Disclosed herein are techniques to make the synthesized monitoring conditions of partially-observable hybrid systems robust to partial observability of sensor uncertainty and partial controllability due to actuator disturbance. The approach herein shows that the monitoring conditions result in provable safety guarantees with fallback controllers that react to monitor violation at runtime.

A method, apparatus, and system are for determining signal rules and annotating data. The method, according to an embodiment, includes: determining data obtaining logic based on assembly model information corresponding to the assembly; wherein the data obtaining logic includes a to-be-obtained data object and an obtaining rule; determining at least one physical signal corresponding to the data obtaining logic; and determining, based on the data obtaining logic and the at least one physical signal corresponding to the data obtaining logic, a signal rule corresponding to the obtaining rule. By annotating the running data of an assembly, the context of the data may be indicated, so that the running data of the assembly can be made more consistent, easier to maintain, and/or applied to a new environment. Moreover, since the annotation information of data can adopt a common format, it may be more suitable for information migration and system configuration.

Methods and systems for assessing, detecting, and responding to malfunctions involving components of autonomous vehicle and/or smart homes are described herein. Autonomous operation features and related components can be assessed using direct or indirect data regarding operation. Such assessment may be performed to determine the condition of components for salvage following a collision or other loss-event. To this end, the information regarding a plurality of components may be received. A component of the plurality of components may be identified for assessment. Assessment may including causing test signals to be sent to the identified component. In response to the test signal, one or more responses may be received. The received response may be compared to an expected response to determine whether the identified component is salvageable.

A method includes receiving raw data and generating a manufacturing data packet (MDP) that includes at least a portion of the raw data. Generating the MDP includes associating metadata with the raw data and associating a timestamp with the raw data. The timestamp is synchronized to a common reference time. A data model associated with the MDP is obtained. The data model includes one or more predefined data types and one or more predefined data fields. A first data type from the one or more predefined data types is determined based at least in part on characteristics of the raw data. An algorithm is determined based at least in part on the first data type. The MDP is processed according to the algorithm to produce an output. The first data type is associated with the raw data. The output is associated with a data field of the first data type.

Disclosed is a malfunction early-warning method for production logistics delivery equipment. After a sensor obtains past signal data, performing feature extraction and dimensionality reduction so as to obtain a feature vector; using a growing neural gas (GNG) algorithm to divide normal state data into different operation situations so as to obtain several cluster centers, and calculating the Euclidean distance between the feature vector and the cluster centers obtained from current operation data, so as to obtain a similarity trend; constructing a past memory matrix, using an improved particle swarm algorithm to optimize an LS-SVM regression model parameter, and calculating the residual value of the current state. Finally, combining the residual value and the similarity trend to obtain a risk coefficient, assessing the equipment state, and issuing an early warning for an equipment malfunction.

Systems, methods, and processor-readable storage media for AI-assisted electrical power grid fault analysis predict the cause of a fault and cause the fault to be remedied by receiving an indication that a first fault has occurred, identifying a plurality of additional fault records associated with the first fault, obtaining a first prediction of the cause of the fault based on the first fault record and the plurality of fault records by applying the fault records to a machine learning model, obtaining a second prediction of the cause of the fault by applying the fault records to a rules-based model, and obtaining a final prediction of the cause of the first fault based on the first prediction and the second prediction. The final prediction of the cause of the first fault is used to cause the predicted cause of the first fault to be remedied.

The present disclosure discloses a method, system and device for replaying movement of a robot. In an embodiment, the method includes a controller receiving a log file in which information about a movement of the robot is recorded; the controller obtaining information of position points passed by the robot when performing the movement based on the log file; and the controller sending the information of position points passed by the robot when performing the movement to a replaying device, to enable the replaying device to replay the movement of the robot according to the information of position points. The technical solutions of the present disclosure may increase the accuracy of locating where the problem is when errors or something unexpected happened to the robot.

Methods and systems for assessing, detecting, and responding to malfunctions involving components of autonomous vehicle and/or smart homes are described herein. Autonomous operation features and related components can be assessed using direct or indirect data regarding operation. Such assessment may be performed to determine the condition of components for salvage following a collision or other loss-event. To this end, the information regarding a plurality of components may be received. A component of the plurality of components may be identified for assessment. Assessment may including causing test signals to be sent to the identified component. In response to the test signal, one or more responses may be received. The received response may be compared to an expected response to determine whether the identified component is salvageable.

In an embodiment, a data processing method comprises storing one or more generic machine operating definitions, wherein each of the generic machine operating definitions describes expected operational behavior of one or more types of machines during one or more operating states; analyzing operating data that describes past operation of a plurality of machines of a plurality of types; based at least in part on the operating data and the one or more generic machine operating definitions, generating and storing one or more machine operating models that describe expected operational behavior corresponding to a plurality of operating states of the plurality of machines; wherein the one or more machine operating models comprise a plurality of data patterns, wherein each of the data patterns is associated with a different set of one or more operating states of one or more machines; wherein the method is performed by one or more computing devices.

Methods and systems for enhancing the functionality of a semi-autonomous vehicle are described herein. The semi-autonomous vehicle may receive a communication from a fully autonomous vehicle within a threshold distance of the semi-autonomous vehicle. If the vehicles are travelling on the same route or the same portion of a route, the semi-autonomous vehicle may navigate to a location behind the fully autonomous vehicle. Then the semi-autonomous vehicle may operate autonomously by replicating one or more functions performed by the fully autonomous vehicle. The functions and/or maneuvers performed by the fully autonomous vehicle may be detected via sensors in the semi-autonomous vehicle and/or may be identified by communicating with the fully autonomous vehicle to receive indications of upcoming maneuvers. In this manner, the semi-autonomous vehicle may act as a fully autonomous vehicle.