METHOD FOR OPERATING A VEHICLE

Abstract

Method (M) for operating a vehicle (100) based on a trackable trajectory (150), comprising: determining (S18, S20) a minimum distance (190) based on a predicted speed of the vehicle (100) along the trajectory (150); and initiating (S30) an evasive measure (200) if a distance (180) between a travel path (160) along the trajectory (150) and a detected object (170) is smaller than the minimum distance (190).

Description

[0001] The present invention relates to a method for operating a vehicle, a computer program product, a control device for a vehicle, and a vehicle with the control device.

[0002] While a vehicle is following a – usually trained – trajectory, it may come so close to an object in the vehicle's surroundings that a driver or passenger fears a collision. This fear reduces driving comfort.

[0003] Avoiding an object to avoid a collision is known. For example, US 2019 / 01 18 801 A1 describes a parking device configured to park a vehicle along a learned path. If the path of the host vehicle crosses the path of a vehicle in the host vehicle's vicinity with a high probability, the parking device changes the host vehicle's path to avoid the other vehicle.

[0004] Against this background, it is an object of the present invention to provide a means to increase driving comfort if an object is located in the vicinity of a trajectory to be followed.

[0005] Accordingly, a method for operating a vehicle based on a trackable trajectory is proposed. The proposed method includes the steps of determining a minimum distance based on a predicted speed or as a function of the predicted speed of the vehicle along the trajectory; and initiating a speed reduction and / or evasive action if a distance between a predicted position of the vehicle along the trajectory and a detected object is smaller than the minimum distance.

[0006] The proposed method causes the vehicle to avoid an object even if no collision is imminent, but a driver or passenger of the vehicle can only inadequately assess this because the trajectory of the vehicle passes very closely to the object.

[0007] A trajectory can be understood as a predefined path. The trajectory can be and / or contain a set of positions or waypoints. The trajectory can preferably be traced in both directions, such as in the recording direction and against the recording direction. The trajectory can preferably be traced backward. The trajectory can be provided, for example, in the form of a digital data set.

[0008] The specified trajectory is preferably a trained trajectory. For example, a parking assistance system or another system of the vehicle is configured to record and save a manually driven trajectory in a training mode. For example, various sensor signals are recorded that characterize a driving state of the vehicle, such as speed, position, steering angle, and the like, as clearly as possible. In addition, sensor signals from the vehicle's environmental sensors are recorded, which, for example, enable an image of the vehicle's surroundings, in particular the position of obstacles in the surroundings. By playing back the vehicle's driving state synchronously, i.e., repeating it, the trained trajectory can be followed. To follow the specified trajectory, it is desirable to take current environmental sensor data into account.Therefore, the parking assistance system receives a sensor signal indicative of the surroundings. The parking assistance system can receive this signal directly from one or more of the vehicle's environmental sensors, for example, and combine several sensor signals from different environmental sensors. Alternatively, the parking assistance system can receive the sensor signal in a preprocessed state, for example, in the form of a digital map of the surroundings in which detected obstacles in the surroundings are marked.

[0009] The proposed method for operating a vehicle is preferably a method for parking a vehicle in and / or out of a parking space or parking space based on a traceable parking entry and / or exit trajectory, which preferably ends and / or begins in a parking space. The parking space is part of a parking facility that contains several parking spaces and at least one driveway connecting the parking spaces. For example, the parking entry and / or exit trajectory may lead from an entrance to the parking facility to the parking space and / or from the parking space to an exit from the parking facility.

[0010] According to one embodiment, the proposed method may include: detecting an object in the surroundings of the vehicle; determining a predicted distance between the vehicle at a predicted position along the trajectory and the detected object; determining a minimum distance based on a predicted speed of the vehicle at the future position; and initiating an evasive action if the predicted distance is smaller than the minimum distance.

[0011] The distance can be understood as the predicted distance. The distance between a predicted position of the vehicle along the trajectory and the detected object can be understood as the distance between the vehicle at the predicted position along the trajectory and the detected object.

[0012] The terms predicted distance, predicted position and predicted speed may mean that this distance, position and speed will exist at the same future time according to a current plan.

[0013] If an output variable is determined based on an input variable, this may mean that the output variable is determined as a function of the input variable.

[0014] The set of all predicted positions of the vehicle, including in particular the predicted position closest to the object, can preferably be mapped or implemented as a travel path. The travel path is preferably a predicted travel path. A travel path can be understood as a space containing all spaces or volumes occupied by the vehicle in the future along the trajectory. According to one option, the object is preferably an object outside a travel path of the vehicle along the trajectory.

