Control system and control method for a hybrid approach to determining a possible trajectory for a motor vehicle

Abstract

Control system (10) designed and intended for use in a motor vehicle (12) to detect lanes, road boundaries, road markings and / or other motor vehicles in an area (22, 24, 26) in front of, to the side of and / or behind the motor vehicle (12) based on environmental data obtained from at least one environmental sensor(s) (14, 16, 18) arranged on the motor vehicle, wherein the at least one environmental sensor is designed to provide an electronic control unit (20) of the control system (10) with the environmental data representing the area in front of, to the side of and / or behind the motor vehicle (12), and wherein the control system (10) is at least designed and intended to - To determine information regarding the current driving situation of the motor vehicle (12) based on the provided environmental data, - to determine at least one component of a future driving maneuver for the motor vehicle (12) based on the information regarding the current driving situation of the motor vehicle (12), - to determine a plurality of sample trajectories for the motor vehicle (12) based on the identified component of the future driving maneuver for the motor vehicle (12), - to determine from the plurality of sample trajectories for the motor vehicle (12) one trajectory for the motor vehicle (12) which the motor vehicle (12) is to follow in its further journey, - to update the information regarding the current driving situation of the motor vehicle (12) and / or the provided environmental data, characterized in that the control system (10) is further set up and designed for - to adapt the trajectory for the motor vehicle (12) using an objective function and based on the updated provided environmental data and / or based on the updated information regarding the current driving situation of the motor vehicle (12), - to determine the information regarding the current driving situation of the motor vehicle (12) based on the provided environmental data in the form of discrete sampling values, - to determine a plurality or all of the discrete sampling values ​​as nodes and / or edges of a graph, and to create a connected graph from the determined nodes and / or edges, - to choose the nodes and / or edges of the graph as stopping points for the trajectory, and - to calculate the trajectory for the motor vehicle (12) using a spline-based interpolation between the selected stopping points.

Description

Background of the invention

[0001] This document describes a control system and a control method for determining a trajectory that a motor vehicle should follow as the best possible response to a current driving situation. The control system and the control method are based primarily on environmental sensors in the vehicle itself and support a driver or an autonomously driving vehicle. In partially and fully autonomous vehicles, it helps to increase the safety and driving comfort of the vehicle's occupants by employing an efficient and robust planning and optimization approach for determining the trajectory. State of the art

[0002] The increasingly diverse functions of self-driving vehicles create a growing need for reliable and fast control systems and algorithms for motion planning (trajectory planning) of at least partially autonomous vehicles. A major challenge here is the increasing number of road users in an ever more complex and dynamically changing vehicle environment. In the architecture of control systems for partially or fully autonomous vehicles, in addition to the recognition and control of specific traffic situations, decision-making and motion planning significantly influence the overall performance of the respective vehicle.

[0003] The increasing sophistication of control systems and algorithms for trajectory planning in (semi-)autonomous vehicles in recent years demonstrates the complexity of automated driving. The challenge in motion planning typically lies in determining a comfortable and collision-free trajectory based on a robust computational model that considers both static and dynamic objects in the vehicle's environment. Furthermore, it is desirable to calculate this trajectory as quickly as possible and optimize it online, adapting it to the constantly changing vehicle environment to ensure real-time performance of the (semi-)autonomous systems in a dynamically evolving setting.

[0004] Various approaches to trajectory planning have been developed in the past. These include, for example, motion planning algorithms or techniques for sampling-based trajectory planning. These approaches employ, for example, (local) continuous or (global) discrete optimization techniques to calculate and optimize trajectory planning.

[0005] Discrete planning and optimization techniques offer the possibility of appropriate decision-making, but also have the disadvantage that a large number of calculations to be carried out result in a large amount of time, which prevents online or real-time calculations for quick reaction to a current driving situation.

[0006] Local continuous planning and optimization techniques typically deliver quickly optimized solutions, but they must be appropriately initialized to handle the combinatorial tasks that arise in the dynamic vehicle environment.

[0007] In modern vehicles, advanced driver assistance systems (ADAS) offer a variety of monitoring and guidance functions to make driving safer. These systems monitor the vehicle's surroundings based on environmental data gathered from one or more sensors located on the vehicle, in relation to the vehicle's driving trajectory.

[0008] Well-known driver assistance systems determine, for example, whether the vehicle is within its lane and whether the driver is unintentionally drifting to one side of the lane or is about to leave it. These systems generate a "digital representation" of the road and, in particular, the lane from the collected environmental data. Objects are detected and tracked while driving, such as curbs, lane markings, lane markings, directional arrows, etc. Moving objects, such as other vehicles, are also detected and tracked.

[0009] Furthermore, so-called "blind spot monitors" are among today's driver assistance systems. These use technologies such as radar, lidar, video, or similar to determine whether another vehicle, road user, or object is located to the side and / or behind the vehicle, such that a lane change or turn could lead to a collision.

[0010] Furthermore, in so-called ACC (Adaptive Cruise Control) systems, the vehicle's speed is automatically adjusted to the speed of a vehicle ahead. A specific distance to the vehicle in front is to be maintained at all times. To achieve this, such systems determine the direction of travel and / or the speed of the vehicle ahead in order to prevent the vehicle from crossing its path in a way that could lead to a critical situation. This applies both to lane changes and turning maneuvers, as well as to rear-end collisions.

[0011] In human-driven vehicles, driver assistance systems typically provide a warning function to alert the driver to a critical situation or a necessary maneuver, or to suggest a suitable maneuver. Similarly, driver assistance systems can also be used in autonomous vehicles to provide the autonomous control system with relevant environmental data.

[0012] DE 10 2014 215 244 A1 describes a method for determining a trajectory for longitudinal and / or lateral guidance of a vehicle, in which a large number of potentially possible driving maneuvers are determined by means of a global planning process, such a driving maneuver is selected and a target trajectory is determined from a local planning process for the selected driving maneuver.

[0013] DE 10 2015 208 790 A1 discloses a method for automatically determining a trajectory for a vehicle, in which one or more partial trajectories are determined for several sections and at least one part of the trajectory is formed from each partial trajectory for a respective section.

[0014] From DE 10 2011 081 159 A1 a method for carrying out an evasive maneuver is known in which an optimal trajectory segment for the evasive maneuver is determined by means of a non-linear program.

[0015] DE 10 2013 219 023 A1 concerns a procedure for assisting a driver when changing lanes.

[0016] DE 101 32 386 A1 relates to a driver assistance system that links environmental information with a driver reaction prediction to make decisions regarding assistance measures. Underlying problem

[0017] In road traffic, situations can arise that require a driver or a (semi-)autonomous driver assistance system of a motor vehicle to execute a driving maneuver. For example, even a curved lane layout can necessitate a corresponding driving maneuver by the motor vehicle.

[0018] The current situation of a vehicle is not constant, but rather continuously changing in reality. For example, other road users may intentionally or unintentionally change lanes or speed due to an accident. Furthermore, the vehicle's current driving situation also changes due to the driver's behavior and / or the changing lane layout. Reacting appropriately and promptly to such changes in the current situation poses a significant challenge for both conventional driver assistance systems and human drivers. Conventional driver assistance systems, for instance, calculate a trajectory that the vehicle should follow in the current driving situation.The complex and dynamically changing traffic situations and the ever-increasing density of traffic today result in rising resource consumption by these conventional driver assistance systems. Furthermore, conventional driver assistance systems have limitations regarding the execution speed of the continuous optimization of a calculated trajectory.

