Method for vehicle operation, processing device and vehicle control device

Abstract

The invention relates to a method for operating a vehicle (10) of a vehicle (12), comprising processing (16) of environmental sensor data (18) of at least one environmental sensor (22) detecting a vehicle environment (20) of the vehicle (12), environmental perception (24) of the vehicle environment (20) including at least one environmental object (26) with an environmental model (28) depending on the environmental sensor data (18), providing (30) safety requirements (32) for the environmental perception (24) valid at a first time (t1), providing (30) estimated safety capabilities (34) of the environmental perception (24) effective at the first time (t1), safety comparison (36) of the safety requirements (32) with the safety capabilities (34) and calculation (38) of a planned operating parameter (40) of the vehicle (12) depending on the safety comparison (36). Furthermore, the invention relates to a processing device (14) and a vehicle control device (54).

Description

[0001] The invention relates to a method for vehicle operation according to claim 1. Furthermore, the invention relates to a processing device and a vehicle control device. State of the art

[0002] In the field of autonomous vehicles, the continuous detection and interpretation of the vehicle's surroundings is crucial. Fundamental to this is environment sensing, which uses sensors such as LIDAR, radar, ultrasound, and cameras to collect information about the vehicle's surroundings. This information is contained in the data from the surrounding sensors and is processed by the environment perception system, which allows objects to be detected, classified, and their movements to be predicted. Environment perception provides a comprehensive and detailed picture of the vehicle's surroundings, which is crucial for safe vehicle operation.

[0003] The functions of autonomous driving can be divided into three levels. The perception level focuses on environmental perception, including the interpretation of the vehicle's surroundings using an environmental model. Based on this, the planning level uses a behavior planner to make decisions about vehicle behavior and a trajectory planner to determine the vehicle's movement trajectory based on the perception of the surroundings. Finally, the action level implements the planned actions in the vehicle, for example, by controlling actuators.

[0004] The behavior planner plans the tactical behavior, for example actions such as "follow lane" or "change lane" for longer periods of time, for example 8 seconds. The trajectory planner plans the operative implementation of the specific trajectory with destination and speed for shorter periods of time, for example 3 seconds. Both planners calculate several alternatives over these periods and evaluate them according to predefined cost functions. One criterion that is checked here is the dynamically safe driveability of a driving maneuver. This is often determined in the downstream "motion control system" functional module for implementing the planned actions, taking into account, among other things, the current and future dynamic state of the vehicle, the states of the actuators and the nature of the environment, e.g. friction values.

[0005] However, one of the biggest challenges of automated driving is managing unavoidable functional deficiencies in environmental perception, particularly according to ISO / PAS 21448. ISO / PAS 21448 relates to road vehicles and the safety of the intended functionality. It is related to SOTIF (Safety of the Intended Functionality). It addresses safety risks that can arise when the vehicle functions as intended but may still act unsafely due to unexpected events or scenarios in the environment. This is particularly relevant for driver assistance systems, especially ADAS and autonomous driving systems, where the complexity and potential for unforeseen scenarios are higher.

[0006] Such deficiencies include, for example, an inability of the function to correctly detect and safely process the situation, including functions that use machine learning algorithms, or insufficient robustness of the function with regard to sensor input fluctuations or different environmental conditions.

[0007] A common approach is to identify potential limitations and vulnerabilities through analysis or by recording data from real-world driving, and to minimize these by adapting the environmental sensors and the perception system, including the algorithms. Other approaches are known to identify operational limitations, such as those caused by adverse weather conditions, and to address them adaptively or rule-based, for example, by reducing speed. Disclosure of the invention

[0008] According to the present invention, a method for vehicle operation with the features of claim 1 is proposed. This allows an explicit and predictive assessment of the reliability and adequacy of the environment perception to be provided for the calculation of the planned operating parameters. A proactive safeguarding of the perception capability is enabled. Operating situations in which the vehicle experiences safety-critical situations due to the inadequacy of the environment perception can be avoided. The calculation of the planned operating parameters can react more flexibly to the safety capabilities of the environment perception. By incorporating the safety capabilities of the environment perception, the environment perception can be implemented more cost-effectively, since, in particular, it is not necessary to maintain perception capabilities for all conceivable and anticipated situations in order to ensure safety in these situations.

[0009] The vehicle can be a motor vehicle, a truck, a two-wheeled vehicle, a mobile robot, or an industrial robot. The vehicle can assume at least a semi-autonomous or autonomous operating state during driving.

[0010] The environment sensor can be a LIDAR sensor, a radar sensor, an ultrasonic sensor and / or a camera.

[0011] The vehicle environment can include, preferably exclusively, the immediate surroundings of the vehicle.

