DETECTION OF UNCOVERED OBJECTS

Abstract

A system for monitoring a vehicle's environment comprises a perception system that communicates with a vehicle sensor, the perception system being designed to receive perception data from the vehicle sensor. The system also includes a scenario detection module designed to detect a first object based on the perception data and to analyze the behavior of the first object in order to predict whether a detection scenario occurs or will occur, in which case a concealed object is revealed. The system further includes a control module designed to, based on the detection of the concealed object as a revealed object, at least control a vehicle to react to the concealed object and / or present information regarding the concealed object to a user.

Description

INTRODUCTION

[0001] This disclosure relates to the field of vehicle perception. In particular, this disclosure relates to systems and methods for monitoring vehicle environments and for controlling a vehicle perception system based on the detection of detected objects.

[0002] Vehicles are increasingly equipped with sensors and perception devices that enhance the situational awareness of vehicle control systems and drivers, thereby supporting autonomous driving and / or driver assistance. For example, vehicles can feature autonomous and / or semi-autonomous driving modes, such as fully autonomous driving and automated control of certain functions (e.g., parking assist, automated steering during highway driving, brake assist, etc.). Perception systems should be capable of detecting a wide variety of dynamic situations and objects. Improving aspects of object detection and response to dynamic events is desirable. SUMMARY

[0003] According to an exemplary embodiment, a system for monitoring a vehicle's environment comprises a perception system that communicates with a vehicle sensor, wherein the perception system is configured to receive perception data from the vehicle sensor. The system also comprises a scenario detection module configured to detect a first object based on the perception data and to analyze the behavior of the first object in order to predict whether a detection scenario occurs or will occur, in which a concealed object is revealed. The system further comprises a control module configured to perform at least one control operation of a vehicle to react to the concealed object and / or to present information regarding the concealed object to a user, based on the detection of the concealed object as the revealed object.

[0004] In addition to one or more of the features described herein, the perception system is designed to operate in a normal detection mode and a modified detection mode, with object detection in the normal detection mode being performed on the basis of a normal set of criteria and object detection in the modified detection mode being performed on the basis of a modified set of criteria, and the scenario detection module being designed to cause the perception system to switch from the normal detection mode to the modified detection mode based on the prediction that the detection scenario occurs or will occur.

[0005] In addition to one or more of the features described here, the normal detection mode specifies that the perception system performs object detection based on an initial number of detection modalities, and the modified detection mode specifies that the perception system performs object detection based on a reduced number of detection modalities, the reduced number being smaller than the initial number.

[0006] In addition to one or more of the features described here, a first delay is assigned to the normal detection mode and a second delay is assigned to the modified detection mode, the second delay being shorter than the first delay.

[0007] In addition to one or more of the features described here, the scenario detection module is designed to predict, based on a maneuver performed by the first object, that the detection scenario occurs or will occur.

[0008] In addition to one or more of the features described here, the first object is a vehicle traveling ahead of the vehicle, the concealed object is a third vehicle in front of the vehicle traveling ahead, and the maneuver is an aggressive maneuver performed by the first object.

[0009] In addition to one or more of the features described here, the scenario detection module is designed to predict, based on a classification of behavior according to a machine learning model, that the detection scenario occurs or will occur.

[0010] In addition to one or more of the features described here, the first object is a vehicle driving ahead of the vehicle, and the machine learning model is designed to determine whether the behavior is classified as an aggressive maneuver.

[0011] In addition to one or more of the features described herein, the perception system is designed to perform object detection according to a normal detection mode and a modified detection mode, wherein the normal detection mode is associated with a first delay, the modified detection mode is associated with a second delay that is shorter than the first delay, and the scenario detection module is designed to cause the perception system to operate in the modified detection mode based on determining that the behavior is classified as an aggressive maneuver.

[0012] According to a further embodiment, a method for monitoring a vehicle's environment comprises: receiving perception data from a vehicle sensor of a vehicle's perception system, detecting a first object in the environment around the vehicle based on the perception data, and analyzing the behavior of the first object to predict whether a detection scenario occurs or will occur, wherein a concealed object is revealed in the detection scenario. The method further comprises, based on the prediction that the detection scenario occurs or will occur, and based on the detection of the concealed object as the revealed object, executing a control action of the vehicle to react to the concealed object and presenting information regarding the concealed object to a user.