[0015] According to one option, the distance between the vehicle and the object is determined as the distance between an outer surface of the object and a nearest point / line / surface of the driving path. According to another option, the distance between the vehicle and the object is determined as the distance between an outer surface of the object and a predicted centerline of the vehicle. Both options can differ essentially in the amount of the selected minimum distance. Since a driving path has a wider cross-section in a (tight) curve than along a straight line, the minimum distance can be selected to be smaller if the distance to the driving path is determined.

[0016] The method preferably includes the step of recognizing an object type of the object using an object recognition model, which is preferably a trained object recognition model. The minimum distance is preferably also determined based on the recognized object type. This makes it possible to adapt the minimum distance to a different danger perception of a (typical) driver / passenger. Further development may include different minimum distances for an object type indicating an immobile object, an object type indicating a non-self-moving object, and / or an object type indicating a self-moving and stationary object. Examples of an immobile object may be a building, a wall, a railing, and / or a lamppost.Examples of a non-self-moving object can be a flowerpot, a waste bin, and / or a piece of luggage. A parked bicycle and / or a lawnmower can also be included. Examples of a self-moving and stationary object can be a parked car, a lawnmower, a parked bicycle, and / or a delivery robot. This option means that the minimum distance can be selected or preset to be greater, the more likely the object is to move. This option therefore improves driving comfort.

[0017] In particular, the method can provide for detecting the object in the vehicle's surroundings based on sensor data representing the vehicle's surroundings. The sensor data preferably originates from at least one vehicle-specific or vehicle-mounted sensor device. This enables particularly reliable detection of the object.

[0018] The method can preferably provide for detecting the object in the vehicle's surroundings based on a current map of the surroundings. For example, an environment map generation method executed in parallel and independently of this method can provide such a map. If multiple methods access such a map, this is not only a possible but also efficient option.

[0019] It can be provided that the minimum distance is also determined based on, preferably depending on, the size of the detected object. This option can also correspond, in particular, to a driver's sense of safety. This option thus improves driving comfort.

[0020] Optionally, the method may include determining the minimum distance depending on whether the object is recorded in the trajectory; wherein a greater minimum distance is determined if the object is not recorded in the trajectory than if the object is recorded in the trajectory. Preferably, "recorded in the trajectory" can mean "contained in a data set that contains and / or is linked to the trajectory." If an object has moved since the trajectory was recorded, it is more likely that the object will be moved in the near future. This option therefore improves driving comfort.

[0021] It may be intended to initiate evasive action only if the object is not recorded in the trajectory. For example, the method may include not initiating evasive action if the object is recorded in the trajectory or a data set indicating or linked to the trajectory, or a trajectory data set. If the object was already in the same position at the recording point, and the vehicle nevertheless passed close to the object, the short distance appears acceptable to the driver, so that evasive action may not seem necessary. This option therefore improves driving comfort by preventing what is perceived as unnecessary evasive maneuvers or stopping.

[0022] It may also be possible to prevent the evasive action from being initiated if a) the object is recorded in the trajectory, and b) the predicted speed is not greater than the vehicle's speed during a recording run of the trajectory. The recording run is preferably a recording run underlying the trajectory. If a driver passes the object closely during the recording run, but at a low speed, passing it at a faster speed and at the same speed may be unpleasant for the same driver. This option therefore improves driving comfort.

[0023] The initiated evasive action can, for example, be selected from a group that includes: a) generating an evasive trajectory that maintains the minimum distance to the object; and / or b) stopping the vehicle in front of the object. These preferred evasive actions enable the vehicle to operate in a manner that is perceived as safe, thus ensuring a high level of driving comfort.

[0024] Furthermore, a method for operating a vehicle based on a trackable trajectory is proposed, comprising: determining a minimum distance based on a predicted speed of the vehicle along the trajectory; and initiating a speed reduction if a distance between a predicted position of the vehicle along the trajectory and a detected object is smaller than the minimum distance.

[0025] The vehicle's speed is preferably reduced to a standstill. In particular, the speed reduction is achieved by frictional braking and / or regenerative braking and / or, in particular, simply by releasing the accelerator pedal.

[0026] In addition, an evasive action can be initiated if the distance between the predicted position of the vehicle along the trajectory and the detected object is smaller than the minimum distance.

[0027] Furthermore, a computer program product is proposed which comprises instructions which, when executed by a computer, cause the computer to carry out the above-described method for operating a vehicle. A computer program product, such as a computer program means, can be provided or delivered, for example, as a storage medium, such as a memory card, USB stick, CD-ROM, DVD, or in the form of a downloadable file from a server in a network. This can be done, for example, in a wireless communications network by transmitting a corresponding file with the computer program product or the computer program means.