[0019] The task is therefore to provide a control system and a control procedure for a motor vehicle that robustly increase the vehicle's driving safety and comfort, taking into account the current traffic situation. Furthermore, the computation time should be reduced compared to conventional control systems and procedures. Proposed solution

[0020] This problem is solved by a control system having the features of claim 1 and a control method having the features of claim 8.

[0021] Preferred embodiments will become apparent from dependent claims 2 to 7 and subsidiary claim 9 as well as the following description.

[0022] One aspect concerns a control system designed and intended for use in a motor vehicle, which, based on environmental data obtained from at least one environmental sensor(s) arranged on the motor vehicle, is capable of detecting lanes, road boundaries, lane markings, and / or other motor vehicles in an area in front of, to the side of, and / or behind the motor vehicle. The at least one environmental sensor is configured to provide an electronic control unit of the control system with the environmental data representing the area in front of, to the side of, and / or behind the motor vehicle. The control system is at least configured and intended to determine information regarding the current driving situation of the motor vehicle based on the provided environmental data and, based on this information, to determine at least one component of a future driving maneuver for the motor vehicle.The control system is furthermore configured and designed, at least, to determine a plurality of sample trajectories for the vehicle based on the identified component of the future driving maneuver, and from these plurality of sample trajectories, to determine one trajectory for the vehicle which the vehicle is to follow during its further journey. Finally, the control system is at least configured and designed to update the information regarding the current driving situation of the vehicle and / or the provided environmental data, and to adjust the trajectory for the vehicle based on an objective function and the updated environmental data and / or the updated information regarding the current driving situation of the vehicle.

[0023] The component of the future driving maneuver can be a lateral component. It can also be a longitudinal component. Alternatively, the component of the future driving maneuver can consist of a combination of lateral and longitudinal components.

[0024] The lateral component can include, for example, lane keeping, a lane change to the left and / or a lane change to the right, each starting from a lane currently being traveled by the motor vehicle.

[0025] The longitudinal component can, for example, include the longitudinal speed and / or longitudinal acceleration of the vehicle. Alternatively or additionally, the longitudinal component can include data and / or control signals for one or more electronic control systems of the vehicle that are capable of performing or at least initiating adaptive cruise control (ACC) and / or adaptive chassis control (DCC) and / or emergency braking in accordance with corresponding output signals.

[0026] The control system can be set up and designed to make a driving maneuver preselection and / or a driving maneuver selection for determining the pattern trajectories and to additionally make the pattern trajectories based on the driving maneuver preselection and / or the driving maneuver selection.

[0027] The beginning of the next leg of the journey can mark the end of the current driving situation.

[0028] The adjustment of the vehicle's trajectory based on the objective function and the updated environmental data provided, and / or based on updated information regarding the current driving situation, can occur continuously or at specific intervals. A subsequent adjustment may require a reinitialization of the objective function.

[0029] The control system can be set up and designed to determine the trajectory from the plurality of pattern trajectories using an objective function that is the same as the objective function for fitting the trajectory for the motor vehicle.

[0030] The same objective function can also be used, for example, to determine the pattern trajectories.

[0031] This allows for comparison options during the aforementioned reinitialization of the objective function.

[0032] The objective function could, for example, be a cost function.

[0033] According to certain embodiments, the information regarding the current driving situation of the vehicle includes at least the lateral distance of the vehicle to its currently occupied lane. In these cases, the control system can further be configured and designed to determine whether the component of the future driving maneuver will be lane keeping or lane change, based on the lateral distance of the vehicle to its currently occupied lane.

[0034] The lateral distance can be measured, for example, with respect to the vehicle's longitudinal axis. A lane change can include a left lane change and a right lane change. Maintaining a lane can include staying in the left lane, staying in the middle lane, and / or staying in the right lane.

[0035] The information regarding the current driving situation of the motor vehicle may also include the lateral distance of one or more other motor vehicles (or their respective longitudinal axes) to their currently occupied lanes in the vicinity of the motor vehicle.

[0036] According to certain embodiments, the information regarding the current driving situation of the vehicle can also include the longitudinal distance of the vehicle along its currently traversed lane to another vehicle. In these cases, the control system can be configured and designed to determine a further component of the future driving maneuver based on this component and the longitudinal distance of the vehicle to the other vehicle.

[0037] Alternatively or additionally, the information regarding the current driving situation of the vehicle can include a relative speed and / or a relative acceleration between the vehicle and the other vehicle. The relative acceleration can, but does not necessarily have to, be derived from the relative speed by the control system or another electronic control unit of the vehicle.

[0038] The other component may be the longitudinal component mentioned above, but the present disclosure is not limited to it.

[0039] The other motor vehicle may be stationary (parked) or moving.

[0040] According to certain embodiments, the control system can also be set up and designed to determine the information regarding the current driving situation of the motor vehicle based on the provided environmental data in the form of discrete sampling values.

[0041] Furthermore, the control system can be configured and designed to identify a majority or all of the discrete sampling values ​​as nodes and / or edges of a graph and to determine a connected graph from the identified nodes and / or edges. In this way, a graph-based method for identifying and processing the discrete sampling values ​​can be implemented.

[0042] Furthermore, the control system can be configured and designed to select the nodes and / or edges of the graph as stopping points for the trajectory and to calculate the trajectory for the motor vehicle using spline-based interpolation between the selected stopping points.

[0043] According to certain embodiments, the control system can also be configured and designed to determine the updated information and / or the updated environmental data in the form of continuous values.

[0044] Within the scope of this disclosure, the continuous values ​​may, for example, be quasi-continuous values, where each value is assigned a measurement time and the quasi-continuous values ​​are ordered according to the measurement time. For efficiency reasons, the continuous values ​​may consist of only a subset of the quasi-continuous values, for example, every second or every third quasi-continuous value.

[0045] Furthermore, the control system can be set up and designed to combine the updated information and / or the updated environmental data in the form of continuous values ​​with the information regarding the current driving situation of the vehicle in the form of discrete sampling values ​​for the purpose of adapting the trajectory for the motor vehicle.

[0046] In this way, a hybrid planning approach for the trajectory can be realized, which combines discrete and continuous planning and optimization methods and thus compensates for the inherent disadvantages of the individual planning and optimization methods.

[0047] Combining information regarding the current driving situation of the vehicle in the form of discrete sampling values ​​with the updated information and / or with the updated environmental data in the form of continuous values ​​can at least include initializing and / or reinitializing the adaptation of the trajectory for the vehicle based on the objective function.

[0048] Alternatively or additionally, combining the information regarding the current driving situation of the motor vehicle in the form of discrete sampling values ​​with the updated information and / or with the updated environmental data in the form of continuous values ​​may include initializing and / or reinitializing the determination of the continuous values ​​based on the updated information and / or based on the updated environmental data.

[0049] Another aspect concerns a control method that, based on environmental data obtained from at least one environmental sensor(s) mounted on the motor vehicle, detects lanes, road boundaries, lane markings, and / or other motor vehicles in an area in front of, to the side of, and / or behind the motor vehicle, wherein the control method is executed in particular by means of a control system described above. The control method comprises the following steps: - Determining information regarding the current driving situation of the motor vehicle based on the provided environmental data, - Determining at least one component of a future driving maneuver for the motor vehicle based on information regarding the current driving situation of the motor vehicle, - Determining a plurality of pattern trajectories for the motor vehicle based on the determined component of the future driving maneuver for the motor vehicle, - Determining a trajectory for the motor vehicle, which the motor vehicle is to follow during its further journey, from the plurality of model trajectories for the motor vehicle, - Updating information regarding the current driving situation of the vehicle and / or the provided environmental data, and - Adjusting the trajectory for the motor vehicle based on an objective function and on the updated provided environmental data and / or on the updated information regarding the current driving situation of the motor vehicle.

