Sensor output confidence adjustment apparatus and sensor output confidence adjustment method

Abstract

Disclosed are a sensor output confidence level adjustment device and a sensor output confidence level adjustment method. The sensor output confidence level adjustment device includes: a sensor information acquisition unit that acquires information about different types of sensors; a sensor consistency determination unit that determines consistency between the different types of sensors based on the information about the different types of sensors; a driving environment determination unit that determines a driving environment of a vehicle when the consistency between the different types of sensors is lower than a reference value; and a confidence level adjustment unit that determines the applicability of a confidence level of the different types of sensors based on the consistency between the different types of sensors and the driving environment, and adjusts the confidence level of the different types of sensors again based on this.

Description

Technical Field

[0001] This invention relates to a sensor output confidence adjustment device, and more specifically, to a sensor output confidence adjustment device and method for adjusting sensor output confidence using context information. Background Technology

[0002] Recently developed vehicle sensors not only provide information about the physical state of the object being detected, such as its position and velocity, but also provide information indicating the state of the sensor's output.

[0003] For example, information indicating the output status of a sensor may include: Age, which indicates how much time has passed since the sensor output was generated; status, which indicates whether the output was generated by estimating a pre-established motion model without actually measuring the object, or by actually measuring the object; and confidence level, which takes into account various factors.

[0004] Confidence level is one of the most important pieces of information because it is directly related to whether or not the provided sensor output is used.

[0005] Sensor manufacturers design output information using different methods. However, generally speaking, confidence level is intended to indicate the reliability, validity, and relevance of sensor output.

[0006] Typically, vehicle manufacturers use sensor output information within limits associated with its confidence level.

[0007] However, in some cases, despite the high accuracy of the sensor output, its applicability to the system using the sensor may be limited.

[0008] Therefore, there is a need to develop a sensor output confidence adjustment device that uses contextual information to adjust the confidence level of the sensor output, in order to improve the accuracy of the sensor output and the applicability of the system using the sensor.

[0009] The information contained in the background section of this invention is only intended to facilitate an understanding of the general background of this invention and should not be construed as an admission or in any way implying that such information constitutes prior art known to those skilled in the art. Summary of the Invention

[0010] Various aspects of the present invention aim to provide a sensor output confidence adjustment device and a sensor output confidence adjustment method that substantially eliminate one or more problems caused by the limitations and disadvantages of related technologies.

[0011] This invention provides a sensor output confidence adjustment device and a sensor output confidence adjustment method. The device and method are configured to readjust the confidence of different types of sensors based on the consistency between different types of sensors and the driving environment of the vehicle, thereby improving the performance and stability of the sensor fusion system.

[0012] However, the objectives to be achieved by the exemplary embodiments are not limited to those described above, and other objectives not mentioned herein will be clearly understood by those skilled in the art through the following description.

[0013] To achieve the above and other objectives, a sensor output confidence adjustment device according to various exemplary embodiments of the present invention may include: a sensor information acquisition unit configured to acquire information about different types of sensors; a sensor consistency judgment unit configured to judge the consistency between different types of sensors based on the information about different types of sensors; a driving environment judgment unit configured to judge the driving environment of the vehicle when the consistency between different types of sensors is lower than a reference value; and a confidence adjustment unit configured to judge the applicability of the confidence of different types of sensors based on the consistency between different types of sensors and the driving environment, and readjust the confidence of different types of sensors accordingly.

[0014] Furthermore, the sensor output confidence adjustment method according to various exemplary embodiments of the present invention is a method for determining the applicability of the sensor output confidence of a sensor output confidence adjustment device. The sensor output confidence adjustment device includes a sensor information acquisition unit, a sensor consistency judgment unit, a driving environment judgment unit, and a confidence adjustment unit. The sensor output confidence adjustment method may include: the sensor information acquisition unit acquiring information about different types of sensors; the sensor consistency judgment unit judging the consistency between different types of sensors based on the information about the different types of sensors; when the consistency between different types of sensors is lower than a reference value, the driving environment judgment unit judging the driving environment; and the confidence adjustment unit judging the applicability of the confidence of different types of sensors based on the consistency between different types of sensors and the driving environment, and readjusting the confidence of different types of sensors accordingly.

