Abstract: Methods, systems, and apparatus, including computer-readable media storing executable instructions, for enhancing robot learning. In some implementations, a robot stores first embeddings generated using a first machine learning model, and the first embeddings include one or more first private embeddings that are not shared with other robots. The robot receives a second machine learning model from a server system over a communication network. The robot generates a second private embedding for each of the one or more first private embeddings using the second machine learning model. The robot adds the second private embeddings to the cache of the robot and removes the one or more first private embeddings from the cache of the robot.

Abstract: A method includes receiving, by a control system of a robotic device, data about an object in an environment from a remote computing device, where the data comprises at least location data and identifier data. The method further includes, based on the location data, causing at least one appendage of the robotic device to move through a predetermined learning motion path. The method additionally includes, while the at least one appendage moves through the predetermined learning motion path, causing one or more visual sensors to capture a plurality of images for potential association with the identifier data. The method further includes sending, to the remote computing device, the plurality of captured images to be displayed on a display interface of the remote computing device.

Abstract: A centre pivot liner (10) which includes a body (12), and a bearing formation (14) mountable about the body (12) for in use, defining a bearing surface (16) of the centre pivot liner (10) and wherein the bearing formation (14) has a coefficient of friction value less than that of the body (12).

Abstract: A pedestal liner which includes an elongate body and a bearing formation mountable about the elongate body for in use, defining a bearing surface of the elongate body, wherein the bearing formation has a coefficient of friction value less than that of the elongate body.

Abstract: A method includes receiving, by a control system of a robotic device, data about an object in an environment from a remote computing device, where the data comprises at least location data and identifier data. The method further includes, based on the location data, causing at least one appendage of the robotic device to move through a predetermined learning motion path. The method additionally includes, while the at least one appendage moves through the predetermined learning motion path, causing one or more visual sensors to capture a plurality of images for potential association with the identifier data. The method further includes sending, to the remote computing device, the plurality of captured images to be displayed on a display interface of the remote computing device.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for sharing learned information among robots. In some implementations, a robot obtains sensor data indicating characteristics of an object. The robot determines a classification for the object and generates an embedding for the object using a machine learning model stored by the robot. The robot stores the generated embedding and data indicating the classification for the object. The robot sends the generated embedding and the data indicating the classification to a server system. The robot receives, from the server system, an embedding generated by a second robot and a corresponding classification. The robot stores the received embedding and the corresponding classification in the local cache of the robot. The robot may then use the information in the cache to identify objects.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for sharing learned information among robots. In some implementations, a robot obtains sensor data indicating characteristics of an object. The robot determines a classification for the object and generates an embedding for the object using a machine learning model stored by the robot. The robot stores the generated embedding and data indicating the classification for the object. The robot sends the generated embedding and the data indicating the classification to a server system. The robot receives, from the server system, an embedding generated by a second robot and a corresponding classification. The robot stores the received embedding and the corresponding classification in the local cache of the robot. The robot may then use the information in the cache to identify objects.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for evaluating robot learning. In some implementations, a system receives classification examples from a plurality of remote devices over a communication network. The classification examples can include (i) a data representation generated by a remote device based on sensor data captured by the remote device and (ii) a classification corresponding to the data representation. The system assigns quality scores to the classification examples based on a level of similarity of the data representations with other data representations. The system selects a subset of the classification examples based on the quality scores assigned to the classification examples. The system trains a machine learning model using the selected subset of the classification examples.

Abstract: Methods, systems, and apparatus, including computer-readable media storing executable instructions, for enhancing robot learning. In some implementations, a robot stores first embeddings generated using a first machine learning model, and the first embeddings include one or more first private embeddings that are not shared with other robots. The robot receives a second machine learning model from a server system over a communication network. The robot generates a second private embedding for each of the one or more first private embeddings using the second machine learning model. The robot adds the second private embeddings to the cache of the robot and removes the one or more first private embeddings from the cache of the robot.

Abstract: A method includes receiving, by a control system of a robotic device, data about an object in an environment from a remote computing device, where the data comprises at least location data and identifier data. The method further includes, based on the location data, causing at least one appendage of the robotic device to move through a predetermined learning motion path. The method additionally includes, while the at least one appendage moves through the predetermined learning motion path, causing one or more visual sensors to capture a plurality of images for potential association with the identifier data. The method further includes sending, to the remote computing device, the plurality of captured images to be displayed on a display interface of the remote computing device.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for evaluating robot learning. In some implementations, one or more computers receive object classification examples from a plurality of robots. Each object classification example includes (i) an embedding that a robot generated using a machine learning model, and (ii) an object classification corresponding to the embedding. The object classification examples are evaluated based on a similarity of the received embeddings with respect to other embeddings. A subset of the object classification examples is selected based on the evaluation of the quality of the embeddings. The subset of the object classification examples is distributed to the robots in the plurality of robots.