[0050] Another aspect concerns a motor vehicle that includes a control system described above.

[0051] Compared to conventional driver assistance systems, the solution presented here improves the accurate assessment and recognition of the current driving situation of the vehicle and other vehicles. Furthermore, it provides a real-time planning and optimization approach for a vehicle's trajectory, which, through the combination of discrete and continuous planning approaches, enables the robust and rapid determination of the best possible trajectory for a future driving maneuver.

[0052] This optimal trajectory can therefore be determined as an appropriate response to the current traffic situation in which the vehicle is located. The environmental data acquired by means of at least one sensor constantly changes according to the actual traffic and driving situation and can be updated cyclically.

[0053] Using the trajectory for a future driving maneuver of one's own vehicle increases driving comfort and safety by taking into account the vehicle's driving dynamics and the dynamically changing environment when adjusting the trajectory.

[0054] It is evident to a person skilled in the art that the aspects and features described above can be combined arbitrarily in a control system and / or a control method. Although some of the features described above were described in relation to a control system, it is understood that these features can also apply to a control method. Likewise, the features described above in relation to a control method can apply to a control system in a corresponding manner. Brief description of the drawing

[0055] Further objectives, features, advantages, and applications will become apparent from the following description of exemplary embodiments, which are not to be understood as limiting, with reference to the accompanying drawings. All features described and / or illustrated, individually or in any combination, depict the subject matter disclosed herein. The dimensions and proportions of the components shown in the figures are not to scale. Identical or functionally equivalent components are designated with the same reference numerals. Fig. Figure 1 schematically shows a motor vehicle with a control system and at least one environmental sensor according to certain embodiments. Fig. Figure 2 schematically contrasts a discrete planning and optimization approach with a continuous planning and optimization approach. Fig. Figure 3 schematically shows the architecture of a hybrid approach for planning and adapting a trajectory for the motor vehicle according to certain embodiments. Fig. Figure 4 schematically shows diagrams for determining a lateral maneuver component (left) and for determining a longitudinal maneuver component (right) according to certain embodiments. Fig. Figure 5 schematically shows a diagram for adapting the selected trajectory for the motor vehicle according to certain embodiments. Fig. 6 schematically represents the relationship of the elements in the Fig. 2 planning approaches shown within the framework of a hybrid approach to planning and adapting a trajectory for the motor vehicle according to certain exemplary embodiments. Fig. Figure 7 schematically shows sample trajectories and a selected trajectory for the motor vehicle according to specific embodiments. Fig. Figure 8 schematically shows a flowchart of a control procedure according to specific exemplary embodiments. Detailed description of the drawings

[0056] In the following disclosure, certain aspects are primarily described with reference to the control system. However, these aspects are naturally also valid within the context of the disclosed control method, which can, for example, be executed by a central control unit (ECU) of a motor vehicle. This can be done by performing suitable read and write accesses to a memory associated with the motor vehicle. The control method can be implemented within the motor vehicle in hardware, software, or a combination of both. This includes digital signal processors, application-specific integrated circuits, field-programmable gate arrays, and other suitable switching and computing components.

[0057] Fig. Figure 1 schematically shows a motor vehicle 12 comprising a control system 10. The control system 10 is coupled to at least one environmental sensor 14, 16, 18 located on the motor vehicle 12 in order to obtain environmental data from the at least one sensor 14, 16, 18. The control system 10 may include an electronic control unit (ECU; not shown in the figure). For example, the control system 10, with the help of the ECU and / or other electronic control systems, may at least be configured and intended to determine a trajectory for the motor vehicle 12, which the motor vehicle 12 is to follow during further travel. For this purpose, the ECU receives, for example, signals from the environmental sensors 14, 16, 18, processes these signals and the associated environmental data, and generates corresponding control and / or output signals.

[0058] In the Fig. Figure 1 shows three environmental sensors 14, 16, 18 that send corresponding signals to the control system 10 or the electronic control unit (ECU). In particular, at least one environmental sensor 14 is arranged on the motor vehicle 12, facing forward in the direction of travel of the motor vehicle 12, and detects an area 22 in front of the motor vehicle 12. This at least one environmental sensor 14 can be located, for example, in the area of ​​a front bumper, a front lamp, and / or a front radiator grille of the motor vehicle 12. Thus, the environmental sensor 14 detects an area 22 directly in front of the motor vehicle 12.

[0059] At least one additional or alternative environmental sensor 16, also directed forward in the direction of travel of the motor vehicle 12, is shown in the area of ​​the windshield of the motor vehicle 12. For example, this environmental sensor 16 can be arranged between an interior rearview mirror of the motor vehicle 12 and its windshield. Such an environmental sensor 16 detects an area 24 in front of the motor vehicle 12, whereby, depending on the shape of the motor vehicle 12, an area 24 directly in front of the motor vehicle 12 may not be detected due to the front section (or its geometry) of the motor vehicle 12.

[0060] Furthermore, at least one environmental sensor 18 can be arranged laterally and / or at the rear of the motor vehicle 12. This optional environmental sensor 18 detects an area 26 that lies laterally and / or behind the motor vehicle 12 in the direction of travel. For example, the data or signals from this at least one environmental sensor 18 can be used to verify information detected by the other environmental sensors 14, 16 and / or to determine the curvature of a lane traveled by the motor vehicle 12.

[0061] The at least one environmental sensor 14, 16, 18 can be implemented in any way and may include a front camera, a rear camera, a side camera, a radar sensor, a lidar sensor, an ultrasonic sensor, and / or an inertial sensor. For example, the environmental sensor 14 can be implemented as a front camera, a radar sensor, a lidar sensor, or an ultrasonic sensor. A front camera is particularly suitable for the higher-positioned environmental sensor 16, while the environmental sensor 18 located at the rear of the vehicle 12 can be implemented as a rear camera, a radar sensor, a lidar sensor, or an ultrasonic sensor.

[0062] The electronic control unit (ECU) processes the environmental data obtained from the environmental sensor(s) 14, 16, 18 located on the motor vehicle 12 in order to obtain information regarding the static environment (immoving environmental objects such as road boundaries, lane markings, stationary obstacles) as well as the dynamic environment (moving environmental objects such as other moving motor vehicles or road users) of the motor vehicle 12.

[0063] The electronic control unit (ECU) processes the environmental data obtained from the environmental sensor(s) 14, 16, 18 located on the vehicle 12 to detect a lane being traveled by the vehicle 12, including a first and a second lateral lane boundary in front of the vehicle 12. Additionally, the ECU processes the environmental data obtained from the environmental sensor(s) 14, 16, 18 located on the vehicle 12 to detect a lane occupied by another road user, such as another vehicle (adjacent to the lane being traveled by the vehicle 12, where "adjacent" means that one or more other lanes may also be located between the adjacent lanes), as well as its lateral lane boundaries in front of the vehicle 12. The other vehicle or...The other road users can either be stationary or moving in or against the direction of travel of the motor vehicle 12.

[0064] For this purpose, the environmental sensors 14, 16, 18 of the electronic control unit (ECU) provide environmental data representing the area in front of, to the side of, and / or behind the vehicle. For this, the control system 10 is connected via at least one data channel or bus (in Fig. (1 shown as a dashed line) is connected to at least one environmental sensor 14, 16, 18. The data channel or bus can be implemented using a cable or wirelessly.

