Method and apparatus for operating a vehicle to avoid or eliminate traffic jams

Abstract

Method and device for operating a vehicle to avoid or eliminate traffic jams. The invention relates to an improved possibility of avoiding or eliminating traffic jams. In particular, the invention relates to a method for operating a vehicle (100), wherein a dynamic object (200) is predicted to intersect at least part of a first traffic area portion (140) occupied by the vehicle (100), wherein the vehicle (100) is in a waiting state for release to continue driving. A trajectory (150) of the vehicle (100) is then determined, which trajectory (150) at least eliminates or avoids the intersection of the dynamic object (200) with the first traffic area portion (140). Furthermore, the invention relates to a device for operating a vehicle, a program element and a computer-readable medium having such a program element.

Description

Technical Field

[0001] The invention relates to a method and a device for operating a vehicle, which may in particular be an at least partially autonomously driven vehicle. The invention also relates to a program element and a computer-readable storage medium having such a program element. Background Art

[0002] In particular in the field of at least partially automated vehicles, dynamic objects such as pedestrians, cars, trucks, buses, etc. can be recognized. For this purpose, for example, object classification can be used, based on which a driving strategy of the vehicle can be determined, for example, a trajectory of the at least partially automated vehicle can be planned for continued driving, etc. Data from vehicle environment detection, data from digital maps, information about applicable traffic regulations, etc. can be used for this purpose.

[0003] Traffic situations can also be considered in which a number of vehicles meet one another and block one another from continuing to drive, for example because the driving paths cross one another. In conventional vehicles, such traffic situations are usually solved simply in a cooperative manner by coordination or negotiation of evasive maneuvers such as signs, gestures of the driver, etc., which helps to avoid traffic jams or traffic jams or even avoid traffic jams or traffic jams. Therefore, in particular for at least partially automated vehicles that do not allow negotiation with other road users, a possibility for avoiding or eliminating such or similar traffic situations may be desirable. Summary of the invention

[0004] Embodiments of the invention provide an improved method and device for operating a vehicle according to the independent or coordinated claims. Exemplary developments of the invention are described in the dependent claims, the description and the drawings.

[0005] The method for operating a vehicle according to the first aspect is particularly suitable for operating a vehicle that is at least partially automated. In this case, the method can support at least a part of a driving function of the vehicle, i.e., for example, a part of a driving assistance system. The method can be executed in a computer-supported manner, for example, by an electronic control device or a control device group of the vehicle, wherein the control device can have, for example, at least one processor, a memory for program instructions and / or data, a data interface, etc. The method can be implemented as a program element that can include one or more program modules. The method specifies the following steps:

[0006] - predicting that a dynamic object intersects at least part of a first traffic area portion occupied by the vehicle, wherein the vehicle is in a waiting situation awaiting release to continue traveling.

[0007] The waiting situation can be caused, for example, by traffic control, traffic stagnation, etc. The vehicle does not necessarily have to stop, but can move slowly at walking speed, etc. to a parking area, a parking spot, etc. The intersection with the first traffic area portion can be caused, for example, by not providing a sufficiently large space for the dynamic object, for example due to a required turn of the dynamic object, etc. The prediction can be performed, for example, by calculation based on data detected by the vehicle environment, by map data, etc.

[0008] - determining at least one trajectory of the vehicle, for example in a planned or similar manner, which at least one trajectory eliminates or avoids at least an intersection of the object with the first traffic area portion.

[0009] The determined trajectory can in particular be part of an avoidance maneuver in order to give or release the space that is expected to be required by the dynamic object. Thus, the vehicles can eliminate a (also newly formed) traffic jam by meeting the dynamic object in turn, by giving the dynamic object the required driving space, in particular on its own portion of the traffic area, so that the dynamic object can continue its travel with as little hindrance as possible.

[0010] This configuration can avoid congestion situations caused by the vehicle, in other words, the vehicle cooperates with the dynamic object. This can, for example, maintain the traffic flow in the vehicle environment. This can help to increase customer value and avoid discomfort to vehicle passengers.

[0011] According to an extension, the vehicle can be guided along the determined trajectory to a second traffic area section for which no intersection with the object is predicted. In other words, the vehicle can release its own traffic area section. This allows the required driving space to be given to the dynamic object.

[0012] In one development, the second traffic area section can be arranged behind the first traffic area section in the direction of travel of the vehicle, and the trajectory can be oriented in the (actual) direction of travel of the vehicle. The trajectory can, for example, be at an angle to the direction of travel, so that the trajectory can include reverse driving, lateral driving, queuing, and combinations thereof. This allows the driving space required by the dynamic object to be released reliably and quickly.

