Procedure for operating an ego vehicle

Abstract

The invention relates to a method for operating an autonomous ego vehicle (3), wherein data from an environment, including a vehicle ahead (4), is acquired by means of sensors (6) at least in one direction of travel in front of the ego vehicle (3) and made available to a computing unit (7), wherein the sensors (6) and / or the computing unit (7) track a trajectory (T) of a vehicle ahead (4) traveling back and forth across several lanes (2.1 to 2.4) of a multi-lane roadway (1), wherein the vehicle ahead (4) is recognized as an emergency vehicle (4) by means of an activated special light signal (8) and / or an activated special acoustic signal (9) and a movement pattern in the trajectory (T) lasting for more than 20 seconds is detected, in which the emergency vehicle (4) travels across several lanes (2.1 to 2.4).4) drives back and forth, the driving behavior of the ego vehicle (3) is adjusted so that it drives at a distance behind the emergency vehicle (4) and stops when the emergency vehicle (4) stops.

Description

[0001] The invention relates to a method for operating an ego vehicle according to the preamble of claim 1.

[0002] In road traffic, vehicles may be found driving unsafely or not following traffic rules, especially on multi-lane roads, repeatedly changing lanes. In some countries, such as the USA, it is common practice for drivers of emergency vehicles, such as police vehicles, to have their vehicles swerve back and forth across the entire width of the roadway to close multi-lane roads. Human road users are familiar with this practice and interpret it accordingly.

[0003] US 2022 / 355802 A1 describes systems and methods for determining whether a vehicle is driving unsafely or unsatisfactorily. In some implementations, a system may determine one or more driving scores for a vehicle based on observations of a driving behavior of the vehicle during a period of time. The system may generate an unsatisfactory driving indication based on at least one of the one or more driving scores exceeding a threshold. The system may notify one or more entities of unsatisfactory driving. In some aspects, the system may identify one or more dangerous driving characteristics exhibited by the vehicle during the period of time based on the observations received from the one or more entities. The system may also generate the unsatisfactory driving indication based at least in part on the identified dangerous driving characteristics.

[0004] The invention is based on the object of specifying a novel method for operating an ego vehicle.

[0005] The object is achieved according to the invention by a method for operating an ego vehicle having the features of claim 1.

[0006] Advantageous embodiments of the invention are the subject of the subclaims.

[0007] A method for operating an autonomous ego vehicle is proposed, wherein data of an environment including a vehicle driving ahead at least in one direction of travel in front of the ego vehicle are recorded by means of a sensor system and provided to a computing unit, wherein a trajectory of a vehicle driving ahead traveling back and forth across several lanes of a multi-lane roadway is tracked by the sensor system and / or the computing unit.According to the invention, when the vehicle in front is recognized as an emergency vehicle by means of a special light signal and / or a special acoustic signal that is switched on, and when a movement pattern in the trajectory that lasts for more than 20 seconds and in which the emergency vehicle travels back and forth across several lanes is recognized, the driving behavior of the ego vehicle is adapted so that it travels at a distance behind the emergency vehicle and stops when the emergency vehicle stops.

[0008] The inventive solution enables an autonomous ego vehicle to correctly interpret complex, non-compliant behaviors of other road users. This can prevent accidents and other dangerous situations. Furthermore, the autonomous ego vehicle ensures compliance with legal regulations. Police officers are authorized to enforce traffic laws, which an autonomous vehicle must also adhere to. Otherwise, the operator of the autonomous vehicle faces legal consequences such as fines or fleet shutdown.

[0009] The present invention can be used, for example, in an autonomous commercial vehicle, an autonomous bus or an autonomous passenger car.

[0010] Embodiments of the invention are explained in more detail below with reference to drawings.

[0011] Showing: Fig. 1 a schematic view of a roadway with several lanes, an autonomous ego vehicle and a preceding emergency vehicle, Fig. 2 a schematic view of the ego vehicle and the emergency vehicle, and Fig. 3 a schematic view of an exemplary processing chain of the autonomous ego vehicle.

[0012] Corresponding parts are provided with the same reference numerals in all figures.

[0013] Fig. 1 is a schematic view of a roadway 1 with multiple lanes 2.1, 2.2, 2.3, 2.4. An autonomous ego vehicle 3 is traveling on one of the lanes 2.1, 2.2, 2.3, 2.4, for example lane 2.2. A leading vehicle 4, for example an emergency vehicle 4, in particular a police vehicle, travels in front of the ego vehicle 3 and oscillates back and forth along a trajectory T over an extended period of time across all lanes 2.1, 2.2, 2.3, 2.4, committing traffic violations V when crossing a solid lane marking 5 between the lanes 2.2, 2.3. In some countries, for example in the USA, this movement pattern means that the driver of the emergency vehicle 4 requests the following vehicles not to overtake the emergency vehicle 4, but to follow slowly or even to stop if necessary.This movement pattern therefore contains a semantic signal that is understood by a human driver familiar with the semantic signal.

[0014] Fig. 2 is a schematic view of the ego vehicle 3, for example, a commercial vehicle, and the emergency vehicle 4. The ego vehicle 3 has a sensor system 6 for detecting the surroundings of the ego vehicle 3, in particular in the direction of travel in front of the ego vehicle 3. The sensor system 6 can, for example, have at least one camera and / or at least one radar sensor and / or at least one lidar sensor. The sensor system 6 is coupled to a computing unit 7, which is configured to detect and track objects in the surroundings detected by the sensor system 6. Furthermore, the sensor system 6 can have at least one microphone for detecting noises from the surroundings.