[0065] Alternatively or additionally, the control system 10 or its electronic control unit (ECU) can also receive data from one or more other assistance systems 20 (hereinafter also referred to as driver assistance system 20) or another control unit 20 of the motor vehicle 12, which specifies, or can be derived from, the lanes occupied by the motor vehicle 12 and other road users, including their lateral lane boundaries. Thus, data and information already obtained by other systems can be used by the control system 10.

[0066] Furthermore, the control system 10 or its electronic control unit (ECU) determines a driving situation using the environmental sensors, i.e., based on the environmental data acquired with the help of at least one environmental sensor 14, 16, 18. Here, too, an existing driver assistance system 20 or an electronic control unit 20 can alternatively or additionally provide data and / or information that define a driving situation or from which a driving situation can be quickly derived. Depending on the determined driving situation, at least one possible trajectory is then determined, which the vehicle 12 is to follow during the further course of the journey. This trajectory is essentially adapted in real time to changes in the current driving situation of the vehicle 12; in other words, the trajectory is optimized.

[0067] The driver assistance system 20 or the electronic control unit 20 can be further configured and designed to control the motor vehicle semi-autonomously. In this case, the control system 10 is configured and designed to output data for autonomous driving to the driver assistance system 20 or the electronic control unit 20. In particular, the control system 10 (or its ECU) can output data to component 20 specifying the course of the determined trajectory and / or the adapted trajectory that the motor vehicle 12 is to follow subsequently (for example, beginning immediately after adaptation or upon termination of the current driving situation). The data can also be transmitted via a data channel or bus, either wired or wirelessly.

[0068] The approach presented in this disclosure for planning and adapting the trajectory for the motor vehicle 12 in real time is based on a combination of discrete (sampling) values ​​and continuous values ​​(or at least quasi-continuous values) of the environmental data provided to the control system 10. Fig. Section 2 compares approaches to trajectory planning and optimization based on discrete values ​​(top representation) and continuous values ​​(bottom representation), as used in certain implementation examples.

[0069] In the image above in Fig. Figure 2 shows motor vehicle 12 in the right lane of a two-lane roadway 36. The right lane is bounded by a right lane marking 32 and a left lane marking 32. Lane marking 32 also represents the right lane marking of a left lane of roadway 30, which in turn is bounded on the left by a left lane marking 34. Lane marking 32 may, but does not necessarily, represent a virtual center line of roadway 36. Alternatively, lane marking 32 may actually be present on roadway 36. A further motor vehicle 28 is located in the right lane of roadway 36 at a distance in front of motor vehicle 12. In this example, the other motor vehicle 28 may be stationary or also moving in the direction of travel of motor vehicle 12.For example, vehicle 12 can follow another vehicle 28 at a constant distance based on speed control (following). The driver assistance system 20 can, for example, output the relevant data for this purpose.

[0070] For the subsequent journey of motor vehicle 12 in the upper representation of the Fig. 2. The control system 10 of the motor vehicle 12 detects the other motor vehicle 28 by means of at least one environmental sensor 14, 16, 18 and determines driving-related information of the other motor vehicle 28. Within the scope of this disclosure, this driving-related information of the other motor vehicle 28 may include information regarding the current driving situation of the motor vehicle 12. The information regarding the current driving situation of the motor vehicle 12 further includes, for example, the current speed and / or the current acceleration and / or the current jerk of the motor vehicle 12, which are provided to the control system 10 in a suitable manner by other control systems or the ECU of the motor vehicle 12. The current speed may be a lateral and / or a longitudinal speed.The current acceleration can also be lateral and / or longitudinal. Finally, the jerk can also be lateral and / or longitudinal.

[0071] Furthermore, the information regarding the current driving situation of vehicle 12 may include a distance between vehicle 12 and vehicle 28 and / or a relative speed between vehicle 12 and vehicle 28 and / or a relative acceleration between vehicle 12 and vehicle 28. The distance, relative speed, and relative acceleration may, in turn, refer to lateral and / or longitudinal distances, relative speeds, and / or relative accelerations.To determine these, the control system 10 can, for example, use the environmental data provided by the at least one environment sensor 14, 16, 18 to determine lateral and longitudinal distances to the other motor vehicle 28 as well as lateral and longitudinal speeds and accelerations of the other motor vehicle 28 and relate these to the lateral and longitudinal speeds of the motor vehicle 12.

[0072] In the image above in Fig. 2. The control system 10 determines discrete values ​​(indicated by black squares) from the environmental data provided by the at least one environmental sensor 14, 16, 18. The control system 10 determines from these discrete values ​​(hereinafter also called sampling values) the values ​​shown in the upper representation of the Fig. The system analyzes the two trajectories shown (the curves that each begin at the front of the vehicle 12 and either follow the current lane or indicate a lane change to the left or right) and selects the best possible trajectory 38 from these trajectories. This is therefore a discrete (sampling-based) planning and optimization approach.

[0073] The selection is made, for example, based on a target function, among other things, on requirements for the driving comfort and safety of the driver of the motor vehicle 12. Thus, in the example shown above, from Fig. Trajectory 38 is selected because, for example, the other vehicle 28 is traveling at a lower speed than vehicle 12 in the current driving situation and therefore needs to be overtaken. Since there is no further lane of roadway 36 to the right of the lane marking, vehicle 12 must move into the left lane of roadway 36 to overtake. To ensure that this is done comfortably for the driver of vehicle 12 and simultaneously avoids a collision, trajectory 38 is chosen; this does not require a sudden maneuver (changing lanes to the left) and allows sufficient safety distance to the vehicle 28 ahead during overtaking, thus minimizing the risk of a rear-end collision.

[0074] For large state-space dimensions, finding the best possible solution in the current driving situation can lead to inefficiently long computation times for the control systems used. Therefore, it may be necessary to find a compromise between finding the best possible solution for the current driving situation of vehicle 12 (globally) and the computation time required, since an increasing number of discrete sampling values, an increasing number of pattern trajectories to be determined, and ultimately the selection of the best possible trajectory from these pattern trajectories all increase the necessary computation time. On the other hand, there is a risk that conventional control systems have insufficient resources to process such a volume of data at all, or at least efficiently.

[0075] Furthermore, taking into account the dynamic vehicle environment and including a temporal component can increase the computational effort and thus the computing time.

[0076] To obtain faster solutions in this regard, continuous planning or optimization approaches can be used, for example. A diagram of such an approach is shown below. Fig. 2 shown. In the present example, the following is shown with reference to the above illustration of the Fig. The determined trajectory 38 was optimized or adapted. Trajectory 38 is therefore shown in the lower representation of the Fig. 2. Further improvements are made based on the desired driving comfort and the necessary driving safety for the current driving situation. Each of the black dots located on trajectory 38 represents a (quasi-)continuous value of this trajectory 38 and can be adjusted by the control system 10, after selection of trajectory 38, in such a way as to allow for an even smoother and safer overtaking maneuver of the other vehicle 28 by the vehicle 12. In this example, the last quasi-continuous value corresponds to the black square from the diagram above. Fig. 2, which marks the end of trajectory 38, together. The white points with black outlines in the upper and lower representations of the Fig. 2 each designate the starting point (located directly at the front of the motor vehicle 12) for the trajectory to be determined and adjusted in the lateral and longitudinal directions on the roadway 36. While no information is lost due to discretization when using continuous planning and optimization approaches, these are generally local planning and optimization approaches that require suitable initialization and, consequently, suitable reinitialization. For example, the above, with reference to the lower representation of the Fig. The starting point mentioned in point 2 represents an initialization or reinitialization point for the continuous planning and optimization approach. Additionally, these approaches converge towards local minima in the vicinity of the initialization and / or reinitialization point. Therefore, an insufficient or insufficiently robust initialization or reinitialization can, in turn, lead to increased computational effort.

