Abstract: Example systems and methods allow for runtime control of robotic devices during a construction process. One example method includes determining at least one sequence of robot operations corresponding to at least one robot actor, causing the at least one robot actor to execute a portion of the at least one sequence of robot operations during a first time period, receiving an interrupt signal from a mobile computing device indicating a modification to the at least one sequence of robot operations, where the mobile computing device is configured to display a digital interface including one or more robot parameters describing the at least one robot actor and one or more tool parameters describing operating characteristics of at least one physical tool, and causing the at least one robot actor to execute a portion of the at least one modified sequence of robot operations during a second time period.

Abstract: Systems and methods are provided for specifying safety rules for robotic devices. A computing device can determine information about any actors present within a predetermined area of an environment. The computing device can determine a safety classification for the predetermined area based on the information. The safety classification can include: a low safety classification if the information indicates zero actors are present within the predetermined area, a medium safety classification if the information indicates any actors are present within the predetermined area all are of a predetermined first type, and a high safety classification if the information indicates at least one actor present within the predetermined area is of a predetermined second type. After determining the safety classification for the predetermined area, the computing device can provide a safety rule for operating within the predetermined area to a robotic device operating in the environment.

Abstract: Example embodiments may relate to methods and systems for selecting a grasp point on an object. In particular, a robotic manipulator may identify characteristics of a physical object within a physical environment. Based on the identified characteristics, the robotic manipulator may determine potential grasp points on the physical object corresponding to points at which a gripper attached to the robotic manipulator is operable to grip the physical object. Subsequently, the robotic manipulator may determine a motion path for the gripper to follow in order to move the physical object to a drop-off location for the physical object and then select a grasp point, from the potential grasp points, based on the determined motion path. After selecting the grasp point, the robotic manipulator may grip the physical object at the selected grasp point with the gripper and move the physical object through the determined motion path to the drop-off location.

Abstract: One method disclosed includes identifying, in a map of markers fixed in an environment, two co-located markers within a threshold distance of each other, where each of the two co-located markers has a non-overlapping visibility region. The method further includes determining a set of detected markers based on sensor data from a robotic device. The method additionally includes identifying, from the set of detected markers, a detected marker proximate to a first marker of the two co-located markers. The method also includes enforcing a visibility constraint based on the non-overlapping visibility region of each of the two co-located markers to determine an association between the detected marker and a second marker of the two co-located markers. The method further includes determining a location of the robotic device in the environment relative to the map based on the determined association.

Abstract: Systems and methods are provided for specifying safety rules for robotic devices. A computing device can determine information about any actors present within a predetermined area of an environment. The computing device can determine a safety classification for the predetermined area based on the information. The safety classification can include: a low safety classification if the information indicates zero actors are present within the predetermined area, a medium safety classification if the information indicates any actors are present within the predetermined area all are of a predetermined first type, and a high safety classification if the information indicates at least one actor present within the predetermined area is of a predetermined second type. After determining the safety classification for the predetermined area, the computing device can provide a safety rule for operating within the predetermined area to a robotic device operating in the environment.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for controlling a robot along a goal path. An initial Cartesian path is generated based on a goal path on a workpiece. Dynamic properties of the robot while the robot traverses an initial joint-space trajectory having an initial velocity profile are obtained. An adjusted velocity profile over the Cartesian path is generated based on the obtained dynamic properties. A trajectory is generated by combining the initial Cartesian path and the adjusted velocity profile.

Abstract: Systems and methods related to roadmaps for robotic devices are provided. A computing device can receive a roadmap representing a plurality of paths through an environment. The computing device can discretize the roadmap to obtain a discrete planning graph having a plurality of states corresponding to discretized segments of the plurality of paths of the roadmap such that states corresponding to adjacent discretized path segments are connected in the discrete planning graph. The computing device can determine a Boolean equation representing at least a portion of the discrete planning graph. The computing device can determine a sequence of states from the plurality of states of the discrete planning graph such that the determined sequence of states satisfies the Boolean equation. The computing device can provide a route through the environment for a robotic device based on the determined sequence of states.

