Underground vehicle positioning method, device, equipment, medium and product

Abstract

The invention discloses an underground vehicle positioning method, device and equipment, a medium and a product. The method comprises the following steps: determining a current candidate pose set corresponding to a to-be-positioned vehicle according to a historical candidate pose set corresponding to the to-be-positioned vehicle at a previous moment and a plurality of historical pose variations; performing semantic matching according to the roadway semantic features, a semantic map corresponding to the mine roadway where the to-be-positioned vehicle is located and the current candidate pose set to determine a semantic matching pose; performing point cloud matching according to the semantic matching pose, the scanning point cloud data corresponding to the to-be-positioned vehicle at the current moment and a point cloud map corresponding to the mine laneway to determine a point cloud matching pose; and carrying out pose fusion on the point cloud matching pose and a predetermined track prediction pose corresponding to the to-be-positioned vehicle at the current moment so as to obtain a target positioning pose corresponding to the to-be-positioned vehicle. According to the technical scheme, the effect of accurately positioning the underground vehicle according to integration and cooperative work of various vehicle-mounted sensors is achieved.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving environment perception technology, and in particular to an underground vehicle positioning method, device, equipment, medium and product. Background Art

[0002] Underground mining areas have natural advantages such as few people and single obstacles, which are conducive to the development of unmanned driving applications. Underground mining is dangerous. Mining requires the deployment of a large number of equipment, vehicles, and personnel underground. Disasters and accidents caused by various natural or man-made factors pose a great threat to the personal safety of underground workers. Effective organization and management of underground personnel and vehicles, as well as rescue of accidents and disasters, require accurate location data of underground personnel, vehicles, and equipment. Remote control and intelligent control of underground equipment are even more inseparable from real-time and accurate location data of underground equipment. Precise positioning technology has become an important technical support for safe production in mines.

[0003] In the related technology, underground vehicle positioning is usually carried out by installing positioning equipment (such as UWB or magnetic nail hardware equipment) in the mine, and then combining the positioning equipment with the vehicle sensor data to perform underground vehicle positioning. However, this positioning method may have problems such as complicated operation process, time-consuming and labor-intensive, and high installation and maintenance costs. In addition, there are various obstacles underground, such as ores, equipment, pipelines, etc. These obstacles may block the UWB signal and the scanning path of the lidar, resulting in low vehicle positioning accuracy. Summary of the invention

[0004] The present invention provides an underground vehicle positioning method, device, equipment, medium and product to achieve the effect of accurately positioning the underground vehicle based on the integration and coordinated operation of multiple vehicle-mounted sensors.

[0005] According to one aspect of the present invention, a method for positioning an underground vehicle is provided, the method comprising:

[0006] Determine a current candidate pose set corresponding to the vehicle to be positioned at the current moment according to a historical candidate pose set corresponding to the last moment of the vehicle to be positioned at the current moment and a predetermined historical pose change corresponding to the vehicle to be positioned at multiple historical moments;

[0007] Acquire the lane semantic features corresponding to the vehicle to be located at the current moment, and perform semantic matching according to the lane semantic features, the semantic map corresponding to the mine lane where the vehicle to be located is located, and the current candidate pose set, so as to determine the semantic matching pose corresponding to the vehicle to be located at the current moment; wherein the lane semantic features are used to indicate lane traffic objects existing in the lane;

[0008] Performing point cloud matching according to the semantic matching posture, the scanning point cloud data corresponding to the vehicle to be positioned at the current moment, and the point cloud map corresponding to the mine tunnel to determine the point cloud matching posture corresponding to the vehicle to be positioned at the current moment;

[0009] The point cloud matching posture and the predetermined trajectory prediction posture corresponding to the vehicle to be positioned at the current moment are fused to obtain the target positioning posture corresponding to the vehicle to be positioned at the current moment.