[0077] Within the scope of this disclosure, the control system 10 is configured and designed to combine the discrete planning and optimization approach presented above with the continuous planning and optimization approach presented above for the planning and optimization of the trajectory that the motor vehicle 12 is to follow during its further journey. In other words, the control system 10 uses a hybrid planning and optimization approach to determine the best possible trajectory for the future journey of the motor vehicle 12 and to adapt it, at least substantially, in real time (online) to the current driving situation of the motor vehicle 12. The individual discrete and continuous planning and optimization approaches to be combined are not limited to those described above with reference to Fig. The two described examples are not limited to this. Rather, the control system 10 is designed and intended to combine all suitable discrete planning and optimization approaches with all suitable continuous planning and optimization approaches. These include, among others, decision trees or random forests, methods of deterministic discretization and / or (continuous) spline-based interpolation using cubic polynomials and / or polynomials of the fourth, fifth, or higher order, and this list is not exhaustive.

[0078] An overview of the approach presented within the scope of this disclosure, based on a combination of continuous and discrete values ​​of the environmental data provided to the control system 10, for planning the trajectory or several trajectories and determining the best possible trajectory of the planned trajectories for the further course of travel of the motor vehicle 12, which in particular underlies the control system 10 and the control method presented here, is provided Fig. 3. It becomes clear from this that the control system 10 first makes a preliminary selection of maneuvers at a decision level. This preliminary selection can, for example, be based on the environmental data provided to the control system 10. In the description of the architecture of the planning and optimization approach used by the control system 10, reference will also be made at appropriate points to the Fig. 4 and Fig. 5 referred.

[0079] For example, if the analysis of the current driving situation of vehicle 12 by the control system 10 indicates that an overtaking maneuver must be initiated because another vehicle in front of vehicle 12 is braking sharply, the maneuver preselection can consist of a lane change. Generally, the set of basic maneuvers from which the maneuver preselection is made can include at least the maneuvers of lane change and lane keeping.

[0080] An overview of how the pre-selection of maneuvers (this applies equally to the subsequent selection of maneuvers) can be carried out within the framework of the present disclosure is provided Fig. 4. According to this example, a lateral maneuver (also called a lateral maneuver component) is first selected based on the environmental data provided to the control system 10 by the at least one environmental sensor 14, 16, 18. Both the static and the dynamic environment of the vehicle 12 are taken into account. Alternatively, only the static or the dynamic vehicle environment can be considered. In the overtaking maneuver of the vehicle 12 mentioned above, the decision here would be based on the other vehicle 28 braking sharply (see Figure 1). Fig. 4) The lateral maneuver of changing lanes is performed. Since, due to the two-lane roadway 36, only one overtaking maneuver is possible, in which vehicle 12 overtakes the other vehicle 28 in the left lane of roadway 36, the lane change to the left is selected by the control system 10 at a lower decision level. A further [description] is shown in the left-hand diagram. Fig. Alternative 4 shown represents lane keeping, which can be used in a different scenario than the one described above, for example, during distance-controlled following of vehicle 12 behind vehicle 28. Lane keeping can be further divided into lane keeping left, lane keeping center, and lane keeping right (in the Fig. (not shown in Figure 4), for example, to prepare a subsequent driving maneuver for the motor vehicle 12. However, the present disclosure is not limited to the lateral maneuver classes described above. Alternatively, more or fewer or other maneuvers may be defined from which the maneuver or maneuver component is preselected. The same may apply to the maneuver selection to be made subsequently.

[0081] Based on the determined lateral maneuver component, a longitudinal maneuver or a longitudinal maneuver component is then determined in the present example. However, the present disclosure is not limited to this. The lateral and longitudinal maneuver components can alternatively also be determined independently of each other by the control system 10. In the present case, however, as shown in the right-hand illustration, Fig. As can be seen in Figure 4, the lateral maneuver component, as well as the static and / or dynamic environment, is used by the control system 10 to determine the lateral maneuver component. The lateral maneuver component can, for example, consist of a specific absolute or relative distance, speed, and / or acceleration specification in conjunction with specific points along the roadway currently being traveled by the vehicle 12, through which the trajectory to be generated is to pass. These specifications can then be implemented, for example, by means of the driver assistance system 20 and / or the further electronic control system 20 of the vehicle 12. For this purpose, the driver assistance system 20 can include or comprise an adaptive cruise control assistant and / or an adaptive chassis control assistant and / or an emergency braking assistant.

[0082] As from Fig. As can be seen in section 3, the maneuver preselection or the corresponding data (i.e., data that characterize the selected maneuver) are passed as a maneuver hypothesis to a trajectory planning level of the control system 10. There, this data is processed by a planning module (in the Fig. 3 (referred to as a sampling-based trajectory planner) is read or recorded. This initiates the planning of the trajectories, from which a trajectory for the further journey of the motor vehicle 12 is later selected. In other words, the sampling-based trajectory planner uses a previously described trajectory (referring to the above representation of the Fig. 2. The discrete planning approach for trajectory candidates (also called pattern trajectories) described above is implemented.

[0083] The sampling-based trajectory planner first generates discrete sampling states, which consist of discrete longitudinal (in the direction of travel of the vehicle 12) values ​​and discrete lateral (perpendicular to the direction of travel of the vehicle 12) values. In other words, during this planning phase, the sampling-based trajectory planner of the control system 10 sets lateral and longitudinal states that are then used in trajectory generation. These lateral and longitudinal states can, but do not necessarily have to, correspond to the values ​​defined with respect to Fig. correspond to the 4 described lateral or longitudinal maneuver components.

[0084] Trajectory processing also takes place at the trajectory planning level. Here, the discrete lateral and longitudinal states, or the lateral and longitudinal maneuver components, or a combination of these lateral and longitudinal states or maneuver components, are used, for example, as stopping points of one or more pattern trajectories, which are used during trajectory generation in Fig. 3. For a stopping point of a pattern trajectory, the control system 10 can, for example, combine a lateral and a longitudinal state, each of which has the same time instance, i.e., mark a point in the lateral and longitudinal direction on the currently traveled roadway of the motor vehicle 12 at a specific future time, through which the pattern trajectory to be generated is to run.

[0085] Optional and therefore marked with a dotted rectangle in Fig. As indicated in section 3, a simplified optimization (pre-optimization) or an adjustment of one or more of the generated pattern trajectories can be performed by the control system 10. This can be done using the optimization approach described below or with another suitable optimization approach.

[0086] Finally, the generated pattern trajectories are used within the framework of the Fig. In the trajectory selection shown in Figure 3, the best possible trajectory for the current driving situation or the future driving path of the vehicle 12 is selected. In this example, this selection is carried out using an objective function, which can correspond to a cost function. The same objective function can also be used in determining the sample trajectories. Since this selection is currently based solely on the maneuver hypothesis, all data and / or trajectories generated by the sampling-based trajectory planner are fed back to a module at the decision level (see the dashed arrow in Figure 3). Fig. 3, which leads to the “maneuver selection”.

[0087] The objective function incorporates, for example, target states that relate to the dynamic and static environment of the vehicle 12 in the current driving situation, as well as driving comfort and the feasibility of the sample trajectories and / or the trajectory selected from them. One or more target states can, for example, be a point on the current roadway (or on an adjacent lane) of the vehicle 12 in the lateral and / or longitudinal direction, possibly paired with one or more time instances.

