Abstract: An agent engine allocates a collection of agents to scan the surface of an object model. Each agent operates autonomously and implements particular behaviors based on the actions of nearby agents. Accordingly, the collection of agents exhibits swarm-like behavior. Over a sequence of time steps, the agents traverse the surface of the object model. Each agent acts to avoid other agents, thereby maintaining a relatively consistent distribution of agents across the surface of the object model over all time steps. At a given time step, the agent engine generates a slice through the object model that intersects each agent in a group of agents. The slice associated with a given time step represents a set of locations where material should be deposited to fabricate a 3D object. Based on a set of such slices, a robot engine causes a robot to fabricate the 3D object.

Abstract: Techniques are disclosed for controlling robotic systems to perform assembly tasks. In some embodiments, a robot control application receives sensor data associated with one or more parts. The robot control application applies a grasp perception model to predict one or more grasp proposals indicating regions of the one or more parts that a robotic system can grasp. The robot control application causes the robotic system to grasp one of the parts based on a corresponding grasp proposal. If the pose of the grasped part needs to be changed in order to assemble the part with one or more other parts, the robot control application determines movements of the robotic system required to re-grasp the part in a different pose. In addition, the robot control application determines movements of the robot system for assembling the part with the one or more other parts based on results of a motion planning technique.

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: One embodiment of the present invention sets forth a technique for controlling the execution of a physical process. The technique includes receiving, as input to a machine learning model that is configured to adapt a simulation of the physical process executing in a virtual environment to a physical world, simulated output for controlling how the physical process performs a task in the virtual environment and real-world data collected from the physical process performing the task in the physical world. The technique also includes performing, by the machine learning model, one or more operations on the simulated output and the real-world data to generate augmented output. The technique further includes transmitting the augmented output to the physical process to control how the physical process performs the task in the physical world.

Abstract: A robot system is configured to identify gestures performed by an end-user proximate to a work piece. The robot system then determines a set of modifications to be made to the work piece based on the gestures. A projector coupled to the robot system projects images onto the work piece that represent the modification to be made and/or a CAD model of the work piece. The robot system then performs the modifications.

Abstract: A robot is configured to assist an end-user with creative tasks. While the end-user modifies the work piece, the robot observes the modifications made by the end-user and determines one or more objectives that the end-user may endeavor to accomplish. The robot then determines a set of actions to perform that assist the end-user with accomplishing the objectives.

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: One embodiment of the present invention sets forth a technique for performing tasks associated with a construction project. The technique includes transmitting to a worker, via a mobile computing device worn by the worker, a first instruction related to performing a first task included in a plurality of tasks associated with a construction project, and transmitting to a light-emitting device a command to provide a visual indicator to the worker that facilitates performing the first task, based on an input received from the mobile computing device, determining that the worker has completed the first task of the construction project, selecting, from a database that tracks eligibility of each of the plurality of tasks, a second task included in the plurality of tasks that the worker is eligible to perform, and transmitting to the worker, via the mobile computing device, a second instruction related to performing the second task.

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 robot system is configured to fabricate three-dimensional (3D) objects using closed-loop, computer vision-based control. The robot system initiates fabrication based on a set of fabrication paths along which material is to be deposited. During deposition of material, the robot system captures video data and processes that data to determine the specific locations where the material is deposited. Based on these locations, the robot system adjusts future deposition locations to compensate for deviations from the fabrication paths. Additionally, because the robot system includes a 6-axis robotic arm, the robot system can deposit material at any locations, along any pathway, or across any surface. Accordingly, the robot system is capable of fabricating a 3D object with multiple non-parallel, non-horizontal, and/or non-planar layers.

Abstract: A control application implements computer vision techniques to cause a positioning robot and a welding robot to perform fabrication operations. The control application causes the positioning robot to place elements of a structure at certain positions based on real-time visual feedback captured by the positioning robot. The control application also causes the welding robot to weld those elements into place based on real-time visual feedback captured by the welding robot. By analyzing the real-time visual feedback captured by both robots, the control application adjusts the positioning and welding operations in real time.

Abstract: A robot system models the behavior of a user when the user occupies an operating zone associated with a robot. The robot system predicts future behaviors of the user, and then determines whether those predicted behaviors interfere with anticipated behaviors of the robot. When such interference may occur, the robot system generates dynamics adjustments that can be implemented by the robot to avoid such interference. The robot system may also generate dynamics adjustments that can be implemented by the user to avoid such interference.

