Enclosed are embodiments for sampling driving scenarios for training machine learning models. In an embodiment, a method comprises: assigning, using at least one processor, a set of initial physical states to a set of objects in a map for a set of simulated driving scenarios, wherein the set of initial physical states are assigned according to one or more outputs of a random number generator; generating, using the at least one processor, the set of simulated driving scenarios in the map using the initial physical states of the objects in the set of objects; selecting, using the at least one processor, samples of the simulated driving scenarios; training, using the at least one processor, a machine learning model using the selected samples; and operating, using a control circuit, a vehicle in an environment using the trained machine learning model.

A method for operating a motor vehicle incorporates polling regarding the control of the motor vehicle, leading to an improvement in the working conditions of a plurality of evaluation units accessing sensor units of the motor vehicle. Control commands for controlling the motor vehicle are determined from this polling by a conflict checking unit. The conflict checking unit determines the feasibility of the control commands, taking into consideration predetermined verification criteria with regard to conflicts between the individual control commands and the practicability of the individual control commands. The conflict checking unit also determines a control specification for a vehicle control unit based on the feasibilities and certain decision criteria. Finally, the motor vehicle is controlled by use of the vehicle control unit in accordance with the control specification.

A method for determining the values of parameters for a controller of a vehicle, wherein respective error measures are calculated for different sets of values and a set of values is selected based on the error measures.

Provided is a learning system 10 for an operation inference learning model 70 for controlling an automatic driving robot 4, the learning system 10 training the operation inference learning model 70 by reinforcement learning, and comprising the operation inference learning model 70, which infers operations of a vehicle 2 for making the vehicle 2 run in accordance with a defined command vehicle speed based on a running state of the vehicle 2 including a vehicle speed, and the automatic driving robot 4, which is installed in the vehicle 2 and which makes the vehicle 2 run based on the operations. In the learning system 10 for an operation inference learning model 70 for controlling an automatic driving robot 4, the operation inference learning model 70 is pre-trained by reinforcement learning by applying the simulated running state output by the vehicle learning model 60 to the operation inference learning model 70, and after the pre-training by reinforcement learning has ended, the operation inference learning model 70 is further trained by reinforcement learning by applying, to the operation inference learning model 70, the running state acquired by the vehicle 2 being run based on the operations inferred by the operation inference learning model 70.

Systems and methods are disclosed for optimizing values of a set of tunable parameters of an autonomous driving vehicle (ADV). The controllers can be a linear quadratic regular, a “bicycle model,” a model-reference adaptive controller (MRAC) that reduces actuation latency in control subsystems such as steering, braking, and throttle, or other controller (“controllers”). An optimizer selects a set tunable parameters for the controllers. A task distribution system pairs each set of parameters with each of a plurality of simulated driving scenarios, and dispatches a task to the simulator to perform the simulation with the set of parameters. Each simulation is scored. A weighted score is generated from the simulation. The optimizer uses the weighted score as a target objective for a next iteration of the optimizer, for a fixed number of iterations. A physical real-world ADV is navigated using the optimized set of parameters for the controllers in the ADV.

A vehicle-mounted processing device of learning-use data including a data acquisition unit acquiring data relating to operation of the vehicle, a neural network storage unit storing a neural network which outputs output values relating to operational control of the vehicle if data which was acquired at the data acquisition unit is input, and a learning-use data storage unit storing learning-use data of weights of the neural network. If the frequency of learning of the weights of the neural network on the vehicle or the frequency of transmission of the learning-use data to the server becomes lower, the amount of storage per unit time of the learning-use data successively stored in the learning-use data storage unit or the amount of the learning-use data which finishes being stored in the learning-use data storage unit is made to decrease.

A control method is provided for controlling a lateral position of a motor vehicle. The control method includes calculating a sighting distance of a detector means embedded in the vehicle, calculating a first component of a steering angle setpoint of a steered wheels of the vehicle, and calculating a second component of the steering angle setpoint. The first component is an open loop component of a control system, while the second component is a closed loop component of the control system. The first component is weighted by a gain that is a decreasing function of the sighting distance.

A method for determining the values of parameters for a controller of a vehicle, wherein respective error measures are calculated for different sets of values and a set of values is selected based on the error measures.

A computer-based system for testing a server-based vehicle function, which is designed to implement a method comprising the following steps: a function model of the vehicle function is simulated by a first simulator on a server, an at least partial vehicle model is simulated by a second simulator and the vehicle function is tested, while a data connection between the first simulator and the second simulator is systematically influenced.

In various examples, rapid resolution of deep neural network (DNN) failure modes may be achieved by deploying patch neural networks (PNNs) trained to operate effectively on the failure modes of the DNN. The PNNs may operate on the same or additional data as the DNN, and may generate new signals in addition to those generated using the DNN that address the failure modes of the DNN. A fusion mechanism may be employed to determine which output to rely on for a given instance of the DNN/PNN combination. As a result, failure modes of the DNN may be addressed in a timely manner that requires minimal deactivation or downtime for the DNN, a feature controlled using the DNN, and/or semi-autonomous or autonomous functionality as a whole.