Abstract: A machine learning-based method of generating a radiotherapy treatment plan for a patient, comprises dose prediction and dose mimicking, wherein the dose prediction step involves using a machine learning system that has been trained to consider at least one optimality criterion related to physical or technical restrictions that will affect the delivery of the treatment plan. Thus, at least one of the factors that are normally taken into account in the dose mimicking step is introduced in the dose prediction step. The invention also relates to a method of training such a machine learning system for use in radiotherapy treatment planning, a computer program product and a computer system.

Abstract: A method (400) and a control unit (210) for ground bearing capacity analysis. The method (400) steps include determining (401) a shape of the terrain segment (130) ahead of a vehicle (100), based on sensor measurements; predicting (402) a distance between a sensor (120) of the vehicle (100) and the ground (110) at the terrain segment (130), before the vehicle (100) moves into the terrain segment (130); measuring (403) the distance between the sensor (120) of the vehicle (100) and the ground (110) when the vehicle (100) has moved into the terrain segment (130); and determining (404) that the terrain segment (130) is to be avoided due to insufficient bearing capacity when the predicted (402) distance between the sensor (120) and the ground (110) exceeds the measured (403) distance between the sensor (120) and the ground (110). Also, a method (600) and control unit (210) for route planning of the vehicle (100) are described.

Abstract: A method (400) and a control unit (210) for ground bearing capacity analysis. The method (400) steps include determining (401) a shape of the terrain segment (130) ahead of a vehicle (100), based on sensor measurements; predicting (402) a distance between a sensor (120) of the vehicle (100) and the ground (110) at the terrain segment (130), before the vehicle (100) moves into the terrain segment (130); measuring (403) the distance between the sensor (120) of the vehicle (100) and the ground (110) when the vehicle (100) has moved into the terrain segment (130); and determining (404) that the terrain segment (130) is to be avoided due to insufficient bearing capacity when the predicted (402) distance between the sensor (120) and the ground (110) exceeds the measured (403) distance between the sensor (120) and the ground (110). Also, a method (600) and control unit (210) for route planning of the vehicle (100) are described.