Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using a demonstration device for robotic demonstration learning. One of the methods includes generating, by a demonstration device for a robot, a representation of a sequence of states input by a user of the demonstration device. The representation is provided by the demonstration device to a robot execution system. The representation of the sequence of actions is translated into a plurality of robot commands corresponding to the representation of the sequence of states input by the user on the demonstration device. The plurality of robot commands corresponding to the sequence of actions input by the user on the demonstration device are executed. Demonstration data is generated from one or more sensor streams of the robot while executing the plurality of robot commands corresponding to the sequence of actions input by the user on the demonstration device.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using skill templates for robotic demonstration learning. One of the methods includes receiving a skill template for a task to be performed by a robot, wherein the skill template defines a state machine having a plurality of subtasks and one or more respective transition conditions between one or more of the subtasks. Local demonstration data for a demonstration subtask of the skill template is received, where the local demonstration data is generated from a user demonstrating how to perform the demonstration subtask with the robot. A machine learning model is refined for the demonstration subtask and the skill template is executed on the robot, causing the robot to transition through the state machine defined by the skill template to perform the task.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for integrating sensor streams for robotic demonstration learning. One of the methods includes selecting, by a learning system for a robot, a base update rate for combining multiple sensor streams into a task state representation. The learning system repeatedly generates the task state representation at the base update rate, including combining, during each time period defined by the update rate, the task state representation from most recently updated sensor data processed by the plurality of neural networks. The learning system repeatedly uses the task state representations to generate commands for the robot at the base update rate.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for distributing skill templates for robotic demonstration learning. One of the methods includes receiving, from the user device by a skill template distribution system, a selection of an available skill template. The skill template distribution system provides a skill template, wherein the skill template comprises information representing a state machine of one or more tasks, and wherein the skill template specifies which of the one or more tasks are demonstration subtasks requiring local demonstration data. The skill template distribution system trains a machine learning model for the demonstration subtask using a local demonstration data to generate learned parameter values.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using simulated local demonstration data for robotic demonstration learning. One of the methods includes receiving perceptual data of a workcell of a robot to be configured to execute a task according to a skill template, wherein the skill template specifies one or more subtasks required to perform the skill, wherein at least one of the subtasks is a demonstration subtask that relies on learning visual characteristics of the workcell. A virtual model is generated of a portion of the workcell. A training system generates simulated local demonstration data from the virtual model of the portion of the workcell and tunes a base control policy for the demonstration subtask using the simulated local demonstration data generated from the virtual model of the portion of the workcell.

Abstract: The present invention relates to a method for operating a wireless communication device in a cellular network, the wireless communication device comprising a communication unit and a controlling appliance, interconnected by a control interface, the communication unit comprising a network access manager unit, the method comprising for the communication unit the steps of: —receiving from the cellular network a network access guidance —handling the received network access guidance at the network access manager unit, —as part of handling the network access guidance, interpreting the received network access guidance and providing information relating to the network access guidance resulting from said interpretation step to the controlling appliance, —ascertaining by means of the control interface from the controlling appliance a response relating to said network access guidance, —handling in the network access manager unit the response relating to said network access guidance.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing online robotic motion planning from pre-generated motion plans. A library of pre-generated motion plans for performing a particular task is maintained. Each pre-generated motion plan comprises a plurality of waypoints and one or more actions. One or more present observations of a robot in a workcell are obtained. The one or more observations are classified. A pre-generated candidate motion plan that matches the labels assigned to the present observations of the robot in the workcell is selected from the library of pre-generated motion plans. The pre-generated candidate motion plan is adapted according to the present observations of the robot in the workcell to generate a final motion plan to be executed by the robot.

Abstract: A physics engine executed on a processor to simulate real-time rigid body dynamics of a simulated physical system with permissive penetration functionality is provided. The physics engine may be configured to iteratively loop through a collision detection phase, solving phase, updating phase, and display phase. When a penetration between a pair of bodies is due to an initial penetration from a prior collision detection phase, the physics engine may permit the initial penetration between the pair of objects during the current solving phase by not applying a bias or position change to correct for the initial penetration. Also the physics engine may be configured to detect geometry changes and modify the initial penetration distance accordingly.

Abstract: A computer-implemented technique is described herein for generating a digital representation of real-world surfaces in an environment. The technique involves receiving sensor data captured by one or more depth-sensing devices. The technique then provides a low-detail (LD) representation of surfaces in the physical environment based on the sensor data; that LD representation describes one or more planes in the physical environment. The technique then generates a high-detail (HD) representation of the surfaces based on the sensor data and the LD representation. Finally, the technique provides an output result based on the LD representation and/or the HD representation. According to one illustrative aspect, the technique produces the HD representation such that it is non-duplicative of information that is already present in the LD representation. The technique performs this task by identifying and excluding HD information that is already adequately represented by the LD representation.

Abstract: A computing system, including at least one imaging sensor configured to collect imaging data of a physical environment. The computing system may further include a processor configured to generate, based on the imaging data, a first anchor graph including a first plurality of anchors connected by a first plurality of edges. Each anchor of the first plurality of anchors may indicate a respective estimated position in the physical environment. The processor may be further configured to detect a change in the estimated position of at least one anchor of the first plurality of anchors relative to the at least one imaging sensor. Based on the change in the estimated position, the processor may reposition the first anchor graph relative to the at least one imaging sensor. Estimated lengths of the first plurality of edges and estimated angles between the first plurality of edges may remain fixed.

