It is an object of the present invention to obtain a work determination apparatus capable of preventing or reducing a time lag between the occurrence and determination of an anomaly in work. A work determination apparatus (30) includes: a sensor data output unit (31) that outputs sensor data with an output interval of an integral multiple of a control period with which a motion of a robot (1) is controlled, the sensor data representing a state of work of the robot (1); and a determination unit (32) that determines a quality of the work of the robot (1) by inference using a recurrent neural network, based on the sensor data outputted from the sensor data output unit (31).

A robot may include a base; a base link connected to the base; an arm link coupled to the base link; an arm connected to the arm link; a hand connected to the arm; a storage; and a controller. The base link and arm link move so that a center of a coupling shaft of the arm link and the arm moves in a line. When the robot is within a predetermined range of a latest coordinate, the robot moves to the return-to-origin position in a direction from the transfer direction, otherwise the controller calculates the transfer path based on past teaching, and determines if there is a path close to the latest coordinate. If there is path, the controller determines whether the hand section is outside of a safe area, and if so, pulls the hand to a safe area and then moves the robot to the return-to-origin position.

A robot may include a base; a base link connected to the base; an arm link coupled to the base link; an arm connected to the arm link; a hand connected to the arm; a storage; and a controller. The base link and arm link move so that a center of a coupling shaft of the arm link and the arm moves in a line. When the robot is within a predetermined range of a latest coordinate, the robot moves to the return-to-origin position in a direction from the transfer direction, otherwise the controller calculates the transfer path based on past teaching, and determines if there is a path close to the latest coordinate. If there is path, the controller determines whether the hand section is outside of a safe area, and if so, pulls the hand to a safe area and then moves the robot to the return-to-origin position.

Systems and methods may include an unmanned lawn mower that includes a predictive model service. The predictive model service may be trained by a machine learning system and may serve to autonomously control the unmanned lawn mower. In this way, the unmanned lawn mower may navigate throughout a lawn and may cut the lawn and/or perform other lawn maintenance procedures during the navigation. The system may also include a variety of sensors and cameras to detect image data and environmental data of an area surrounding the unmanned lawn mower. The image data and the environmental data may be provided to the predictive model service in order to control the operation of the unmanned lawn mower in real-time.

Systems and methods may include an unmanned lawn mower that includes a predictive model service. The predictive model service may be trained by a machine learning system and may serve to autonomously control the unmanned lawn mower. In this way, the unmanned lawn mower may navigate throughout a lawn and may cut the lawn and/or perform other lawn maintenance procedures during the navigation. The system may also include a variety of sensors and cameras to detect image data and environmental data of an area surrounding the unmanned lawn mower. The image data and the environmental data may be provided to the predictive model service in order to control the operation of the unmanned lawn mower in real-time.

A method and system for automatic recovery of a machine after a collision event occurred within a workspace environment of the machine is provided. The method may include recording a plurality of configurations of a machine during execution of a task; calculating based on the plurality of recorded configurations, a swept volume occupied by the machine during execution of the task; in response to a collision event, determining, based on the swept volume, a recovery sequence of movements for the machine; and using the recovery sequence of movements to lead the machine back to a predefined known safe position after the collision event occurred.