[0013] According to one development, for the prediction, a measure can be determined with which the object is expected to intersect the first traffic area section, and at least one point, line, surface, segment, etc., which is outside the determined measure or in the immediate vicinity of the determined measure, can be determined. The measure can be, for example, an area measure or the like. This allows a reliable determination of the expected required travel space.

[0014] In one development, the second traffic area portion can be determined based on the determined at least one point, line, surface, segment, etc. In other words, the second traffic area portion can extend away from where the dynamic object and the vehicle are expected to no longer intersect or touch each other. If necessary, a safe distance to the dynamic object or its predicted trajectory can be maintained. In this way, the traffic space can be well utilized without the vehicle wasting space unnecessarily.

[0015] According to one development, the free drivability of the vehicle environment between the first and second traffic area sections can be checked to determine the trajectory and the trajectory can be determined at least as far as the obstacle. For example, the drivability of the backing-up space associated with the vehicle can be taken into account at the same time. If the backing-up space is still blocked by other road users or static objects before reaching the parking point, only the largest possible area is determined as the trajectory or only the largest possible area is driven. This makes it possible to avoid or eliminate blocking situations in a driving-friendly manner.

[0016] In one development, the objects can be classified on the vehicle side for the prediction and / or the contours of the objects can be at least partially determined. For example, it can be determined for the prediction whether a recognized dynamic object, due to its width, length, etc., poses a threat of partially intersecting the traffic area of ​​the vehicle based on the existing lane geometry. The classification can include, for example, object types such as buses, trucks and other objects exceeding a certain size and length. This allows the prediction to be made more reliably and accurately.

[0017] According to an extension, kinematic data of the object can be determined for the prediction. This can be done, for example, by evaluating data of the vehicle environment. It can thus be determined with which surface the dynamic object will intersect the first traffic area portion of the vehicle, taking into account the kinematic data. At the boundary of this surface, the second traffic area portion can be determined, for example, based on the farthest end. This can lead to a more accurate prediction.

[0018] In one development, the vehicle can wait at a traffic sign regulating forward travel, selected from the group consisting of: traffic lights, stop signs, give way signs, etc. Such traffic situations can serve as triggers for the prediction, wherein, for example, corresponding program elements are executed for predicting and determining the trajectory.

[0019] According to an extension, the dynamic object can be facing the vehicle head-on, ie, has a driving direction that is oriented toward the driving direction of the vehicle (if necessary also at a certain angle). For example, the dynamic object can turn from an intersection to the road on which the vehicle is traveling, etc.

[0020] The device for running a vehicle according to the second aspect can be particularly suitable for running with the aid of the above method. In particular, the device has a first data interface, which is arranged to obtain detection data of the vehicle environment. In addition, data of a digital map, etc. can also be obtained via the first data interface. The device also has a data processing device, which, for example, has a processor, a data memory for storing program instructions, etc., and is arranged to predict at least from the detection data the intersection of a dynamic object with at least part of the first vehicle area portion occupied by the vehicle when the vehicle stops or moves at walking speed waiting for a release signal to continue driving. In addition, the data processing device is arranged to determine the trajectory of the vehicle, which at least eliminates or avoids the intersection of the object with the first traffic area portion. The device also has a second data interface, which is arranged to provide travel control data for the vehicle, the travel control data including the determined trajectory.

[0021] Thereby, the effects discussed above with respect to the method can be basically achieved.

[0022] In one development, the prediction can be performed by an artificial intelligence module implemented in the data processing device, which can, for example, have an artificial neural network which is optionally trained for this task.

[0023] According to a third aspect, the invention relates to a program element, in particular a computer program, for operating a vehicle, which, when executed by a processor of a data processing device, is configured to carry out the method according to the first aspect.

[0024] A fourth aspect of the invention relates to a computer-readable storage medium having a program element, in particular a computer program, according to the third aspect.

[0025] Further measures to improve the invention are described in detail below together with the description of preferred exemplary embodiments of the invention based on the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Hereinafter, advantageous embodiments of the present invention will be described in detail with reference to the accompanying drawings.

[0027] Figure 1 A schematic diagram showing a device for operating a vehicle according to an embodiment of the present invention is shown,

[0028] Figure 2 A schematic diagram showing an exemplary traffic situation that can be considered together with a method or a device for operating a vehicle according to an embodiment of the present invention, and

[0029] Figure 3A flow chart of a method for operating a vehicle according to one specific embodiment of the present invention is shown.

