Method and device for determining position of target, equipment, vehicle and medium

Abstract

The embodiment of the invention relates to a method and device for determining the position of a target, equipment, a vehicle and a medium. The method includes identifying a scene of the vehicle during driving based on environmental sensing information from at least one sensor on the vehicle. The method further includes, in response to determining that the identified scene is a predetermined scene, mapping sensing data sensed by the plurality of sensors for the target into a first coordinate system, where the first coordinate system indicates a first positional relationship of the target with the road during driving. The method further includes, in response to determining that the identified scene is not the predetermined scene, mapping the sensed sensing data into a second coordinate system, the second coordinate system indicating a second positional relationship of the target to the vehicle. The method further includes determining a position of the target by fusing the sensed data in the respective coordinate systems. In this way, the appropriate coordinate system can be selected for sensing fusion according to the scene, and therefore it is ensured that the position determination for the target is accurate and reliable.

Description

Technical Field

[0001] Embodiments of the present disclosure generally relate to the field of driving, and more particularly to methods and apparatuses, devices, vehicles, and media for determining the position of a target. Background Art

[0002] In autonomous driving or assisted driving, target detection is a key technology for identifying and locating various objects around a vehicle, including other vehicles, pedestrians, road signs, and obstacles. Determining the positions of these targets can help vehicle driving systems (such as advanced driver assistance systems (ADAS) and autonomous driving (AD) systems) better understand the driving environment, and thus make safer and more effective decisions and take appropriate actions during driving.

[0003] The position of a target can be presented in a coordinate system for easy processing by a vehicle driving system, such as the vehicle's own coordinate system. Through machine learning techniques such as image recognition, various targets that appear during driving are detected and discriminated, providing important decision-making basis for the vehicle driving system. With the continuous progress of related technologies, the accuracy and real-time performance of target position determination have also been significantly improved. Summary of the Invention

[0004] Embodiments of the present disclosure provide a method and an apparatus, a device, a vehicle, and a medium for determining the position of a target.

[0005] According to a first aspect of the present disclosure, there is provided a method for determining the position of a target. The method includes identifying a scene during the driving of the vehicle based on environmental sensing information from at least one sensor on the vehicle. The method further includes, in response to determining that the identified scene is a predetermined scene, mapping the sensing data sensed by a plurality of sensors for the target into a first coordinate system, where the first coordinate system indicates a first positional relationship between the target and the road during driving. The method further includes, in response to determining that the identified scene is not a predetermined scene, mapping the sensed sensing data into a second coordinate system, where the second coordinate system indicates a second positional relationship between the target and the vehicle. The method further includes determining the position of the target by fusing the sensing data in the corresponding coordinate system.

[0006] According to a second aspect of the present disclosure, there is provided an apparatus for determining the position of a target. The apparatus includes an identification module configured to identify a scene during the driving of the vehicle based on environmental sensing information from at least one of a plurality of sensors on the vehicle. The apparatus further includes a first mapping module configured to map sensing data sensed by the plurality of sensors for the target into a first coordinate system, the first coordinate system indicating a first positional relationship between the target and the road during driving; the apparatus further includes a second mapping module configured to, in response to determining that the identified scene is not a predetermined scene, map the sensed sensing data into a second coordinate system, the second coordinate system indicating a second positional relationship between the target and the vehicle; and the apparatus further includes a fusion module configured to determine the position of the target by fusing the sensing data in the respective coordinate systems of the first coordinate system and the second coordinate system.

[0007] According to a third aspect of the present disclosure, there is provided an electronic device. The electronic device includes at least one processor. The electronic device further includes a memory coupled to the at least one processor and having instructions stored thereon that, when executed by the at least one processor, cause the electronic device to perform the steps of the method in the first aspect of the present disclosure.

[0008] According to a fourth aspect of the present disclosure, there is provided a vehicle. The vehicle includes the electronic device in the third aspect of the present disclosure.

[0009] According to a fifth aspect of the present disclosure, there is provided a computer-readable storage medium. Computer-executable instructions are stored on the computer-readable storage medium, and when the computer-executable instructions are executed by a processor of the computer, the steps of the method in the first aspect of the present disclosure are implemented.

[0010] The solution for determining the position of a target according to an embodiment of the present disclosure can select a suitable coordinate system according to the identified different scenes for fusing sensing data, thereby ensuring that the determination of the position of the target is accurate and reliable. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] By describing the exemplary embodiments of the present disclosure in more detail in conjunction with the accompanying drawings, the above and other objects, features, and advantages of the present disclosure will become more apparent. Among them, in the exemplary embodiments of the present disclosure, the same or similar reference numerals generally represent the same or similar components, assemblies, etc.

[0012] Figure 1 A schematic diagram illustrating an example environment in which the method and / or device according to an embodiment of the present disclosure may be implemented;

[0013] Figure 2 A flowchart illustrating the determination of the position of a target according to an embodiment of the present disclosure;

[0014] Figure 3 The figure illustrates a schematic diagram of a scenario-based dynamic sensing fusion process according to an embodiment of the present disclosure;

[0015] Figure 4 The figure illustrates a schematic diagram of the fusion of sensor objects to the vehicle coordinate system in a predetermined scenario;

[0016] Figure 5 The figure illustrates a schematic diagram of the fusion of sensor objects to the road structure coordinate system according to an embodiment of the present disclosure;

[0017] Figure 6 The figure illustrates a flowchart of a sensor object fusion process according to an embodiment of the present disclosure;

[0018] Figure 7 The figure shows a schematic diagram of a device for determining the position of a target according to an embodiment of the present disclosure; and

[0019] Figure 8 The figure illustrates a schematic block diagram of an example device suitable for implementing embodiments of the present disclosure.