[0013] In addition to one or more of the features described here, the perception system is designed to operate in a normal detection mode and a modified detection mode, wherein in the normal detection mode object detection is performed on the basis of a normal set of criteria and in the modified detection mode object detection is performed on the basis of a modified set of criteria.

[0014] In addition to one or more of the features described here, the procedure includes initiating, based on the prediction that the detection scenario occurs or will occur, that the perception system switches from the normal detection mode to the modified detection mode.

[0015] In addition to one or more of the features described here, the normal detection mode specifies that the perception system performs object detection based on an initial number of detection modalities, and the modified detection mode specifies that the perception system performs object detection based on a reduced number of detection modalities, the reduced number being smaller than the initial number.

[0016] In addition to one or more of the features described here, the prediction of whether the detection scenario occurs or will occur is based on a maneuver performed by the first object.

[0017] In addition to one or more of the features described here, predicting whether the detection scenario occurs or will occur is based on classifying the behavior according to a machine learning model.

[0018] In addition to one or more of the features described here, the first object is a vehicle driving ahead of the vehicle, and the machine learning model is designed to determine whether the behavior is classified as an aggressive maneuver.

[0019] According to a further embodiment, a vehicle system comprises a perception system that communicates with a vehicle sensor, wherein the perception system is designed to receive perception data from the vehicle sensor and to perform object detection. The perception system is designed to operate in a normal detection mode and a modified detection mode, wherein object detection in the normal detection mode is performed based on a normal set of criteria and object detection in the modified detection mode is performed based on a modified set of criteria.The vehicle system also includes a scenario detection module designed to detect an initial object based on perception data and analyze the behavior of that initial object to predict whether a detection scenario is occurring or will occur, in which a concealed object is revealed. Based on the prediction that the detection scenario is occurring or will occur, the scenario detection module is designed to cause the perception system to switch from normal detection mode to modified detection mode.

[0020] In addition to one or more of the features described here, the normal detection mode specifies that the perception system performs object detection based on an initial number of detection modalities, and the modified detection mode specifies that the perception system performs object detection based on a reduced number of detection modalities, the reduced number being smaller than the initial number.

[0021] In addition to one or more of the features described here, the scenario detection module is designed to predict, based on a maneuver performed by the first object, whether the detection scenario occurs or will occur.

[0022] In addition to one or more of the features described here, the scenario detection module is designed to predict whether the detection scenario occurs or will occur, based on a classification of behavior according to a machine learning model.

[0023] The features and advantages mentioned above, as well as further features and advantages of the disclosure, are readily apparent from the following detailed description in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Further features, advantages and details are listed only as examples in the following detailed description, which refers to the drawings; they show: Fig. 1 a schematic top view of a motor vehicle according to an exemplary embodiment; Fig. 2. An example of a situation in which a disclosure scenario may occur; Fig. 3. An example of a detection scenario in which a target performs an aggressive maneuver that results in the detection of another object; Fig. 4 a flowchart illustrating aspects of a method for detecting uncovered objects according to an exemplary embodiment; and Fig. 5 a computer system according to an exemplary embodiment. DETAILED DESCRIPTION

[0025] The following description is merely exemplary and is not intended to limit the present disclosure, its application, or its uses. It should be noted that in the drawings, the same reference numerals consistently denote the same or corresponding parts and features.

[0026] According to one or more exemplary embodiments, methods and systems are created for monitoring and detecting or predicting detected objects. A "detected object" is an object that is detected (i.e., observed in a projected lane of a vehicle) or whose detection is predicted, such that the vehicle's perception system cannot normally detect the object in time for the vehicle to react to the object (e.g., avoid the object entirely or at least reduce the damage).

[0027] One embodiment of a system is designed to monitor a vehicle's surroundings while driving and analyze perceptual data to predict whether a detection scenario will occur. The detection scenario can be predicted using a machine learning classifier to classify objects, object maneuvers, and other features of the environment. According to one embodiment, based on the prediction of a detection scenario, the system causes the perception system to switch from a normal operating mode to a modified operating mode. In the modified operating mode, the perception system is designed to detect objects based on a modified set of criteria, enabling the perception system to uniquely identify objects in a shorter time than if the perception system were operating in normal mode.