[0012] The environmental sensor data can be provided by environmental sensing. During environmental sensing, raw data from the physical environment can be collected using at least one environmental sensor. The capability, reliability, and / or integrity of the environmental sensing can depend on a range, a resolution, and / or a weather condition. Environmental sensing can at least partially involve the processing of the environmental sensor data. In this regard, ASIL (Automotive Safety Integrity Level) according to ISO 26262, which refers to the probability that internal processing is faulty due to an electrical / electronic failure, can be applicable.

[0013] The environmental object can be a building, a living being, a device, an object, another vehicle, a plant or a road surface.

[0014] Environment perception can process and interpret the environment sensor data provided by the environment sensor. This can include attempting to understand the meaning of the information contained in the environment sensor data about the vehicle's surroundings and the at least one environment object. For example, it can be recognized whether the environment object is a car, a pedestrian, or a bicycle and / or whether it is moving or stationary. Machine learning and computer vision techniques can be used in environment perception, in particular to recognize patterns in the environment sensor data and / or to correctly classify the at least one environment object. The goal of environment perception is a reliable and accurate representation of the environment in real time.

[0015] The environment model can be created and / or modified using the environment perception. The environment model can be a real-time representation of the vehicle's surroundings. The environment model can include a map or a 3D model of the vehicle's surroundings.

[0016] The planned operating parameter can be an emergency operating parameter applied in a fallback solution to maximize driving safety, for example, during a Minimal Risk Maneuver (MRM). The planned emergency operating situation can relate to the current situation or future situations. The planned operating parameter can be the operating parameter to be applied at the initial point in time or at a different point in time, particularly at a previous or subsequent point in time.

[0017] The operating parameter can be a vehicle parameter, a driving operation parameter of the vehicle's driving operation, and / or a movement parameter of the vehicle. The operating parameter can actually be adjustable and / or variable by at least one actuator. The operating parameter can be a longitudinal speed, longitudinal acceleration, lateral speed, lateral acceleration, and / or a vehicle position. The operating parameter can be a signal, in particular a visual, acoustic, and / or vibrating signal.

[0018] The calculation of the planned operating parameter may depend on a current environmental perception of the currently existing vehicle environment.

[0019] The safety requirements for environmental perception can be predefined safety conditions for environmental detection by the at least one environmental sensor, for processing the environmental sensor data, and / or for the environmental model. The safety capabilities of environmental perception can be the performance, reliability, and / or availability of the environmental detection by the at least one environmental sensor, the processing of the environmental sensor data, and / or the environmental model. The safety capability can include or be safety integrity (in particular according to ISO 26262). The safety capabilities can include classifying and / or quantifying statistical parameters, for example, defined by the relevant standard ISO / PAS 8800.The safety requirements and / or safety capabilities may include completeness of the environmental information, in particular all relevant environmental objects and environmental situations, accuracy, reliability, in particular correct classification, status detection and / or movement detection of the environmental object, robustness against external influences, for example against weather influences or lighting conditions and / or redundancy.

[0020] The provided safety requirements and / or safety capabilities can be limited to a specified area of ​​the vehicle's environment. The environmental area can be specified for the safety comparison. The environmental area can be a sub-area of ​​a 3D grid that divides the vehicle's environment, in particular regularly. The safety comparison can be performed for each sub-area.

[0021] The provided security capabilities may depend on a state of environmental perception, possible constraints, such as occlusions, environmental conditions, such as weather conditions, visibility conditions, resource capacity, system states, errors, and / or out-of-distribution detection or anomaly detection. The security capabilities may be calculated and provided taking into account at least one of these parameters.

[0022] In a preferred embodiment of the invention, it is advantageous if the first point in time follows the current point in time at which the calculation is performed. The security comparison can be performed for additional points in time using the security requirements and security capabilities valid at the respective points in time. The security requirements and security capabilities used in the security comparison preferably refer to a common point in time or period.

[0023] In a preferred embodiment of the invention, it is advantageous if the first time is the current time, in particular the time at which the calculation is executed. The planned operating parameter can be an operating parameter to be applied at the first or a subsequent time.

[0024] In a specific embodiment of the invention, it is advantageous if the calculation also includes the safety impacts of the vehicle due to the planned operating parameter. The safety impacts can include the safety of the vehicle, the environment, and / or the environment due to the vehicle. The planned operating parameter can be calculated primarily with the goal of increasing safety.

[0025] A preferred embodiment of the invention is advantageous in which the calculation includes trajectory planning for at least one movement trajectory of the vehicle. The calculation can include behavior planning for at least one vehicle behavior of the vehicle. The trajectory planning can depend on the behavior planning. The behavior planning can plan the tactical behavior of the vehicle, for example "follow lane" or "change lane," for a first period. The trajectory planning can plan the operative implementation of the specific movement trajectory, in particular with target point and speed, for a second period. The first period is preferably longer than the second period. The first period can at least partially include the second period. The first and second periods can be spaced apart in time. The behavior planning and / or trajectory planning can depend on the environmental model.

