Boundary Detection Method, Device, Equipment and Storage Medium for Operating Region

Abstract

The present invention belongs to the technical field of autonomous driving, and discloses a method, device, equipment and storage medium for boundary detection of an operating domain. The method includes: obtaining a set of influence parameter points of the operating domain of autonomous driving; determining evaluation values of each point to be detected in the set of influence parameter points according to a preset evaluation function; performing boundary detection on the set of influence parameter points according to a preset boundary detection method and the evaluation values of each point to be detected in the set of influence parameter points to obtain a boundary detection result; and determining the operating domain boundary of the autonomous driving according to the boundary detection result. By the above method, boundary detection is performed on the set of influence parameter points composed of factors that affect the operating boundary of autonomous driving, and the operating domain boundary of autonomous driving is determined based on the boundary detection result, which not only considers the diversity of the form of the operating domain boundary of autonomous driving, but also improves the detection efficiency and ensures the accuracy of the operating domain boundary.

Description

Technical Field

[0001] The present invention relates to the technical field of autonomous driving, and in particular, to a method, device, equipment and storage medium for detecting the boundary of an operating domain. Background Art

[0002] An autonomous vehicle, also known as a driverless vehicle, a computer-driven vehicle, or a wheeled mobile robot, is an intelligent vehicle that realizes driverless operation through a computer system. The research and development of autonomous vehicle technology has also had a history of several decades in the 20th century and showed a trend approaching practical application at the beginning of the 21st century. Relying on the collaborative cooperation of artificial intelligence, visual computing, radar, monitoring devices and the global positioning system, a computer can automatically and safely operate a motor vehicle without any active operation by a human. The boundary of the operating domain of the autonomous driving system is related to the personal safety of traffic participants, and it is particularly important to determine the boundary of the operating domain during the development of the autonomous driving system. However, in the prior art, the method used for detecting the designed operating domain boundary of the autonomous driving system is still a comprehensive detection based on influencing factors, which is not only inefficient but also has low accuracy. Summary of the Invention

[0003] The main purpose of the present invention is to provide a method, device, equipment and storage medium for detecting the boundary of an operating domain, aiming to solve the technical problem that the prior art cannot efficiently and accurately determine the operating domain boundary of an autonomous driving system.

[0004] To achieve the above purpose, the present invention provides a method for detecting the boundary of an operating domain, and the method for detecting the boundary of the operating domain includes:

[0005] Obtain a set of influence parameter points of the operating domain of autonomous driving;

[0006] Determine the evaluation values of each point to be detected in the set of influence parameter points according to a preset evaluation function;

[0007] Perform boundary detection on the set of influence parameter points according to a preset boundary detection method and the evaluation values of each point to be detected in the set of influence parameter points to obtain a boundary detection result;

[0008] Determine the operating domain boundary of the autonomous driving according to the boundary detection result.

[0009] Optionally, the performing boundary detection on the set of influence parameter points according to a preset boundary detection method and the evaluation values of each point to be detected in the set of influence parameter points to obtain a boundary detection result includes:

[0010] Perform range detection on the set of influence parameter points according to a preset boundary detection method and the evaluation values of each point to be detected in the set of influence parameter points to obtain a set of range detection points;

[0011] Perform a convergence detection on the range detection point set to obtain a convergence point set;

[0012] Perform a boundary loop detection on the convergence point set to obtain a boundary detection point set;

[0013] Obtain a boundary detection result based on the boundary detection point set.

[0014] Optionally, the performing a range detection on the influence parameter point set according to a preset boundary detection method and evaluation values of each point to be detected in the influence parameter point set to obtain a range detection point set includes:

[0015] Determine a first generation point and a first activation point included in the activation point generation space corresponding to the influence parameter point set according to the preset boundary detection method;

[0016] Determine a first generation evaluation value of the first generation point and a first activation evaluation value of the first activation point according to the evaluation values of each point to be detected in the influence parameter point set;

[0017] Determine a range detection result of the first generation point according to the first generation evaluation value and the first activation evaluation value;

[0018] Generate a range detection point set according to the range detection result.

[0019] Optionally, the determining a range detection result of the first generation point according to the first generation evaluation value and the first activation evaluation value includes:

[0020] Determine a first generation symbol according to the first generation evaluation value;

[0021] Determine a first activation symbol according to the first activation evaluation value;

[0022] Judge whether the first generation symbol and the first activation symbol are the same to obtain a first judgment result;

[0023] When the first judgment result is that the first generation symbol and the first activation symbol are different, generate a range detection result according to the first generation point.