[0015] Furthermore, the computer-readable recording medium according to various exemplary embodiments of the present invention records a program for executing a sensor output confidence adjustment method of a sensor output confidence adjustment device, and can execute the process of the sensor output confidence adjustment method of the sensor output confidence adjustment device.

[0016] Furthermore, a vehicle according to various exemplary embodiments of the present invention may include: different types of sensors configured to sense the vehicle's driving environment; and a sensor output confidence adjustment device configured to determine the applicability of the confidence levels of different types of sensors and readjust the confidence levels of different types of sensors accordingly, wherein the sensor output confidence adjustment device may be configured to: acquire information about different types of sensors; determine the consistency between different types of sensors based on the information about different types of sensors; determine the driving environment when the consistency between different types of sensors is lower than a reference value; determine the applicability of the confidence levels of different types of sensors based on the consistency between different types of sensors and the driving environment, and readjust the confidence levels of different types of sensors accordingly.

[0017] The methods and apparatus of the present invention have other features and advantages, which will become apparent or are set forth in more detail in the accompanying drawings, which, together with the following detailed description, serve to explain certain principles of the invention. Attached Figure Description

[0018] Figure 1 The figure shows a vehicle including a sensor output confidence adjustment device according to various exemplary embodiments of the present invention.

[0019] Figure 2 This is a block diagram illustrating the configuration of a sensor output confidence adjustment device according to various exemplary embodiments of the present invention.

[0020] Figure 3 This is a flowchart illustrating a sensor output confidence adjustment method according to various exemplary embodiments of the present invention; and

[0021] Figure 4 and Figure 5 This is a diagram illustrating the process of adjusting the confidence level based on the vehicle's driving environment.

[0022] It is understood that the accompanying drawings are not necessarily drawn to scale and present slightly simplified representations of various features illustrating the basic principles of the invention. Specific design features of the invention included herein, including, for example, specific dimensions, orientations, positions, and shapes, will be determined in part by the particular intended application and environment of use.

[0023] In the accompanying drawings, reference numerals refer to the same or equivalent parts of the invention. Detailed Implementation

[0024] Reference will now be made in detail to various embodiments of the invention, examples of which are shown in the accompanying drawings and described below. Although the invention will be described in conjunction with exemplary embodiments thereof, it should be understood that this description is not intended to limit the invention to those exemplary embodiments. On the other hand, the invention is intended to cover not only the exemplary embodiments thereof, but also various alternatives, modifications, equivalents and other embodiments that may be included within the spirit and scope of the invention as defined in the appended claims.

[0025] The embodiments will now be described in detail with reference to the accompanying drawings to enable those skilled in the art to readily implement them. However, these embodiments may be embodied in many different forms and should not be construed as being limited to the embodiments set forth herein. In the drawings, for clarity, portions unrelated to the description of the invention will be omitted. Throughout the specification, the same reference numerals refer to the same elements.

[0026] Throughout the specification, when a section "comprises" or "includes" a component, this does not exclude other components, which may be further included unless otherwise stated. The terms "-section," "-unit," and "-module" in the specification refer to a unit that performs at least one function or operation, and can be implemented as a hardware component, a software component, or a combination of hardware and software components.

[0027] In the following text, reference will be made to Figure 1 , Figure 2 , Figure 3 , Figure 4 and Figure 5 The sensor output confidence adjustment apparatus and sensor output confidence adjustment method applicable to exemplary embodiments are described in detail.

[0028] Figure 1 The figure shows a vehicle including a sensor output confidence adjustment device according to various exemplary embodiments of the present invention.

[0029] like Figure 1 As shown, the vehicle may include different types of sensors 10 for sensing the vehicle's driving environment, a sensor fusion system 20, and a judgment / control system 30.

[0030] Here, the sensor output confidence adjustment device according to the exemplary embodiment can be applied to the sensor fusion system 20 necessary for realizing the driver assistance system and the autonomous driving system.

[0031] The sensor fusion system 20 may include a preprocessing unit 210, a sensor data association unit 220, a data fusion unit 230, a tracking unit 240, and a management unit 250.