[0028] The embodiments described here offer a number of advantages. For example, they improve the detection capabilities and the ability of a vehicle or driver to cope with dynamic conditions. Furthermore, they enhance a vehicle's perception system, particularly in situations where uncertainties in perception could lead to a lack of detection.

[0029] Systems in autonomous and manually driven vehicles, such as adaptive cruise control (ACC) systems, rely on radar and cameras to detect and track objects, but radar uncertainties can lead to false detections or missed objects. These uncertainties are even more pronounced with detected objects. Consequently, it can take longer for perception systems to confirm the detection of an object. Such a delay could leave the vehicle or driver with insufficient time to react effectively to a detected object.

[0030] The embodiments described here address such limitations by providing a robust detection algorithm for detected objects. This algorithm employs a systematic approach to mitigate the effects of radar uncertainty by utilizing surrounding objects and features to intelligently infer the presence of objects based on their detected impact on the environment, thus enabling the timely detection of detected objects. These embodiments facilitate object detection in detection scenarios and other challenging situations, such as poor visibility or when objects are partially obscured.

[0031] Fig. Figure 1 shows an embodiment of a motor vehicle 10 comprising a vehicle body 12 that at least partially defines a passenger compartment 14. The vehicle body 12 also carries various vehicle subsystems, including a drive system 16 and other subsystems for supporting the functions of the drive system 16 and other vehicle components, such as a brake subsystem, a suspension system, a steering subsystem, and, if it is a hybrid electric vehicle, a fuel injection subsystem, an exhaust subsystem, and others.

[0032] The vehicle 10 can be a vehicle with an internal combustion engine, an electrically powered vehicle (EV), or a hybrid vehicle. According to one embodiment, the vehicle 10 is a hybrid vehicle comprising an internal combustion engine system 18 and at least one electric motor 20. The vehicle 10 can also be a fully electric vehicle with one or more electric motors.

[0033] The drive system 16 comprises various other components, such as a transmission system 22 for applying torque to a front drive shaft 24 connected to front wheels 26. The drive system 16 is not limited to this. For example, the drive system 16 may include components (e.g., a transmission, the motor 20, and / or an additional motor) for driving a rear drive shaft 28 connected to the rear wheels 30.

[0034] The vehicle 10 also includes various control devices for controlling aspects of the vehicle's operation. Such devices include, for example, an accelerator pedal 32, a steering wheel 34, front brakes 36, and rear brakes 38.

[0035] The vehicle also includes a perception system and a vehicle control system, aspects of which may be integrated into or connected to the vehicle 10. The perception system receives perception data (e.g., images) from various sensors, which may represent different types of detection modalities. According to one embodiment, the sensors include one or more optical cameras 40 designed to capture images, which may be still images and / or video images. Additional devices or sensors, such as one or more radar arrays 42, may be included in the vehicle 10. The perception system is not limited to this and may include other types of sensors, such as lidar, infrared cameras, microphones, and others.

[0036] Control devices and actuators, as well as other components such as the monitoring system, can be controlled via one or more control units, which are collectively represented by a vehicle controller 44. The vehicle controller 44 includes processing components for controlling aspects of vehicle operation, such as the control of the drive, braking, and steering, as well as functions such as monitoring and path planning.

[0037] The vehicle controller 44 can be designed to control the vehicle 10 according to various forms of automated control. According to one embodiment, the vehicle controller 44 is designed for one or more levels of automation, such as automation level 1, automation level 2, and / or automation level 3. Automation level 1 includes driver assistance. Automation level 2 enables vehicle control of steering and acceleration, with the driver being monitored and ready to take over control at any time. In automation level 3 (conditional automation), a vehicle can monitor its surroundings and automatically control its operation.

[0038] According to one embodiment, the perception system comprises a monitoring unit 46 designed to receive data from perception devices such as optical cameras 40 and radar arrays 42. The monitoring unit 46 is designed to detect objects and situations in the environment surrounding the vehicle and to provide object detection information to the driver and / or the vehicle controller 44. For example, the monitoring unit 46 can present object detection and vehicle trajectory information to the driver via an on-board computer system 50 and / or an infotainment system (e.g., as a graphic and / or textual display).