[0030] These figures are only schematic and not drawn to scale. In these figures, identical, identically functioning or similar elements are always provided with the same reference numerals. DETAILED DESCRIPTION

[0031] Figure 1 The vehicle 100 is shown as an at least partially automated motor vehicle. Therefore, the vehicle 100 has actuators (not shown in detail) and vehicle drives that can be electronically controlled for automatic driving control of the vehicle 100, for example for acceleration, braking, steering, etc.

[0032] The vehicle 100 also has a device 110, for example in the form of a driver assistance system, which has a data processing device 120, for example in the form of an electronic control device, for controlling the actuators and the vehicle drive. The data processing device 120 has a processor 121 and a memory 122 for storing program instructions or program elements for operating the vehicle 100. In addition, the device 110 has a first data interface 123 and a second data interface 124, which are, for example, coupled to the data processing device 120 or integrated in the data processing device 120. In addition, the vehicle 100 has a plurality of sensors 130, such as optical sensors, ultrasonic sensors, LIDAR, etc. The optical sensor 130 is here, for example, a camera, which optically detects the area in front of, to the side and behind the vehicle 100, for example, and transmits the detection data via the first data interface 123 to the data processing device 120, which can control the vehicle 100 through the vehicle environment, that is, for example, road traffic, based on the detection data and, if necessary, other data via the second data interface 124.

[0033] The data processing device 120 is configured to predict at least from the detection data that the dynamic object 200 at least partially intersects with the first traffic area portion 140 occupied by the vehicle 100 when the vehicle is in a waiting condition for a release signal to continue driving. In addition, the data processing device 120 is configured to determine a trajectory 150 of the vehicle 100, which at least eliminates or avoids the intersection of the object 200 with the first traffic area portion 140. In addition, the data processing device is configured to provide the vehicle 100 with travel control data via the second data interface 124, the travel control data including the determined trajectory 150 towards the second traffic area portion 160.

[0034] Figure 2An exemplary traffic situation is shown, in which a vehicle 100 is in a waiting situation and in which the vehicle 100 is in the form of a bus and is facing a dynamic object 200 at an angle. The traffic situation includes an intersection, at which two roads meet, wherein forward driving is regulated by a plurality of traffic lights. In this embodiment, the vehicle 100 is stationary and waiting in front of a traffic light, which emits a waiting signal for the vehicle 100 with a red light. The dynamic object 200 turns from the intersection to the road on which the vehicle 100 is waiting in front of the traffic light in a first traffic area section 140.

[0035] Now it will be based on Figure 2 An example method for operating vehicle 100 under this exemplary traffic situation is explained.

[0036] The vehicle 100 detects in advance a dynamic object 200 that is about to collide with the vehicle 100 by means of the sensors 130 and the data processing device 120. In addition, the vehicle 100 determines the object category and / or at least partially determines the contour of the dynamic object 200 by means of the sensors 130 and the data processing device 120. In addition, the vehicle determines kinematic data of the dynamic object 200 by means of the sensors 130 and the data processing device 120, such as the speed at which the dynamic object 200 moves to the vehicle 100, the deceleration or acceleration of the dynamic object 200, the angle between the dynamic object 200 and the vehicle 100, etc.

[0037] Based on these data, the vehicle 100 predicts, with the aid of the data processing device 120, whether the dynamic object 200 will intersect or intersect the first traffic area portion 140, so that the vehicle 100 will block the further travel of the dynamic object 200. For example, a measure such as an overlap measure, an area measure, etc., is determined with which the dynamic object 200 is expected to intersect the first traffic area portion, and at least one point is determined, which is located outside the determined measure or in the immediate vicinity of the measure. To this end, it is determined, based on the lane geometry and the contour of the oncoming dynamic object 200, under consideration of the kinematic data of the dynamic object 200, with which surface the dynamic object 200 will intersect the traffic area portion 140 of the vehicle 100 during its steering maneuver. At the boundary of this surface, a point, a line, etc. is determined at the farthest end, and the parking point of the vehicle 100 (if necessary, taking into account the safety distance), the second traffic area portion 160 and the trajectory 150 are determined relative to this point, this line, etc.

[0038] Furthermore, the vehicle 100 determines with the aid of the sensor 130 and the data processing device 120 whether the vehicle environment between the first and second traffic area sections 140, 160 is freely drivable. In this embodiment, a further road user 300 in the form of a motor vehicle is located behind the vehicle 100 in the direction of travel, and is also waiting at the traffic light to continue driving. In this case, the vehicle 100 determines with the aid of the sensor 130 and the data processing device 120 the second traffic area section 160 and the trajectory 150, so that the vehicle 100 can be controlled until it is close to the further road user 300, if necessary with a safe distance.