[0032] In this case, the sensor output confidence adjustment device according to the exemplary embodiment can be applied to the preprocessing unit 210 that performs reprocessing and redefinition on the information output from the sensor.

[0033] Therefore, the sensor output confidence level adjustment device according to the exemplary embodiment can readjust the output confidence level of the sensor, which is one of the inputs of the sensor fusion system, thereby improving the performance and stability of the sensor fusion system.

[0034] According to an exemplary embodiment of the present invention, when multiple sensors detect the same object simultaneously, the output confidence of each sensor can be readjusted by taking into account the different facts such as the position, velocity, and output confidence of the sensor tracks.

[0035] Here, the differences in sensor output are not only caused by the differences in sensor performance and characteristics, but also by the contextual information based on the vehicle's driving environment and vehicle condition. Therefore, the confidence information of the sensor output can be corrected based on this.

[0036] In this context, the sensor trajectory can include motion information detected by the sensor, such as the position and velocity of an object, as well as various other information. This other information may include object classification performed by the sensor, the age of the trajectory, and the confidence level.

[0037] The sensor output confidence adjustment device according to the exemplary embodiment can acquire information about different types of sensors and determine the consistency between different types of sensors based on the information about different types of sensors. Furthermore, when the consistency between different types of sensors is lower than a reference value, the sensor output confidence adjustment device according to the exemplary embodiment can determine the vehicle's driving environment, determine the applicability of the confidence levels of different types of sensors based on the consistency between different types of sensors and the vehicle's driving environment, and readjust the confidence levels of different types of sensors accordingly.

[0038] According to an exemplary embodiment of the present invention, sensors can be classified into high-reliability sensors and low-reliability sensors based on information that can be obtained in advance, such as the detection accuracy trend according to the sensor type, the detection area, and the driving environment and conditions of the vehicle.

[0039] Regarding the trend of detection accuracy based on sensor type, cameras generally have better lateral position detection accuracy than radar sensors, but lower longitudinal position detection accuracy and may be sensitive to brightness.

[0040] The detection area can vary depending on the sensor specifications and installation location. The vehicle's driving environment and conditions can be related to information such as road curvature, targets, and the vehicle's heading.

[0041] According to an exemplary embodiment of the present invention, some information about a low-reliability sensor can be redefined based on consistency with a high-reliability sensor.

[0042] According to an exemplary embodiment of the present invention, the consistency between sensors can be determined by the following equation based on position and velocity information.

[0043]

[0044] in

[0045]

[0046] here, The vector representing the measurement value of sensor X at time point k, {x X ,y X}and This indicates the longitudinal and lateral positions of the target object relative to the sensors installed in the vehicle, as well as its longitudinal and lateral velocities. This represents the standard deviation of the position and velocity errors. γ represents the design variable and can be determined from the p-value of the chi-square distribution.

[0047] The above equation is typically used in data association methods to determine the correlation between estimated and measured values. In an exemplary embodiment of the present invention, the above equation can be used to determine the consistency between different types of sensors.

[0048] For example, according to an exemplary embodiment of the present invention, when a high-reliability sensor is represented by "A" and a low-reliability sensor is represented by "B", the output confidence of sensor B can be readjusted based on the consistency between sensor A and sensor B.

[0049] The exemplary embodiments may also consider the following situations.

[0050] When there is a first case where the position / velocity consistency between sensor A and sensor B is high, and a second case where the position / velocity consistency between sensor A and sensor B is low, the output confidence of sensor A can have a sufficiently high value because sensor A is assumed to be a high-reliability sensor.

[0051] In the first case, the physical information between the two sensors is highly consistent, and the output confidence level of sensor B can be readjusted to the same level as the output confidence level of sensor A.

[0052] In the second scenario, the consistency of physical information between the two sensors is low, indicating whether the vehicle is in a driving state where the output of sensor B is unreliable. When the output of sensor B is unreliable, the confidence level of sensor B's output can be reduced to prevent the active use of sensor B's information.

[0053] The above situation can be summarized by the following equation.

[0054] The first case can be expressed as follows.

[0055] Then ConfLv(B) = ConfLv(A)

[0056] The second scenario can be expressed as follows.