[0026] The operating parameter can be the vehicle behavior and / or the movement trajectory. The operating parameter can comprise part of a parameter set, for example, including target point, centerline distance, speed, acceleration, and / or steering angle / gradient. The operating parameter can also comprise only one of these parameters, for example, only speed (particularly for visibility) or only distance to the centerline (particularly for visibility). The operating parameter can comprise or influence the vehicle behavior and / or the movement trajectory.

[0027] In a specific embodiment of the invention, it is advantageous if the safety requirements include a required environmental detection range, the safety capabilities include a feasible environmental detection range, and the safety comparison includes coverage of the required environmental detection range with the feasible environmental detection range. The environmental detection range can be the detection range covered or coverable by the environmental detection.

[0028] In a preferred embodiment of the invention, it is advantageous if the calculation comprises a selection of the planned operating parameter from several possible alternative planned operating parameters, wherein safety comparisons are assigned to each of the alternative planned operating parameters. This allows the operating parameter to be selected depending on the respective safety comparison.

[0029] In a specific embodiment of the invention, it is advantageous if the safety comparison determines at least one deviation measure, in particular a deviation magnitude and / or a deviation duration, of a deviation between the safety capabilities and the safety requirements. The planned operating parameter can be calculated depending on the deviation measure. The planned operating parameter can be a selection from several possible operating parameters, and the selection can be dependent on the deviation measure. The deviation measure can be a deviation in the coverage between the required and the feasible detection range.

[0030] According to the present invention, a processing device for a vehicle is further proposed, which is configured to execute the method for vehicle operation with at least one of the previously described features. The processing device can have at least one processor for at least partially executing the method.

[0031] According to the present invention, a vehicle control device for a vehicle is further proposed, which is configured to adjust the planned operating parameter calculated using a method for vehicle operation with at least one of the previously described features. The vehicle control device can be a control unit or a part of a control unit.

[0032] The method for vehicle operation can be implemented as a computer-implemented method. At least one method step, in particular the safety comparison, of the method can be performed in the vehicle using edge computing and / or outside the vehicle using cloud computing. At least one method step of the method can be processed using machine learning. The machine learning can use a neural network. The machine learning can include reinforcement learning.

[0033] Furthermore, the invention relates to a non-transitory, computer-readable medium containing instructions, the execution of which causes at least one processor to carry out said method for vehicle operation with at least one previously described feature.

[0034] Further advantages and advantageous embodiments of the invention emerge from the description of the figures and the illustrations. Character description

[0035] The invention is described in detail below with reference to the figures. They show in detail: Fig. 1: A method for vehicle operation in a specific embodiment of the invention. Fig. 2: A division of a vehicle environment into environmental areas when carrying out a method for vehicle operation in a specific embodiment of the invention. Fig. 3: A driving situation of a vehicle when executing the method for vehicle operation in a further specific embodiment of the invention.

[0036] Fig. 1 shows a method for vehicle operation in a specific embodiment of the invention.The method for vehicle operation 10 of a vehicle 12 can be executed by a processing device 14 of the vehicle 12 and comprises processing 16 of environmental sensor data 18 of at least one environmental sensor 22 detecting a vehicle environment 20 of the vehicle 12, subsequent environmental perception 24 of the vehicle environment 20 including at least one environmental object 26, here a pedestrian in front of the vehicle 12, using an environmental model 28 depending on the environmental sensor data 18, providing 30 safety requirements 32 valid at a first time to the environmental perception 24 and providing 31 estimated safety capabilities 34 of the environmental perception 24 effective at the first time, a safety comparison 36 of the safety requirements 32 with the safety capabilities 34, and a calculation 38 of at least one planned operating parameter 40 of the vehicle 12 depending on the safety comparison 36.The safety requirements 32 can, in turn, result from the planned operating parameters 40, which in turn are based on the environmental model 28. In this recursive calculation, it is particularly important that the data used is consistently reliable.

[0037] The first time may follow the current time at the time the calculation 38 is executed. The calculation 38 may also include safety impacts 42 of the vehicle 12 due to the planned operating parameter 40. The calculation 38 may include trajectory planning 44 of at least one movement trajectory of the vehicle 12 and behavior planning 46 of at least one vehicle behavior of the vehicle 12. The behavior planning 46 and / or trajectory planning 44 may depend on the environmental model 28. The planned operating parameter 40 may include or influence the vehicle behavior and / or the movement trajectory.

[0038] The safety comparison 36 can determine at least one deviation measure 48, in particular a deviation magnitude and / or a deviation duration, of a deviation between the safety capabilities 34 and the safety requirements 32. The calculation 38 of the planned operating parameter 40 can comprise a selection 50 of the planned operating parameter 40 from several possible alternative planned operating parameters 52, wherein the alternative planned operating parameters 52 are each assigned safety comparisons 36.