[0020] In the respective drawings, the same or corresponding reference numerals indicate the same or corresponding parts. Detailed Description of the Embodiments

[0021] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. On the contrary, these embodiments are provided to more thoroughly and completely understand the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the protection scope of the present disclosure.

[0022] In the description of the embodiments of the present disclosure, the term "including" and its variations should be understood as open-ended inclusion, that is, "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The terms "first", "second", etc. may refer to different or the same objects, unless clearly indicated otherwise.

[0023] As described above, target detection is particularly critical in the process of autonomous driving or assisted driving, which is used to identify and locate various objects around the vehicle, including other vehicles, pedestrians, road signs, and obstacles, etc. Determining the positions of these targets can ensure that the vehicle driving system better understands the driving environment, and is particularly helpful for advanced driver assistance systems (ADAS) and autonomous driving (AD) systems to make driving decisions during driving.

[0024] The accurate position of the target contributes to the execution and improvement of various functions of the ADAS / AD system (such as adaptive cruise control, collision warning, etc.). To obtain accurate position information about the target, various in-vehicle or off-vehicle sensors can be used to sense various information about the driving environment for judgment. By inputting these sensor data into the vehicle driving system, the system can process and analyze this information in real time, and through precise calculations, accurately identify and locate the position of the target. In this way, it provides an important guarantee for the safety and reliability of autonomous driving and assisted driving.

[0025] Generally, sensor outputs can be presented in the vehicle's own coordinate system (such as polar coordinate system or Cartesian coordinate system, etc.), for example, object sensor data, including sensor objects for the target, etc. However, traditional methods do not take into account the road structure. In other words, it is independent of the road structure, while the road structure is very important for the ADAS / AD perception and calculation (P&C) module, especially in some given driving scenarios.

[0026] The fusion of sensor data usually fuses object sensor data in a fixed vehicle's own coordinate system or sensor coordinate system, which is also independent of the road structure. In addition, various sensors have different accuracy performances in different driving scenarios. For example, cameras / RADAR can have good accuracy on straight roads and flat roads, but relatively poor accuracy on curved roads or inclined roads. Therefore, when fusing object sensor data, the fusion logic and the corresponding coordinate system should be adjusted according to different driving scenarios.

[0027] In some driving scenarios, the ADAS / AD P&C module is more concerned about the relative position error of an object with respect to the lane lines or the road edge, rather than the absolute position error compared with the true position. However, even when the ADAS / AD P&C module favors scenarios with precise relative positions with respect to the lane lines or the road edge, or when the sensors have good relative position errors with respect to the lane lines or the road edge, traditional object sensor data fusion does not meet the such requirements of the ADAS / AD P&C module, nor does it utilize the such advantages of the sensors, resulting in deterioration of the position determination accuracy of the target in some driving scenarios.

[0028] To address at least the above and other potential issues, embodiments of the present disclosure provide a solution for determining the position of a target. The solution for determining the position of a target according to embodiments of the present disclosure includes identifying a scene during vehicle travel based on environmental sensing information from at least one sensor on the vehicle. The solution further includes, in response to determining that the identified scene is a predetermined scene, mapping the sensing data sensed by multiple sensors for the target into a first coordinate system, where the first coordinate system indicates a first positional relationship between the target and the road during travel. The solution also includes, in response to determining that the identified scene is not a predetermined scene, mapping the sensed sensing data into a second coordinate system, where the second coordinate system indicates a second positional relationship between the target and the vehicle. The solution further includes determining the position of the target by fusing the sensing data in the corresponding coordinate system. In this way, an appropriate coordinate system can be selected according to the scene for sensing fusion, thereby ensuring accurate and reliable determination of the position of the target.

[0029] The following refers to Figures 1 to 8 to illustrate the basic principles and several exemplary implementations of the present disclosure. It should be understood that these exemplary embodiments are provided only to enable those skilled in the art to better understand and then implement the embodiments of the present disclosure, rather than limiting the scope of the present disclosure in any way.

[0030] Figure 1 FIG. is a schematic diagram of an exemplary environment 100 in which a method and / or process according to embodiments of the present disclosure can be implemented. As Figure 1 shown, the exemplary environment 100 may include a vehicle 110, sensing data 120, a computing device 130, and a storage device 140, and these components may be coupled to each other for interaction, as Figure 1 shown. It should be understood that only a limited number of components or parts are shown in the exemplary environment 100 for implementing the embodiments of the present disclosure for the purpose of facilitating understanding and easy illustration. The embodiments of the present disclosure are not limited thereto and may further include other devices and apparatuses. For example, the exemplary environment 100 may further include a display (not shown) configured to display the result of the position determination of the target.

