Volkswagen Ag

Audi Ag

Jens Hoedt

Thomas Eigel

Timur Aminev

Stefan Detering

Felix Kallmeyer

Björn Mennenga

Kristof Van Ende

Micha Helbig

Samuel Schacher

Sören Lindner

Firas Al-hafez

Ulrich Hofmann

A method for assisting maneuver planning for a transportation vehicle driving by automation or for a robot; wherein a state space of an environment of the transportation vehicle or the robot is discretely described by a Markov decision process; wherein optimal action values for discretized actions are determined by dynamic programming, based on discrete states in the state space; wherein a mapping with states in the state space as input values, and with action values for actions in the state space as output values, is learned by a reinforcement learning method; wherein a reinforcement learning agent is initialized based on the optimal action values determined by the dynamic programming; and wherein the learned mapping is provided for maneuver planning. Also disclosed is a device for assisting maneuver planning for a transportation vehicle driving by automation or for a robot.

Method and device for supporting maneuver planning for an automated driving vehicle or a robot

The invention relates to a driver assistance system () for an at least partially automatically driving motor vehicle (), wherein the driver assistance system () comprises at least one environment detection means () which is designed to detect at least one area of an environment (U) of the motor vehicle (), an evaluation device () which is designed to determine a target trajectory (T) to be traveled by the motor vehicle () according to the detected at least one area of the environment (U), and a control device () which is designed to adjust the target trajectory (T) determined by the evaluation device (). According to the invention, the evaluation device () is designed to determine at least one free area value (W) according to the detected at least one area of the environment (U), and to transfer same to the control device (), wherein the control device () has at least one adjustable control parameter (R, R, Rn), and the control device () is designed to adjust the at least one control parameter (R, R, Rn) according to the transferred free area value (W), and to adjust the target trajectory (T) according to the adjusted at least one control parameter (R, R, Rn).

Driver assistance system for an at least partially automatically driving motor vehicle, motor vehicle and method for controlling a vehicle dynamics

The invention relates to a method for supporting a lane changing procedure for a vehicle with a cruise control apparatus, wherein the cruise control apparatus adjusts a speed of the vehicle to a target speed, comprising the following steps: receiving environmental data on an environment of the vehicle using an input apparatus, wherein the environmental data at least comprise information on other vehicles in a target lane, determining a current traffic density and a current flow speed in the target lane based on the environmental data using an evaluation apparatus, adapting the target speed based on the determined current traffic density and the current flow speed by using the evaluation apparatus, forwarding the adapted target speed to the cruise control apparatus. The invention further relates to an associated device.

Method and device for supporting a lane changing procedure for a vehicle

The present invention relates to a method for providing a route stipulation for a route system of a vehicle, comprising the following steps:

Method for providing a route stipulation

A method for driving dynamics control for a transportation vehicle, wherein a manipulated variable of the driving dynamics is controlled by a control circuit having two degrees of freedom, consisting of a pilot control and a controller, to drive through a planned trajectory, wherein the control circuit has an iteratively learning controller which cyclically repeats classifying the planned trajectory by a classification device, retrieving a manipulated variable profile for the iteratively learning controller from a database based on the classification, recording a control fault of the control circuit and/or a manipulated variable of the controller when driving through the planned trajectory by a memory, and adapting the manipulated variable profile of the iteratively learning controller based on the recorded control fault and/or the recorded manipulated variable of the controller. Also disclosed is an associated device.

Method and device for driving dynamics control for a transportation vehicle

A method for adapting a predefined reference line for a transportation vehicle, a device, and a transportation vehicle. A predefined reference line is received by a control unit. A distance value of a maximum lateral distance from the predefined reference line is received by the control unit from an input device and a permissible area is specified that extends along the reference line and the lateral boundary of which is the maximum distance from the reference line that is specified by the distance value. A driving path optimized for a minimum driving time is calculated by a specified first mathematical optimization method starting from the current transportation vehicle position. The first mathematical optimization method has at least one boundary condition that requires a course of the driving path within the permissible area. The distance value is specified by a user input by the input device.

Method for adapting a predetermined reference line for a transportation vehicle and device

A driving assistance device for the semi-autonomous and fully autonomous guidance of a transportation vehicle, wherein the driving assistance device calculates potential return trajectories for the respective return of a transportation vehicle from an initial condition, which deviates from a predefined target trajectory, to the target trajectory, wherein each return trajectory satisfies a respective predetermined driving dynamics profile which defines a permissible value range of a total acceleration, and to which a respective degree of autonomy is assigned. The driving assistance device selects the return trajectories which satisfy a selection criterion with at least one boundary condition as suitable return trajectories, and from the suitable return trajectories identifies that whose driving dynamics profile has a minimum degree of autonomy as the suitable return trajectory and intervenes in the guidance of the transportation vehicle based on the degree of autonomy of the driving dynamics profile of the selected suitable return trajectory.

Driver assistance device for partially and fully autonomous guidance of a transportation vehicle, method, and transportation vehicle

A method and a device for estimating coefficients of friction of a wheel of a vehicle with respect to an underlying surface including decomposing a supplied trajectory into individual curve segments, estimating a lateral force and a slip angle for a front axle of the vehicle, assigning respectively estimated lateral forces and slip angles relating to the associated individual curve segments and storing these value pairs in a memory, estimating a tire characteristic curve for each of the curve segments based on the value pairs stored for the respective curve segment in the memory, estimating a coefficient of friction for each curve segment based on the respectively estimated tire characteristic curve, and storing the estimated coefficients of friction relating to the respectively associated curve segments in a coefficient of friction map.

Growing community of inventors

Hannover, Germany

Jens Hoedt