[0024] Optionally, the performing a convergence detection on the range detection point set to obtain a convergence point set includes:

[0025] Determine a second generation point and a second activation point included in the activation point generation space corresponding to the range detection point set;

[0026] Determine a second generation evaluation value of the second generation point and a second activation evaluation value of the second activation point according to the evaluation values of each point to be detected in the influence parameter point set;

[0027] Determine the convergence detection result of the second generation point according to the generation direction of the second generation point, the second generation evaluation value, and the second activation evaluation value;

[0028] Generate a convergence point set according to the convergence detection result.

[0029] Optionally, the determining the convergence detection result of the second generation point according to the generation direction of the second generation point, the second generation evaluation value, and the second activation evaluation value includes:

[0030] Determine a second generation symbol according to the second generation evaluation value;

[0031] Determine a second activation symbol according to the second activation evaluation value;

[0032] When the generation direction of the second generation point is a preset direction, determine whether the second generation symbol and the second activation symbol are the same to obtain a second judgment result;

[0033] When the second judgment result is that the second generation symbol and the second activation symbol are different, generate a convergence detection result according to the second generation point.

[0034] Optionally, the performing boundary loop detection on the convergence point set to obtain a boundary detection point set includes:

[0035] Determine a third generation point and a third activation point in the activation point generation space of the convergence point set;

[0036] Determine a third generation evaluation value of the third generation point and a third activation evaluation value of the third activation point according to the evaluation values of the points to be detected in the influence parameter point set;

[0037] Determine an evaluation value sequence of the third generation point according to the third generation evaluation value, the third activation evaluation value, and a preset evaluation value type;

[0038] Determine a boundary detection point set according to the evaluation value sequence.

[0039] In addition, to achieve the above object, the present invention also proposes a boundary detection device for an operating domain, and the boundary detection device for the operating domain includes:

[0040] An acquisition module, configured to acquire an influence parameter point set of an operating domain of an autonomous driving;

[0041] A determination module, configured to determine the evaluation value of each point to be detected in the influence parameter point set according to a preset evaluation function;

[0042] A detection module, configured to perform boundary detection on the influence parameter point set according to a preset boundary detection method and the evaluation values of each point to be detected in the influence parameter point set, so as to obtain a boundary detection result;

[0043] The determination module is further configured to determine the operation domain boundary of the autonomous driving according to the boundary detection result.

[0044] In addition, to achieve the above object, the present invention further provides a boundary detection device for an operation domain, where the boundary detection device for the operation domain includes: a memory, a processor, and a boundary detection program for the operation domain stored on the memory and executable on the processor, and the boundary detection program for the operation domain is configured to implement the boundary detection method for the operation domain as described above.

[0045] In addition, to achieve the above object, the present invention further provides a storage medium, on which a boundary detection program for an operation domain is stored, and when the boundary detection program for the operation domain is executed by a processor, it implements the boundary detection method for the operation domain as described above.

[0046] The present invention obtains an influence parameter point set of the operation domain of autonomous driving; determines the evaluation value of each point to be detected in the influence parameter point set according to a preset evaluation function; performs boundary detection on the influence parameter point set according to a preset boundary detection method and the evaluation values of each point to be detected in the influence parameter point set, so as to obtain a boundary detection result; determines the operation domain boundary of the autonomous driving according to the boundary detection result. By the above method, boundary detection is performed on the influence parameter point set composed of the factors affecting the operation boundary of autonomous driving, and the operation domain boundary of autonomous driving is determined based on the boundary detection result. It not only considers the diversity of the boundary form of the autonomous driving operation domain, is applicable to the measured autonomous driving system under various complex forms, but also describes the boundary in the form of a dense point set, improves the detection efficiency, and ensures the accuracy of the operation domain boundary. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 is a schematic structural diagram of a boundary detection device for an operation domain of a hardware operation environment related to an embodiment of the present invention;

[0048] Figure 2 is a schematic flowchart of a first embodiment of the boundary detection method for the operation domain of the present invention;

[0049] Figure 3 is a schematic overall flowchart of an embodiment of the boundary detection method for the operation domain of the present invention;

[0050] Figure 4 is a schematic flowchart of a second embodiment of the boundary detection method for the operation domain of the present invention;

[0051] Figure 5Schematic diagram of the generation structure of an embodiment of the boundary detection method for the operation domain of the present invention;

[0052] Figure 6 Block diagram of the structure of the first embodiment of the boundary detection device for the operation domain of the present invention.