[0031] According to embodiments of the present disclosure, the vehicle 110 may be any type of motorized or non-motorized vehicle capable of carrying people and / or goods and being movable. The vehicle 110 typically includes one or more wheels, one or more seats, one or more load-bearing structures (such as a carriage, a cabin, etc.), one or more power systems (such as an engine, an electric motor, etc.), one or more control systems (such as a steering wheel, an accelerator pedal, etc.), and one or more safety systems (such as seat belts, airbags, etc.), and so on.

[0032] As Figure 1As shown, vehicle 110 is illustrated as an automobile. However, this is merely exemplary and not restrictive. By way of example, vehicle 110 may include, but is not limited to, passenger cars, trucks, off-road vehicles, sports cars, motorcycles, etc. In addition, vehicle 110 may be based on fossil energy or clean energy, or a combination thereof. Vehicles based on fossil energy mainly refer to vehicles that use fossil fuels such as oil and natural gas as the power source, such as traditional gasoline vehicles, diesel vehicles, etc. Vehicles based on clean energy refer to vehicles that use clean energy as the power source, such as electric vehicles, hydrogen fuel cell vehicles, solar vehicles, etc.

[0033] According to an embodiment of the present disclosure, vehicle 110 may include a plurality of sensors configured to sense various information during the driving of vehicle 110, such as driving scenarios, targets in the driving environment, etc. The sensed information can be used to implement driving-specific functions such as autonomous driving or assisted driving functions. These sensors can work in cooperation with the computing device 130 to provide precise perception and decision control of the environment around vehicle 110. The plurality of sensors included in vehicle 110 may include visual sensors (e.g., cameras, lidar LIDAR, radar RADAR, or ultrasonic sensor system USS, etc.) for capturing sensed data 120 indicating the driving environment and scenarios during the driving of vehicle 110. It should be understood that the examples of these sensors are not limited to the above, and may also include, for example, infrared sensors, depth sensors, etc.

[0034] According to an embodiment of the present disclosure, the sensed data 120 may include the scenarios during the driving of vehicle 110 and the targets in the environment around vehicle 110 (such as other vehicles, pedestrians, road signs, and obstacles, etc.). The sensed data 120 can be sensed by, for example, a plurality of sensors on vehicle 110 for these targets, can be stored in the storage device 140, and can be accessed by the computing device 130. The sensed data 120 may include object sensed data, which includes sensor objects for the targets. For example, as Figure 1 shown, the camera sensor object 121 corresponding to the camera, the LIDAR sensor object 122 corresponding to the LIDAR, the RADAR sensor object corresponding to the RADAR, and the USS sensor object corresponding to the USS, etc. It should be understood that the examples of the sensor objects for the targets are not limited to this, and may also include, for example, the infrared sensor object and the depth sensor object corresponding to the infrared sensor or the depth sensor. These sensor objects describe the positions of the targets based on the corresponding sensors.

[0035] According to an embodiment of the present disclosure, the scenarios during the driving of the vehicle 110 may include straight roads, flat roads, curved roads, inclined roads, etc. This is merely exemplary, and examples of such scenarios may include but are not limited to tunnels, intersections, overpasses, etc. In some embodiments, the sensing data 120 may be presented in the form of an image or in the form of a video including image frames, and the present disclosure does not limit this. In addition, the embodiments of the present disclosure do not limit the size and format of the sensing data 120, and appropriate size and format can be adopted according to actual needs.

[0036] According to an embodiment of the present disclosure, the computing device 130 may include an in-vehicle computing device, an out-of-vehicle computing device, and combinations thereof. The computing device 130 may have computing capabilities corresponding to the execution of ADAS / AD functionality and be configured to perform the determination of the position of the target according to the embodiments of the present disclosure. During the execution of the determination of the position of the target according to the embodiments of the present disclosure, the computing device 130 may access the storage device 140 and perform corresponding calculations. It should be understood that the computing device 130 is Figure 1 shown as one computing device in, but this is only illustrative and not restrictive, and there may be a greater number of computing devices in the example environment 100. In the following, the corresponding operations of the computing device 130 will be further described in detail.

[0037] By way of example and not limitation, the computing device 120 may include but are not limited to personal computers, laptop computers, server computers, mobile devices (such as smartphones, tablets, etc.), wearable electronic devices, multimedia players, personal digital assistants (PDAs), smart home devices, consumer electronic products, or distributed computing environments including any one or more of the above devices.

[0038] According to an embodiment of the present disclosure, the storage device 130 may be configured to store the sensing data 120 from the vehicle 110, the data stream from or to the computing device 130, etc. It should be understood that the storage device 130 is Figure 1 shown as one storage device in, but this is only illustrative and not restrictive, and there may be a greater number of storage devices in the example environment 100.

[0039] By way of example and not limitation, the storage device 130 may include but are not limited to local storage devices, remote storage devices, or combinations thereof. In some embodiments, the multiple storage devices in the storage device 130 may include but are not limited to mechanical hard disk drives (HDDs), solid state drives (SSDs), etc., and some of the multiple storage devices may be arranged locally while others may be arranged remotely, for example, coupled together via a line or a network.

[0040] Above in combination withFigure 1 An example environment 100 is described in which the methods and / or processes according to embodiments of the present disclosure may be implemented. The following will be described in conjunction with Figure 2 a flowchart of a method 200 for determining the position of a target according to an embodiment of the present disclosure. Through this method 200, it is possible to select an adapted coordinate system to fuse the sensing data according to different scenarios identified during the driving of the vehicle 110, thereby ensuring the accuracy and reliability of the determination of the position of the target.