[0057] Then ConfLv(B) = α·ConfLv(B) where 0 < α < 1

[0058] Here, ConfLv(X) represents the output confidence information about sensor X and can be defined as having a value from 0 to 1.

[0059] Furthermore, in an exemplary embodiment of the present invention, the following conditions can be representatively considered to determine whether the vehicle is in a driving state where the sensor output is unreliable.

[0060] The conditions to be considered may include: first, determining whether the target's position output by the low-reliability sensor corresponds to the boundary region of the low-reliability sensor's field of view (FOV); second, determining the road curvature; third, determining the heading in degrees for each of the target and the vehicle; and fourth, determining whether there are obstacles or curbs on the road. For the second case to be verified, all of the above conditions need to be considered simultaneously.

[0061] Figure 2 This is a block diagram illustrating the configuration of a sensor output confidence adjustment device according to various exemplary embodiments of the present invention.

[0062] like Figure 2As shown, a sensor output confidence adjustment device according to various exemplary embodiments of the present invention may include: a sensor information acquisition unit 310 for acquiring information about different types of sensors; a sensor consistency judgment unit 320 for judging the consistency between different types of sensors based on the information about different types of sensors; a driving environment judgment unit 330 for judging the driving environment when the consistency between different types of sensors is lower than a reference value; and a confidence adjustment unit 340 for judging whether the confidence of different types of sensors is applicable based on the consistency between different types of sensors and the driving environment, and for readjusting the confidence of different types of sensors accordingly.

[0063] Here, the sensor consistency judgment unit 320 can classify the reliability of different types of sensors based on information about different types of sensors, and can judge the consistency between different types of sensors. This information includes the detection accuracy trend, detection area, and vehicle driving environment and conditions based on sensor type.

[0064] For example, the sensor consistency judgment unit 320 can determine the detection accuracy trend based on the sensor type by considering the detection accuracy of the lateral position, the detection accuracy of the longitudinal position, and the sensitivity to brightness. It can determine the detection area by considering the specifications and installation position of each sensor, and it can determine the vehicle's driving environment and conditions by considering the road curvature, the target, and the vehicle's heading.

[0065] Furthermore, when determining the consistency between different types of sensors, the sensor consistency determination unit 320 can classify the relative reliability of different types of sensors based on information about different types of sensors, and can determine the consistency between high-reliability sensors and low-reliability sensors.

[0066] Furthermore, when determining the consistency between different types of sensors, the sensor consistency determination unit 320 can determine the consistency between different types of sensors based on the target's position and velocity information.

[0067] Here, the sensor consistency determination unit 320 can use the following equation to determine the consistency between different types of sensors.

[0068]

[0069] in

[0070]

[0071] here, The vector representing the measurement value of sensor X at time point k, {x X ,y X}and This indicates the longitudinal and lateral positions of the target object relative to the sensors installed in the vehicle, as well as its longitudinal and lateral velocities. The standard deviation of position and velocity errors is represented by γ, and the design variable is represented by γ.

[0072] Subsequently, when the consistency between different types of sensors is lower than the reference value, the driving environment judgment unit 330 can judge the driving environment of the vehicle based on preset conditions.

[0073] Here, the driving environment determination unit 330 can determine the driving environment based on a first condition of determining whether the position of the target output by the low reliability sensor corresponds to the boundary area of ​​the field of view (FOV) of the low reliability sensor, a second condition of determining the road curvature, a third condition of determining the heading in degrees of each of the target and the vehicle, and a fourth condition of determining whether there are obstacles or curbs on the road.

[0074] Subsequently, when the consistency between different types of sensors is higher than the reference value, the confidence adjustment unit 340 can readjust the output confidence of the low-reliability sensor to the same level as the output confidence of the high-reliability sensor.

[0075] The confidence adjustment unit 340 readjusts the output confidence of the low-reliability sensor to the same level as the output confidence of the high-reliability sensor, which can be expressed by the following equation.

[0076] Then ConfLv(B) = ConfLv(A)

[0077] Here, ConfLv(X) represents the output confidence information about sensor X and has a value from 0 to 1.

[0078] The above equation shows that sensor A is a high-reliability sensor and the output confidence of sensor B, ConfLv(B), is redefined using the output confidence of sensor A, ConfLv(A).

