Toyota Jidosha Kabushiki Kaisha

Toyota Motor Engineering & Manufacturing North America, Inc.

International Computer Science Institute

Masayoshi Tsuchinaga

Takashi Yamamoto

Nobuhisa Otsuki

Shintaro Yoshizawa

Takemitsu Mori

Hodaka Kito

Yuka Iwanaga

Takuya Iwata

Mario Fritz

Trevor Darrell

A remote control system includes: a recognition unit configured to recognize, based on a shot image objects that can be grasped; an image adjustment unit configured to cause an imaging unit to shoot, when a part of an area of a shot image designated by handwritten information is a predetermined outer peripheral area of the shot image, an image of a second predetermined area including the part of the area of the shot image designated by the handwritten information and an area adjacent to the first predetermined area, and cause the operation terminal to display the shot image of the second predetermined area; and an estimation unit configured to estimate an object to be grasped which has been requested to be grasped and estimate a content of a motion with regard to the object to be grasped which is requested to be performed by the device to be operated.

Remote control system, remote control method, and control program

A remote control system includes: a recognition unit configured to recognize, based on a shot image, objects that can be grasped, and movable and immovable areas of a device to be operated; an operation terminal configured to receive handwritten information; and an estimation unit configured to estimate an object to be grasped requested to be grasped and estimate a content of a motion with regard to the object to be grasped which is requested to be performed by the device to be operated, in which the estimation unit estimates, a conveyance route positioned in the movable area of the device to be operated among the conveyance routes as a moving route of the device to be operated and estimates a conveyance route positioned in the immovable area of the device to be operated as a moving route of an end effector that grasps the object to be grasped.

A medical data communication apparatus includes a data acquisition unit configured to acquire medical data of a subject output from a medical device from the medical device, the medical device being connected for communication with the medical data communication apparatus without an external network intervening therebetween; a modification unit configured to modify the medical data based on a modification instruction received from a server, the server being connected for communication with the medical data communication apparatus through an external network, the modification instruction being for modifying specific information in the medical data; and an output unit configured to output the medical data modified by the modification unit to the external network based on a request from the server.

Medical data communication apparatus, server, medical data communication method and medical data communication program

The communication control unit of the external communication apparatus requests a communication connection to the server. When a communication connection with the server is established, the communication control unit acquires the server side definition file from the server. The updating unit of the external communication apparatus updates the client side definition file with the server side definition file acquired by the communication control unit. The communication control unit of the external communication apparatus is configured to upload the medical apparatus side data to the server based on the client side definition file. Further, the communication control unit of the external communication apparatus is configured to reject a connection request from the server.

Medical information system, medical apparatus, method, and non-transitory computer readable medium

Methods for recognizing a category of an object are disclosed. In one embodiment, a method includes determining, by a processor, a preliminary category of a target object, the preliminary category having a confidence score associated therewith, and comparing the confidence score to a learning threshold. If the highest confidence score is less than the learning threshold, the method further includes estimating properties of the target object and generating a property score for one or more estimated properties, and searching a supplemental image collection for supplemental image data using the preliminary category and the one or more estimated properties. Robots programmed to recognize a category of an object by use of supplemental image data are also disclosed.

Growing community of inventors

Nisshin, Japan

Masayoshi Tsuchinaga