[0039] The planned operating parameter 40 is actually adjustable and / or changeable by a vehicle control device 54 with a motion control 56 of at least one actuator.

[0040] The safety requirements 32 can, for example, be a latency for setting the operating parameter at the first time, for example, a motion control 56 of a brake actuator for braking the vehicle 12. The safety capabilities 34 can be the actually implementable latency.

[0041] The safety requirements 32 can also be a required distance up to which surrounding objects 26 can be detected at a distance from the vehicle 12, in particular at a distance ahead of the vehicle 12. The safety capabilities 34 can be the visibility conditions existing at the initial point in time and influenced by weather conditions.

[0042] The safety requirements 32 can also specify a minimum environmental detection range for the environmental detection. The safety capabilities 34 can be the environmental detection range of the environmental detection present at the initial point in time and impaired by obscuration or glare of the environmental sensor 22.

[0043] Fig. 2 shows a division of a vehicle environment into environmental regions when carrying out a method for vehicle operation in a specific embodiment of the invention. The provided safety requirements and / or safety capabilities are limited to a predetermined environmental region 58 of the vehicle environment in front of the vehicle 12. The environmental region 58 is a subregion 60 of a 3D grid 62 that divides the vehicle environment 20, in particular regularly. The safety comparison and the calculation of the planned operating parameter can be performed for each subregion 60.

[0044] Fig. 3 shows a driving situation of a vehicle during execution of the vehicle operation method in another specific embodiment of the invention. The safety requirements 32 specify the surroundings detection ranges 64 of the surroundings detection at the first time t1 and at further times 68. The safety capabilities 34 specify the feasible surroundings detection ranges 66 of the surroundings detection at the first time t1 and at the corresponding further times 68.

[0045] The safety comparison includes a coverage 70 of the required surroundings detection area 64 with the feasible surroundings detection area 66. This coverage 70 is present at the first time t1, but not, for example, at the eighth time t8 due to the tree present at the edge of the road as surrounding object 26. The calculation of the planned operating parameter is performed depending on the safety comparison, here the coverage 70. For example, the planned operating parameter at the eighth time t8 can be a reduced vehicle speed. The planned operating parameter can also influence a movement trajectory 72 of the vehicle 12. 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 non-patent literature

[0000] ISO / PAS 21448

[0005]

Claims

[1] Method for vehicle operation (10) of a vehicle (12), comprising processing (16) of environmental sensor data (18) of at least one environmental sensor (22) detecting a vehicle environment (20) of the vehicle (12), environmental perception (24) of the vehicle environment (20) including at least one environmental object (26) with an environmental model (28) depending on the environmental sensor data (18), Providing (30) safety requirements (32) valid at a first time (t1) for the environmental perception (24), Providing (30) estimated safety capabilities (34) of the environment perception (24) effective at the first time (t1), Security comparison (36) of the security requirements (32) with the security capabilities (34) and Calculation (38) of a planned operating parameter (40) of the vehicle (12) depending on the safety comparison (36). [2] Method for vehicle operation (10) according to claim 1, characterized bythat the first time (t1) follows the current time present when the calculation (38) is carried out. [3] Method for vehicle operation (10) according to claim 1, characterized by that the first time (t1) is the current time. [4] Method for vehicle operation (10) according to one of the preceding claims, characterized by that the calculation (38) also includes safety effects (42) of the vehicle (12) due to the planned operating parameter (40). [5] Method for vehicle operation (10) according to one of the preceding claims, characterized by that the calculation (38) includes a trajectory planning (44) of at least one movement trajectory (72) of the vehicle (12). [6] Method for vehicle operation (10) according to one of the preceding claims, characterized bythat the safety requirements (32) include a required environment detection range (64), the safety capabilities (34) include a feasible environment detection range (66) and the safety comparison (36) includes a coverage (70) of the required environment detection range (64) with the feasible environment detection range (66). [7] Method for vehicle operation (10) according to one of the preceding claims, characterized by that the calculation (38) comprises a selection (50) of the planned operating parameter (40) from several possible alternative planned operating parameters (52), wherein safety comparisons (36) are respectively assigned to the alternative planned operating parameters (52). [8] Method for vehicle operation (10) according to one of the preceding claims, characterized bythat the safety comparison (36) determines at least one deviation measure (48), in particular a deviation intensity and / or a deviation duration, of a deviation between the safety capabilities (34) and the safety requirements (32). [9] Processing device (14) for a vehicle (12) which is arranged to carry out the method for vehicle operation (10) according to one of the preceding claims. [10] Vehicle control device (54) for a vehicle (12) which is configured to adjust the planned operating parameter (40) of the vehicle (12) calculated using a method for vehicle operation (10) according to one of claims 1 to 8.

Images