Abstract: Methods, systems, and apparatus, including computer-readable media storing executable instructions, for enhancing robot learning. In some implementations, a robot stores first embeddings generated using a first machine learning model, and the first embeddings include one or more first private embeddings that are not shared with other robots. The robot receives a second machine learning model from a server system over a communication network. The robot generates a second private embedding for each of the one or more first private embeddings using the second machine learning model. The robot adds the second private embeddings to the cache of the robot and removes the one or more first private embeddings from the cache of the robot.

Abstract: Methods, systems, and apparatus, including computer-readable media storing executable instructions, for enhancing robot learning. In some implementations, a robot stores first embeddings generated using a first machine learning model, and the first embeddings include one or more first private embeddings that are not shared with other robots. The robot receives a second machine learning model from a server system over a communication network. The robot generates a second private embedding for each of the one or more first private embeddings using the second machine learning model. The robot adds the second private embeddings to the cache of the robot and removes the one or more first private embeddings from the cache of the robot.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for evaluating robot learning. In some implementations, one or more computers receive object classification examples from a plurality of robots. Each object classification example includes (i) an embedding that a robot generated using a machine learning model, and (ii) an object classification corresponding to the embedding. The object classification examples are evaluated based on a similarity of the received embeddings with respect to other embeddings. A subset of the object classification examples is selected based on the evaluation of the quality of the embeddings. The subset of the object classification examples is distributed to the robots in the plurality of robots.

Abstract: Methods, systems, and apparatus, including computer-readable media storing executable instructions, for enhancing robot learning. In some implementations, a robot stores first embeddings generated using a first machine learning model, and the first embeddings include one or more first private embeddings that are not shared with other robots. The robot receives a second machine learning model from a server system over a communication network. The robot generates a second private embedding for each of the one or more first private embeddings using the second machine learning model. The robot adds the second private embeddings to the cache of the robot and removes the one or more first private embeddings from the cache of the robot.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for sharing learned information among robots. In some implementations, a robot obtains sensor data indicating characteristics of an object. The robot determines a classification for the object and generates an embedding for the object using a machine learning model stored by the robot. The robot stores the generated embedding and data indicating the classification for the object. The robot sends the generated embedding and the data indicating the classification to a server system. The robot receives, from the server system, an embedding generated by a second robot and a corresponding classification. The robot stores the received embedding and the corresponding classification in the local cache of the robot. The robot may then use the information in the cache to identify objects.

Abstract: The invention relates to a device for implementing a system for detecting the observance by a patient of an oxygen-therapy treatment involving an oxygen supply, and for recording the data of said treatment and transmitting said data. The invention also relates to the use of said device, and to a method for tracking the observance of an oxygen-therapy treatment.

Abstract: The invention relates to a device for implementing a system for detecting the observance by a patient of an oxygen-therapy treatment involving an oxygen supply, and for recording the data of said treatment and transmitting said data. The invention also relates to the use of said device, and to a method for tracking the observance of an oxygen-therapy treatment.

Abstract: A device for selectively interconnecting a series of conductors comprises an insulative housing provided with a series of parallel passages through it each adapted to receive a conductive pin whose free end forms the male connection member and whose opposite end is connected to one of the conductors. The various pins all emerge at their free end on a common side of the housing. An insulative cover closes this side of the housing and is provided internally with a plurality of U-shape cross-section conductive bars forming female connection members each facing a plurality of the passages and adapted to cooperate with a plurality of pins by coming into contact with the emergent free ends thereof so as to short-circuit them electrically together.

Abstract: A female electrical contact terminal having a rear tubular shank for connection with an electrical conductor, a forwardly open electrically conductive annular portion for receiving a male terminal, subdivided by a plurality of circumferentially distributed axial slots into a plurality of fingers, each said finger extending axially from a root securely connected to said rear tubular shank up to a free end having an inner swelling, the swelling of all arms defining a male terminal entrance, and a rigid tubular section secured to the roots of the fingers, surrounding the fingers, and limiting radially outwards resilient deformation of the fingers from a free condition of the fingers in which they converge forwardly among from the tubular section. A plurality of such terminal may be located in the insulation of a half-connector.