[0079] Furthermore, when the driving environment determination unit 330 determines that the position of the target output by the low reliability sensor corresponds to the boundary region of the field of view (FOV) of the low reliability sensor, the confidence adjustment unit 340 can readjust the output confidence of the low reliability sensor to a lower level.

[0080] The confidence adjustment unit 340 readjusts the output confidence of the low-reliability sensor to a lower level, which can be expressed by the following equation.

[0081]

[0082] Then ConfLv(B) = α·ConfLv(B) where 0 < α < 1

[0083] Here, ConfLv(X) represents the output confidence information about sensor X, with values ​​ranging from 0 to 1.

[0084] Subsequently, when the driving environment determination unit 330 determines that the position of the target output by the low-reliability sensor does not correspond to the boundary area of ​​the low-reliability sensor's field of view (FOV) and the road environment is complex, the confidence adjustment unit 340 can readjust the output confidence of the low-reliability sensor to a lower level. Here, the driving environment determination unit 330 can determine whether the road environment is complex based on the number of surrounding vehicles and / or road obstacles (e.g., traffic cones, road limiters, barriers, etc.) detected by different types of sensors. For example, when the number of surrounding vehicles detected by different types of sensors exceeds a predetermined number, the driving environment determination unit 330 can determine that the road environment is complex.

[0085] When the driving environment judgment unit 330 determines that the position of the target output by the low reliability sensor does not correspond to the boundary area of ​​the field of view (FOV) of the low reliability sensor and the road environment is not complex, the confidence adjustment unit 340 may not readjust the output confidence of the low reliability sensor.

[0086] As described above, according to an exemplary embodiment of the present invention, the applicability of the confidence levels of different types of sensors is determined based on the consistency between different types of sensors and the driving environment of the vehicle, and the confidence levels of different types of sensors are readjusted accordingly, thereby improving the performance and stability of the sensor fusion system.

[0087] Figure 3 This is a flowchart illustrating a sensor output confidence adjustment method according to various exemplary embodiments of the present invention.

[0088] like Figure 3 As shown, according to an exemplary embodiment of the present invention, information about different types of sensors A and B can be obtained (S10).

[0089] Here, we assume that the reliability of sensor A is higher than that of sensor B.

[0090] Subsequently, according to an exemplary embodiment of the present invention, it can be determined whether the consistency between different types of sensors A and B is higher than a reference value based on information about different types of sensors A and B (S20).

[0091] Here, according to an exemplary embodiment of the present invention, the reliability of different types of sensors can be classified based on information about different types of sensors, and the consistency between different types of sensors can be determined. This information includes the detection accuracy trend according to the sensor type, the detection area, and the vehicle's driving environment and conditions.

[0092] For example, according to an exemplary embodiment of the present invention, the detection accuracy trend can be determined based on the sensor type by considering the detection accuracy of the lateral position, the detection accuracy of the longitudinal position, and the sensitivity to brightness. The detection area can be determined based on the specifications and installation location of each sensor, and the vehicle's driving environment and conditions can be determined based on road curvature, the target, and the vehicle's heading.

[0093] Furthermore, according to exemplary embodiments of the present invention, the relative reliability of different types of sensors can be classified based on information about different types of sensors, and the consistency between high-reliability sensors and low-reliability sensors can be determined.

[0094] Subsequently, according to an exemplary embodiment of the present invention, when the consistency between different types of sensors is higher than the reference value, the output confidence of the low-reliability sensor B can be readjusted to increase to the same level as that of the high-reliability sensor A (S30).

[0095] On the other hand, when the consistency between different types of sensors is lower than the reference value, it is determined whether the position of the target output by the low reliability sensor B corresponds to the boundary area of ​​the field of view (FOV) of the low reliability sensor B in the driving environment (S40).

[0096] Subsequently, according to an exemplary embodiment of the present invention, among the factors of the driving environment, when the position of the target output by the low reliability sensor B corresponds to the boundary region of the field of view (FOV) of the low reliability sensor B, the output confidence of the low reliability sensor B can be readjusted to a lower level (S50).

[0097] According to an exemplary embodiment of the present invention, among the factors of the driving environment, when the position of the target output by the low-reliability sensor B does not correspond to the boundary area of ​​the field of view (FOV) of the low-reliability sensor B, it is determined whether the road environment is complex (S60).