[0039] The monitoring unit 46 includes, or is connected to, a scenario detection module 48 designed to detect or predict scenarios associated with increased uncertainty. Such scenarios may include any environmental conditions or features that increase uncertainty, such as poor visibility scenarios and discovery scenarios. According to one embodiment, the scenario detection module 48 is designed to detect or predict a discovery scenario. Discovery scenarios can be predicted using a machine learning model 47, as further described herein.

[0040] A "detection scenario" is a scenario in which an object (which may have been previously obscured or partially obscured) appears in a projected path of vehicle 10, so that vehicle 10 may have to react to avoid a collision or other unintended consequences. In a detection scenario, the perception system may also not be able to positively detect the object in a normal way (i.e., in a normal detection mode) before vehicle 10 may have to react. This would require the use of normal criteria, such as the requirement that multiple modalities be used to detect and confirm the presence of the object.

[0041] As further explained here, the Scenario Detection Module 48 is designed to predict that a detection scenario is occurring or imminent and to instruct the perception system to transition to a detection mode of operation (referred to as the "modified detection mode") that is less stringent or robust than the normal mode of operation. In the modified detection mode, the perception system can analyze perception data more quickly and detect detected objects because the criteria for detecting an object are relaxed in the modified detection mode compared to the normal detection mode.

[0042] In this way, a normal delay that occurs due to a prescribed set of criteria ("normal criteria") in normal detection mode can be reduced to enable faster detection. For example, in normal detection mode, the perception system must analyze both optical images and radar images (or another group of multiple detection modalities). In the modified detection mode, the perception system may only need to use one or fewer modalities (e.g., optical images or radar images) and can therefore determine in a shorter time whether an object is detected.

[0043] The vehicle 10, the monitoring system, the vehicle controller 44, and other vehicle systems are contained in or connected to an on-board computer system 50, which includes one or more processing devices 52 and a user interface 54. The user interface 54 may include a touchscreen, a voice recognition system, and / or various buttons through which a user can interact with functions of the vehicle. The user interface 54 may be designed to interact with a user or driver via visual communication (e.g., text and / or graphic displays), tactile communication or warnings (e.g., vibration), and / or acoustic communication.

[0044] Fig. Figure 2 shows an example of a situation in which a detection scenario could occur. At an initial time t1 (a "current time"), vehicle 10 is traveling on lane 60, for example, a highway. The lane comprises lanes 62 and 64, and vehicle 10 is currently traveling in lane 62. Another vehicle 66 ("ahead vehicle") is traveling in lane 62 ahead of vehicle 10. Furthermore, a third vehicle 68 is traveling in lane 62 ahead of vehicle 66. At the initial time t1, the third vehicle 68 is at least partially obscured from the view of vehicle 10.

[0045] At a second time point t2, the vehicle 66 ahead may decide to maneuver into lane 64. The maneuver may be a relatively gradual one, allowing the vehicle 10's perception system to detect the third vehicle 68 in a normal detection mode. However, if the maneuver is abrupt or aggressive, the perception system may not be able to detect the third vehicle 68 quickly enough to warn vehicle 10 and / or the operator, and to give vehicle 10 sufficient time to react appropriately and effectively avoid the third vehicle 68.

[0046] Fig. Figure 3 shows an example of a maneuver performed by a detected object and associated with a detection scenario. According to this example, the vehicle 66 ahead performs an aggressive evasive maneuver (indicated by arrow 70), in which the vehicle 66 makes an abrupt lane change to avoid or overtake the concealed vehicle 68. In one embodiment, the scenario detection module 48 analyzes the dynamic behavior of the vehicle ahead and determines whether the maneuver is classified as an "aggressive maneuver" (e.g., using a classifier or other machine learning model).

[0047] Fig. Figure 4 shows an embodiment of a method 80 for monitoring a vehicle environment. The method 80 is explained in conjunction with blocks 81-85. The method 80 is not limited to the number or sequence of steps it contains, since some of the steps represented by blocks 81-85 may be performed in a different sequence than that described below, or fewer than all of the steps may be performed.

[0048] Procedure 80 is used in conjunction with vehicle 10. Fig. 1 and the scenario detection module 48, but is not limited to this and can be performed by any suitable processing device or combination of processing devices (e.g. the computer system 50, the monitoring unit 46 or a combination thereof).

