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 provides a method for controlling braking of a vehicle (1) driving along a downhill portion of a road, the vehicle comprising a propulsion arrangement (2, 3), for the propulsion of the vehicle, the method comprising dividing the road portion into a plurality of sections (RS0-RS2), the sections comprising a first section (RS1), and a second section (RS2) following, in the direction of travel of the vehicle, immediately upon the first section (RS1), determining, for the road portion, a road portion control strategy, with a condition that braking on the road portion is done at least partly by means of the propulsion arrangement (2, 3), wherein determining the road portion control strategy comprises determining a speed (SD21), on the second section (RS2), with an aim to minimize the time travelled on the second section, and/or, where the propulsion arrangement comprises an internal combustion engine (2), and a gearbox (3), determining a gear selection (GS2) on the second section (RS2), with an aim to minimize the time travelled on the second section, and wherein determining the road portion control strategy comprises determining, for the first section (RS1), a first section control strategy, with an aim to minimize the time travelled on the first section, and with an aim to provide a vehicle speed at the end of the first section (RS1) which is the same as said determined speed (SD21) on the second section (RS2), and/or to provide a gear selection at the end of the first section which is the same as said determined gear selection (GS2) on the second section (RS2), the method further comprising controlling the vehicle (1) according to the determined road portion control strategy.

A processor unit is configured for determining target torque values (21), which lie within a prediction horizon (20), and target speed values (19), which lie within the prediction horizon (20), by executing an MPC algorithm, which includes a longitudinal dynamics model of a drive train of the motor vehicle. An autonomous driving function of the motor vehicle is carried out in a torque specification operating mode or in a speed specification operating mode as a function of the level of the target torque values (21). In the torque specification operating mode, a prime mover of the drive train is controlled by an open-loop system based on the target torque values (21). In the speed specification operating mode, a speed governor of the drive train is controlled by an open-loop system based on the target speed values (19).

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.

A changing operation assisting apparatus includes a driving assistance control section, an operation section, and an information providing section. The driving assistance control section stores set states regarding driving assistance functions of a vehicle and provides the functions in accordance with the set sates. The set state includes a request state of the function. The operation section is used for changing the set state. The information providing section provides information regarding the set state to a driver of the vehicle. Further, the driving assistance control section executes a setting change confirmation processing upon satisfaction of a specific condition. The setting change confirmation processing is a process of providing confirmation information to confirm whether or not to change the request state of the function, and changing the request state of the function when the driver performs an approving operation in accordance with the confirmation information.

A lane change support device includes a control unit configured to execute lane change control for enabling a vehicle to automatically change lanes from a lane in which the vehicle is traveling to an adjacent lane. The control unit counts a holding time for which an operation part that is operated to a predetermined operation position to start the lane change control is continuously held at the operation position, starts the lane change control when the counted holding time reaches a predetermined threshold time, and calculates a proficiency level of a driver of the vehicle for an operation of the lane change support device during execution of the lane change control and sets the threshold time to be used for a successive lane change control based on the proficiency level.

A method and apparatus for determining a slope of a road using a side view camera of a vehicle, the method includes identifying a road image collected from a side view camera, dividing the road image into a plurality of regions, calculating a slope of a road for each of the plurality of regions based on driving lanes comprised in each of the plurality of regions, and determining a slope between the side view camera and the road using the slope of the road calculated for each of the plurality of regions.

Systems and methods are provided for vehicle navigation. In one implementation, a system may comprise at least one processor. The processor may be programmed to receive images representative of an environment of the host vehicle and analyze the images to identify a first object and a second object. The processor may determine a first predefined navigational constraint implicated by the first object and a second predefined navigational constraint implicated by the second object, wherein the first and second predefined navigational constraints cannot both be satisfied, and the second predefined navigational constraint has a priority higher than the first predefined navigational constraint. The processor may determine a navigational action for the host vehicle satisfying the second predefined navigational constraint, but not satisfying the first predefined navigational constraint and, cause an adjustment of a navigational actuator of the host vehicle in response to the determined navigational action.

The present disclosure relates to user settings on a vehicle. More particularly, this disclosure describes a driver profile reset system and methods thereof to remove those user settings. In an illustrative embodiment, a driver may be presented with a pin pad on a head unit display. The user may enter their pin thereon. The system may authenticate it to enable user settings on the vehicle. Thereafter, the user settings may be removed or wiped from the system to prevent access to such information. The setting, for example, may be removed after the driver unbuckles their seatbelt and opens their door.

A method for performing an at least partially automatic vehicle function of a vehicle depending on a travel route to be assessed by means of a driver assistance system is disclosed. The method comprises providing a plurality of clusters from route data with respect to at least one known travel route, wherein the clusters group the route data sectionwise according to predefined geometric parameters. The method comprises providing recorded course data that indicate a course of the travel route to be assessed and applying the clusters to the course data in order to divide the travel route to be assessed into route sections corresponding to the clusters. The method comprises determining at least one uncertainty quantity which is characteristic of an uncertainty with respect to the assignment made and determining a control quantity as a function of the uncertainty quantity and providing the control quantity for performing the vehicle function.