Abstract: The invention relates to a fuel cell stack (10) having a plurality of fuel cells (20) which have an inlet-side cathode port (22), anode port (24) and coolant port (26) and an outlet-side cathode port (23), anode port (25) and coolant port (27), wherein the fuel cell stack (10) also has: two end plates (30, 31) between which the plurality of fuel cells (20) are arranged, wherein at least one of the end plates (30, 31) has inlet openings (32, 34, 36) and outlet openings (33, 35, 37) for a cathode gas, an anode gas and a coolant, which are each fluidically connected to the inlet-side and outlet-side cathode ports (22, 23), anode ports (24, 25) and coolant ports (26, 27), and at least one sensor (50) which is guided through at least one additional opening (39) in at least one of the end plates (30, 31) into one of the inlet-side or outlet-side cathode ports (22, 23), anode ports (24, 25) or coolant ports (26, 27). The invention also relates to a method for producing the fuel cell stack (10).

Abstract: Disclosed is an evaluation device for determining a vehicle action, wherein the evaluation device is configured to supply an artificial neural network, which outputs the vehicle action, with data regarding a vehicle environment. The artificial neural network predicts an accident situation on the basis of these data, to evaluate a damage function for personal injury and/or material damages, calculated on the basis of simulated vehicle actions, and to determine the vehicle action for which the damage function delivers the lowest results in this accident situation. Also disclosed is a computer program product for obtaining a damage function based on personal injury and/or material damages, a method for training an artificial neural network that minimizes a damage function through reinforcement learning, a system for controlling a vehicle for making situation-dependent decisions, and a driver assistance system that has a system according to the disclosure, or an artificial neural network.