[0053] The realization of the object of the present invention, functional features and advantages will be further described with reference to the embodiments and the accompanying drawings. Specific embodiments

[0054] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0055] Refer to Figure 1 , Figure 1 Schematic diagram of the structure of the boundary detection device for the operation domain of the hardware operation environment involved in the embodiment solution of the present invention.

[0056] As Figure 1 shown, the boundary detection device for the operation domain may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display) and an input unit such as a keyboard (Keyboard). Optionally, the user interface 1003 may further include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless-fidelity (Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM) or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0057] Those skilled in the art can understand that Figure 1 the structure shown in

[0058] does not constitute a limitation on the boundary detection device for the operation domain, and may include more or fewer components than shown, or combine some components, or arrange different components. Figure 1 As

[0059] In Figure 1In the boundary detection device of the operating domain shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the boundary detection device of the operating domain of the present invention can be arranged in the boundary detection device of the operating domain. The boundary detection device of the operating domain calls the boundary detection program of the operating domain stored in the memory 1005 through the processor 1001 and executes the boundary detection method of the operating domain provided by the embodiments of the present invention.

[0060] Embodiments of the present invention provide a method for detecting the boundary of an operating domain. Refer to Figure 2 , Figure 2 It is a schematic flowchart of the first embodiment of a method for detecting the boundary of an operating domain of the present invention.

[0061] The method for detecting the boundary of the operating domain includes the following steps:

[0062] Step S10: Obtain a set of influence parameter points of the operating domain of autonomous driving.

[0063] It should be noted that the execution subject of this embodiment is a terminal device, and the terminal device can be a computer, a tablet computer, a mobile phone, or other intelligent terminals. This embodiment does not limit this. There is a boundary detection system for the operating domain on the terminal device. The boundary detection system for the operating domain obtains a set of influence parameter points of the operating domain of autonomous driving, determines the evaluation values of each point to be detected in the set of influence parameter points according to a preset evaluation function, and performs boundary detection on the set of influence parameter points according to a preset boundary detection method and the evaluation values of each point to be detected in the set of influence parameter points to obtain a boundary detection result.

[0064] It can be understood that the operating domain of autonomous driving is the designed operating domain of the autonomous driving system. Since the designed operating domain of the autonomous driving system is affected by various influencing factors during design, in order to determine under what specific conditions of various influencing factors will cause the failure of the autonomous driving system, boundary detection of the designed operating domain will be carried out. The set of points formed based on various influence parameters is the set of influence parameter points. For example, when the current autonomous driving system can be used normally when the rainfall is not large and there are not many clouds in the sky, in order to determine how much the rainfall is below and how many clouds in the sky are below when the autonomous driving system can be used normally, and when the rainfall exceeds what value or the clouds in the sky exceed what value the autonomous driving system fails, boundary detection is carried out based on the set of influence parameter points formed by rainfall and clouds in the sky. The autonomous driving system can be affected by multiple influencing factors, so the set of influence parameter points is composed of multiple influencing factors. Rainfall and clouds in the sky in this embodiment are only used for illustration.

[0065] Step S20: Determine the evaluation values of each point to be detected in the set of influence parameter points according to a preset evaluation function.

[0066] It should be noted that the preset evaluation function refers to the pre-set evaluation function, and the evaluation value of the preset evaluation function defines the boundary of the operating domain. For example, after inputting the set of influence parameter points into the boundary detection system of the operating domain and performing simulation, if the simulation result is collision or not, the preset evaluation function obtains the corresponding evaluation value according to whether there is a collision or not, and the evaluation value corresponding to each point to be detected in the influence parameters is the evaluation value of each point to be detected. The boundary of the operating domain is defined as: the region where the evaluation value changes from positive to negative. Then, when detecting the boundary of the collision detection ability, the preset evaluation function should set the evaluation values as positive and negative evaluation values according to the situations of collision and non-collision respectively.

[0067] Step S30: Perform boundary detection on the set of influence parameter points according to the preset boundary detection method and the evaluation values of each point to be detected in the set of influence parameter points, and obtain the boundary detection result.