[0088] In addition, as from Fig. As can be seen in Figure 3, a module for trajectory optimization of the control system 10 provides all data generated by the sampling-based trajectory planner based on the maneuver hypothesis, i.e., all sampling values ​​as well as the generated (and, if applicable, pre-optimized) sample trajectories and data regarding trajectory selection. Optimization in the sense of adapting the trajectory to a changed driving situation can therefore already be performed for the trajectory selected based on the maneuver pre-selection or the maneuver hypothesis.

[0089] The optimization and adaptation data obtained in real time are combined appropriately with the data provided by the sampling-based trajectory planner and verified within the framework of an evaluated maneuver hypothesis. This latter step is made possible by incorporating the data obtained during online trajectory adaptation. The respective data can also be provided individually to a module of control system 10 for the purpose of verifying the maneuver hypothesis.

[0090] Based on the evaluated maneuver hypothesis, a maneuver selection is made at the decision level, for example, by a decision module of control system 10. The maneuvers available for selection here may be, but do not necessarily have to be, the same ones that were described above with reference to the maneuver preselection. The selected maneuver, or the data corresponding to it, is then fed back into the sampling-based trajectory planner at the planning level. Additionally, data obtained during the maneuver preselection can be incorporated into the maneuver selection process.

[0091] The sampling-based trajectory planner repeats the processes described above for generating sampling states, including setting lateral and longitudinal states and / or lateral and longitudinal maneuver components, as well as trajectory processing, including trajectory selection and, if necessary, abbreviated (pre-)optimization of the sample trajectories and trajectory selection.

[0092] The selected trajectory (in Fig. 3 (named with initial trajectory) is finally fed – still at the trajectory planning level – to the trajectory optimization module of the control system 10. This trajectory optimization (also called trajectory adaptation within the scope of this disclosure) takes place online, i.e., in real time or at least substantially in real time, and can be initialized and / or reinitialized continuously and / or at specific discrete points in time. The optimized (adapted) trajectory is then made available at a control level to an electronic control unit of the motor vehicle 12, for example, the driver assistance system 20 or the further electronic control unit 20. This provision applies not only to the adapted trajectory, but also to an initial determined and therefore, at best, pre-optimized initial trajectory (see Fig. 3, indicated there by an arrow with a dashed-dotted base), so that the driver assistance system 20 can, for example, cause the motor vehicle 12 to follow this initial trajectory even before the start of or at the start of the adaptation of the initial trajectory.

[0093] The data from the real-time trajectory optimization Fig. The three steps are then appropriately combined with the data provided by the sampling-based trajectory planner and verified within the framework of the evaluated maneuver hypothesis. This allows the next planning cycle to begin, in which some or all of the steps described above are repeated to provide the driver assistance system 20 at the control level with the best possible trajectory adapted to the respective driving situation of the vehicle 12. In particular, the selected trajectory is continuously adjusted in the current driving situation of the vehicle 12 to enable a rapid (essentially real-time) and efficient response to changes in the current driving situation. This enhances the safety and driving comfort of the driver and / or other occupants of the vehicle 12.

[0094] This optimization process will now be repeated with reference to the Fig. 5 and Fig. 6 described. As shown in the flowchart. Fig. 5 - for example, trajectory optimization according to the with reference to Fig. To elaborate further on the example described in point 3, but not necessarily, it first requires the formulation of an optimization problem. In trajectory planning for semi-autonomous vehicles, in addition to avoiding collisions with other road users and / or other objects, it is important that the occupants of vehicle 12 experience a high level of driving comfort. This is achieved by ensuring that vehicle 12 is not subjected to excessively high (negative or positive) acceleration forces as it follows the trajectory in its future course. For this reason, the optimization problem is formulated based on the acceleration and / or jerk of vehicle 12 in the respective current driving situation.In this example, the time integral of the jerk, starting from the current time instance of the current driving situation of vehicle 12 and extending to a subsequent time instance (which, for example, coincides with a planned trajectory goal), is used within an objective function, such as a cost function. The relative costs of the jerk are to be minimized within this objective function in order to determine the best possible trajectory for the current driving situation of vehicle 12. Furthermore, in addition to the jerk, the aforementioned objective function can also include the deviation of a target state (for example, that vehicle 12, in the case of a lane change, should be in the middle of the lane adjacent to the currently driven lane at the end of the pursued trajectory) in the form of additional costs.This deviation can refer not only to lateral deviations but also to longitudinal deviations from the target state. Alternatively and / or additionally, the length of the interval for which the trajectory is planned can be included in the objective function in the form of costs. This allows the overall objective function to result from a combination of lateral and longitudinal objective functions, where each or both of the individual objective functions can be weighted. This objective function can also be used during the planning of the sample trajectories and the determination of the trajectory from the sample trajectories to ensure comparability of the corresponding results when reinitializing the optimization is necessary.

[0095] As from Fig. As can be seen in Figure 5, the optimization problem is solved using the current system state of the motor vehicle and the current environmental data provided to the control system 10. The solution to this optimization problem can, for example, be achieved by considering the following: Fig. The trajectory optimization described in section 3 is represented. The solution to the optimization problem yields one or more reference trajectory points for the current time instance or for a current planning period, which begins with the current time instance t and lasts until the time instance t + Δt. From these reference trajectory points, the control system 10 can create a reference trajectory. This reference trajectory should be adhered to as closely as possible by the trajectory to be determined, which the vehicle 12 is to follow during its further journey. In particular, the control system 10 can determine deviations of individual points and / or all points of the trajectory to be determined, which the vehicle 12 is to follow during its further journey, from the reference trajectory points. These deviations can then be used to adjust the trajectory for the vehicle.

[0096] This is followed by an update of the vehicle status and environmental information of the dynamic vehicle environment, see Fig. 5. For this purpose, the environmental data provided to the control system 10 by the at least one environmental sensor 14, 16, 18, from which information regarding the current driving situation of the vehicle 12 is obtained, is continuously updated. This can be a cyclical, interval-based update of the provided environmental data or, alternatively, a continuous update in real time (also called online update). The updated information regarding the vehicle state (also called the system state of the vehicle 12) and the environmental information is fed back by the control system 10 and used for the next optimization problem to be solved. For example, the updated data can be used for the sampling-based trajectory planner (see Fig. 3) are returned and used there to adjust the determined trajectory and / or to generate new sample trajectories. From the sample trajectories generated in this way, a trajectory can then be selected for further processing or adjustment.

[0097] Due to the architecture described above, in combination with the presented discrete and continuous planning and optimization approaches, a hybrid planning and optimization approach for the trajectory of the motor vehicle 12 is obtained, which combines the advantages of the two approaches and compensates for or at least reduces the disadvantages of the two approaches.

[0098] As from Fig. As can be seen in section 6, the hybrid planning and optimization approach initially proceeds similarly to that which refers to Fig. Using the discrete approach described in section 2, a globally optimal trajectory 38' is determined. With this determined trajectory 38', or with the associated data that characterize this trajectory 38', a continuous planning approach similar to the one with reference to... Fig. The continuous planning approach described in section 2 is initialized. For each initialization, the trajectory 38' is then further adapted to the current driving situation of the vehicle 12 using the continuous planning and optimization approach.

[0099] If a trajectory other than trajectory 38' is to be adapted to the current driving situation using the continuous optimization approach, this requires initialization, i.e., reinitialization of the continuous optimization approach based on the data determined for this other trajectory within the framework of the discrete planning approach. Reinitialization may also be necessary when a planning and optimization cycle associated with a specific time instance t has ended and the data regarding the system state of the vehicle 12 and / or the environmental data have been updated. The reinitialization then represents the initialization of the subsequent planning and optimization cycle, which begins, for example, at time t + Δt and proceeds in the same manner.

