4 results about "Nao robot" patented technology

The invention relates to a method for operating a resource reservation entity (100) configured to reserve radio resources in a cellular network for a plurality of user entities connected to the cellular network, the plurality of user entities comprising at least one first user entity (10, 11) connected to a robotic device (20, 21) and at least one second user entity (30) not connected to any robotic device, the robotic device being controlled by control commands transmitted to the first user entity over the cellular network, the method comprising, at the resource reservation entity: - receiving a first message indicating a future resource requirement needed by the at least one first user entity to control at least one first task to be executed by the robotic device based on the control commands, the resource requirement comprising a first time period defined by a defined start time of the at least one first task and a duration of the at least one first task; - reserving radio resources for the plurality of user entities, wherein, in the reservation, a priority assigned to the at least one first user entity is increased for the duration of the first time period with respect to a priority assigned to the at least one second user entity, and the priority assigned to the at least one first user entity is higher than the priority assigned to the at least one second user entity in the first time period.

Disclosed is a calibration method of a device for non-destructive measurement of the internal structure of large-scale objects (4), comprising a first robotic arm (1) equipped with a source (2) of penetrating ionizing radiation, a second robotic arm (7) equipped with an imaging detector (6) of ionizing radiation, and a server for synchronized control of the robotic arms (1, 7), which is connected for communication to the robotic arms (1, 7). Any robotic arm (1, 7) changes its position at least once by a defined delta change. A change in the position of incidence of a collimated beam (5) of the penetrating ionizing radiation on the imaging detector (6) is measured, or a change in the position of the second robotic arm (7) with the imaging detector (6) is measured to maintain an initial position of incidence of the collimated beam (5) of ionizing radiation on the imaging detector (6). The defined delta change and the associated change in the position of incidence of the collimated beam (5) on the imaging detector (6) or the change in the position of the second robotic arm (7) carrying the imaging detector (6) are used to calculate the relative position of the source (2) of penetrating ionizing radiation in relation to the imaging detector (6) of ionizing radiation.

The application discloses a NAO robot object grasping training method based on direct preference optimization, and comprises the following steps: (1) collecting and saving human expert data, imitation data and trajectory data of interactive grasping actions in a robot simulator using a reinforcement learning strategy; (2) scoring state-action trajectory sequence data pairs in the trajectory data by a human annotator to obtain a trajectory data set based on human preferences; (3) designing a reference strategy network using the human preference data set, designing a parameterized strategy network, constructing a maximum likelihood target in combination with the reference strategy network, and performing gradient descent on the target function to obtain an optimal strategy; (4) training an object recognition model, deploying the object recognition model and the optimal strategy to a real NAO robot, and evaluating the grasping actions of the robot; and (5) iteratively training and evaluating the process until the robot can successfully grasp the target object.