[0028] According to a further aspect of the invention, a control device for a vehicle is proposed, which is configured to carry out the proposed method for operating a vehicle. For example, this control device can have a processing unit for carrying out the steps of the method. For example, this control device can have an interface, such as a bus interface and / or a sensor interface, for reading in sensor data and / or an environmental map. For example, this control device can have an interface, such as the bus interface, for outputting an instruction indicating the initiation of the evasive measure and / or for outputting the initiated evasive measure. The embodiments and features described for the proposed method apply accordingly to the proposed device.

[0029] The respective unit can be implemented in hardware and / or software. In a hardware implementation, the respective unit can be embodied, for example, as a computer or a microprocessor. In a software implementation, the respective unit can be embodied as a computer program product, as a function, as a routine, as an algorithm, as part of a program code, or as an executable object. Furthermore, each of the units mentioned here can also be embodied as part of a higher-level control system of the vehicle, such as a central electronic control device and / or an engine control unit (ECU).

[0030] According to another aspect of the invention, a driver assistance system, preferably a parking assistance system, is proposed, which is configured to carry out the proposed method for operating a vehicle. The parking assistance system is configured, in particular, for semi-autonomous or fully autonomous driving of the vehicle. Semi-autonomous driving is understood, for example, to mean that the parking assistance system controls a steering device and / or an automatic gearshift. Fully autonomous driving is understood, for example, to mean that the parking assistance system also controls a drive device and a braking device.

[0031] According to another aspect of the invention, a vehicle is proposed that includes the proposed control device. The vehicle preferably also includes at least one sensor device in communication with the control device. The vehicle may additionally or alternatively have a communication device in communication with the control device for obtaining an environment map from an external environment map server or the like.

[0032] The vehicle is, for example, a passenger car or a truck. The vehicle preferably comprises a number of sensor units configured to detect the driving state of the vehicle and to detect the vehicle's surroundings. Examples of such sensor units of the vehicle are image recording devices such as a camera, a radar (radio detection and ranging) or a lidar (light detection and ranging), ultrasonic sensors, location sensors, wheel angle sensors, and / or wheel speed sensors. The sensor units are each configured to output a sensor signal, for example, to the parking assistance system or driver assistance system, which performs semi-autonomous or fully autonomous driving depending on the detected sensor signals.

[0033] Further possible implementations of the invention also include combinations of features or embodiments described above or below with respect to the exemplary embodiments that are not explicitly mentioned. In this case, the person skilled in the art will also add individual aspects as improvements or additions to the respective basic form of the invention.

[0034] Further advantageous embodiments and aspects of the invention are the subject of the dependent claims and the exemplary embodiments of the invention described below. The invention will be explained in more detail below using preferred embodiments with reference to the accompanying figures. Fig. 1 shows a schematic plan view of a proposed vehicle adapted to carry out the proposed method according to an embodiment of the invention; Fig. 2 shows a schematic plan view of the vehicle of the Fig. 1 in a driving situation in which the vehicle passes an object in the surroundings of the vehicle along a trajectory slowly and at a short distance; Fig. Figure 3 shows a schematic plan view of the vehicle of Fig. 1 in a driving situation in which the vehicle passes an object in the surroundings of the vehicle quickly and at a greater distance along a trajectory; Fig. 4 shows a schematic plan view of the vehicle of the Fig. 1 in a driving situation in which the vehicle would pass an object in the surroundings of the vehicle quickly and at a short distance along a trajectory and then initiates an evasive action; and Fig. 5 shows a schematic flowchart of the procedure for operating the vehicle according to the embodiment.

[0035] In the figures, identical or functionally equivalent elements have been given the same reference numerals unless otherwise stated.

[0036] Fig. 1 shows a schematic view of a vehicle 100 from a bird's eye view. The vehicle 100 is, for example, a car arranged in an environment 140. The car 100 has a parking assistance system 110, which is embodied, for example, as a control device. Furthermore, a plurality of environmental sensor devices 120, 130 are arranged on the car 100, which are, for example, optical sensors 120 and ultrasonic sensors 130. The optical sensors 120 include, for example, visual cameras, a radar, and / or a lidar. The optical sensors 120 can each capture an image of a respective area from the environment 140 of the car 100 and output it as an optical sensor signal. The ultrasonic sensors 130 are configured to detect a distance to objects arranged in the environment 140 and to output a corresponding sensor signal.Using the sensor signals detected by sensors 120, 130, parking assistance system 110 is capable of driving car 100 semi-autonomously or fully autonomously. In addition to the functions described in the . Fig. In addition to the optical sensors 120 and ultrasonic sensors 130 shown in Figure 1, the vehicle 100 may be provided with various additional sensor devices 120, 130. Examples include a microphone, an acceleration sensor, an antenna with a coupled receiver for receiving electromagnetically transmittable data signals, and the like.

