Abstract: Method and apparatus for object detection by a robot are provided. The method comprises analyzing using a set of trained detection models, one or more first images of an environment of the robot to detect one or more objects in the environment of the robot, generating at least one fine-tuned model by training one or more of the trained detection models in the set, wherein the training is based on a second image of the environment of the robot and annotations associated with the second image, wherein the annotations identify one or more objects in the second image, updating the set of trained detection models to include the generated at least one fine-tuned model, and analyzing using the updated set of trained detection models, one or more third images of the environment of the robot to detect one or more objects in the environment.

Abstract: A robotic device includes a control system. The control system receives a first measurement indicative of a first distance between a center of mass of the machine and a first position in which a first leg of the machine last made initial contact with a surface. The control system also receives a second measurement indicative of a second distance between the center of mass of the machine and a second position in which the first leg of the machine was last raised from the surface. The control system further determines a third position in which to place a second leg of the machine based on the received first measurement and the received second measurement. Additionally, the control system provides instructions to move the second leg of the machine to the determined third position.

Abstract: A method of constrained mobility mapping includes receiving from at least one sensor of a robot at least one original set of sensor data and a current set of sensor data. Here, each of the at least one original set of sensor data and the current set of sensor data corresponds to an environment about the robot. The method further includes generating a voxel map including a plurality of voxels based on the at least one original set of sensor data. The plurality of voxels includes at least one ground voxel and at least one obstacle voxel. The method also includes generating a spherical depth map based on the current set of sensor data and determining that a change has occurred to an obstacle represented by the voxel map based on a comparison between the voxel map and the spherical depth map. The method additional includes updating the voxel map to reflect the change to the obstacle.

Abstract: A method for online authoring of robot autonomy applications includes receiving sensor data of an environment about a robot while the robot traverses through the environment. The method also includes generating an environmental map representative of the environment about the robot based on the received sensor data. While generating the environmental map, the method includes localizing a current position of the robot within the environmental map and, at each corresponding target location of one or more target locations within the environment, recording a respective action for the robot to perform. The method also includes generating a behavior tree for navigating the robot to each corresponding target location and controlling the robot to perform the respective action at each corresponding target location within the environment during a future mission when the current position of the robot within the environmental map reaches the corresponding target location.

Abstract: Systems and methods related to intelligent grippers with individual cup control are disclosed. One aspect of the disclosure provides a method of determining grip quality between a robotic gripper and an object. The method comprises applying a vacuum to two or more cup assemblies of the robotic gripper in contact with the object, moving the object with the robotic gripper after applying the vacuum to the two or more cup assemblies, and determining, using at least one pressure sensor associated with each of the two or more cup assemblies, a grip quality between the robotic gripper and the object.

Abstract: A computer-implemented method executed by data processing hardware of a robot causes the data processing hardware to perform operations. The robot includes an articulated arm having an end effector engaged with a constrained object. The operations include receiving a measured task parameter set for the end effector. The measured task parameter set includes position parameters defining a position of the end effector. The operations further include determining, using the measured task parameter set, at least one axis of freedom and at least one constrained axis for the end effector within a workspace. The operations also include assigning a first impedance value to the end effector along the at least one axis of freedom and assigning a second impedance value to the end effector along the at least one constrained axis. The operations include instructing the articulated arm to move the end effector along the at least one axis of freedom.

Abstract: A robot includes a mobile base, a turntable rotatably coupled to the mobile base, a robotic arm operatively coupled to the turntable, and at least one directional sensor. An orientation of the at least one directional sensor is independently controllable. A method of controlling a robotic arm includes controlling a state of a mobile base and controlling a state of a robotic arm coupled to the mobile base, based, at least in part, on the state of the mobile base.

Abstract: Systems and methods for determining movement of a robot about an environment are provided. A computing system of the robot (i) receives information including a navigation target for the robot and a kinematic state of the robot; (ii) determines, based on the information and a trajectory target for the robot, a retargeted trajectory for the robot; (iii) determines, based on the retargeted trajectory, a centroidal trajectory for the robot and a kinematic trajectory for the robot consistent with the centroidal trajectory; and (iv) determines, based on the centroidal trajectory and the kinematic trajectory, a set of vectors having a vector for each of one or more joints of the robot.

Abstract: A method includes receiving, while a robot traverses a building environment, sensor data captured by one or more sensors of the robot. The method includes receiving a building information model (BIM) for the environment that includes semantic information identifying one or more permanent objects within the environment. The method includes generating a plurality of localization candidates for a localization map of the environment. Each localization candidate corresponds to a feature of the environment identified by the sensor data and represents a potential localization reference point. The localization map is configured to localize the robot within the environment when the robot moves throughout the environment.

