Device, method and machine learning system for determining a state of a transmission for a vehicle

A device configured to determine a state of a transmission for a vehicle, the device configured to:

• provide an input for a first model depending on a route information, a vehicle speed, a probabilistic variable including noise, and an output of a second model, wherein the first model is a generative model and the second model is a physical model;
• determine an output of the first model in response to the input for the first model, wherein the output of the first model characterizes the state of the transmission, wherein the first model includes a first layer that is trained to map the input for the first model determined depending on the route information, the vehicle speed, and the probabilistic variable, to an intermediate state, and wherein the first model includes a second layer that is trained to map the intermediate state to the state of the transmission depending on the output of the second model;
• provide an input for the second model depending on at least one vehicle state and/or the route information;
• and
• determine an output of the second model in response to the input for the second model, wherein the output of the second model characterizes at least one limit for the intermediate state.

A machine learning system, comprising:

• a first model;
• a second model;
• and
• a third model;
• wherein the machine learning system is configured to determine a state of a transmission for a vehicle, the machine learning system configured to:
• provide an input for the first model depending on a route information, a vehicle speed, a probabilistic variable including noise, and an output of the second model, wherein the first model is a generative model and the second model is a physical model;
• determine an output of the first model in response to the input for the first model, wherein the output of the first model characterizes the state of the transmission, wherein the first model includes a first layer that is trained to map the input for the first model determined depending on the route information, the vehicle speed, and the probabilistic variable, to an intermediate state, and wherein the first model includes a second layer that is trained to map the intermediate state to the state of the transmission depending on the output of the second model;
• provide an input for the second model depending on at least one vehicle state and/or the route information;
• and
• determine an output of the second model in response to the input for the second model, wherein the output of the second model characterizes at least one limit for the intermediate state.

A method of training a machine learning system, the machine learning system including a first model, a second model, and a third model, wherein the machine learning system is configured to determine a state of a transmission for a vehicle, the machine learning system configured to:

• (i) provide an input for the first model depending on a route information, a vehicle speed, a probabilistic variable including noise, and an output of the second model, wherein the first model is a generative model and the second model is a physical model, (ii) determine an output of the first model in response to the input for the first model, wherein the output of the first model characterizes the state of the transmission, wherein the first model includes a first layer that is trained to map the input for the first model determined depending on the route information, the vehicle speed, and the probabilistic variable, to an intermediate state, and wherein the first model includes a second layer that is trained to map the intermediate state to the state of the transmission depending on the output of the second model, (iii) provide an input for the second model depending on at least one vehicle state and/or the route information, and (iv) determine an output of the second model in response to the input for the second model, wherein the output of the second model characterizes at least one limit for the intermediate state, the method comprising:
• determining the state of the transmission depending on output of the first model and the second model in response to training data defining input data for the first model and the second model;
• determining an output of the third model characterizing a score indicating an estimate of veracity for the state of the transmission;
• and
• determining at least one parameter of the first model and/or the third model depending on the score wherein the input data for a training cycle includes the state of the transmission, the route information, and the at least one vehicle state.

A non-transitory computer-readable storage medium on which is stored a computer program including computer readable instructions for determining a state of a transmission for a vehicle, the computer readable instructions, when executed by a computer, causing the computer to perform the following steps:

• providing an input for a first model depending on a route information, a vehicle speed, a probabilistic variable including noise, and an output of a second model, wherein the first model is a generative model and the second model is a physical model;
• determining an output of the first model in response to the input for the first model, wherein the output of the first model characterizes the state of the transmission, wherein the first model includes a first layer that is trained to map the input for the first model determined depending on the route information, the vehicle speed, and the probabilistic variable, to an intermediate state, and wherein the first model includes a second layer that is trained to map the intermediate state to the state of the transmission depending on the output of the second model;
• providing an input for the second model depending on at least one vehicle state and/or the route information;
• and
• determining an output of the second model in response to the input for the second model, wherein the output of the second model characterizes at least one limit for the intermediate state.