Seiko Epson Corporation

Yimei Ding

Shuji Uchida

Toshinori Hiraide

Yoshitaka Yamagata

Daisuke Sugiya

A failure prediction method of predicting a failure of a component of a robot including a robot arm having the component and a detection section that detects information on vibration characteristics when the robot arm moves, includes generating a failure prediction model for prediction of the failure of the component by machine learning based on the information on vibration characteristics, and predicting the failure of the component based on an estimated value of failure prediction output by the generated failure prediction model when the information on vibration characteristics is input to the generated failure prediction model.

Failure prediction method and failure prediction apparatus

An information processing method includes causing an information acquisition section to perform a process of acquiring user information including body motion information of a user, causing a processing section to perform a process of determining a swimming style of the user on the basis of the user information, and obtaining evaluation index information which is at least one of calorie consumption information, pulse wave information, and stroke information when the user swims in each swimming style, and causing an output section to output information in which the evaluation index information in each swimming style is correlated with each swimming style.

Information processing method, wearable apparatus, content reproduction device, content reproduction system, and content reproduction method

Disclosed are an error estimation method capable of reducing a processing load, and estimating errors of indexes indicating a state of a moving object with high accuracy by using a signal from a positioning satellite. In one aspect, the error estimation method includes calculating a coordinate transformation matrix between a first coordinate system with a first sensor mounted on a moving object as a reference and a second coordinate system with the moving object as a reference, at a predetermined timing in a cycle of, converting one of an azimuth angle of the moving object based on a detection result in the first sensor and an azimuth angle of the moving object based on a detection result in the second sensor by using the coordinate transformation matrix in a case where the detection result in the second sensor receiving a signal from a positioning satellite is obtained, and estimating errors of indexes indicating a state of the moving object by using a difference between the converted azimuth angle and the other azimuth angle at the predetermined timing after a timing at which the detection result in the second sensor is obtained.

Error estimation method, motion analysis method, error estimation apparatus, and program

A bias estimating method includes: calculating a virtual posture angle which is a posture angle with a bias which is assumed to be zero by the use of detection values of a plurality of axes in a calibration posture where one axis of a multi-axis acceleration sensor is parallel to the vertical direction; and estimating a bias value contained in the detection value of the axis using the detection value of the axis and the virtual posture angle.

Growing community of inventors

Shiojiri, Japan

Yimei Ding