Abstract: An example robot includes: a motor disposed at a joint configured to control motion of a member of the robot; a transmission including an input member coupled to and configured to rotate with the motor, an intermediate member, and an output member, where the intermediate member is fixed such that as the input member rotates, the output member rotates therewith at a different speed; a pad frictionally coupled to a side surface of the output member of the transmission and coupled to the member of the robot; and a spring configured to apply an axial preload on the pad, wherein the axial preload defines a torque limit that, when exceeded by a torque load on the member of the robot, the output member of the transmission slips relative to the pad.

Abstract: A method of estimating one or more mass characteristics of a payload manipulated by a robot includes moving the payload using the robot, determining one or more accelerations of the payload while the payload is in motion, sensing, using one or more sensors of the robot, a wrench applied to the payload while the payload is in motion, and estimating the one or more mass characteristics of the payload based, at least in part, on the determined accelerations and the sensed wrench.

Abstract: An electronic circuit comprises a charge storing component, a set of one or more switching components coupled to the charge storing component, and an additional switching component coupled to each of the one or more switching components in the set. The additional switching component is configured to operate in a first state or a second state based on a received current or voltage. The first state prevents current to flow from the charge storing component to each of the one or more switching components in the set and the second state allows current to flow from the charge storing component to each of the one or more switching components in the set.

Abstract: An example robot includes a hydraulic actuator cylinder controlling motion of a member of the robot. The hydraulic actuator cylinder comprises a piston, a first chamber, and a second chamber. A valve system controls hydraulic fluid flow between a hydraulic supply line of pressurized hydraulic fluid, the first and second chambers, and a return line. A controller may provide a first signal to the valve system so as to begin moving the piston based on a trajectory comprising moving in a forward direction, stopping, and moving in a reverse direction. The controller may provide a second signal to the valve system so as to cause the piston to override the trajectory as it moves in the forward direction and stop at a given position, and then provide a third signal to the valve system so as to resume moving the piston in the reverse direction based on the trajectory.

Abstract: Methods and apparatus for grasping an object by a suction-based gripper of a mobile robot are provided. The method comprises receiving, by a computing device, from a perception system of the mobile robot, perception information reflecting an object to be grasped by the suction-based gripper, determining, by the computing device, uncertainty information reflecting an unknown or uncertain extent and/or pose of the object, determining, by the computing device, a grasp strategy to grasp the object based, at least in part, on the uncertainty information, and controlling, by the computing device, the mobile robot to grasp the object using the grasp strategy.

Abstract: Systems and methods for determining movement of a robot are provided. A computing system of the robot receives information including an initial state of the robot and a goal state of the robot. The computing system determines, using nonlinear optimization, a candidate trajectory for the robot to move from the initial state to the goal state. The computing system determines whether the candidate trajectory is feasible. If the candidate trajectory is feasible, the computing system provides the candidate trajectory to a motion control module of the robot. If the candidate trajectory is not feasible, the computing system determines, using nonlinear optimization, a different candidate trajectory for the robot to move from the initial state to the goal state, the nonlinear optimization using one or more changed parameters.

Abstract: The invention includes systems and methods for fabrication and use of an assembly for a component of a robot. The assembly includes a first member including a set of electrically conductive annular surfaces, and a second member including a set of electrically conductive components configured to contact the set of electrically conductive annular surfaces. The first member and the second member are included within the component of the robot. Each component in the set of electrically conductive components includes a first convex curvilinear portion configured to contact a corresponding annular surface in the set of electrically conductive annular surfaces.

Abstract: A method for calibrating a position measurement system includes receiving measurement data from the position measurement system and determining that the measurement data includes periodic distortion data. The position measurement system includes a nonius track and a master track. The method also includes modifying the measurement data by decomposing the periodic distortion data into periodic components and removing the periodic components from the measurement data.

Abstract: A method of localizing a robot includes receiving odometry information plotting locations of the robot and sensor data of the environment about the robot. The method also includes obtaining a series of odometry information members, each including a respective odometry measurement at a respective time. The method also includes obtaining a series of sensor data members, each including a respective sensor measurement at the respective time. The method also includes, for each sensor data member of the series of sensor data members, (i) determining a localization of the robot at the respective time based on the respective sensor data, and (ii) determining an offset of the localization relative to the odometry measurement at the respective time. The method also includes determining whether a variance of the offsets determined for the localizations exceeds a threshold variance. When the variance among the offsets exceeds the threshold variance, a signal is generated.

Abstract: The invention includes systems and methods for routing data packets in a robot. The method comprises routing, using a first switching device, data packets between a first host processor and a first electronic device of the robot, and routing, using the first switching device, data packets between a second host processor and a second electronic device of the robot.