[0041] At block 210, based on the environmental sensing information from at least one sensor among a plurality of sensors on the vehicle 110, the scenario during the driving of the vehicle 110 is identified. According to an embodiment of the present disclosure, at least one sensor among the plurality of sensors on the vehicle may be configured to identify the scenario during the driving of the vehicle 110. Since different scenarios may correspond to different road structures. Therefore, taking the driving scenario into account can significantly improve the robustness of the sensing data fusion, thereby facilitating the accurate and reliable determination of the position of the target. In some embodiments, the environmental sensing information sensed by the at least one sensor for the driving scenario may be transmitted to the computing device 130 for corresponding calculations (e.g., image recognition).

[0042] At block 220, in response to determining that the identified scenario is a predetermined scenario, the sensing data sensed by the plurality of sensors on the vehicle 110 for the target is mapped into a first coordinate system, and the first coordinate system indicates a first positional relationship between the target and the road during the driving process. In some predetermined scenarios, the consideration of the road structure is particularly important. In the case of, for example, a curved road or an inclined road, if the positional relationship between the target and the road during the driving process is excluded, it is very likely that the result of the determination of the position of the target will deteriorate, thereby affecting the performance of the ADAS / AD functionality.

[0043] According to an embodiment of the present disclosure, the first coordinate system may include a road structure coordinate system, which may map the corresponding sensor objects and the above environmental sensing information, etc. into it based on the sensing data sensed by the plurality of sensors on the vehicle 110 for the target, so as to accurately reflect the positions of the respective objects in the road structure, and further indicate the positional relationship between the target and the road during the driving process. When the sensor has a good relative position error with respect to the lane or the road edge, or when some ADAS / AD functionality requires a relative position error of the target with respect to the lane or the road edge, using such a road structure coordinate system to map the sensing data can facilitate the accurate and reliable determination of the position of the target. Hereinafter, the mapping of the road structure coordinate system according to an embodiment of the present disclosure will be further described in detail.

[0044] At block 230, in response to determining that the identified scenario is not a predetermined scenario, the sensed sensing data is mapped into a second coordinate system, where the second coordinate system indicates a second positional relationship between the target and the vehicle. In a non-predetermined scenario where the road structure has little impact on the determination of the target's position, based on the sensing data sensed by multiple sensors on the vehicle 110 for the target, the corresponding sensor objects and the above-mentioned environmental sensing information, etc., can be mapped into the second coordinate system. The second coordinate system may include a vehicle coordinate system, such as a polar coordinate system and a Cartesian coordinate system, etc., and such non-predetermined scenarios may include straight roads and flat roads, etc.

[0045] At block 240, the position of the target is determined by fusing the sensing data in the respective coordinate systems of the first coordinate system and the second coordinate system. The sensing data including object sensor data comes from multiple sensors on the vehicle 110. That is, multiple sensor objects for the target describe the position of the target by virtue of the characteristics of the corresponding sensors. Through the sensing results of multiple sensors, the advantages of some sensors in specific situations can be amplified, while the shortcomings of other sensors can be avoided. Such fusion enables the accurate and reliable determination of the position of the target. Hereinafter, the sensing data fusion according to the embodiments of the present disclosure will be further described in detail.

[0046] Figure 3 FIG. illustrates a schematic diagram of a scenario-based dynamic sensing fusion process 300 according to an embodiment of the present disclosure. As Figure 3 exemplarily shown, the dynamic sensing fusion process 300 may include a scenario identification sub-process 310, a scenario determination sub-process 315, a first mapping sub-process 320, a second mapping sub-process 330, a first fusion sub-process 340, and a second fusion sub-process 350. The dynamic sensing fusion process 300 and its sub-processes can be abstracted into a dynamic sensing fusion unit and corresponding sub-units for each sub-process (e.g., a scenario identification sub-unit, a first mapping sub-unit, etc.). These units and sub-units can be software-based components or systems for determining the position of the target and can run on a computing device (such as the computing device 130) with computing capabilities.

[0047] According to an embodiment of the present disclosure, in the scene identification sub-process 310, based on the environmental sensing information of at least one sensor among a plurality of sensors on the vehicle 110, the scene during the driving of the vehicle 100 can be identified. The identification of the scene helps to improve the performance of target position determination. In some embodiments, the sensed sensing data may include object sensing data, and by parsing such object sensing data, a plurality of sensor objects for the target can be obtained, where each sensor object among the plurality of sensor objects corresponds to one sensor among the plurality of sensors and describes the position of the target. By way of example and not limitation, based on one or more camera objects in the camera object set from a camera among the plurality of sensors, the computing device 130 can facilitate identifying, for example, a curved road scene during the driving of the vehicle 110 using, for example, image recognition technology and the like.

[0048] According to an embodiment of the present disclosure, in the scene determination sub-process 315, according to the identification result of the scene identification sub-process 310, it can be determined whether the scene during the driving of the vehicle 110 is a predetermined scene that is highly correlated with the target position determination accuracy or a non-predetermined scene that is less correlated with the target position determination accuracy. By way of example and not limitation, the predetermined scene may include but is not limited to a curved road and an inclined road, and the non-predetermined scene may include a straight road and a flat road. In some embodiments, the scene determination sub-process 315 can be implemented by the computing device 130 using a pre-trained classification model.