[0068] It should be noted that the preset boundary detection method refers to the boundary detection method pre-trained based on the boundary detection algorithm. The preset boundary detection method includes a large-range detection part, a convergence part, and a boundary loop detection part. Under the required expected accuracy, perform boundary detection on the set of influence parameter points according to the preset boundary detection method and the evaluation values of each point to be detected, so as to obtain the boundary detection result. As Figure 3 shown, the boundary detection system of the operating domain includes a simulation model of the autonomous driving system to be tested, and is composed of a preset evaluation function and a preset boundary detection method. Bring the set of influence parameter points into the simulation model of the autonomous driving system to be tested for simulation, obtain the simulation results of each point to be detected, obtain the evaluation values of each detection point according to the simulation results and the preset evaluation function, and generate the boundary detection result based on the evaluation values of each point to be detected in the set of influence parameter points and the preset boundary detection algorithm.

[0069] Step S40: Determine the operating domain boundary of the autonomous driving according to the boundary detection result.

[0070] It should be noted that the set of points output in the boundary detection result can determine the operating domain boundary of the autonomous driving.

[0071] In this embodiment, an influence parameter point set of the operating domain of autonomous driving is obtained; an evaluation value of each point to be detected in the influence parameter point set is determined according to a preset evaluation function; boundary detection is performed on the influence parameter point set according to a preset boundary detection method and the evaluation values of the points to be detected in the influence parameter point set, and a boundary detection result is obtained; the operating domain boundary of the autonomous driving is determined according to the boundary detection result. In the above manner, boundary detection is performed on the influence parameter point set composed of the factors that affect the operating boundary of autonomous driving, and the operating domain boundary of autonomous driving is determined based on the boundary detection result. This not only considers the diversity of the shapes of the operating domain boundaries of autonomous driving and is applicable to the autonomous driving systems to be measured under various complex shapes, but also describes the boundary in the form of a dense point set, improving the detection efficiency and ensuring the accuracy of the operating domain boundary.

[0072] Reference Figure 4 , Figure 4 is a schematic flowchart of the second embodiment of a method for detecting the boundary of an operating domain according to the present invention.

[0073] Based on the above first embodiment, in the method for detecting the boundary of the operating domain in this embodiment, step S30 includes:

[0074] Step S31: Perform range detection on the influence parameter point set according to a preset boundary detection method and the evaluation values of the points to be detected in the influence parameter point set, and obtain a range detection point set.

[0075] It should be noted that range detection refers to large-range detection, and the range detection point set refers to the point set that can be classified into the converging part for the next step of detection. Large-range detection is performed according to the evaluation values of the points to be detected in the influence parameter point set and the points to be detected, and a range detection point set is obtained.

[0076] It can be understood that, in order to obtain an accurate range detection point set, further, the performing range detection on the influence parameter point set according to a preset boundary detection method and the evaluation values of the points to be detected in the influence parameter point set, and obtaining a range detection point set includes: determining a first generated point and a first activation point included in the activation point generation space corresponding to the influence parameter point set according to a preset boundary detection method; determining a first generated evaluation value of the first generated point and a first activation evaluation value of the first activation point according to the evaluation values of the points to be detected in the influence parameter point set; determining a range detection result of the first generated point according to the first generated evaluation value and the first activation evaluation value; and generating a range detection point set according to the range detection result.

[0077] In a specific implementation, when performing large-scale detection, generation points are selected in the activation point generation space. The selected generation points are the first generation points, and the evaluation value of the first generation point is obtained. The evaluation value of the first generation point is the first generated evaluation value. Also, the first activation point and the first activation evaluation value of the first activation point are obtained. Based on the relationship between the first generated evaluation value and the first activation evaluation value, the belonging part of the first generation point is determined. According to the first generation points belonging to the convergence part in the judgment result, a range detection result is generated. Finally, a range detection point set is formed based on the points in the range detection result. The basic structure of the point set generation method in this embodiment is as follows Figure 5 as shown, p i is the activation point for generating generation points. δ n is the protection neighborhood of p i Within this neighborhood, no generation points can be generated. δ' n is the generation neighborhood of p i Generation points are kept within this neighborhood. If there is no generable space in the activation point generation space, that is, the protection neighborhoods of multiple points cover the generation neighborhood, then this activation point is put into dormancy.

[0078] It should be noted that, in order to obtain an accurate range detection result, further, determining the range detection result of the first generation point according to the first generated evaluation value and the first activation evaluation value includes: determining a first generated symbol according to the first generated evaluation value; determining a first activation symbol according to the first activation evaluation value; judging whether the first generated symbol and the first activation symbol are the same to obtain a first judgment result; when the first judgment result is that the first generated symbol and the first activation symbol are different, generating a range detection result according to the first generation point.