[0049] Furthermore, procedure 80 is described with reference to the provisions set out in the Fig. 2 and Fig. The situation shown in Figure 3 and the scenario depicted therein are explained. Procedure 80 is not limited to this and can be used in any situation where a previously concealed or undetected object is revealed.

[0050] In Block 81, the perception system monitors the environment during vehicle operation in a normal detection mode and detects one or more objects. The normal detection mode includes an identification procedure that prescribes functions such as inputting image data into a machine learning model (e.g., a deep neural network (DNN)) and identifying objects in the environment.

[0051] Normal detection mode may require the use of multiple modalities to identify an object. For example, in normal detection mode, the perception system uses both optical images from one or more cameras 40 and radar images from one or more radar arrays 42 for object identification. A data fusion process may be performed in combination with other processes (e.g., object classification) to detect an object. For example, the monitoring unit 46 receives optical and radar images and detects that the vehicle 66 is traveling ahead.

[0052] Vehicle 10 can be operated manually, autonomously, or semi-autonomously. For example, object detection information can be supplied to an autonomous control system or used for semi-autonomous control such as adaptive cruise control (ACC). Additionally or alternatively, information about the environment is presented to a user (e.g., the driver), for example, on a touchscreen or a head-up display.

[0053] In Block 82, the Scenario Detection Module 48 collects historical data relating to the trajectory and behavior of a detected object (i.e., an object detected via the normal detection mode). This historical data is used to predict the trajectory of the detected object. The historical data can consist of recorded observations of the object (and / or objects of a similar type and / or objects in similar environments). The observations include one or more behaviors associated with a specific maneuver or action of the object.

[0054] The object's behavior can be predicted by comparing its detected behaviors with past behaviors. In one embodiment, a machine learning model is used to predict the detected object's trajectory.

[0055] For example, the perception system monitors the vehicle 66 ahead and identifies various behaviors, such as changes in speed and direction, and determines which behaviors of the vehicle 66 ahead are aggressive maneuvers or other behaviors that are associated with detection scenarios. For example, trajectories from previous observations are used for comparison.

[0056] In block 83, the scenario detection module 48 determines whether the observed behavior indicates a detection scenario. In a detection scenario, the uncertainties associated with the detection modalities can be relatively high, which can lead to a corresponding delay. In a normal detection mode, the delay may be due to increased processing time to reduce or minimize false positive results.

[0057] The observed behavior can be compared with stored behaviors in a lookup table (or other data structure) to determine whether the observed behavior indicates a discovery scenario. According to one embodiment, a machine learning model is used to learn behaviors associated with discovery scenarios, and perceptual data is fed into the model to identify behaviors that correspond to a discovery scenario.

[0058] For example, the scenario detection module 48 performs a maneuver evaluation in which perceptual data is fed into a trained machine learning model, such as a classifier. Various criteria can be used to classify behavior, such as kinematic and dynamic analyses of the vehicle ahead 66 and / or any other observations. For example, semantic cues, such as whether the brake lights are on, observed movements of the driver of the vehicle ahead (which might indicate, for example, nervousness), road features (e.g., solid or dashed center lines), traffic signs, and others can be used.

[0059] If the detected behavior in block 84 is classified into a category that is associated with a detection scenario, the scenario detection module 48 determines that a detection scenario exists and that a hidden object may be detected.

[0060] In Block 85, the perceptual system is adapted based on the determination to modify one or more criteria for object detection. This adaptation allows the perceptual system to make a positive object identification in a shorter time than if it were using normal criteria. Although changing the criteria may decrease the reliability of detection, the perceptual system can detect a hidden object more quickly.

[0061] After entering the modified detection mode, the perception system monitors the vehicle's surroundings and performs object detection using the adapted criteria. If a detected object (e.g., the third vehicle 68 from Fig. 2 and Fig. 3) If an object is detected, the vehicle can be controlled autonomously or semi-autonomously to react to the detected object. Additionally or alternatively, information about the detected object is presented to a user or driver.