[0049] According to an embodiment of the present disclosure, in the first mapping sub-process 320, in response to determining that the scene during the driving of the vehicle 110 is a predetermined scene, that is, the road structure needs to be considered during the target position determination, by transforming the object sensing data in the first coordinate system, the coordinates of each sensor object among the plurality of sensor objects in the first coordinate system can be determined. The first position relationship between the target indicated by the first coordinate system and the road during the driving process includes the lateral position relationship between the target and the road. The mapping process of the sensor object to the road structure coordinate system fully considers the relative position relationship between the target and the road, so that the positions of each object can be accurately reflected in the road structure in these scenarios where the road structure needs to be considered, and further indicates the position relationship between the target and the road during the driving process. In some embodiments, an example of the road structure coordinate system may include the Frenet coordinate system. It should be understood that the first position relationship is not limited to the lateral position relationship between the target and the road, but may also include the longitudinal position relationship between the target and the vehicle 110 in the road structure coordinate system.

[0050] In some embodiments, during the driving of the vehicle 110 in a predetermined scene (such as a curved road, an inclined road, etc.), the relative distance from the lane or the road edge remains unchanged. Hereinafter, the progress of the vehicle 110 in the predetermined scene will be further described in detail with reference to the drawings.

[0051] According to an embodiment of the present disclosure, in the second mapping sub-process 330, in response to determining that the scenario during the driving of the vehicle 110 is not a predetermined scenario, that is, the road structure does not need to be considered during the determination of the target position, by converting the object sensing data in the second coordinate system, the coordinates of each sensor object among the multiple sensor objects in the second coordinate system are determined. The second position relationship between the target indicated by the second coordinate system and the road during the driving process includes the longitudinal position relationship between the target and the vehicle 110. In the case where it is determined that the road structure does not need to be considered, for example, when the vehicle 110 is traveling on a ratio road, the mapping process of the sensor object to the ego-vehicle coordinate system is more reasonable, and redundant operations that cause waste of computing power are avoided.

[0052] According to an embodiment of the present disclosure, in the first fusion sub-process 340, in response to converting the object sensing data in the first coordinate system, the sensor objects can be fused in the first coordinate system. Moreover, in the second fusion sub-process 350, in response to converting the object sensing data in the second coordinate system, the sensor objects can be fused in the second coordinate system. In this way, dynamic sensing data fusion can be performed according to different scenarios, robustly ensuring the accuracy and reliability of the determination of the target position. The improvement of the present disclosure on sensing data fusion will be further described in detail below.

[0053] Figure 4 The figure illustrates a schematic diagram of the fusion of sensor objects to the ego-vehicle coordinate system in a predetermined scenario. Figure 4 Exemplarily, it is described that the vehicle 110 travels along a curved road, for example, and there is another vehicle traveling along the curved road in front of the vehicle 110, that is, the target 410. According to an embodiment of the present disclosure, based on the analysis of the object sensing data included in the sensing data sensed by multiple sensors on the vehicle 110 for the target 410, multiple sensor objects can be obtained, such as Figure 4 the camera object 411 (circular identifier) and the RADAR object 412 (square identifier) in. It should be understood that for the convenience of illustration, only the camera object 411 and the RADAR object 412 are shown. The embodiments of the present disclosure are not limited thereto, and may also include a RADAR object corresponding to RADAR, a USS object corresponding to USS, etc.

[0054] As Figure 4As shown, sensor objects, i.e., camera object 411 and RADAR object 412, are mapped in the Cartesian coordinate system established for vehicle 110. Camera object 411 and RADAR object 412 can each describe the position of target 410. In other words, camera object 411 can indicate the position sensed by the camera for target 410, while RADAR object 412 can indicate the position sensed by the RADAR for target 410. However, the fusion result of camera object 411 and RADAR object 412 (i.e., fusion trajectory 413 (star mark)) deviates from the actual target 410 and is an inaccurate position estimate. That is to say, in such a driving scenario, the road structure must be considered, otherwise it will lead to undesired position information.

[0055] Figure 5 FIG. illustrates a schematic diagram of the fusion of sensor objects into a road structure coordinate system according to an embodiment of the present disclosure. Figure 5 Exemplarily, it is described that vehicle 110 travels along a curved road, for example, and there is another vehicle traveling along the curved road in front of vehicle 110, i.e., target 510. According to an embodiment of the present disclosure, based on the analysis of object sensing data in the sensing data sensed by a plurality of sensors included on vehicle 110 for target 510, a plurality of sensor objects can be obtained, such as Figure 4 camera object 511 (circular mark) and RADAR object 512 (square mark) in.

[0056] According to an embodiment of the present disclosure, vehicle 110 can maintain a constant relative distance from a lane (such as, Figure 5 lane lines 514 and 514’ in) or the road edge (such as, Figure 5 road edge lines 515 and 515’ in) during the driving process in a predetermined scenario. In other words, vehicle 110 can maintain traveling along the center line 516 of the lane on the curved road. The same can be true for target 510 on its corresponding lane, but the center line of the lane is not shown to avoid redundancy.

