Electric vehicle powertrain calibration

A system comprising:

• a test bench comprising:
• a plurality of sensors for measuring values of a performance characteristic of a powertrain of an electric vehicle;
• and
• a plurality of controllers for adjusting values of a plurality of variables associated with the operation of the powertrain, the plurality of variables including:
• a set of context variables representing operational conditions of the electric vehicle;
• and
• a set of decision variables representing parameters of the powertrain adjustable by an ECU of the electric vehicle;
• and
• a data system comprising at least one processor and at least one non-transitory storage medium holding instructions which, when executed by the at least one processor, causes the data processing system to carry out operations comprising:
• obtaining, from the test bench, measurements of the performance characteristic of the powertrain at one or more test points in an input space, the input space having dimensions corresponding to at least one context variable of the set of context variables and at least one decision variable of the set of decision variables;
• training, using the obtained measurements of the performance characteristic at the one or more test points, a Gaussian process model arranged to predict values of the performance characteristic, wherein the Gaussian process model has a covariance function with a specified dependence on points in the input space, the specified dependence corresponding to a specified physical relationship between the performance characteristic and at least a chosen variable associated with the powertrain, the chosen variable being taken from the set of decision variables or the set of context variables;
• and
• generating, in dependence on outputs of the trained Gaussian process model, a calibration map for the powertrain, the calibration map providing a mapping from values of the set of context variables to mapped values of the set of decision variables.