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.

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.

The material contained in this disclosure pertains to robotics related to convertible robots incorporating telecommunication elements. Embodiments of the system and apparatuses described can facilitate instant communication with family and friends, health status monitoring and support from caregivers; and promote optimal health, longevity, and independent living by providing high-tech economical solutions at each stage of the aging process. Embodiments of the system and apparatuses may be converted from an independent telecommunications robot, to a robotic walker, to a robotic wheelchair.

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.

A data processing method for a care-giving robot and an apparatus comprises receiving data from a target object comprising a capability parameter of the target object, generating a growing model capability parameter matrix of the target object that includes the capability parameter, a capability parameter adjustment value, and a comprehensive capability parameter that is calculated based on the capability parameter; adjusting the capability parameter adjustment value in the growing model capability parameter matrix, to determine an adjusted capability parameter adjustment value; determining whether the adjusted capability parameter adjustment value exceeds a preset threshold; and sending the adjusted capability parameter adjustment value to a machine learning engine when the adjusted capability parameter adjustment value is within a range of the preset threshold.

A method is described for providing deficit-adjusted adaptive assistance during movement phases of an impaired ankle. The method includes determining, on the processor, a value for a deficit parameter for each movement phase of a compound ankle function based on a difference between a parameter trace for a normal subject and the parameter trace for an impaired subject. The method further includes determining, on the processor, an adaptive magnitude for the robot-applied torque based on the value for the deficit parameter. The method further includes applying, to the robot joint, the adaptive magnitude for the robot-applied torque in only a first plane for the current movement phase, based on an adaptive timing. An apparatus is also described for providing deficit-adjusted adaptive assistance during movement phases of the impaired ankle.

A robot apparatus includes a grasping section that grasps an object, a recognition section that recognizes a graspable part and a handing-over area part of the object, and a grasp planning section that plans a path of the grasping section for handing over the object to a recipient by the handing-over area part. The robot apparatus further includes a grasp control section that controls grasp operation of the object by the grasping section in accordance with the planned path.

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.

A remote control system includes: an imaging unit that shoots an environment in which a device to be operated including an end effector is located; a recognition unit that recognizes objects that can be grasped by the end effector based on a shot image of the environment shot by the imaging unit; an operation terminal that displays the shot image and receive handwritten input information input to the displayed shot image; and an estimation unit that, based on the objects that can be grasped and the handwritten input information input to the shot image, estimates an object to be grasped which has been requested to be grasped by the end effector from among the objects that can be grasped and estimates a way of performing a grasping motion by the end effector, the grasping motion having been requested to be performed with regard to the object to be grasped.

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.