[0037] The following is based on the Fig. 2 to 5, an embodiment of a proposed method M for operating the vehicle 100 is presented. This embodiment includes optional features.

[0038] In all three Fig. 2 to 4, the vehicle 100 is shown in a trip planning situation, wherein the vehicle 100 is following or will follow a trajectory 150, preferably provided as a data set. When the vehicle 100 follows the trajectory 150, it fills a travel path 160.

[0039] In the environment 140 there is an object 170. The object 170 has a distance of 180 from the travel path 160.

[0040] In the Fig. 2 shows that vehicle 100 is following trajectory 150 at low speed. Therefore, according to the proposed method M, a small minimum distance 190 is determined, which is indicated by a line. Although object 170 is close to travel path 160, distance 180 is greater than minimum distance 190. Therefore, no evasive action is taken.

[0041] In the Fig. 3 shows that the vehicle 100 follows the trajectory 150 at high speed, but the object 170 is still at a greater distance 180 from the travel path 160 than the minimum distance 190. Therefore, no evasive action is taken.

[0042] In the Fig. 4 shows that the vehicle 100 also plans to follow the trajectory 150 at the high speed, but the object 170 is as close as in the situation of Fig. 2. Therefore, the distance 180 of the object 170 is less than the minimum distance 190. As a result, the trajectory 150 is changed by taking a speed reduction and / or evasive action 200, which is illustrated here as an evasive maneuver.

[0043] The proposed method M for operating the vehicle 100 is briefly described below, including optional steps.

[0044] In a step S10, the trajectory 150 is provided. The trajectory 150 is preferably a planned trajectory 150 along which the vehicle 100 will travel unless a steering intervention and / or a drive intervention is performed by a driver or another control method or control unit.

[0045] In a step S12, the object 170 is detected in the environment 140 of the vehicle 100, for example by means of the environmental sensors 120, 130. The object 170 is in all cases the Fig. 2 to 4 an object 170 outside the predicted travel path 160 of the vehicle 100 along the provided trajectory 150. The modified travel path according to the evasive action 200 of the Fig. 4 is not shown for reasons of clarity.

[0046] In a step S14, an object type of the object 170 is recognized using an object recognition model. The object recognition model is, for example, an object recognition model trained on sensor signals from the environmental sensors 120, 130, which is executed by the control device 110. For example, the object recognition model can be provided and / or executed by a method executed in parallel.

[0047] In a step S16, the predicted distance 180 between the vehicle 100 and the detected object 170 is determined, specifically at a future position of the vehicle 100 along the trajectory 150 that is closest to the object 170. The future position is represented by the travel path 160, or an outer contour of the vehicle 100 at all future positions along the trajectory 150 is indicated by the travel path 160.

[0048] In a step S18, the minimum distance 190 between the driving path 160 at the predicted or planned position of the vehicle 100 and the detected object 170 is determined.

[0049] In a step S20, the minimum distance 190 is determined based on the predicted speed of the vehicle 100 at the future position.

[0050] Different speeds can be provided along the trajectory 150, for example, as a result of acceleration, deceleration, and / or temporary deceleration. Therefore, it can be provided that the minimum distance 190 along the trajectory 150 is determined in accordance with the respective planned speed along the trajectory 150.

[0051] Furthermore, in a step S22, the minimum distance 190 may also be determined based on the detected object type. For example, in a step S24, the minimum distance 190 is selected from a group of different minimum distances depending on the object type. The group contains, for example, a minimum distance 190 for an object type that indicates an immobile object, such as a wall. The group contains, for example, a larger minimum distance 190 for an object type that indicates a non-self-moving object, such as a garbage container 170. The group contains, for example, an even larger minimum distance 190 for an object type that indicates a self-moving and stationary object, such as a stationary bicycle.

[0052] In a step S26, the minimum distance is also determined based on the size of the detected object 170. For a larger object 170, a larger minimum distance 190 is provided than for a smaller object 170.

[0053] In a step S28, the minimum distance 190 is determined depending on whether or not the object 170 is recorded in the data set containing and / or linked to the trajectory 150. Preferably, a greater minimum distance 190 is determined if the object 170 is not recorded in the data set containing and / or linked to the trajectory than if the object 170 is recorded in the data set of the trajectory 150.

[0054] In a step S30, an evasive action 200 is initiated if the predicted distance is smaller than the minimum distance 180, 190. Initiating the evasive action may, for example, include controlling a steering device and / or a drive and / or braking device of the vehicle 100.