[0057] Hereinafter, for ease of understanding, the Frenet coordinate system will be described as the road structure coordinate system. It should be understood that other different road structure coordinate systems can also be adopted in the embodiments of the present disclosure. According to an embodiment of the present disclosure, based on the position of vehicle 110 itself, the coordinate system origin of the Frenet coordinate system can be defined, and based on the center line 516 of the lane along which vehicle 110 travels during the driving process, the longitudinal reference line of the coordinate system of the Frenet coordinate system (i.e., Figure 5 the S axis shown in) can be defined, and based on the perpendicular distance between the road edge line (such as road edge line 515) of vehicle 110 during the driving process and the longitudinal reference line of the coordinate system, the transverse reference line of the coordinate system of the Frenet coordinate system (i.e.,Figure 5 the L axis shown in

[0058] As Figure 5 shown, in the Frenet coordinate system established for vehicle 110, sensor objects, i.e., camera object 511 and RADAR object 512, are mapped. The camera object 511 and the RADAR object 512 can each describe the position of the target 510. In other words, the camera object 511 can indicate the position sensed by the camera for the target 510, while the RADAR object 512 can indicate the position sensed by the RADAR for the target 510. In such a driving scenario, embodiments of the present disclosure consider the road structure to make the determination of the position of object 510 more accurate and reliable.

[0059] According to an embodiment of the present disclosure, by determining the longitudinal distance of each sensor object in the sensor objects along the longitudinal reference line of the coordinate system, the longitudinal coordinate of the corresponding sensor object can be identified, and by determining the lateral distance of each sensor object in the sensor objects along the lateral reference line of the coordinate system, the lateral coordinate of the corresponding sensor object can be identified. For example, as Figure 5 shown, the abscissa of the camera object 511 can be D. After determining the coordinates of each sensor object in the Frenet coordinate system, these sensor objects can be fused to obtain an accurate position estimate of the target 510.

[0060] Figure 6 FIG. shows a flowchart of a sensor object fusion process 600 according to an embodiment of the present disclosure. At 610, the sensor weights assigned to each of the multiple sensors on vehicle 110 can be obtained, and at 620, based on the sensor weights assigned to each sensor, the coordinates of the multiple sensor objects in the corresponding coordinate systems of the first coordinate system and the second coordinate system can be aligned, and the aligned coordinates indicate the position of the target. By way of example and not limitation, sensor A may perform excellently in some aspects, while sensor B may be weaker than sensor A in these aspects. Therefore, during the fusion of the sensed objects, a larger weight X can be given to the sensor A object of sensor A, and a weight Y smaller than X can be given to the sensor B object of sensor B. In this way, during the alignment process of the coordinates of the sensor A object and the sensor B object, the coordinates of the sensor A object are more favored. The sensor object fusion process 600 according to an embodiment of the present disclosure can consider the performance strengths and weaknesses of different sensors and improve the accuracy of the position determination of the target. It should be understood that the sensor object fusion process 600 is applicable to both the road structure coordinate system and the ego-vehicle coordinate system.

[0061] Return reference Figure 5, in a road structure coordinate system (here, its example is the Frenet coordinate system), the fusion result of mapping the sensor object and performing weighted sensing fusion (i.e., the fusion trajectory 513 (star mark)) significantly and preferably deviates from the undesired fusion trajectory 513' of the target 510. Thus, the position of the target 510 can be accurately and reliably determined.

[0062] Figure 7 FIG. shows a schematic diagram of a device 700 for determining the position of a target according to an embodiment of the present disclosure. The device 700 may include a plurality of units or modules for performing corresponding steps in the method 200 as Figure 2 discussed. As Figure 7 shown, the device 700 includes: an identification module 710 configured to identify a scene during the driving of the vehicle based on environmental sensing information from at least one sensor among a plurality of sensors on the vehicle; a first mapping module 720 configured to map sensing data sensed by the plurality of sensors for the target into a first coordinate system, the first coordinate system indicating a first positional relationship between the target and the road during the driving; a second mapping module 730 configured to, in response to determining that the identified scene is not the predetermined scene, map the sensed sensing data into a second coordinate system, the second coordinate system indicating a second positional relationship between the target and the vehicle; and a fusion module 740 configured to determine the position of the target by fusing the sensing data in the corresponding coordinate systems of the first coordinate system and the second coordinate system.

[0063] In some embodiments, the sensed sensing data includes object sensing data, and the device 700 further includes an analysis module configured to obtain a plurality of sensor objects for the target by analyzing the object sensing data, each sensor object in the plurality of sensor objects corresponding to one of the plurality of sensors and describing the position of the target.

[0064] In some embodiments, the device 700 further includes a first conversion module configured to determine the coordinates of each sensor object in the plurality of sensor objects in the first coordinate system by converting the object sensing data in the first coordinate system, wherein the first positional relationship includes a lateral positional relationship between the target and the road.

[0065] In some embodiments, during the driving of the vehicle in the predetermined scene, the relative distance from the lane or the road edge remains unchanged, the predetermined scene includes a curved road or an inclined road, and the first coordinate system includes a Frenet coordinate system.

