The subject technology is related to methods and apparatus for training a set of regression machine learning models with a training set to produce a set of predictive values for a pending manufacturing request, the training set including data extracted from a set of manufacturing transactions submitted by a set of entities of a supply chain. A multi-objective optimization model is implemented to (1) receive an input including the set of predictive values and a set of features of a physical object, and (2) generate an output with a set of attributes associated with a manufacture of the physical object in response to receiving the input, the output complying with a multi-objective condition satisfied in the multi-objective optimization model.

There is provided a computer implemented method of manufacturing a truss of a three dimensional (3D) object representation, comprising: receiving a definition of the 3D object representation, arranging within an interior space of the 3D object representation, a plurality of instances of a sphere having a common radius to create a packed sphere arrangement, computing nodes of a truss for the 3D object representation, each respective node positioned at a center of each respective instance of each sphere of the packed sphere arrangement, computing beams of the truss by connecting adjacent nodes with respective beams, and providing code instructions for execution by a manufacturing device controller of a manufacturing device for manufacturing the truss.

Methods and systems are provided, which convert points in a cloud into a model for 3D printing in a computationally efficient manner and while maintaining and possibly adjusting shape, volume and color information. Methods include deriving, from the points, a crude watertight mesh with respect to the points, e.g., an alpha shape, determining, using normal vectors associated with the points, locations of the points with respect to the mesh (e.g., as being inside, outside or within the model) and using the derived mesh to define the model with respect to the determined locations of the points. Combining the computational geometry approach with the field approach is synergetic and results in better information content of the resulting model for 3D printing while consuming less computational resources.

Parameters of a set of tools are stored on a storage device. The tools are part of a manufacturing assembly usable for removing one or more support structures from a part. The support structures are formed with the part to facilitate additive manufacturing of the part. A near-net shape is modeled which includes the part combined with the support structures. A process plan is developed that includes subtractive manufacturing operations by the manufacturing assembly that remove the support structures. The process plan repeatedly updates the near-net shape as each one of the support structures is incrementally removed.

A system and method for improving additive manufacturing, including additive manufacturing toolpaths, is provided. The system and method includes a toolpath generator that obtains initial toolpaths of an object, identifies isolated paths in the toolpaths, and adds bridge connections between neighboring isolated paths in each layer to improve the toolpaths. The bridge connections facilitate the continuous and non-stop deposition of each layer according to improved toolpaths during additive manufacture, which can reduce total deposition time and improve the resultant additive manufacture.

In some embodiments, techniques are provided for verifying that a fabrication system can fabricate a proposed segmented design. A paintbrush pattern that represents capabilities of the fabrication system is determined. One or more forbidden patterns that the fabrication system is not capable of fabricating are determined based on the paintbrush pattern. The proposed segmented design is then searched for the forbidden patterns. If any forbidden patterns are found, the proposed segmented design is determined to not be fabricable by the fabrication system. If no forbidden patterns are found, then the proposed segmented design is determined to be fabricable by the fabrication system.

Aspects relate to methods and systems for manufacturing orientation selection, using machine learning. An exemplary method includes receiving, using a computing device, a computer model representative of a part for manufacture, inputting, using the computing device, the computer model to a machine learning model, determining, using the computing device, a plurality of candidate orientations as a function of the machine learning model and the computer model, and ranking, using the computing device, each candidate orientation of the plurality of candidate orientations as a function of the machine learning model and the computer model.

In one aspect, there is provided a method performed by one or more data processing apparatus, the method including obtaining a baseline image of a baseline biological organism brain, obtaining a follow-up image of a target biological organism brain, wherein the follow-up image shows at least a damaged region of the target biological organism brain, processing the baseline image and the follow-up image to generate data defining a predicted anatomical microstructure of the damaged region of the target biological organism brain before the target biological organism brain was damaged, and generating a design for a neural prosthesis for replacing the damaged region of the target biological organism brain based on the predicted anatomical microstructure of the damaged region of the target biological organism brain before the target biological organism brain was damaged.

The present invention includes a method for generating a three-dimensional model of a bone and generating a cut plan for excavating a portion of the bone according to the cut plan to allow the insertion of a custom implant. In a particular arrangement, the method also includes excavating the bone with an autonomous extremity excavator utilizing the cut plan generated by a processor. In a further arrangement, the method includes generating a digital model of a custom implant and generating, using the digital model, a physical model sharing the same dimensions as the digital module using manufacturing device.

An off-the-shelf oral splint that is operatively secured to the maxilla and mandible to assist in reduction and provide maintenance of reduction of maxillary and mandibular fractures in the edentulous or partially edentulous patient. The oral splint is fabricated into a plurality of standardized sizes. These sizes are determined by imaging a population of jaws, measuring dimensions thereof, manipulating (e.g., calculating the mean) these dimensions, and generating a size that is representative of a subset of that population. This can be done for all sizes that would represent individuals in that population. The splint itself is fabricated virtually by creating “U-shapes”, splitting them horizontally into halves, creating an evacuation channel, and generating a coupling mechanism to hold the halves together. The splint can then be printed or otherwise manufactured.