[0055] In step S32, the evasive action 200 is not initiated if the object 170 is recorded in the trajectory data set. In a further development, the evasive action 200 may not be initiated in step S34 if the object 170 is recorded in the trajectory 150 or the trajectory data set, and the predicted speed is not greater than a speed of the vehicle 100 during a recording run underlying the trajectory 150.

[0056] In a step S36, the evasive measure 200 is selected from a group that includes: generating an evasive trajectory that maintains the minimum distance 180, 190 from the object 170; and / or stopping the vehicle 100 in front of the object 170.

[0057] In a next step S38, the vehicle 100 travels along the trajectory 150 including the evasive measure 200. This ensures a high level of driving comfort.

[0058] Although the present invention has been described using exemplary embodiments, it can be modified in many ways. LIST OF REFERENCE SYMBOLS 100 vehicles 110 Control device 120 optical sensor 130 ultrasonic sensor 140 surroundings 150 Trajectory 160 driving tube 170 objects 180 minimum distance 190 line (minimum distance) 200 evasive measures M Method of operating a vehicle S10 Providing a trajectory S12 Detection of an object in the vehicle's surroundings S14 Detecting an object type of the object S16 Determining a predicted distance S18 Determining a minimum distance S20 Determining a minimum distance depending on a predicted speed S22 Determining the minimum distance depending on the object type S24 Selecting a minimum distance depending on an object type S26 Determining the minimum distance depending on the object size S28 Determining the minimum distance depending on whether the object is registered in the trajectory S30 Initiation of an evasive measure S32 Not initiating the evasive action if the object is recorded in the trajectory S34 Not initiating the evasive action if the object is recorded in the trajectory and the predicted speed is not greater than a recorded speed of the trajectory S36 Selecting the alternative measure S38 Descendants along the trajectory

Claims

[1] Method (M) for operating a vehicle (100) based on a trackable trajectory (150), comprising: Determining (S18, S20) a minimum distance (190) based on a predicted speed of the vehicle (100) along the trajectory (150); and Initiating (S30) an evasive measure (200) if a distance (180) between a predicted position of the vehicle along the trajectory (150) and a detected object (170) is smaller than the minimum distance (190). [2] Method according to claim 1, characterized by that the procedure includes: Recognizing (S14) an object type of the object (170) by means of an object recognition model, which is preferably a trained object recognition model; and Determining (S22, S23) the minimum distance (190) based on the detected object type. [3] Method according to claim 2, wherein different minimum distances (190) are provided for an object type indicating an immobile object, an object type indicating a non-self-moving object (170), and / or an object type indicating a self-moving and stationary object. [4] Method according to one of the preceding claims, characterized by that the procedure includes: Determining (S26) the minimum distance (190) is determined based on a size of the detected object (170). [5] Method according to one of the preceding claims, characterized by that the procedure includes: Determining (S28) the minimum distance (190) depending on whether the object (170) is recorded in the trajectory (150); wherein preferably a greater minimum distance (190) is determined if the object (170) is not recorded in the trajectory (150) than if the object (170) is recorded in the trajectory (150). [6] Method according to one of the preceding claims, characterized by that the procedure includes: Not initiating (S32) the evasive action (200) if the object (170) is recorded in the trajectory (150). [7] Method according to claim 6, characterized by that the procedure includes: Not initiating (S34) the evasive action if the predicted speed is not greater than a recording speed of the trajectory (150). [8] Method according to one of the preceding claims, characterized by that the procedure includes: Selecting (S36) the alternative measure (200) from a group containing: Generating an avoidance trajectory that maintains the minimum distance (190) to the object (170); and / or Stopping the vehicle (100) in front of the object (170). [9] Method (M) for operating a vehicle (100) based on a trackable trajectory (150), comprising: Determining (S18, S20) a minimum distance (190) based on a predicted speed of the vehicle (100) along the trajectory (150); and Initiating (S30) a speed reduction if a distance (180) between a predicted position of the vehicle along the trajectory (150) and a detected object (170) is smaller than the minimum distance (190). [10] Method according to claim 9, characterized by Initiating (S30) an evasive measure (200) if the distance (180) between the predicted position of the vehicle along the trajectory (150) and the detected object (170) is smaller than the minimum distance (190). [11] Computer program product comprising instructions which, when executed by a computer, cause the computer to carry out the method (M) for operating a vehicle (100) according to any one of claims 1-10. [12] Control device (110) for a vehicle (100) which is designed to carry out the method (M) for operating a vehicle (100) according to one of claims 1-10. [13] Vehicle (100) with a control device (110) according to claim 12.

Images