[0098] Subsequently, according to an exemplary embodiment of the present invention, when it is determined that the road environment is complex, the output confidence of the low-reliability sensor B can be readjusted to a lower level (S50).

[0099] On the other hand, when the road environment is determined to be uncomplicated, the output confidence of the low-reliability sensor B does not need to be readjusted (S70).

[0100] Subsequently, according to an exemplary embodiment of the present invention, the applicability of the confidence levels of different types of sensors can be determined based on the consistency between different types of sensors and the vehicle's driving environment, and the confidence levels of different types of sensors can be readjusted accordingly. Afterwards, it is determined whether a termination request exists (S80). If a termination request exists, the above process can be terminated.

[0101] Figure 4 and Figure 5 This is a diagram illustrating the process of adjusting the confidence level based on the vehicle's driving environment.

[0102] Figure 4 The vehicle's driving environment is shown, where the position of the target output by sensor B corresponds to the boundary region of sensor B's field of view (FOV).

[0103] like Figure 4 As shown, when two sensors, A and B, each have different fields of view (FOV) and the target object is located in the boundary region of sensor B's field of view (FOV), the output information of sensor B is unreliable.

[0104] Therefore, motion information such as the position and velocity of the target object, the age indicating the sensor's output state, and the sensor's confidence information are also unreliable.

[0105] Therefore, according to an exemplary embodiment of the present invention, although the information output by sensor B, such as the position and velocity of the target object, is not adjusted by taking into account the information output by sensor A, the output confidence of sensor B can be redefined based on the consistency of the information output by sensor A and sensor B.

[0106] Figure 5 It shows the complex driving environment of the vehicle.

[0107] like Figure 5 As shown, in a complex driving environment, it can be assumed that the vehicle to be followed is traveling at a low speed in front of the vehicle in an area close to the road boundary bars.

[0108] In the current situation, sensors that generate measurements based on reflected wave information, such as radar, can generate measurements from the road boundary fence near the vehicle in front.

[0109] Although the current information has position and speed values ​​similar to those of a target vehicle traveling at low speed, and is highly reliable because these values ​​are generated based on actual objects, these values ​​may not be used to follow the vehicle in front.

[0110] In complex driving environments, it is necessary to selectively use the information provided by sensors.

[0111] Therefore, according to an exemplary embodiment of the present invention, when sensor A reliably outputs information about the position and speed of the target vehicle, such as a camera, even in complex driving environments, the confidence level of sensor B can be readjusted based on the confidence level of sensor A.

[0112] In other words, according to an exemplary embodiment of the present invention, the criterion for determining the consistency between the information of sensor A and the information of another sensor can be set to be more stringent, such that when the criterion is not met, the confidence level of the other sensor is readjusted to a lower level and it is not used.

[0113] As described above, according to an exemplary embodiment of the present invention, the applicability of the confidence levels of different types of sensors is determined based on the consistency between different types of sensors and the driving environment of the vehicle, and the confidence levels of different types of sensors are readjusted accordingly, thereby improving the performance and stability of the sensor fusion system.

[0114] Meanwhile, an exemplary embodiment provides a computer-readable recording medium containing a program for performing a sensor output confidence adjustment method of a sensor output confidence adjustment device, and thereby enabling the execution of the process of the sensor output confidence adjustment method of the sensor output confidence adjustment device according to the exemplary embodiment.

[0115] This invention can be implemented as code that can be recorded on a computer-readable recording medium and thus read by a computer system. Computer-readable recording media include various recording devices that store data that can be read by a computer system. Examples of computer-readable recording media include hard disk drives (HDDs), solid-state drives (SSDs), silicon disk drives (SDDs), read-only memory (ROM), random access memory (RAM), read-only optical discs (CD-ROMs), magnetic tapes, floppy disks, and optical data storage devices.

[0116] As is evident from the above description, the sensor output confidence adjustment device and sensor output confidence adjustment method configured as described above according to at least one exemplary embodiment are configured to determine the applicability of the confidence of different types of sensors based on the consistency between different types of sensors and the driving environment of the vehicle, and readjust the confidence of different types of sensors accordingly, thereby improving the performance and stability of the sensor fusion system.