[0066] In some embodiments, the apparatus 700 further includes a coordinate system definition module configured to: define the coordinate system origin of the first coordinate system based on the position of the vehicle; define the coordinate system longitudinal reference line of the first coordinate system based on the center line of the lane along which the vehicle travels during the driving; and define the coordinate system lateral reference line of the first coordinate system based on the perpendicular distance between the road edge line of the vehicle during the driving and the coordinate system longitudinal reference line.

[0067] In some embodiments, the apparatus 700 further includes an object coordinate identification module configured to: identify the longitudinal coordinate of a corresponding sensor object by determining the longitudinal distance of each sensor object in the sensor objects along the coordinate system longitudinal reference line; and identify the lateral coordinate of the corresponding sensor object by determining the lateral distance of each sensor object in the sensor objects along the coordinate system lateral reference line.

[0068] In some embodiments, the apparatus 700 further includes a second conversion module configured to: determine the coordinates of each sensor object in the plurality of sensor objects in the second coordinate system by converting the object sensing data in the second coordinate system, where the second coordinate system includes a polar coordinate system or a Cartesian coordinate system, and where the second position relationship includes the longitudinal position relationship between the target and the vehicle.

[0069] In some embodiments, the apparatus 700 further includes a weighted sensing fusion module configured to: align the coordinates of the plurality of sensor objects in the respective coordinate systems of the first coordinate system and the second coordinate system based on the sensor weights assigned to each of the plurality of sensors, and the aligned coordinates indicate the position of the target.

[0070] In some embodiments, the plurality of sensors include a camera, a Light Detection and Ranging (LIDAR), a Radio Detection and Ranging (RADAR), or an Ultrasonic Sensor System (USS), and the sensor objects include: a camera object, a LIDAR object, a RADAR object, or a USS object.

[0071] Figure 8FIG. 0 shows a schematic block diagram of an example device 800 that can be used to implement embodiments of the present disclosure. As shown, the device 800 includes a central processing unit (CPU) 801 that can perform various appropriate actions and processes according to computer program instructions stored in a read-only memory (ROM) 802 or computer program instructions loaded from a storage unit 808 into a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the device 800 can also be stored. The CPU 801, ROM 802, and RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0072] Multiple components in the device 800 are connected to the I / O interface 805, including: an input unit 806, such as a keyboard, a mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a magnetic disk, an optical disk, etc.; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the device 800 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0073] Each of the processes and treatments described above, such as method 200 and process 300 and their sub-processes, can be executed by a processing unit 901. For example, in some embodiments, method 200 and process 300 and their sub-processes can be implemented as a computer software program that is tangibly included in a machine-readable medium, such as the storage unit 808. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the CPU 801, one or more actions of method 200 and process 300 and their sub-processes described above can be executed. According to an embodiment of the present disclosure, a vehicle is provided that can include the device 700 and / or an electronic device (including at least one processor and a memory) as described above to perform various aspects of the present disclosure.

[0074] The present disclosure can be a method, a device, an electronic device, a vehicle, a computer-readable storage medium, and / or a computer program product. The computer program product can include a computer-readable storage medium having computer-readable program instructions for performing various aspects of the present disclosure loaded thereon.

[0075] A computer-readable storage medium can be a tangible device that can hold and store instructions for use by an instruction execution device. A computer-readable storage medium may be, for example—but not limited to—an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanically encoded device such as a punched card or raised structures in grooves having instructions stored thereon, and any suitable combination of the foregoing. The computer-readable storage medium as used herein is not construed as an instantaneous signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., an optical pulse through an optical fiber cable), or an electrical signal transmitted through a wire.

[0076] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to respective computing / processing devices, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network may include a copper transmission cable, an optical fiber transmission, a wireless transmission, a router, a firewall, a switch, a gateway computer, and / or an edge server. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in each computing / processing device.

[0077] The computer program instructions for performing the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine - related instructions, microcode, firmware instructions, state - setting data, or source code or object code written in any combination of one or more programming languages, including object - oriented programming languages such as Smalltalk, C++, etc., and conventional procedural programming languages such as the "C" language or similar programming languages. The computer - readable program instructions may be executed entirely on the user's computer, partially on the user's computer, executed as a stand - alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or, alternatively, may be connected to an external computer (e.g., through the Internet using an Internet service provider). In some embodiments, by using the state information of the computer - readable program instructions to customize an electronic circuit, such as a programmable logic circuit, a field - programmable gate array (FPGA), or a programmable logic array (PLA), the electronic circuit can execute the computer - readable program instructions to implement various aspects of the present disclosure.

[0078] Aspects of the present disclosure are described herein with reference to the flowchart and / or block diagram of methods, apparatus (systems), and computer program products according to embodiments of the present disclosure. It should be understood that each block of the flowchart and / or block diagram, and the combinations of blocks in the flowchart and / or block diagram, can be implemented by computer - readable program instructions.

[0079] These computer - readable program instructions can be provided to a processing unit of a general - purpose computer, a special - purpose computer, or other programmable data - processing apparatus to produce a machine such that, when the instructions are executed by the processing unit of the computer or other programmable data - processing apparatus, a device is produced that implements the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer - readable program instructions can also be stored in a computer - readable storage medium, and these instructions cause a computer, a programmable data - processing apparatus, and / or other devices to work in a particular manner, so that the computer - readable medium storing the instructions includes a manufacture that includes instructions for implementing various aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0080] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices, causing a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other devices to produce a computer-implemented process such that the instructions executed on the computer, other programmable data processing apparatus, or other devices implement the functions / acts specified in one or more boxes of the flowchart and / or block diagram.

