A position and an orientation of an object are measured with high accuracy. An approximate position-orientation of a target object is obtained, positional information of the target object is obtained by measuring the target object using a noncontact sensor, positional information of contact positions touched by a contact sensor is obtained by bringing the contact sensor into contact with the target object, and a position-orientation of the target object is obtained by associating shape information of the target object with the positional information of the target object and the positional information of the contact positions in accordance with the approximate position-orientation.

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.

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.

An aroma display that enables, by an easy operation, generation of scents fit for situations, at various scenes and times includes: a message receiving unit 180 for receiving an external message; a correspondence storage means for storing correspondence between an event name and aroma information related to a scent to be generated at the event; an event information extracting means for extracting event information including an event name and time information related to the event from the message received by the message receiving unit 180; aroma information reading units 185 and 186 for reading aroma information corresponding to the event name from the correspondence storage means; and an aroma generating unit 194 generating a scent in accordance with the aroma information read by aroma information reading units 185 and 186.

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.

A position and an orientation of an object are measured with high accuracy. An approximate position-orientation of a target object is obtained, positional information of the target object is obtained by measuring the target object using a noncontact sensor, positional information of contact positions touched by a contact sensor is obtained by bringing the contact sensor into contact with the target object, and a position-orientation of the target object is obtained by associating shape information of the target object with the positional information of the target object and the positional information of the contact positions in accordance with the approximate position-orientation.

A method of acquiring sensor data on a construction site by at least one sensor of a construction robot system comprising at least one construction robot is provided, wherein a sensor is controlled using a trainable agent, thus improving the quality of acquired sensor data. A construction robot system, a computer program product, and a training method are also provided.

In a computer-implemented method and system for capturing the condition of a structure, the structure is scanned with a three-dimensional (3D) scanner. The 3D contact scanner includes a tactile sensor system having at least one tactile sensor for generating 3D data points based on tactile feedback resulting from physical contact with at least part of the structure. A 3D model is constructed from the 3D data and is then analyzed to determine the condition of the structure.

In a computer-implemented method and system for capturing the condition of a structure, the structure is scanned with a three-dimensional (3D) scanner. The 3D contact scanner includes a tactile sensor system having at least one tactile sensor for generating 3D data points based on tactile feedback resulting from physical contact with at least part of the structure. A 3D model is constructed from the 3D data and is then analyzed to determine the condition of the structure.

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.