[0079] It can be understood that the symbol of the first generated evaluation value and the symbol of the first activation evaluation value are obtained. The symbol of the first generated evaluation value is the first generated symbol, and the symbol of the first activation evaluation value is the first activation symbol. Judging whether the first generated symbol and the first activation symbol are the same to obtain a first judgment result. When the first judgment result is that the first generated symbol and the first activation symbol are different, the first generation points where the first generated symbol and the first activation symbol are different belong to the convergence part, and a range detection result is generated based on the first generation points belonging to the convergence part.

[0080] Step S32: Perform convergence detection on the range detection point set to obtain a convergence point set.

[0081] It should be noted that the convergence point set refers to the point set that can be included in the boundary loop detection part for the next step of detection. Convergence detection is performed on the range detection point set generated by the large-scale detection part to obtain a convergence point set.

[0082] It can be understood that, in order to obtain an accurate set of convergence points, further, the convergence detection of the range detection point set to obtain a set of convergence points includes: determining a second generation point and a second activation point included in the activation point generation space corresponding to the range detection point set; determining a second generation evaluation value of the second generation point and a second activation evaluation value of the second activation point according to the evaluation values of the points to be detected in the influence parameter point set; determining the convergence detection result of the second generation point according to the generation direction of the second generation point, the second generation evaluation value, and the second activation evaluation value; and generating a set of convergence points according to the convergence detection result.

[0083] In a specific implementation, during the convergence part, a generation point is selected in the activation point generation space, and the selected generation point is the second generation point, and the evaluation value of the second generation point is obtained, and the evaluation value of the second generation point is the second generation evaluation value. And the second activation point and the second activation evaluation value of the second activation point are obtained. Based on the first generation evaluation value, the first activation evaluation value, and the generation direction of the second generation point, the belonging part of the second generation point is judged, and the convergence detection result is generated according to the second generation points belonging to the boundary loop detection part in the judgment result. Finally, a set of convergence points is formed according to the points in the convergence detection result.

[0084] It should be noted that, in order to obtain an accurate convergence detection result, further, the determining the convergence detection result of the second generation point according to the generation direction of the second generation point, the second generation evaluation value, and the second activation evaluation value includes: determining a second generation symbol according to the second generation evaluation value; determining a second activation symbol according to the second activation evaluation value; when the generation direction of the second generation point is a preset direction, judging whether the second generation symbol and the second activation symbol are the same to obtain a second judgment result; and when the second judgment result is that the second generation symbol and the second activation symbol are different, generating a convergence detection result according to the second generation point.

[0085] It can be understood that before the second generation point is generated, there is an expected change in the second generation evaluation value when obtaining the generation direction of the second generation point. There are only two generation directions for the second generation point: the gradient ascent direction and the descent direction. For example, if it is desired to generate a gradient ascent point, the absolute value of the second generation evaluation value should be greater than the absolute value of the second activation evaluation value. Conversely, if it is desired to generate a gradient descent point, the evaluation value relationship is opposite. Further, according to the expected direction, if the second generation point does not meet the expectation, it is discarded and regarded as a discarded point. On the premise of meeting the expectation, if the generation direction is the gradient descent direction and the descent direction is the preset direction, it is determined whether the second generation symbol and the second activation symbol are the same. When the second judgment result is that the second generation symbol and the second activation symbol are different, the second generation point based on the difference between the second generation symbol and the second activation symbol belongs to the boundary cycle detection part, and a convergence detection result is generated based on the second generation point belonging to the boundary cycle detection part.

[0086] Step S33: Perform boundary cycle detection on the convergence point set to obtain a boundary detection point set.

[0087] It should be noted that the boundary detection point set refers to the set of boundary points of the operation domain. Boundary cycle detection is performed on the convergence point set generated by the convergence part to obtain the boundary detection point set.

[0088] It can be understood that in order to obtain an accurate boundary detection point set, further, the performing boundary cycle detection on the convergence point set to obtain a boundary detection point set includes: determining a third generation point and a third activation point in the activation point generation space of the convergence point set; determining a third generation evaluation value of the third generation point and a third activation evaluation value of the third activation point according to the evaluation values of the points to be detected in the influence parameter point set; determining an evaluation value sequence of the third generation point according to the third generation evaluation value, the third activation evaluation value, and the preset evaluation value type; and determining the boundary detection point set according to the evaluation value sequence.