[0015] The emergency vehicle 4 can be identified as an emergency vehicle 4, for example, by its external design, for example its paintwork and / or foiling, and / or by a switched-on special light signal 8, for example blue lights, and / or by a switched-on special acoustic signal 9, for example a siren.

[0016] The computing unit 7 of the ego vehicle 3 can Fig. 3 shown recognition module 17, which is configured to recognize the emergency vehicle 4 based on these features.

[0017] The recognition module 17 can further be configured to detect and track the trajectory T of a preceding vehicle 4, in particular over a longer period of time of, for example, more than 20 seconds, and to recognize the semantic signal, in particular when the preceding vehicle 4 has been recognized as an emergency vehicle 4 based on its external design and / or by a switched-on special light signal 8 and / or by a switched-on special acoustic signal 9.

[0018] A virtual driver of the autonomous ego vehicle 3, for example a Fig. The behavior planning module 12 shown in Figure 3 can be configured to adapt the driving behavior of the ego vehicle 3 according to the detected semantic signal, for example to drive at a distance behind the emergency vehicle 4 and to stop when the emergency vehicle 4 stops.

[0019] If the recognition module 17 has not recognized the preceding vehicle 4 as an emergency vehicle 4 based on its external design and / or the lack of a special light signal 8 and / or the lack of a special acoustic signal 9 and / or the trajectory T with violations V against the traffic regulations lasts for less than the specified period, for example 20 seconds or less, then it can be concluded that the preceding vehicle 4 is a reckless or drunk driver. In this case, the driving behavior of the ego vehicle 3 can also be adjusted accordingly, for example, it can drive at a distance behind the preceding vehicle 4. Furthermore, a message about the recognized reckless or drunk driver can be sent to a Fig. 3 shown backend 16 can be dropped off.

[0020] Fig.Figure 3 is a schematic view of an exemplary processing chain of the autonomous ego vehicle 3. Environmental data is acquired by the sensor system 6 and fed to the computing unit 7. In the computing unit 7, the data from the sensor system 6 is fused in a fusion unit 10 and compared with an internal digital map 11 and localized. The fused data from the fusion unit 10 is fed to a behavior planning module 12. The behavior planning module 12 is configured to control an actuator system 13 of the ego vehicle 3 for steering, accelerator, and brake.

[0021] The digital map 11 can be connected to a satellite navigation system 14.

[0022] The behavior planning module 12 has a situation analysis module 18 and a trajectory generator 19.

[0023] The computing unit 7 further comprises a recognition module 17 which is coupled to the situation analysis module 18 for data exchange.

[0024] The recognition module 17 can also communicate with a backend 16 via an interface 15, in particular wirelessly. List of reference symbols 1 lane 2.1, 2.2, 2.3, 2.4 lane 3 Ego vehicle 4 vehicle ahead, emergency vehicle 5 lane markings 6 Sensor technology 7 Computing unit 8 special light signal 9 special acoustic signal 10 Fusion Unit 11 map 12 Behavior Planning Module 13 Actuators 14 Satellite navigation system 15 Interface 16 backend 17 Detection module 18 Situation analysis module 19 Trajectory generator T trajectory V Violation QUOTES CONTAINED IN THE DESCRIPTION

[0000] This list of documents submitted by the applicant was generated automatically and is included solely for the convenience of the reader. This list is not part of the German patent or utility model application. The DPMA assumes no liability for any errors or omissions. Cited patent literature

[0000] US 2022 / 355802 A1

[0003]

Claims

[1] Method for operating an autonomous ego vehicle (3), wherein data of an environment including a preceding vehicle (4) are recorded by means of a sensor system (6) at least in one direction of travel in front of the ego vehicle (3) and provided to a computing unit (7), wherein a trajectory (T) of a preceding vehicle (4) traveling back and forth across several lanes (2.1 to 2.4) of a multi-lane roadway (1) is tracked by the sensor system (6) and / or the computing unit (7), characterized bythat when the vehicle (4) in front is recognized as an emergency vehicle (4) by means of a switched-on special light signal (8) and / or a switched-on special acoustic signal (9) and when a movement pattern in the trajectory (T) lasting for more than 20 seconds is recognized, in which the emergency vehicle (4) drives back and forth across several lanes (2.1 to 2.4), the driving behavior of the ego vehicle (3) is adapted so that it drives at a distance behind the emergency vehicle (4) and stops when the emergency vehicle (4) stops. [2] Method according to claim 1, characterized by that the vehicle (4) driving ahead is also recognized as an emergency vehicle (4) based on its external design. [3] Method according to claim 1 or 2, characterized bythat if the vehicle in front (4) is not recognized as an emergency vehicle (4) based on its external design and / or due to a missing special light signal (8) and / or due to a missing special acoustic signal (9) and / or if the trajectory (T) with violations (V) against the traffic regulations lasts for 20 seconds or less, it is concluded that the driver in the vehicle in front (4) is reckless or drunk and the driving behavior of the ego vehicle (3) is adapted so that it drives at a distance behind the vehicle in front (4), wherein a message about the recognized reckless or drunk driver is also sent to a backend (16).

Images