[0062] According to one embodiment, the scenario detection module 48 causes the monitoring unit 46 to switch the perception system from the normal detection mode to a modified detection mode in response to the prediction of a detection scenario. In the modified detection mode, the criteria used for object detection are modified. Specifically, the detection criteria are less stringent in the modified detection mode, allowing the monitoring unit 46 to perform object detection in a shorter time.

[0063] According to one embodiment, the normal detection mode requires the perception system to perform object detection based on an initial set of detection modalities. The modified detection mode allows object detection using a reduced number of detection modalities.

[0064] For example, the perception system uses Fig. 1 In normal detection mode, both optical images from one or more cameras 40 and radar images from one or more radar arrays 42 are used for object identification. A data fusion process can be performed in combination with other processes (e.g., object classification) to detect an object. If the vehicle 66 ahead performs a lane change in the normal manner, so that the third vehicle 68 is visible, but vehicle 10 has time to react, the perception system detects the third vehicle according to normal detection mode.

[0065] However, if a detection scenario is predicted, the perception system switches to the modified detection mode and performs object detection. The third vehicle, number 68, is detected only using optical or radar images.

[0066] According to one embodiment, the perception system is switched to the modified detection mode by adjusting (e.g., reducing or setting to zero) one or more weights assigned to one or more modalities. For example, when the perception system is in the modified detection mode, a weight assigned to the optical image data or radar data is set to zero or reduced. Because detection can be performed faster (in the modified detection mode), the driver and / or the vehicle can react more quickly than when using the normal detection mode.

[0067] In addition to adjusting the object detection criteria, Procedure 80 can include one or more other actions. For example, the user can be presented with information about the environment, detected objects, and / or the detection scenario. For instance, the driver can be informed that the perception system has switched to the modified detection mode, that a previously concealed object has been detected, and / or that a detection scenario has been identified. Other information can include trajectory and object information, for example, in a graphical display.

[0068] The vehicle 10 can be controlled autonomously or to assist the driver. For example, the vehicle controller 44 controls the vehicle 10 to perform an evasive maneuver, or a driver assistance system is activated.

[0069] Fig.Figure 5 shows aspects of an embodiment of a computer system 140 that can perform various aspects of the embodiments described herein. The computer system 140 comprises at least one processing device 142, which generally includes one or more processors for performing aspects of the image acquisition and analysis methods described herein.

[0070] Components of the computer system 140 include the processing device 142 (such as one or more processors or processing units), a memory 144, and a bus 146 that connects various system components, including the system memory 144, to the processing device 142. The system memory 144 can be a non-transient, computer-readable medium and may comprise multiple computer-readable media. Such media may be any available media accessible to the processing device 142 and may include both volatile and non-volatile media, as well as removable and non-removable media.

[0071] For example, system memory 144 includes non-volatile memory 148, such as a hard disk, and may also include volatile memory 150, such as random access memory (RAM) and / or cache memory. The computer system 140 may further include other removable / non-removable, volatile / non-volatile computer system storage media.

[0072] The system memory 144 can comprise at least one program product with a set of (e.g., at least one) program modules designed to execute functions of the embodiments described herein. For example, the system memory 144 stores various program modules that generally execute the functions and / or methods of the embodiments described herein. One or more modules 152 may be included to execute the functions described herein. The system 140 is not limited to this, as other modules may be included.As used here, the term "module" refers to a processing circuit arrangement that may include an application-specific integrated circuit (ASIC), an electronic circuit, a processor (shared, dedicated or in a group) and memory that executes one or more software or firmware programs, a combinational logic circuit and / or other suitable components that provide the described functionality.

[0073] The processing device 142 can also communicate with one or more external devices 156, such as a keyboard, a pointing device, and / or any other devices (e.g., network card, modem, etc.), which enable the processing device 142 to communicate with one or more other computing devices. Communication with various devices can take place via input / output interfaces (I / O interfaces) 164 and 165.

[0074] The processing device 142 can also communicate via a network adapter 168 with one or more networks 166, such as a local area network (LAN), a wide area network (WAN), a bus network, and / or a public network (e.g., the Internet). It should be noted that other hardware and / or software components, not shown here, can also be used in conjunction with the computer system 140. Examples include, but are not limited to: microcode, device drivers, redundant processing units, external hard disk drive arrays, RAID systems, and data archiving systems, etc.