[0089] In a specific implementation, when performing boundary loop detection, generation points are selected in the activation point generation space. The selected generation points are the third generation points, and the evaluation values of the third generation points are obtained. The evaluation values of the third generation points are the third generation evaluation values. The third activation point and the third activation evaluation value of the third activation point are also obtained. Based on the third generation evaluation value, the third activation evaluation value, and the preset evaluation value types, the evaluation value sequence of the third generation point is determined. The preset evaluation value types refer to the pre-set classification of evaluation values, which are zero evaluation value type, zero positive evaluation value type, zero negative evaluation value type, and positive and negative evaluation value type. The convergence point set is classified into these four categories according to its generation sequence and its evaluation value. For example: if the evaluation values of the third activation point and its past sequence are all zero, and the evaluation value of its third generation point is positive, then the points in the past sequence, the third generation point, and the third activation point are all classified into the zero positive evaluation value type. On the contrary, if the third activation point and the past sequence only contain zeros and positives, and the evaluation value of the third generation point is negative, then the sequence and the third generation point are both classified into the positive and negative evaluation value type. Similarly, the zero evaluation value type only contains sequences with an evaluation value of zero, the zero negative evaluation value type only contains sequences with an evaluation value of zero or negative, and the third generation points with an evaluation value of positive and negative evaluation value type are output as the boundary detection point set.

[0090] Step S34: Obtain a boundary detection result according to the boundary detection point set.

[0091] It should be noted that after obtaining the boundary detection point set, the boundary detection result can be formed based on the boundary detection point set.

[0092] In this embodiment, by performing range detection on the influence parameter point set according to the preset boundary detection method and the evaluation values of the points to be detected in the influence parameter point set, a range detection point set is obtained; convergence detection is performed on the range detection point set to obtain a convergence point set; boundary loop detection is performed on the convergence point set to obtain a boundary detection point set; and a boundary detection result is obtained according to the boundary detection point set. By detecting the influence parameter point set in three parts, the accuracy of the detection result is ensured, and the detection efficiency is also improved.

[0093] In addition, referring to Figure 6 , an embodiment of the present invention also provides a boundary detection device for an operating domain. The boundary detection device for the operating domain includes:

[0094] An acquisition module 10, configured to acquire an influence parameter point set of the operating domain of autonomous driving.

[0095] A determination module 20, configured to determine the evaluation values of the points to be detected in the influence parameter point set according to a preset evaluation function.

[0096] A detection module 30, configured to perform boundary detection on the influence parameter point set according to a preset boundary detection method and the evaluation values of the points to be detected in the influence parameter point set, and obtain a boundary detection result.

[0097] The determining module 20 is further configured to determine the operation domain boundary of the autonomous driving according to the boundary detection result.

[0098] In this embodiment, by obtaining a set of influence parameter points of the operation domain of the autonomous driving; determining the evaluation values of the points to be detected in the set of influence parameter points according to a preset evaluation function; performing boundary detection on the set of influence parameter points according to a preset boundary detection method and the evaluation values of the points to be detected in the set of influence parameter points to obtain a boundary detection result; and determining the operation domain boundary of the autonomous driving according to the boundary detection result. In the above manner, by performing boundary detection on the set of influence parameter points composed of the factors that affect the operation boundary of the autonomous driving and determining the operation domain boundary of the autonomous driving based on the boundary detection result, not only the diversity of the operation domain boundary form of the autonomous driving is considered, which is applicable to the autonomous driving system to be measured under various complex forms, but also the boundary is described in the form of a dense point set, which improves the detection efficiency and ensures the accuracy of the operation domain boundary.

[0099] In one embodiment, the detection module 30 is further configured to perform range detection on the set of influence parameter points according to a preset boundary detection method and the evaluation values of the points to be detected in the set of influence parameter points to obtain a set of range detection points;

[0100] Performing convergence detection on the set of range detection points to obtain a set of convergence points;

[0101] Performing boundary loop detection on the set of convergence points to obtain a set of boundary detection points;

[0102] Obtaining a boundary detection result according to the set of boundary detection points.