[0081] The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions noted in the blocks may occur out of the order noted in the figures. For example, two consecutive blocks may in fact be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block of the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented by a dedicated hardware-based system that performs the specified functions or acts, or by a combination of dedicated hardware and computer instructions.

[0082] The embodiments of the present disclosure have been described above. The above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The choice of terms used herein is intended to best explain the principles of the embodiments, the practical application, or the technical improvement of the technology in the market, or to enable other ordinary skilled in the art to understand the embodiments disclosed herein.

Claims

1. A method for determining the position of a target, comprising: Identifying a scenario during the driving of the vehicle based on environmental sensing information from at least one of a plurality of sensors on the vehicle; In response to determining that the identified scenario is a predetermined scenario, mapping sensing data sensed by the plurality of sensors for the target into a first coordinate system, the first coordinate system indicating a first positional relationship between the target and the road during the driving; In response to determining that the identified scenario is not the predetermined scenario, mapping the sensed sensing data into a second coordinate system, the second coordinate system indicating a second positional relationship between the target and the vehicle; And Determining the position of the target by fusing the sensing data in the corresponding coordinate systems of the first coordinate system and the second coordinate system.

2. The method according to claim 1, wherein the sensed sensing data includes object sensing data, and the method further comprises: Obtaining a plurality of sensor objects for the target by parsing the object sensing data, each sensor object in the plurality of sensor objects corresponding to one of the plurality of sensors and describing the position of the target.

3. The method according to claim 2, wherein mapping the sensed sensing data into the first coordinate system includes: Determining the coordinates of each sensor object in the plurality of sensor objects in the first coordinate system by transforming the object sensing data in the first coordinate system, and Wherein the first positional relationship includes a lateral positional relationship between the target and the road.

4. The method according to claim 3, wherein: The relative distance of the vehicle from the lane or the road edge remains unchanged during the driving in the predetermined scenario, the predetermined scenario includes a curved road or an inclined road, and The first coordinate system includes a Frenet coordinate system.

5. The method according to claim 4, further comprising: Defining an origin of the coordinate system of the first coordinate system based on the position of the vehicle; Defining a longitudinal reference line of the coordinate system of the first coordinate system based on the center line of the lane along which the vehicle travels during the driving; And Defining a lateral reference line of the coordinate system of the first coordinate system based on the perpendicular distance between the road edge line of the vehicle during the driving and the longitudinal reference line of the coordinate system.

6. The method according to claim 5, wherein determining the coordinates of each sensor object in the plurality of sensor objects in the first coordinate system includes: Identifying the longitudinal coordinates of the corresponding sensor object by determining the longitudinal distance of each sensor object in the sensor object along the longitudinal reference line of the coordinate system; And Identifying the lateral coordinates of the corresponding sensor object by determining the lateral distance of each sensor object in the sensor object along the lateral reference line of the coordinate system.

7. The method according to claim 2, wherein mapping the sensed sensing data into the second coordinate system includes: Determining the coordinates of each sensor object among the plurality of sensor objects in the second coordinate system by transforming the object sensing data in the second coordinate system, and wherein the second coordinate system includes a polar coordinate system or a Cartesian coordinate system, and wherein the second positional relationship includes the longitudinal positional relationship between the target and the vehicle.

8. The method according to claim 3 or 7, wherein determining the position of the target by fusing the sensing data in the respective coordinate systems of the first coordinate system and the second coordinate system includes: Aligning the coordinates of the plurality of sensor objects in the respective coordinate systems of the first coordinate system and the second coordinate system based on sensor weights assigned to each of the plurality of sensors, the aligned coordinates indicating the position of the target.

9. The method according to claim 8, wherein: The plurality of sensors includes a camera, a Light Detection and Ranging (LIDAR), a Radio Detection and Ranging (RADAR), or an Ultrasonic Sensor System (USS), and The sensor objects include: a camera object, a LIDAR object, a RADAR object, or a USS object.

10. An apparatus for determining the position of a target, comprising: An identification module configured to identify a scene during travel of the vehicle based on environmental sensing information from at least one of a plurality of sensors on the vehicle; A first mapping module configured to, in response to determining that the identified scene is a predetermined scene, map sensing data sensed by the plurality of sensors for the target into a first coordinate system, the first coordinate system indicating a first positional relationship between the target and a road during the travel; A second mapping module configured to, in response to determining that the identified scene is not the predetermined scene, map the sensed sensing data into a second coordinate system, the second coordinate system indicating a second positional relationship between the target and the vehicle; And A fusion module configured to determine the position of the target by fusing the sensing data in the respective coordinate systems of the first coordinate system and the second coordinate system.

11. An electronic device, comprising: At least one processor; And A memory coupled to the at least one processor and having instructions stored thereon, the instructions, when executed by the at least one processor, cause the device to perform the method according to any one of claims 1-9.

12. A vehicle comprising the electronic device according to claim 11.

13. A computer-readable storage medium having computer-executable instructions stored thereon, wherein the computer-executable instructions, when executed by a processor, implement the method according to any one of claims 1-9.

Images