operating data and disturbance data, the operating data describing infrastructure components of the water resource infrastructure, the disturbance data comprising a disturbance signal describing a disturbance expected to disturb the water resource infrastructure. The control mechanism scheduler generates classes for disturbance signals, generates simulations of the water resource infrastructure, and generates schedules of setpoints for control mechanisms actuable to control the infrastructure components of the water resource infrastructure in accordance with approaching a predetermined objective.

Abstract: A method and system provide for searching a computer-aided design (CAD) drawing. A CAD drawing is obtained and includes vector based geometric entities. For each entity, primitives are extracted and held in a graph with graph nodes that record entity paths. A feature coordinate system is created for each of the entities using the primitives. The primitives are transformed from a world coordinate system to feature coordinates of the feature coordinate system. Geometry data of the transformed entities is encoded into index codes that are utilized in an index table as keys with the graph nodes as values. A target geometric entity is identified and a target index code is determined and used to query the index table to identify instances of the target geometric entity in the CAD drawing. Found instances in the CAD drawing are displayed in a visually distinguishable manner.

Abstract: A method, apparatus, and system provide the ability to simulate dynamic motion for a computerized model (of finite mesh elements). An element diagonal lumped mass matrix of the mesh, an estimate of a highest element eigenvector and eigenvalue of the mesh, and a kinematic state of the model are computed. Processing iterates until exceeding a time duration. Incremental strain and stress tensors, and hypo-elastic material constants are computed. Within the time duration iteration, eigenvalues are converged, a power-sweep stress field is computed from the strain field using the material constants; divergence of the power-sweep stress field is computed using the current gradient operator; and a power-sweep estimate is computed. Upon convergence, the stability limit is determined and utilized as a time interval for simulating the dynamic motion.

Abstract: One embodiment of the present invention sets forth a technique for generating simulated training data for a physical process. The technique includes receiving, as input to at least one machine learning model, a first simulated image of a first object, wherein the at least one machine learning model includes mappings between simulated images generated from models of physical objects and real-world images of the physical objects. The technique also includes performing, by the at least one machine learning model, one or more operations on the first simulated image to generate a first augmented image of the first object. The technique further includes transmitting the first augmented image to a training pipeline for an additional machine learning model that controls a behavior of the physical process.

Abstract: A computer-implemented method for computationally determining ventilation efficiency when generating a building design comprises: generating a first three-dimensional (3D) mesh based on a first 3D building model; performing a first fluid dynamic computer simulation based on the first 3D mesh and first environmental data associated with the first 3D building model to generate a first output data set; and computing, based on the first output data set, a first value for a ventilation performance metric that is associated with the first 3D building model.