[0103] In one embodiment, the detection module 30 is further configured to determine a first generated point and a first activation point included in the generated space of activation points corresponding to the set of influence parameter points according to a preset boundary detection method;

[0104] Determining a first generated evaluation value of the first generated point and a first activation evaluation value of the first activation point according to the evaluation values of the points to be detected in the set of influence parameter points;

[0105] Determining a range detection result of the first generated point according to the first generated evaluation value and the first activation evaluation value;

[0106] Generating a set of range detection points according to the range detection result.

[0107] In one embodiment, the detection module 30 is further configured to determine a first generated symbol according to the first generated evaluation value;

[0108] Determining a first activation symbol according to the first activation evaluation value;

[0109] Determine whether the first generated symbol and the first activation symbol are the same to obtain a first determination result;

[0110] When the first determination result is that the first generated symbol and the first activation symbol are different, generate a range detection result according to the first generation point generation range.

[0111] In one embodiment, the detection module 30 is further configured to determine a second generated point and a second activation point included in the activation point generation space corresponding to the range detection point set;

[0112] Determine a second generation evaluation value of the second generated point and a second activation evaluation value of the second activation point according to the evaluation values of the points to be detected in the influence parameter point set;

[0113] Determine a convergence detection result of the second generated point according to the generation direction of the second generated point, the second generation evaluation value, and the second activation evaluation value;

[0114] Generate a convergence point set according to the convergence detection result.

[0115] In one embodiment, the detection module 30 is further configured to determine a second generated symbol according to the second generation evaluation value;

[0116] Determine a second activation symbol according to the second activation evaluation value;

[0117] When the generation direction of the second generated point is a preset direction, determine whether the second generated symbol and the second activation symbol are the same to obtain a second determination result;

[0118] When the second determination result is that the second generated symbol and the second activation symbol are different, generate a convergence detection result according to the second generated point.

[0119] In one embodiment, the detection module 30 is further configured to determine a third generated point and a third activation point in the activation point generation space of the convergence point set;

[0120] Determine a third generation evaluation value of the third generated point and a third activation evaluation value of the third activation point according to the evaluation values of the points to be detected in the influence parameter point set;

[0121] Determine an evaluation value sequence of the third generated point according to the third generation evaluation value, the third activation evaluation value, and a preset evaluation value type;

[0122] Determine a boundary detection point set according to the evaluation value sequence.

[0123] Since this device adopts all the technical solutions of all the above embodiments, it at least has all the beneficial effects brought by the technical solutions of the above embodiments, and will not be elaborated one by one here.

[0124] In addition, an embodiment of the present invention further provides a storage medium, on which a boundary detection program for the running domain is stored. When the boundary detection program for the running domain is executed by a processor, the steps of the boundary detection method for the running domain as described above are implemented.

[0125] Since this storage medium adopts all the technical solutions of all the above embodiments, it at least has all the beneficial effects brought by the technical solutions of the above embodiments, and will not be elaborated one by one here.

[0126] It should be noted that the above-described work process is only illustrative and does not limit the protection scope of the present invention. In actual applications, those skilled in the art can select some or all of them according to actual needs to achieve the purpose of the solution of this embodiment, and no limitation is made here.

[0127] In addition, for the technical details not described in detail in this embodiment, reference can be made to the boundary detection method for the running domain provided in any embodiment of the present invention, and no further elaboration will be made here.

[0128] In addition, it should be noted that in this article, the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such a process, method, article or system. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of another identical element in the process, method, article or system including that element.

[0129] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0130] Through the description of the above embodiments, those skilled in the art can clearly understand that the above embodiment methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as a read-only memory (ROM) / RAM, magnetic disk, optical disc), and includes several instructions for causing a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in various embodiments of the present invention.

[0131] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention accordingly. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be similarly included in the patent protection scope of the present invention.

Claims

1. A boundary detection method for a running domain, characterized in that The boundary detection method for the operating domain includes: Obtaining a set of influence parameter points for the operating domain of autonomous driving; Determining the evaluation values of each point to be detected in the set of influence parameter points according to a preset evaluation function; Performing boundary detection on the set of influence parameter points according to a preset boundary detection method and the evaluation values of each point to be detected in the set of influence parameter points to obtain a boundary detection result; Determining the operating domain boundary of the autonomous driving according to the boundary detection result; Wherein, the performing boundary detection on the set of influence parameter points according to a preset boundary detection method and the evaluation values of each point to be detected in the set of influence parameter points to obtain a boundary detection result includes: Performing range detection on the set of influence parameter points according to a preset boundary detection method and the evaluation values of each point to be detected in the set of influence parameter points to obtain a set of range detection points; Performing convergence detection on the set of range detection points to obtain a set of convergence points; Performing boundary loop detection on the set of convergence points to obtain a set of boundary detection points; Obtaining a boundary detection result according to the set of boundary detection points.