Abstract: Example implementations may relate to optimization of observer robot locations. In particular, a control system may detect an event that indicates desired relocation of observer robots within a worksite. Each such observer robot may have respective sensor(s) configured to provide information related to respective positions of a plurality of target objects within the worksite. Responsively, the control system may (i) determine observer robot locations within the worksite at which one or more of the respective sensors are each capable of providing information related to respective positions of one or more of the plurality of target objects and (ii) determine a respectively intended level of positional accuracy for at least two respective target objects. Based on the respectively intended levels of positional accuracy, the control system may select one or more of the observer robot locations and may direct one or more observer robots to relocate to the selected locations.

Abstract: Disclosed herein is a worksite automation process that involves: generating a first sequence of tasks to build the product according to a model. The process further involves causing one or more robotic devices to build the product by beginning to execute the first sequence of tasks. Further, during the execution of the first sequence of tasks, performing a buildability analysis to determine a feasibility of completing the product by executing the first sequence of tasks. Based on the analysis, determining that it is not feasible to complete the product by executing the first sequence of tasks, and in response, generating a second sequence of tasks to complete the product according to the model. Then, causing the one or more robotic devices to continue building the product by beginning to execute the second sequence of tasks.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for enhanced path planning. In some implementations, a first path is determined for travel by a robot, the first path extending from an origin to a destination. Path segments are determined based on the first path. A corner between two of the path segments has an angle less than a predetermined threshold is determined. In response to determining that the corner between two of the path segments has an angle less than the predetermined threshold, a bypass path segment is determined that bypasses the corner. A second path for the robot to travel is determined based on the path segments and the bypass path segment. Data indicating the second path is provided to the robot.

Abstract: Techniques for controlling a robot are described in this document. In some implementations, a method includes determining a first target position of a first point located at the first end of the first link based on pose data for an end effector of a robot having a wrist offset. A second target position of a first joint connecting the first link to a second link is determined. A third target position of a second joint located at the first end of a third link is determined, including defining a first plane that includes the second target position of the first joint. A position and size of a circle that lies within a second plane is determined. A point on a perimeter of the circle is selected as the third target position. Movement data based on each position of each joint is provided to a control system.

Abstract: In one aspect, a method is described. The method may include providing an end effector tool of a robotic device configured to perform a task on a work surface within a worksite coordinate frame. The method may further include providing first location data indicating a first location of the end effector tool with respect to the work surface, providing second location data indicating a second location of the end effector tool within the worksite coordinate frame, and providing third location data indicating a third location of the end effector tool within the worksite coordinate frame. The method may further include tracking the location of the end effector tool based on the first, second, and third location data, and, based on the tracked location of the tool, instructing the robotic device to manipulate the end effector tool to perform a task on the work surface.

Abstract: Methods, systems, and computer programs stored on computer storage devices, for coordinating movements of robots are disclosed. One of the methods includes, for each robot in a group of robots, identifying a set of tasks assigned to the robot and generating a plurality of candidate motion plans. The method further includes, for each candidate motion plan: (i) generating a 3D model that represents a volume of space through which the robot would move in executing the sequence of motions represented by the candidate motion plan, and (ii) determining a score for the candidate motion plan. The method further includes determining conflicts between candidate motion plans of different robots, selecting a motion plan from the candidate motion plans based on the score for the selected motion plan and the conflicts, and providing the selected motion plans for execution by the group of robots.