Abstract: A robot system is configured to fabricate three-dimensional (3D) objects using closed-loop, computer vision-based control. The robot system initiates fabrication based on a set of fabrication paths along which material is to be deposited. During deposition of material, the robot system captures video data and processes that data to determine the specific locations where the material is deposited. Based on these locations, the robot system adjusts future deposition locations to compensate for deviations from the fabrication paths. Additionally, because the robot system includes a 6-axis robotic arm, the robot system can deposit material at any locations, along any pathway, or across any surface. Accordingly, the robot system is capable of fabricating a 3D object with multiple non-parallel, non-horizontal, and/or non-planar layers.

Abstract: A robot system is configured to fabricate three-dimensional (3D) objects using closed-loop, computer vision-based control. The robot system initiates fabrication based on a set of fabrication paths along which material is to be deposited. During deposition of material, the robot system captures video data and processes that data to determine the specific locations where the material is deposited. Based on these locations, the robot system adjusts future deposition locations to compensate for deviations from the fabrication paths. Additionally, because the robot system includes a 6-axis robotic arm, the robot system can deposit material at any locations, along any pathway, or across any surface. Accordingly, the robot system is capable of fabricating a 3D object with multiple non-parallel, non-horizontal, and/or non-planar layers.

Abstract: A technique for displaying a representative path associated with a robotic device. The technique includes detecting at least one reference point within a first image of a workspace, generating the representative path based on path instructions associated with the robotic device and the at least one reference point, and displaying the representative path within the workspace.

Abstract: A robotic assembly cell is configured to generate a physical mesh of physical polygons based on a simulated mesh of simulated triangles. A control application configured to operate the assembly cell selects a simulated polygon in the simulated mesh and then causes a positioning robot in the cell to obtain a physical polygon that is similar to the simulated polygon. The positioning robot positions the polygon on the physical mesh, and a welding robot in the cell then welds the polygon to the mesh. The control application captures data that reflects how the physical polygon is actually positioned on the physical mesh, and then updates the simulated mesh to be geometrically consistent with the physical mesh. In doing so, the control application may execute a multi-objective solver to generate an updated simulated mesh that meets specific design criteria.

Abstract: An agent engine allocates a collection of agents to scan the surface of an object model. Each agent operates autonomously and implements particular behaviors based on the actions of nearby agents. Accordingly, the collection of agents exhibits swarm-like behavior. Over a sequence of time steps, the agents traverse the surface of the object model. Each agent acts to avoid other agents, thereby maintaining a relatively consistent distribution of agents across the surface of the object model over all time steps. At a given time step, the agent engine generates a slice through the object model that intersects each agent in a group of agents. The slice associated with a given time step represents a set of locations where material should be deposited to fabricate a 3D object. Based on a set of such slices, a robot engine causes a robot to fabricate the 3D object.

Abstract: A robotic assembly cell is configured to generate a physical mesh of physical polygons based on a simulated mesh of simulated triangles. A control application configured to operate the assembly cell selects a simulated polygon in the simulated mesh and then causes a positioning robot in the cell to obtain a physical polygon that is similar to the simulated polygon. The positioning robot positions the polygon on the physical mesh, and a welding robot in the cell then welds the polygon to the mesh. The control application captures data that reflects how the physical polygon is actually positioned on the physical mesh, and then updates the simulated mesh to be geometrically consistent with the physical mesh. In doing so, the control application may execute a multi-objective solver to generate an updated simulated mesh that meets specific design criteria.

Abstract: One embodiment of the present invention sets forth a technique for controlling the execution of a physical process. The technique includes receiving, as input to a machine learning model that is configured to adapt a simulation of the physical process executing in a virtual environment to a physical world, simulated output for controlling how the physical process performs a task in the virtual environment and real-world data collected from the physical process performing the task in the physical world. The technique also includes performing, by the machine learning model, one or more operations on the simulated output and the real-world data to generate augmented output. The technique further includes transmitting the augmented output to the physical process to control how the physical process performs the task in the physical world.

Abstract: An agent engine allocates a collection of agents to scan the surface of an object model. Each agent operates autonomously and implements particular behaviors based on the actions of nearby agents. Accordingly, the collection of agents exhibits swarm-like behavior. Over a sequence of time steps, the agents traverse the surface of the object model. Each agent acts to avoid other agents, thereby maintaining a relatively consistent distribution of agents across the surface of the object model over all time steps. At a given time step, the agent engine generates a slice through the object model that intersects each agent in a group of agents. The slice associated with a given time step represents a set of locations where material should be deposited to fabricate a 3D object. Based on a set of such slices, a robot engine causes a robot to fabricate the 3D object.