[0075] The terms "a / r / s" do not imply a quantity restriction, but rather the presence of at least one of the mentioned elements. The term "or" means "and / or" unless the context clearly indicates otherwise. References to "an aspect" throughout the description mean that a specific element (e.g., a feature, structure, step, or property) described in connection with that aspect is contained in at least one aspect described here and may or may not be present in other aspects. Furthermore, it is important to understand that the described elements can be combined in any suitable way across the various aspects.

[0076] When an element such as a layer, film, area, or substrate is described as being "on" another element, it may be located directly on top of the other element, or there may be intervening elements. Conversely, when an element is described as being "directly on" another element, there are no intervening elements.

[0077] Unless otherwise stated herein, all testing standards are the latest standards in force at the time of filing this application or, if priority is claimed, the standards in force at the time of filing the earliest priority application in which the testing standard appears.

[0078] Unless otherwise defined, the technical and scientific terms used herein have the same meanings as generally understood by experts in the field to which this disclosure relates.

[0079] Although the foregoing disclosure has been described with reference to exemplary embodiments, it will be clear to those skilled in the art that various modifications can be made and elements replaced by equivalents without departing from the scope of the disclosure. Furthermore, many adaptations can be made to fit a particular situation or material to the teachings of the disclosure without deviating from its essential scope. Therefore, the present disclosure is not intended to be limited to the disclosed embodiments but to encompass all embodiments that fall within its scope.

Claims

[1] System for monitoring a vehicle environment, comprising: a perception system that communicates with a vehicle sensor, wherein the perception system is designed to receive perception data from the vehicle sensor; a scenario detection module designed to detect a first object based on perception data and to analyze the behavior of the first object to predict whether a detection scenario occurs or will occur, revealing a concealed object in the detection scenario; and a control module designed to control a vehicle in order to react to the hidden object, and / or to present information regarding the hidden object to a user, based on the detection of the hidden object as a revealed object. [2] System according to claim 1, wherein the perception system is designed to operate in a normal detection mode and a modified detection mode, object detection in the normal detection mode is performed on the basis of a normal set of criteria, object detection in the modified detection mode is performed on the basis of a modified set of criteria, and the scenario detection module is designed to cause the perception system to switch from the normal detection mode to the modified detection mode based on the prediction that the detection scenario occurs or will occur. [3] System according to claim 2, wherein the normal detection mode requires that the perception system performs object detection based on a first number of detection modalities, and the modified detection mode requires that the perception system performs object detection based on a reduced number of detection modalities, wherein the reduced number is smaller than the first number. [4] System according to claim 2, wherein a first delay is assigned to the normal detection mode and a second delay is assigned to the modified detection mode, wherein the second delay is smaller than the first delay. [5] System according to claim 1, wherein the scenario detection module is designed to predict, on the basis of a maneuver performed by the first object, that the detection scenario occurs or will occur. [6] System according to claim 5, wherein the first object is a vehicle traveling ahead of the vehicle, the concealed object is a third vehicle in front of the vehicle traveling ahead, and the maneuver is an aggressive maneuver performed by the first object. [7] System according to claim 1, wherein the scenario detection module is designed to predict, based on the classification of behavior according to a machine learning model, that the detection scenario occurs or will occur. [8] System according to claim 7, wherein the first object is a vehicle traveling ahead of the vehicle and the machine learning model is designed to determine whether the behavior is classified as an aggressive maneuver. [9] System according to claim 8, wherein the perception system is designed to perform object detection according to a normal detection mode and a modified detection mode, wherein the normal detection mode is associated with a first delay, the modified detection mode is associated with a second delay which is shorter than the first delay, and the scenario detection module is designed to cause the perception system to operate in the modified detection mode based on determining that the behavior is classified as an aggressive maneuver. [10] Methods for monitoring a vehicle environment, comprising: Receiving perception data from a vehicle sensor of a vehicle's perception system; Detecting a first object in an environment around the vehicle based on perception data; Analyzing the behavior of the first object to predict whether a disclosure scenario occurs or will occur, revealing a hidden object in the disclosure scenario; and based on the prediction that the detection scenario occurs or will occur, and based on the detection of the concealed object as a detected object, performing a control of the vehicle to react to the concealed object, and / or presenting information regarding the concealed object to a user.

Images