[0100] For example, for initialization and / or reinitialization, start states and / or end states for the trajectory 38' to be adapted, possibly together with temporal information regarding the attainment of these start states and / or end states, are passed to the planning module as data for carrying out the continuous planning approach. The start states and / or end states are therefore generally points in the lateral and longitudinal directions on the roadway 36 in connection with a time instance t (initial state) and t+Δt (final state). Within the framework of optimization, i.e., the adaptation of the trajectory 38' to the current driving situation of the vehicle 12, the control system 10 compares, for example, certain (interpolated) points (see the interpolated states in the lower representation in the continuous approach, which is initialized or reinitialized by certain data of the discrete approach) using the continuous approach. Fig. 6) of trajectory 38' with points of the determined reference trajectory (not shown in the figure), whereby points with the same or successive time instances are compared. If certain deviations occur, for example along the roadway 36 (longitudinal direction or x-direction) or perpendicular to the roadway 36 (lateral direction or y-direction), which are, for example, greater than a predefined value, these individual points are adjusted in the x- and / or y-direction such that a maximum predefined deviation to the corresponding point of the reference trajectory is at least maintained or undercut.The adjustment therefore does not necessarily mean that a deviating point of trajectory 38' is replaced with a point of a reference trajectory; it can simply involve a local approximation (adjustment) of the deviating point to the corresponding point of the reference trajectory or to another suitable point of the reference trajectory. Here, too, considerations of vehicle dynamics, and thus comfort, as well as safety, play a role in determining the smoothest possible future driving maneuver, and the corresponding trajectory that characterizes the temporal and spatial progression of this maneuver, for the vehicle 12, ideally without high acceleration forces.

[0101] Another exemplary driving situation in which the hybrid planning and optimization approach of the present disclosure is used is now described with reference to Fig. As described in Figure 7, the upper diagram again shows vehicle 12 following another vehicle 28. Several possible trajectories that vehicle 12 could follow in the current driving situation are also shown. The determination of these trajectories can, for example, be based on spline interpolation of the discrete values ​​obtained using the discrete planning and optimization approach.

[0102] In the example presented here, which is not to be understood as restrictive, the determination of the trajectories in the above representation is based on Fig. 7. Based on graph-theoretical considerations. For this purpose, 10 nodes and / or edges for a graph are determined from a specific number or from all discrete sampling values ​​by the control system, and finally the (connected) graph itself is determined. Some, several, or all of these graphs then represent, for example, the pattern trajectories used by the sampling-based trajectory planner (see, for example, [reference]). Fig. 3) of the control system 10 are determined, and the best possible path for the future journey of the vehicle 12 is selected by the control system 10. The nodes / edges can also represent stopping points for a spline-based interpolation of the graphs or trajectories. Thus, a graph-based method is used to determine and process the discrete sampling values.

[0103] The in Fig. The scenario 7, or rather the determination and adaptation of the best possible trajectory for the motor vehicle 12 in its current driving situation or based on its current driving situation, is now additionally considered with reference to the in Fig. 8 control methods presented are described.

[0104] Fig. Figure 8 shows a flowchart for a control procedure that is based on environmental data obtained from at least one environmental sensor 14, 16, 18 located on the motor vehicle 12, including lanes, road boundaries, road markings and / or other motor vehicles such as the other motor vehicle 28 (see Figure 8). Fig. 7) detects in an area in front of, to the side of, and / or behind the motor vehicle 12. The control procedure can, for example, be executed by the control system 10 of the motor vehicle 12 described above. All features described within the framework of the control system 10 can also be applied to the control procedure. In particular, all features described above regarding the objective function, the component-based determination of future driving maneuvers, the application and combination of the discrete and continuous planning and optimization approaches, as well as the initialization and reinitialization, are transferable to the control procedure.

[0105] In a first step, S10, information regarding the current driving situation of the motor vehicle 12 is determined.

[0106] This information may include, among other things, the lateral distance of the longitudinal axis of the motor vehicle 12 to the left lane marking 32 or the right lane marking 30 and / or the longitudinal distance and / or a relative speed between the motor vehicle 12 and the other (further) motor vehicle 28.

[0107] In a second step S12, a component of a future driving maneuver for the vehicle 12 is determined based on information regarding the current driving situation of the vehicle 12. For example, if the vehicle 12 is located approximately in the middle of the currently driven lane (the right lane of carriageway 36 from Fig. 7) and the distance between the vehicles 12, 28 is comparatively small (for example, in relation to the current speed of the motor vehicle 12), the component will consist of keeping in lane and / or braking to avoid a collision with the motor vehicle 28.

[0108] In a third step S14, a plurality of sample trajectories for the vehicle 12 are determined based on the identified component of the future driving maneuver for the vehicle 12. The majority of the determined sample trajectories are shown in the upper representation of the Fig. Figure 7 indicates a combination of different possible pattern trajectories. The black squares represent nodes and / or stopping points of a sub-trajectory, each running between two edges / nodes. The individual sub-trajectories can be combined arbitrarily by the control system 10, resulting in a multitude of pattern trajectories.

[0109] In a fourth step S16, a trajectory for the vehicle 12 is determined from the plurality of sample trajectories, which the vehicle 12 is to follow during its further journey. For example, based on dynamic and static collision checks regarding moving and stationary objects and / or obstacles located in the vicinity of the vehicle 12, which are carried out by the control system 10 based on the provided environmental data, certain sample trajectories are excluded, thus determining the best possible trajectory for the vehicle 12. In the upper representation of the Fig. Figure 7 shows, for example, that some of the sample trajectories run outside lane 36 and are therefore not suitable as trajectories for the further course of travel. However, the trajectories for an overtaking maneuver on the left lane of lane 36 and those for following are still possible trajectories for vehicle 12.

[0110] In the lower representation of the Fig. Figure 7 shows that, among the numerous sample trajectories, the trajectory in bold is determined by the control system 10 as the trajectory that the motor vehicle 12 is to follow during its further journey. In the lower illustration from Fig. 7. The control system 10 therefore determines a trajectory as the best possible trajectory in the current driving situation, which indicates a lane change to the left. An earlier lane change by the vehicle 12, and thus following a different trajectory, would impair the driving comfort of the occupants of the vehicle 12, as the vehicle 12 would have to accelerate quickly. A lane change that is too late is also not an option, as this could result in a collision with the other vehicle 28. Generally, the control system 10 determines in the Fig. The situation shown in Figure 7, which illustrates an example of changing lanes to the left or following a trajectory for the overtaking maneuver, is chosen because the other vehicle 28 is either stationary or moving at a significantly lower speed than vehicle 12. Additionally, for example, the lateral distance of vehicle 12 to the lane boundary 32 may be small (especially smaller than in the Fig. Figure 7 shows where vehicle 12 is located approximately in the middle of its lane, so that vehicle 12 has a comparatively shorter path to the overtaking lane when overtaking. Selecting this trajectory, like determining the pattern trajectories, can be based on the objective function described above.

[0111] In a fifth step S18, the information regarding the current driving situation of the motor vehicle and / or the provided environmental data is updated.

