Abstract: A system and method for ground truth estimation of an autonomous navigation system is described. The method includes calibrating a ground truth estimation system for the navigator, by determining a calibration pose of the navigator as disposed in relation to each of a plurality of landmarks during a calibration period. The method also includes directing the navigator to travel to a sequence of waypoints, the waypoints including a selected sequence of the landmarks. The method further includes determining the ground truth estimation based on an accuracy pose of the navigator as disposed in relation to the sequence of landmarks, and the calibration poses for the sequence of landmarks.

Abstract: Various technologies described herein pertain to correction of an input depth image captured by a depth sensor. The input depth image can include pixels, and the pixels can have respective depth values in the input depth image. Moreover, per-pixel correction values for the pixels can be determined utilizing depth calibration data for a non-linear error model calibrated for the depth sensor. The per-pixel correction values can be determined based on portions of the depth calibration data respectively corresponding to the pixels and the depth values. The per-pixel correction values can be applied to the depth values to generate a corrected depth image. Further, the corrected depth image can be output.

Abstract: Various technologies described herein pertain to automatic in-situ calibration and registration of a depth sensor and a robotic arm, where the depth sensor and the robotic arm operate in a workspace. The robotic arm can include an end effector. A non-parametric technique for registration between the depth sensor and the robotic arm can be implemented. The registration technique can utilize a sparse sampling of the workspace (e.g., collected during calibration or recalibration). A point cloud can be formed over calibration points and interpolation can be performed within the point cloud to map coordinates in a sensor coordinate frame to coordinates in an arm coordinate frame. Such technique can automatically incorporate intrinsic sensor parameters into transformations between the depth sensor and the robotic arm. Accordingly, an explicit model of intrinsics or biases of the depth sensor need not be utilized.

Abstract: Data about a physical object in a real-world environment is automatically collected and labeled. A mechanical device is used to maneuver the object into different poses within a three-dimensional workspace in the real-world environment. While the object is in each different pose an image of the object is input from one or more sensors and data specifying the pose is input from the mechanical device. The image of the object input from each of the sensors for each different pose is labeled with the data specifying the pose and with information identifying the object. A database for the object that includes these labeled images can be generated. The labeled images can also be used to train a detector and classifier to detect and recognize the object when it is in an environment that is similar to the real-world environment.

Abstract: Data about a physical object in a real-world environment is automatically collected and labeled. A mechanical device is used to maneuver the object into different poses within a three-dimensional workspace in the real-world environment. While the object is in each different pose an image of the object is input from one or more sensors and data specifying the pose is input from the mechanical device. The image of the object input from each of the sensors for each different pose is labeled with the data specifying the pose and with information identifying the object. A database for the object that includes these labeled images can be generated. The labeled images can also be used to train a detector and classifier to detect and recognize the object when it is in an environment that is similar to the real-world environment.

Abstract: Various technologies described herein pertain to automatic in-situ calibration and registration of a depth sensor and a robotic arm, where the depth sensor and the robotic arm operate in a workspace. The robotic arm can include an end effector. A non-parametric technique for registration between the depth sensor and the robotic arm can be implemented. The registration technique can utilize a sparse sampling of the workspace (e.g., collected during calibration or recalibration). A point cloud can be formed over calibration points and interpolation can be performed within the point cloud to map coordinates in a sensor coordinate frame to coordinates in an arm coordinate frame. Such technique can automatically incorporate intrinsic sensor parameters into transformations between the depth sensor and the robotic arm. Accordingly, an explicit model of intrinsics or biases of the depth sensor need not be utilized.

Abstract: Various technologies described herein pertain to automatic in-situ calibration and registration of a depth sensor and a robotic arm, where the depth sensor and the robotic arm operate in a workspace. The robotic arm can include an end effector. A non-parametric technique for registration between the depth sensor and the robotic arm can be implemented. The registration technique can utilize a sparse sampling of the workspace (e.g., collected during calibration or recalibration). A point cloud can be formed over calibration points and interpolation can be performed within the point cloud to map coordinates in a sensor coordinate frame to coordinates in an arm coordinate frame. Such technique can automatically incorporate intrinsic sensor parameters into transformations between the depth sensor and the robotic arm. Accordingly, an explicit model of intrinsics or biases of the depth sensor need not be utilized.