Abstract: This specification describes systems, methods, devices, and other techniques for planning workspaces for automated fabrication processes. A computing system facilitates planning by receiving a set of parameters for planning a layout of a workspace for an automated fabrication process, and generating a plurality of candidate workspace layouts, including selecting, for each candidate workspace layout, (i) one or more robots for performing tasks in the automated fabrication process and (ii) corresponding locations for the one or more robots within the workspace. The system determines an optimal workspace layout based on the plurality of candidate workspace layouts, generates a workspace layout specification for the optimal workspace layout, and provides the workspace layout specification to one or more second computing systems.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for a mobile robotic frame system. In some implementations, a mobile robot includes a motorized frame that is configured to travel to a location. The mobile robot includes a positioning assembly coupled to the motorized frame, a robotic arm having a manipulator, and sensors coupled to the motorized frame. A control system is configured to process data from the sensors and, based on the data from the sensors, provide control data to (i) move the motorized frame, (ii) adjust one or more movable components of the positioning assembly, and (ii) move the robotic arm relative to the motorized frame. The one or more movable components and the robotic arm are operable to position the manipulator at any position in a three-dimensional work volume with 6 degrees of freedom while the motorized frame remains at the location.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for planning a path of motion for a robot. In some implementations, a candidate path of movement is determined for each of multiple robots. A swept region, for each of the multiple robots, is determined that the robot would traverse through along its candidate path. At least some of the swept regions for the multiple robots is aggregated to determine amounts of overlap among the swept regions at different locations. Force vectors directed outward from the swept regions are assigned, wherein the force vectors have different magnitudes assigned according to the respective amounts of overlap of the swept regions at the different locations. A path for a particular robot to travel is determined based on the swept regions and the assigned magnitudes of the forces.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a feature extraction neural network to generate domain-invariant feature representations from domain-varying input images. In one aspect, the method includes obtaining a training dataset comprising a first set of target domain images and a second set of real domain images that each have pixel-wise level alignment with a corresponding target domain image, and training the feature extraction neural network on the training dataset based on optimizing an objective function that includes a term that depends on a similarity between respective feature representations generated by the network for a pair of target and source domain images.

Abstract: A method includes receiving a first time-parameterized path for the first robotic device, and an indication of a second robotic device having a second time-parameterized path that overlaps with the first time-parameterized path at a first location. The method also includes executing, by the first robotic device, a first portion of the first time-parameterized path before reaching the first location, wherein execution of the first portion corresponds to a first rate of progress of the first robotic device along the first time-parameterized path. The first robotic device then receives a communication signal from the second robotic device indicating a second rate of progress of the second robotic device along the second time-parameterized path. The method then includes the first robotic device determining a difference between the first rate of progress and the second rate of progress, and modifying execution of the first time-parameterized path based on the determined difference.

Abstract: Systems, methods, devices, and other techniques for planning and re-planning robot motions. The techniques can include obtaining a schedule that defines an execution order for a plurality of plans, each plan defining a sequence of tasks; providing instructions to the robotic system to execute plans from the plurality of plans according to the schedule; obtaining measurements for one or more parameters that represent a state of the robotic system or its environment that results from execution of at least one plan from the plurality of plans; determining, based on the measurements, that a particular plan from the plurality of plans, which has not completed execution, is to be revised; generating, using the measurements, a revised version of the particular plan; and adjusting the schedule so as to resolve a conflict between the revised version of the particular plan and at least one other plan in the plurality of plans.

Abstract: Example systems and methods are disclosed for implementing vehicle operation limits to prevent vehicle load failure during vehicle teleoperation. The method may include receiving sensor data from sensors on a vehicle that carries a load. The vehicle may be controlled by a remote control system. The load weight and dimensions may be determined based on the sensor data. In order to prevent a vehicle load failure, a forward velocity limit and an angular velocity limit may be calculated. Vehicle load failures may include the vehicle tipping over, the load tipping over, the load sliding off of the vehicle, or collisions. The vehicle carrying the load may be restricted from exceeding the forward velocity limit and/or the angular velocity limit during vehicle operation. The remote control system may display a user interface indicating to a remote operator the forward velocity limit and the angular velocity limit.