2. The boundary detection method of the operating domain according to claim 1, wherein The performing range detection on the set of influence parameter points according to a preset boundary detection method and the evaluation values of each point to be detected in the set of influence parameter points to obtain a set of range detection points includes: Determining a first generation point and a first activation point included in the activation point generation space corresponding to the set of influence parameter points according to a preset boundary detection method; Determining a first generation evaluation value of the first generation point and a first activation evaluation value of the first activation point according to the evaluation values of each point to be detected in the set of influence parameter points; Determining a range detection result of the first generation point according to the first generation evaluation value and the first activation evaluation value; Generating a set of range detection points according to the range detection result.

3. The boundary detection method for the operating domain according to claim 2, wherein The determining a range detection result of the first generation point according to the first generation evaluation value and the first activation evaluation value includes: Determining a first generation symbol according to the first generation evaluation value; Determining a first activation symbol according to the first activation evaluation value; Judging whether the first generation symbol and the first activation symbol are the same to obtain a first judgment result; When the first judgment result is that the first generation symbol and the first activation symbol are different, generating a range detection result according to the first generation point.

4. The boundary detection method of the operating domain according to claim 1, wherein The performing convergence detection on the set of range detection points to obtain a set of convergence points includes: Determining a second generation point and a second activation point included in the activation point generation space corresponding to the set of range detection points; Determining a second generation evaluation value of the second generation point and a second activation evaluation value of the second activation point according to the evaluation values of each point to be detected in the set of influence parameter points; Determining a convergence detection result of the second generation point according to the generation direction of the second generation point, the second generation evaluation value, and the second activation evaluation value; Generating a set of convergence points according to the convergence detection result.

5. The boundary detection method for the operating domain according to claim 4, wherein The determining a convergence detection result of the second generation point according to the generation direction of the second generation point, the second generation evaluation value, and the second activation evaluation value includes: Determining a second generation symbol according to the second generation evaluation value; Determining a second activation symbol according to the second activation evaluation value; When the generation direction of the second generation point is the preset direction, determine whether the second generation symbol is the same as the second activation symbol to obtain a second judgment result; When the second judgment result is that the second generation symbol is different from the second activation symbol, generate a convergence detection result according to the second generation point.

6. The boundary detection method of the operating domain according to claim 1, characterized in that The boundary loop detection of the convergence point set to obtain a boundary detection point set includes: Determine a third generation point and a third activation point in the activation point generation space of the convergence point set; Determine a third generation evaluation value of the third generation point and a third activation evaluation value of the third activation point according to the evaluation values of the points to be detected in the influence parameter point set; Determine the evaluation value sequence of the third generation point according to the third generation evaluation value, the third activation evaluation value and the preset evaluation value type; Determine the boundary detection point set according to the evaluation value sequence.

7. A boundary detection device for a running domain, characterized in that The boundary detection device of the operating domain includes: An acquisition module, configured to acquire an influence parameter point set of the operating domain of autonomous driving; A determination module, configured to determine the evaluation value of each point to be detected in the influence parameter point set according to a preset evaluation function; A detection module, configured to perform boundary detection on the influence parameter point set according to a preset boundary detection method and the evaluation values of the points to be detected in the influence parameter point set to obtain a boundary detection result; The determination module is further configured to determine the operating domain boundary of the autonomous driving according to the boundary detection result; The detection module is further configured to perform range detection on the influence parameter point set according to a preset boundary detection method and the evaluation values of the points to be detected in the influence parameter point set to obtain a range detection point set; perform convergence detection on the range detection point set to obtain a convergence point set; perform boundary loop detection on the convergence point set to obtain a boundary detection point set; and obtain a boundary detection result according to the boundary detection point set.

8. A boundary detection device for a running domain, characterized in that, The device includes: a memory, a processor, and a boundary detection program of the operating domain stored on the memory and executable on the processor, and the boundary detection program of the operating domain is configured to implement the boundary detection method of the operating domain according to any one of claims 1 to 6.

9. A storage medium, characterized in that, A boundary detection program of the operating domain is stored on the storage medium, and when the boundary detection program of the operating domain is executed by a processor, it implements the boundary detection method of the operating domain according to any one of claims 1 to 6.

Images