[0039] When the dynamic object completely leaves the previous traffic situation, the vehicle 100 is determined and controlled to continue traveling. When the traffic light gives a release signal, that is, a green light, the vehicle 100 is controlled to continue traveling.

[0040] Figure 3 The method for operating a vehicle 100 is summarized in a flow chart. First, in a first step S1, an intersection of a dynamic object 200 with at least part of a first traffic area portion 140 occupied by the vehicle 100 is predicted, wherein the vehicle 100 is in a waiting state for release to continue driving. Then, in a second step S2, a trajectory 150 of the vehicle 100 is determined, which at least solves or avoids the intersection of the dynamic object 200 with the first traffic area portion 140.

Claims

1. A method for operating a vehicle (100), comprising the following steps: Predicting a dynamic object (200) to intersect at least a portion of a first traffic area portion (140) occupied by the vehicle (100), wherein the vehicle (100) is in a waiting state for release to continue traveling, wherein predicting the at least partial intersection comprises: determining a surface where the dynamic object is expected to intersect a first traffic area portion (140) of the vehicle (100); and Determining the farthest end of the boundary of the surface relative to the travel direction of the vehicle (100); Determining a trajectory (150) of the vehicle (100), wherein the trajectory (150) at least eliminates or avoids an intersection of the dynamic object (200) with the first traffic area portion (140), wherein determining the trajectory (150) of the vehicle (100) comprises: Determining a second traffic area portion (160) based on the farthest end, the second traffic area portion being arranged behind the vehicle in the driving direction of the vehicle (100); Checking whether there is an obstacle in the vehicle environment between the first traffic area portion (140) and the second traffic area portion (160); and - determining a maximum possible area as a trajectory based on the setback space up to the obstacle (150); and controlling the vehicle to travel along the determined trajectory, wherein determining the surface comprises calculating an area measure of a first traffic area portion (140) of the vehicle (100) that the dynamic object is expected to intersect; and Wherein determining the outermost end of the boundary of the face includes determining a point immediately adjacent to the calculated area measure.

2. The method according to claim 1, characterized in that For the prediction, the dynamic object (200) is classified on the vehicle side and / or the contour of the dynamic object (200) is at least partially determined.

3. The method according to any one of claims 1 to 2, characterized in that Kinematic data of the dynamic object (200) are determined for the prediction.

4. The method according to any one of claims 1 to 2, characterized in that The vehicle (100) waits at a traffic sign regulating forward travel, wherein the traffic sign is selected from: a traffic light, a stop sign, and a give way sign.

5. A device for operating a vehicle (100), comprising: a first data interface (123) configured to obtain detection data of the vehicle environment, and a data processing device (120) configured to: When the vehicle (100) is in a waiting state for a release signal to continue driving, at least from the detection data, predicting at least a partial intersection of a dynamic object (200) with a first traffic area portion (140) occupied by the vehicle (100), wherein the data processing device is configured to predict the at least partial intersection: determining a surface where the dynamic object is expected to intersect a first traffic area portion (140) of the vehicle (100); and Determining the farthest end of the boundary of the surface relative to the direction of travel of the vehicle (100); and Determining a trajectory (150) of the vehicle (100), the trajectory (150) at least eliminating or avoiding an intersection of the dynamic object (200) with the first traffic area portion (140), wherein the data processing device is configured to determine the trajectory (150) of the vehicle (100): Determining a second traffic area portion (160) based on the farthest end, the second traffic area portion being arranged behind the vehicle in the driving direction of the vehicle (100); Checking whether there is an obstacle in the vehicle environment between the first traffic area portion (140) and the second traffic area portion (160); and - determining a maximum possible area as a trajectory based on the setback space up to the obstacle (150), controlling the vehicle to travel along the determined trajectory, wherein determining the surface comprises calculating an area measure of a first traffic area portion (140) of the vehicle (100) that the dynamic object is expected to intersect; and Determining the farthest end of the boundary of the surface includes determining a point proximate to the calculated area measurement, and a second data interface (124) configured to provide travel control data for the vehicle (100), the travel control data including the determined trajectory (150). 6 . A program product, comprising a computer program which, when executed by a computer, is configured to carry out the method according to claim 1 . 7 . A computer-readable medium having program instructions stored thereon, wherein the program instructions are configured to execute the method according to any one of claims 1 to 4 when executed by a computer.

Images