[0117] However, the effects achievable by the present invention are not limited to those described above, and those skilled in the art will clearly understand other effects not mentioned herein through the above description.

[0118] To facilitate the interpretation and accurate definition of the appended claims, the features of the exemplary embodiments are described using the terms "upper," "lower," "inner," "outer," "upper," "lower," "upward," "downward," "front," "rear," "behind," "inside," "outside," "inward," "outer," "internal," "external," "internal," "external," "forward," and "backward" to indicate the features of the exemplary embodiments, with reference to the positions of the features of the exemplary embodiments in the accompanying drawings. It will be further understood that the term "connection" or its derivatives refer to both direct and indirect connections.

[0119] For purposes of illustration and description, the foregoing description of specific exemplary embodiments of the invention has been provided. These descriptions are not intended to be exhaustive or to limit the invention to the precise forms disclosed, and it will be apparent that many modifications and variations can be made in accordance with the foregoing teachings. The exemplary embodiments were chosen and described to explain certain principles of the invention and its practical application, enabling others skilled in the art to implement and utilize various exemplary embodiments of the invention, as well as various alternatives and modifications thereof. The scope of the invention is intended to be defined by the appended claims and their equivalents.

Claims

1. A sensor output confidence adjustment device, comprising: The sensor information acquisition unit acquires information about different types of sensors; A sensor consistency determination unit determines the consistency between the different types of sensors based on information about those different types of sensors. The driving environment determination unit determines the vehicle's driving environment when the consistency between the different types of sensors is lower than a reference value. as well as Confidence adjustment unit, wherein the confidence adjustment unit: Determine the confidence level of the different types of sensors; as well as Based on the consistency between the different types of sensors and the driving environment, the confidence level of at least one of the different types of sensors is readjusted.

2. The sensor output confidence adjustment device according to claim 1, wherein, The sensor consistency judgment unit judges the reliability of the different types of sensors based on information about the different types of sensors. The information includes the detection accuracy trend of the sensor type, the detection area, and the vehicle's driving environment and conditions.

3. The sensor output confidence adjustment device according to claim 1, wherein, When determining the consistency between the different types of sensors, the sensor consistency determination unit: Based on information about the different types of sensors, the relative reliability of the different types of sensors is determined; Based on the aforementioned relative reliability, the different types of sensors are classified into high-reliability sensors and low-reliability sensors; and Determine the consistency between the high-reliability sensor and the low-reliability sensor.

4. The sensor output confidence adjustment device according to claim 1, wherein, When determining the consistency between the different types of sensors, the sensor consistency determination unit determines the consistency between the different types of sensors based on the target's position and velocity information.

5. The sensor output confidence adjustment device according to claim 1, wherein, When the consistency between the different types of sensors is lower than the reference value, the driving environment judgment unit judges the driving environment based on preset conditions.

6. The sensor output confidence adjustment device according to claim 5, wherein, The preset conditions include a first condition, a second condition, a third condition, and a fourth condition, and The driving environment determination unit determines the driving environment based on the first condition of determining whether the position of the target output by the sensor corresponds to the boundary area of ​​the sensor's field of view (FOV), the second condition of determining the road curvature, the third condition of determining the heading in degrees of each of the target and the vehicle, and the fourth condition of determining whether there are obstacles or curbs on the road.

7. The sensor output confidence adjustment device according to claim 1, wherein, When the consistency between the different types of sensors is higher than the reference value, the confidence adjustment unit readjusts the output confidence of the low-reliability sensor to the same level as the output confidence of the high-reliability sensor.

8. The sensor output confidence adjustment device according to claim 1, wherein, Among the factors of the driving environment, when the driving environment judgment unit determines that the position of the target output by the low reliability sensor corresponds to the boundary region of the field of view (FOV) of the low reliability sensor, the confidence adjustment unit readjusts the output confidence of the low reliability sensor to a lower level.

9. The sensor output confidence adjustment device according to claim 1, wherein, Among the factors of the driving environment, when the driving environment judgment unit determines that the position of the target output by the low reliability sensor does not correspond to the boundary area of ​​the field of view (FOV) of the low reliability sensor and the road environment is complex, the confidence adjustment unit readjusts the output confidence of the low reliability sensor to a lower level.