Abstract: Various technologies described herein pertain to automatic in-situ calibration and registration of a depth sensor and a robotic arm, where the depth sensor and the robotic arm operate in a workspace. The robotic arm can include an end effector. A non-parametric technique for registration between the depth sensor and the robotic arm can be implemented. The registration technique can utilize a sparse sampling of the workspace (e.g., collected during calibration or recalibration). A point cloud can be formed over calibration points and interpolation can be performed within the point cloud to map coordinates in a sensor coordinate frame to coordinates in an arm coordinate frame. Such technique can automatically incorporate intrinsic sensor parameters into transformations between the depth sensor and the robotic arm. Accordingly, an explicit model of intrinsics or biases of the depth sensor need not be utilized.

Abstract: Various technologies described herein pertain to correction of an input depth image captured by a depth sensor. The input depth image can include pixels, and the pixels can have respective depth values in the input depth image. Moreover, per-pixel correction values for the pixels can be determined utilizing depth calibration data for a non-linear error model calibrated for the depth sensor. The per-pixel correction values can be determined based on portions of the depth calibration data respectively corresponding to the pixels and the depth values. The per-pixel correction values can be applied to the depth values to generate a corrected depth image. Further, the corrected depth image can be output.

Abstract: A system and method for ground truth estimation of an autonomous navigation system is described. The method includes calibrating a ground truth estimation system for the navigator, by determining a calibration pose of the navigator as disposed in relation to each of a plurality of landmarks during a calibration period. The method also includes directing the navigator to travel to a sequence of waypoints, the waypoints including a selected sequence of the landmarks. The method further includes determining the ground truth estimation based on an accuracy pose of the navigator as disposed in relation to the sequence of landmarks, and the calibration poses for the sequence of landmarks.

Abstract: A multi-level monitoring system is provided for monitoring multiple performance aspects of a cloud service concurrently in order to generate a full and reliable performance analysis of the cloud service. The multi-level monitoring system may include a set of components for carrying out the performance analysis of the cloud service which may be deployed together to operate externally, internally, or concurrently with the cloud service. The component framework of the multi-level monitoring system may include a main component, a plug-in associated with the main component, a definition database, a log database, and an output database. The main components of an example multi-level monitoring framework may include a probe runner component for probing the cloud service, a monitor component for generating alerts based on probe results, and a responder component for processing the alerts and taking appropriate actions to improve the cloud service performance.

Abstract: A multi-level monitoring system is provided for monitoring multiple performance aspects of a cloud service concurrently in order to generate a full and reliable performance analysis of the cloud service. The multi-level monitoring system may include a set of components for carrying out the performance analysis of the cloud service which may be deployed together to operate externally, internally, or concurrently with the cloud service. The component framework of the multi-level monitoring system may include a main component, a plug-in associated with the main component, a definition database, a log database, and an output database. The main components of an example multi-level monitoring framework may include a probe runner component for probing the cloud service, a monitor component for generating alerts based on probe results, and a responder component for processing the alerts and taking appropriate actions to improve the cloud service performance.

Abstract: A method for verifying that a sequence of tasks is more likely to be successful prior to executing the sequence of tasks. First, a projection algorithm is performed to generate a precondition and postconditions list for the entire sequence. In order to execute the sequence of tasks, it is determined whether or not all of the preconditions in the preconditions list are satisfied. If they are not, then the sequence of task fails without performing any of the sequence of tasks. On the other hand, if the sequence preconditions are all satisfied, the sequence of tasks is executed one at a time. If any of the sequence of tasks fails, then the tasks that have been executed may be compensated to return to the initial state. Once execution completes assuming none of the task executions failed, the postconditions for the sequence are checked.

Abstract: A method of executing a task in a manner that verifies that performance of the task will likely be successful. This may be accomplished using a task object that specifies one or more preconditions that must be satisfied in order for the task to be successful. The preconditions are verified using condition objects. If the preconditions are not satisfied, the task fails before its execution even began. On the other hand, if the preconditions are satisfied, the task is executed. This may be accomplished by, for example, calling an execution method of the task object. If the execution fails, the task may be undone by, for example, calling a compensation method of the task object. After execution, one or more postconditions may be verified in a similar manner. If the postconditions are not satisfied, then the compensation method may be called in that circumstance as well.