A method of maintaining stability of a motor vehicle having a first axle, a second axle, and a steering actuator configured to steer the first axle includes determining localization and heading of the vehicle. The method also includes determining a current side-slip angle of the second axle and setting a maximum side-slip angle of the second axle using the friction coefficient at the vehicle and road surface interface. The method additionally includes predicting when the maximum side-slip angle would be exceeded using the localization, heading, and determined current side-slip angle as inputs to a linear computational model. The method also includes updating the model using the prediction of when the maximum side-slip angle would be exceeded to determine impending instability of the vehicle. Furthermore, the method includes correcting for the impending instability using the updated model and the maximum side-slip angle via modifying a steering angle of the first axle.

Techniques for generating simulations for evaluating a performance of a controller of an autonomous vehicle are described. A computing system may evaluate the performance of the controller to navigate the simulation and respond to actions of one or more objects (e.g., other vehicles, bicyclists, pedestrians, etc.) in a simulation. Actions of the objects in the simulation may be controlled by the computing system (e.g., by an artificial intelligence) and/or one or more users inputting object controls, such as via a user interface. The computing system may calculate performance metrics associated with the actions performed by the vehicle in the simulation as directed by the autonomous controller. The computing system may utilize the performance metrics to verify parameters of the autonomous controller (e.g., validate the autonomous controller) and/or to train the autonomous controller utilizing machine learning techniques to bias toward preferred actions.

Techniques for generating simulations for evaluating a performance of a controller of an autonomous vehicle are described. A computing system may evaluate the performance of the controller to navigate the simulation and respond to actions of one or more objects (e.g., other vehicles, bicyclists, pedestrians, etc.) in a simulation. Actions of the objects in the simulation may be controlled by the computing system (e.g., by an artificial intelligence) and/or one or more users inputting object controls, such as via a user interface. The computing system may calculate performance metrics associated with the actions performed by the vehicle in the simulation as directed by the autonomous controller. The computing system may utilize the performance metrics to verify parameters of the autonomous controller (e.g., validate the autonomous controller) and/or to train the autonomous controller utilizing machine learning techniques to bias toward preferred actions.

The invention relates to a control device for a driver assistance system, wherein the control device comprises a sensor interface via which the control device can be connected to at least one sensor module to receive data from the at least one sensor module, a power processor which is adapted to detect objects and to provide object data based on the data from the at least one sensor module, and a system interface via which the control device can be connected to a higher-level control device of the driver assistance system for forwarding object data provided by the power processor.

The invention relates to a control device for a driver assistance system, wherein the control device comprises a sensor interface via which the control device can be connected to at least one sensor module to receive data from the at least one sensor module, a power processor which is adapted to detect objects and to provide object data based on the data from the at least one sensor module, and a system interface via which the control device can be connected to a higher-level control device of the driver assistance system for forwarding object data provided by the power processor.

Provided is a program updating process according to which even when power supply to an electronic control unit stops during program updating, invalid data's remaining in a storage area at completion of program updating is prevented without acquiring a power supply status of a vehicle. An electronic control unit includes a communication interface, a nonvolatile memory, and an arithmetic processing unit that executes a program. The nonvolatile memory includes a program storage area and a data storage area. The program storage area has a program updating process unit that carries out an updating process, and a program updating target unit that stores an updating program. The arithmetic processing unit reads the program updating process unit as the program and executes the program, divides an updating program received by the communication interface into divided updating programs each having a given size, and writes each of the divided updating programs to the program updating target unit. The arithmetic processing unit stores updating progress data in the data storage area, the updating progress data indicating a position of the divided updating program having been written to the program updating target unit.

Provided is a program updating process according to which even when power supply to an electronic control unit stops during program updating, invalid data's remaining in a storage area at completion of program updating is prevented without acquiring a power supply status of a vehicle. An electronic control unit includes a communication interface, a nonvolatile memory, and an arithmetic processing unit that executes a program. The nonvolatile memory includes a program storage area and a data storage area. The program storage area has a program updating process unit that carries out an updating process, and a program updating target unit that stores an updating program. The arithmetic processing unit reads the program updating process unit as the program and executes the program, divides an updating program received by the communication interface into divided updating programs each having a given size, and writes each of the divided updating programs to the program updating target unit. The arithmetic processing unit stores updating progress data in the data storage area, the updating progress data indicating a position of the divided updating program having been written to the program updating target unit.

Stochastic nonlinear model predictive control (SNMPC) allows to directly take uncertainty of the dynamics and/or of the system's environment into account, e.g., by including probabilistic chance constraints. However, SNMPC requires the approximate computation of the probability distributions for the state variables that are propagated through the nonlinear system dynamics. This invention proposes the use of Gaussian-assumed density filters (ADF) to perform high-accuracy propagation of mean and covariance information of the state variables through the nonlinear system dynamics, resulting in a tractable SNMPC approach with improved control performance. In addition, the use of a matrix factorization for the covariance matrix variables in the constrained optimal control problem (OCP) formulation guarantees positive definiteness of the full trajectory of covariance matrices in each iteration of any optimization algorithm. Finally, a tailored adjoint-based sequential quadratic programming (SQP) algorithm is described that considerably reduces the computational cost and allows a real-time feasible implementation of the proposed ADF-based SNMPC method to control nonlinear dynamical systems under uncertainty.

Stochastic nonlinear model predictive control (SNMPC) allows to directly take uncertainty of the dynamics and/or of the system's environment into account, e.g., by including probabilistic chance constraints. However, SNMPC requires the approximate computation of the probability distributions for the state variables that are propagated through the nonlinear system dynamics. This invention proposes the use of Gaussian-assumed density filters (ADF) to perform high-accuracy propagation of mean and covariance information of the state variables through the nonlinear system dynamics, resulting in a tractable SNMPC approach with improved control performance. In addition, the use of a matrix factorization for the covariance matrix variables in the constrained optimal control problem (OCP) formulation guarantees positive definiteness of the full trajectory of covariance matrices in each iteration of any optimization algorithm. Finally, a tailored adjoint-based sequential quadratic programming (SQP) algorithm is described that considerably reduces the computational cost and allows a real-time feasible implementation of the proposed ADF-based SNMPC method to control nonlinear dynamical systems under uncertainty.

Systems for collision avoidance by an autonomous vehicle include a navigational controller adapted to (i) control a driving path of the autonomous vehicle, (ii) process sensor signals from a first sensor system, and (iii) determine whether an object is present in the driving path of the autonomous vehicle based on the sensor signals from the first sensor system. The systems can also include a processor, operationally independent from the navigational controller, adapted to (a) process sensor signals from a second sensor system and (b) determine whether an object is present in the driving path of the autonomous vehicle based on the sensor signals from the second sensor system.