[0112] In a sixth step S20, the trajectory for the vehicle 12 is adjusted based on an objective function (for example, the objective function described above) and on the updated provided environmental data and / or on the updated information regarding the current driving situation of the vehicle 12. With regard to the driving situation from Fig. 7 This means that, assuming that motor vehicle 12 is to follow the other motor vehicle 28 at a constant speed and distance, a trajectory for lane keeping is initially selected. This could, for example, consist of connecting the four squares lying in a line on the right-hand lane of roadway 36. However, when updating the environmental data and / or the information regarding the current driving situation, it is determined that following this trajectory would result in a possible collision with the other motor vehicle 28 (in Fig. 7 above by the course of the trajectory between the third and fourth black squares through the further motor vehicle 28). The trajectory can then be adjusted so that it matches the bolded path of movement from the lower illustration. Fig. 7 corresponds. In particular, the first part of the planned trajectory (between the first and second black square on the right lane in Fig. 7) retain and only the further course of this trajectory is adjusted so that - for example, prompted by the driver assistance system 20 - the motor vehicle 12 makes a lane change to the left and subsequently overtakes the other motor vehicle 28.

[0113] In particular, the planning and optimization approach described above can be used in the context of adapting the trajectory, in order to optimize at least the changing part of the trajectory and to find an even more efficient solution for the best possible trajectory, which increases the driving comfort and driving safety of the occupants of the motor vehicle 12 in the current traffic situation.

[0114] Within the scope of this disclosure, the inherent disadvantages of both approaches can be at least reduced by combining the discrete, for example, graph-based approach for determining and selecting the pattern trajectories or the trajectory for the further course of the motor vehicle 12 with the continuous approach for optimizing the selected trajectory. For example, the number of discrete sampling values ​​required to determine the pattern trajectories for the sampling-based trajectory planner can be significantly reduced compared to using a purely discrete planning and optimization approach, due to the subsequent continuous adjustment, which is (re)initialized with the results of one or more pattern trajectories.

[0115] Furthermore, the number of discrete sampling values ​​addressed can be further reduced by pre-selecting maneuvers at the decision level before the start of trajectory planning by the sampling-based trajectory planner.

[0116] Overall, this provides an efficient (because it is quick to implement and resource-saving) and robust planning and optimization approach for the trajectory, which is intended to follow the vehicle 12 in its further journey.

[0117] It is understood that the exemplary embodiments described above are not exhaustive and do not limit the subject matter disclosed herein. In particular, it is apparent to the person skilled in the art that they can combine the features of the various embodiments and / or omit various features of the embodiments without deviating from the subject matter disclosed herein.

Claims

[1] Control system (10) which is designed and intended for use in a motor vehicle (12), based on environmental data obtained from at least one environmental sensor(s) (14, 16, 18) arranged on the motor vehicle, to detect lanes, lane boundaries, lane markings and / or other motor vehicles in an area (22, 24, 26) in front of, to the side of and / or behind the motor vehicle (12), wherein the at least one environmental sensor is designed to provide an electronic controller (20) of the control system (10) with the environmental data representing the area in front of, to the side of and / or behind the motor vehicle (12), and wherein the control system (10) is designed and intended at least to - to determine information regarding a current driving situation of the motor vehicle (12) based on the provided environmental data, - to determine at least one component of a future driving maneuver for the motor vehicle (12) based on the information relating to the current driving situation of the motor vehicle (12), - to determine a plurality of sample trajectories for the motor vehicle (12) based on the determined component of the future driving maneuver for the motor vehicle (12), - to determine from the plurality of sample trajectories for the motor vehicle (12) a trajectory for the motor vehicle (12) which the motor vehicle (12) is to follow in its further course of travel, - to update the information regarding the current driving situation of the motor vehicle (12) and / or the provided environmental data, characterized by that the control system (10) is further arranged and intended - adapt the trajectory for the motor vehicle (12) based on a target function and based on the updated environmental data provided and / or based on the updated information regarding the current driving situation of the motor vehicle (12), - to determine the information regarding the current driving situation of the motor vehicle (12) based on the provided environmental data in the form of discrete sampling values, - to determine a majority or all of the discrete sampling values ​​as nodes and / or edges of a graph, to create a connected graph from the determined nodes and / or edges, - to choose the nodes and / or edges of the graph as breakpoints for the trajectory, and - to calculate the trajectory for the motor vehicle (12) by means of a spline-based interpolation between the selected stopping points. [2] Control system (10) according to claim 1, which is arranged and intended to determine the trajectory from the plurality of sample trajectories based on a target function which is equal to the target function for adapting the trajectory for the motor vehicle (12). [3] Control system (10) according to claim 1 or 2, wherein the information relating to the current driving situation of the motor vehicle (12) includes at least a lateral distance of the motor vehicle (12) to the lane it is currently traveling in, and wherein the control system (10) is further configured and intended to determine the component of the future driving maneuver as lane keeping or lane changing based on the lateral distance of the motor vehicle to the lane it is currently traveling in. [4] Control system (10) according to claim 3, wherein the information regarding the current driving situation of the motor vehicle (12) further includes a longitudinal distance of the motor vehicle (12) along its currently traveled lane to another motor vehicle (28), and wherein the control system (10) is configured and intended to determine a further component of the future driving maneuver based on the determined component of the future driving maneuver and / or based on the longitudinal distance of the motor vehicle (12) to the other motor vehicle (28). [5] Control system (10) according to one of the preceding claims, which is further arranged and intended to determine the updated information and / or the updated environmental data in the form of continuous values. [6] Control system (10) according to one of the preceding claims, wherein the control system (10) is further configured and intended to combine the updated information and / or the updated environmental data in the form of continuous values ​​with the information relating to the current driving situation of the motor vehicle (12) in the form of discrete sampling values ​​for adapting the trajectory for the motor vehicle (12). [7] Control system (10) according to claim 6, wherein combining the information relating to the current driving situation of the motor vehicle (12) in the form of discrete sampling values ​​with the updated information and / or with the updated environmental data in the form of continuous values ​​comprises at least initializing and / or reinitializing the adaptation of the trajectory for the motor vehicle (12) based on the target function. [8] Control method which, in a motor vehicle (12), based on environmental data obtained from at least one environmental sensor(s) (14, 16, 18) arranged on the motor vehicle (12), detects lanes, lane boundaries, lane markings and / or other motor vehicles in an area in front of, to the side of and / or behind the motor vehicle (12), and wherein the control method comprises the steps: - Determining information regarding a current driving situation of the motor vehicle (12) based on the provided environmental data, - determining at least one component of a future driving maneuver for the motor vehicle (12) based on the information regarding the current driving situation of the motor vehicle (12), - determining a plurality of sample trajectories for the motor vehicle (12) based on the determined component of the future driving maneuver for the motor vehicle (12), - determining a trajectory for the motor vehicle (12) which the motor vehicle (12) is to follow in its further journey from the plurality of sample trajectories for the motor vehicle (12), - Updating the information regarding the current driving situation of the motor vehicle (12) and / or the provided environmental data, and is characterized by the steps: - adapting the trajectory for the motor vehicle (12) based on a target function and based on the updated environmental data provided and / or based on the updated information regarding the current driving situation of the motor vehicle (12), - determining the information regarding the current driving situation of the motor vehicle (12) based on the provided environmental data in the form of discrete sampling values, - Determining a majority or all of the discrete sampling values ​​as nodes and / or edges of a graph, - Creating a connected graph from the specified nodes and / or edges, - Selecting the nodes and / or edges of the graph as breakpoints for the trajectory, and - Calculating the trajectory for the motor vehicle (12) by means of a spline-based interpolation between the selected stopping points. [9] Motor vehicle (12) comprising a control system according to one of claims 1 to 7.

Images