10. The sensor output confidence adjustment device according to claim 1, wherein, Among the factors of the driving environment, when the driving environment judgment unit determines that the position of the target output by the low reliability sensor does not correspond to the boundary area of ​​the field of view (FOV) of the low reliability sensor and the road environment is not complex, the confidence adjustment unit does not readjust the output confidence of the low reliability sensor.

11. A sensor output confidence adjustment method for a sensor output confidence adjustment device, the sensor output confidence adjustment device comprising a sensor information acquisition unit, a sensor consistency judgment unit, a driving environment judgment unit, and a confidence adjustment unit, the sensor output confidence adjustment method comprising: The sensor information acquisition unit acquires information about different types of sensors; The sensor consistency determination unit determines the consistency between the different types of sensors based on information about those different types of sensors. When the sensor consistency determination unit determines that the consistency between the different types of sensors is lower than the reference value, the driving environment determination unit determines the driving environment. as well as The confidence adjustment unit determines the confidence levels of the different types of sensors and, based on the consistency between the different types of sensors and the driving environment, readjusts the confidence level of at least one of the different types of sensors.

12. The sensor output confidence adjustment method according to claim 11, wherein, Determining the consistency between the different types of sensors includes: Based on information about the different types of sensors, the reliability of the different types of sensors is determined. The information about the different types of sensors includes the detection accuracy trend according to the sensor type, the detection area, and the vehicle's driving environment and conditions.

13. The sensor output confidence adjustment method according to claim 11, wherein, Determining the consistency between the different types of sensors includes: Based on information about the different types of sensors, determine the relative reliability of the different types of sensors; Based on the aforementioned relative reliability, the different types of sensors are classified into high-reliability sensors and low-reliability sensors; and Determine the consistency between the high-reliability sensor and the low-reliability sensor.

14. The sensor output confidence adjustment method according to claim 11, wherein, Determining the consistency between the different types of sensors includes: The consistency between the different types of sensors is determined based on the target's position and velocity information.

15. The sensor output confidence adjustment method according to claim 11, wherein, Readjusting the confidence levels of the different types of sensors includes: When the consistency between the different types of sensors is higher than the reference value, the output confidence level of the low-reliability sensor is readjusted to the same level as the output confidence level of the high-reliability sensor.

16. The sensor output confidence adjustment method according to claim 11, wherein, Readjusting the confidence levels of the different types of sensors includes: Among the factors of the driving environment, when the driving environment judgment unit determines that the position of the target output by the low reliability sensor corresponds to the boundary region of the field of view (FOV) of the low reliability sensor, the output confidence of the low reliability sensor is readjusted to a lower level.

17. The sensor output confidence adjustment method according to claim 11, wherein, Readjusting the confidence levels of the different types of sensors includes: Among the factors of the driving environment, when the driving environment judgment unit determines that the position of the target output by the low reliability sensor does not correspond to the boundary area of ​​the field of view (FOV) of the low reliability sensor and the road environment is complex, the output confidence of the low reliability sensor is readjusted to a lower level.

18. The sensor output confidence adjustment method according to claim 11, wherein, Readjusting the confidence levels of the different types of sensors includes: Among the factors of the driving environment, when the driving environment judgment unit determines that the position of the target output by the low reliability sensor does not correspond to the boundary area of ​​the field of view (FOV) of the low reliability sensor and the road environment is not complex, the output confidence of the low reliability sensor is not readjusted.

19. A non-transitory computer-readable recording medium that records a program for performing the method described in claim 11.

20. A vehicle comprising: Different types of sensors sense the vehicle's driving environment; as well as Sensor output confidence adjustment device, wherein the sensor output confidence adjustment device: Obtain information about different types of sensors; Based on information about the different types of sensors, determine the consistency between the different types of sensors; When the sensor output confidence adjustment device determines that the consistency between different types of sensors is lower than the reference value, it determines the driving environment. Determine the confidence level of the different types of sensors; as well as Based on the consistency between the different types of sensors and the driving environment, the confidence level of at least one of the different types of sensors is readjusted.

Images