Abstract: A method of operating a robot performing a task when receiving instructions to discontinue the task and perform an additional task. Having performed the additional task, the robot will revert to the position of performing the first task and continue the first task.

Abstract: A method for obtaining a three-dimensional model of an inspection site, using a perception module, is disclosed. The perception module comprises a detection unit, e.g. comprising one or more cameras and/or a three-dimensional laser scanner, configured to obtain a three-dimensional image. At least one three-dimensional image is obtained by means of the detection unit. A three-dimensional model of surroundings of the perception module is created, based on the obtained three-dimensional image. The created three-dimensional model and a plan of the inspection site are compared and features of the created three-dimensional model and features of the plan of the inspection site are matched. A site-specific three-dimensional model of the inspection site is formed, based on the created three-dimensional model and the plan of the inspection site, and based on the comparison.