Abstract: A computing system, including at least one imaging sensor configured to collect imaging data of a physical environment. The computing system may further include a processor configured to generate, based on the imaging data, a first anchor graph including a first plurality of anchors connected by a first plurality of edges. Each anchor of the first plurality of anchors may indicate a respective estimated position in the physical environment. The processor may be further configured to detect a change in the estimated position of at least one anchor of the first plurality of anchors relative to the at least one imaging sensor. Based on the change in the estimated position, the processor may reposition the first anchor graph relative to the at least one imaging sensor. Estimated lengths of the first plurality of edges and estimated angles between the first plurality of edges may remain fixed.

Abstract: A computer-implemented technique is described herein for generating a digital representation of real-world surfaces in an environment. The technique involves receiving sensor data captured by one or more depth-sensing devices. The technique then provides a low-detail (LD) representation of surfaces in the physical environment based on the sensor data; that LD representation describes one or more planes in the physical environment. The technique then generates a high-detail (HD) representation of the surfaces based on the sensor data and the LD representation. Finally, the technique provides an output result based on the LD representation and/or the HD representation. According to one illustrative aspect, the technique produces the HD representation such that it is non-duplicative of information that is already present in the LD representation. The technique performs this task by identifying and excluding HD information that is already adequately represented by the LD representation.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for reducing latency in transmitting and presenting map user interfaces. In one aspect, a method includes receiving, from a client device, a request for presentation of an interactive map user interface that depicts (i) a region and (ii) data related to an account for sub-regions of the region. One or more servers render a map of the region. The server(s) generate an image file representing an image of the rendered map. A different visual characteristic is assigned to each different sub-region. The server(s) configure a user interface of the client device to present (i) the image with each of the different sub-regions being presented according to the different visual characteristics and (ii) account data related to a sub-region when the client device detects a user interaction with the sub-region.

Abstract: A method for accessing network data from a plurality of sources using a single identification value. The method may include the steps of: receiving the single identification value at a control computer from an application running in a web page on a client computer via a network; searching a database for a match of the identification value; and sending a collection to the client computer via the network in response to matching the identification value in the database. The collection may include a plurality of resources related to the identification value in the database. At least two of the resources may identify at least two other computers on the network that provide data to the web page. The other computers may provide distinct services.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for reducing latency in transmitting and presenting map user interfaces. In one aspect, a method includes receiving, from a client device, a request for presentation of an interactive map user interface that depicts (i) a region and (ii) data related to an account for sub-regions of the region. One or more servers render a map of the region. The server(s) generate an image file representing an image of the rendered map. A different visual characteristic is assigned to each different sub-region. The server(s) configure a user interface of the client device to present (i) the image with each of the different sub-regions being presented according to the different visual characteristics and (ii) account data related to a sub-region when the client device detects a user interaction with the sub-region.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for reducing latency in network communications and data presentation. In one aspect, a user session is initiated in which data related to an account is presented to the user. A user group to which the given user has been assigned is identified. A first dataset related to the account is selected based on the user group. A second dataset related to the account is selected based on types of data previously requested by various other users in the user group. A user interface for the account is updated to present at least a portion of the first dataset. Latency in updating the user interface is reduced when presenting additional portions of the first dataset or the second dataset by providing, to the client device, the second dataset prior to receiving a request for the second dataset.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for reducing latency in network communications and data presentation. In one aspect, a user session is initiated in which data related to an account is presented to the user. A user group to which the given user has been assigned is identified. A first dataset related to the account is selected based on the user group. A second dataset related to the account is selected based on types of data previously requested by various other users in the user group. A user interface for the account is updated to present at least a portion of the first dataset. Latency in updating the user interface is reduced when presenting additional portions of the first dataset or the second dataset by providing, to the client device, the second dataset prior to receiving a request for the second dataset.

Abstract: The present invention relates to a method for operating a wireless communication device in a cellular network, the wireless communication device comprising a communication unit and a controlling appliance, interconnected by a control interface, the communication unit comprising a network access manager unit, the method comprising for the communication unit the steps of: —receiving from the cellular network a network access guidance —handling the received network access guidance at the network access manager unit, —as part of handling the network access guidance, interpreting the received network access guidance and providing information relating to the network access guidance resulting from said interpretation step to the controlling appliance, —ascertaining by means of the control interface from the controlling appliance a response relating to said network access guidance, —handling in the network access manager unit the response relating to said network access guidance.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for reducing latency in transmitting and presenting map user interfaces. In one aspect, a method includes receiving, from a client device, a request for presentation of an interactive map user interface that depicts (i) a region and (ii) data related to an account for sub-regions of the region. One or more servers render a map of the region. The server(s) generate an image file representing an image of the rendered map. A different visual characteristic is assigned to each different sub-region. The server(s) configure a user interface of the client device to present (i) the image with each of the different sub-regions being presented according to the different visual characteristics and (ii) account data related to a sub-region when the client device detects a user interaction with the sub-region.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for reducing latency in network communications and data presentation. In one aspect, a user session is initiated in which data related to an account is presented to the user. A user group to which the given user has been assigned is identified. A first dataset related to the account is selected based on the user group. A second dataset related to the account is selected based on types of data previously requested by various other users in the user group. A user interface for the account is updated to present at least a portion of the first dataset. Latency in updating the user interface is reduced when presenting additional portions of the first dataset or the second dataset by providing, to the client device, the second dataset prior to receiving a request for the second dataset.