[0010] According to another aspect of the present invention, there is provided an underground vehicle positioning device, the device comprising:

[0011] A candidate pose set determination module is used to determine a current candidate pose set corresponding to the vehicle to be positioned at the current moment according to a historical candidate pose set corresponding to the previous moment of the vehicle to be positioned at the current moment and a predetermined historical pose change corresponding to the vehicle to be positioned at multiple historical moments;

[0012] A semantic matching posture determination module is used to obtain the lane semantic features corresponding to the vehicle to be located at the current moment, and perform semantic matching based on the lane semantic features, the semantic map corresponding to the mine lane where the vehicle to be located is located, and the current candidate posture set to determine the semantic matching posture corresponding to the vehicle to be located at the current moment; wherein the lane semantic features are used to indicate lane traffic objects existing on the lane;

[0013] A point cloud matching posture determination module is used to perform point cloud matching according to the semantic matching posture, the scanning point cloud data corresponding to the vehicle to be positioned at the current moment, and the point cloud map corresponding to the mine tunnel, so as to determine the point cloud matching posture corresponding to the vehicle to be positioned at the current moment;

[0014] The positioning posture determination module is used to perform posture fusion on the point cloud matching posture and the predetermined trajectory prediction posture corresponding to the vehicle to be positioned at the current moment, so as to obtain the target positioning posture corresponding to the vehicle to be positioned at the current moment.

[0015] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0016] at least one processor; and

[0017] a memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the underground vehicle positioning method described in any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to implement the underground vehicle positioning method described in any embodiment of the present invention when executed by a processor.

[0020] According to another aspect of the present invention, a computer program product is provided. The computer program product includes a computer program. When the computer program is executed by a processor, the underground vehicle positioning method described in any embodiment of the present invention is implemented.

[0021] The technical solution of the embodiment of the present invention determines the current candidate pose set corresponding to the vehicle to be positioned at the current moment according to the historical candidate pose set corresponding to the previous moment of the vehicle to be positioned at the current moment and the predetermined historical pose change corresponding to multiple historical moments of the vehicle to be positioned; further, obtains the semantic features of the laneway corresponding to the vehicle to be positioned at the current moment, and performs semantic matching according to the laneway semantic features, the semantic map corresponding to the mine laneway where the vehicle to be positioned is located, and the current candidate pose set to determine the semantic matching pose corresponding to the vehicle to be positioned at the current moment; further, according to the semantic matching pose, the scanning point cloud data corresponding to the vehicle to be positioned at the current moment and the change amount of the historical pose corresponding to the mine laneway where the vehicle to be positioned is located, the semantic matching pose is determined. Point cloud matching is performed on the point cloud map corresponding to the mine tunnel to determine the point cloud matching posture corresponding to the vehicle to be positioned at the current moment; further, the point cloud matching posture and the predetermined trajectory prediction posture corresponding to the vehicle to be positioned at the current moment are fused to obtain the target positioning posture corresponding to the vehicle to be positioned at the current moment, which solves the problems of complicated operation process, time-consuming and labor-intensive, high cost and low positioning accuracy in the underground vehicle positioning method in the related technology, realizes the effect of accurately positioning the underground vehicle based on the integration and collaborative work of multiple on-board sensors, and realizes the effect of improving the vehicle positioning accuracy, positioning stability and reliability on the basis of reducing the positioning cost.

[0022] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 is a flow chart of an underground vehicle positioning method provided according to Embodiment 1 of the present invention;

[0025] Figure 2 is a flow chart of an underground vehicle positioning method provided according to Embodiment 2 of the present invention;

[0026] Figure 3 is a structural schematic diagram of an underground vehicle positioning device provided according to Embodiment 3 of the present invention;

[0027] Figure 4 It is a structural schematic diagram of an electronic device for implementing the underground vehicle positioning method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] Embodiment 1

[0031] Figure 1This is a flow chart of a method for locating an underground vehicle provided in the first embodiment of the present invention. This embodiment is applicable to the situation of locating an underground vehicle. The method can be executed by an underground vehicle positioning device. The underground vehicle positioning device can be implemented in the form of hardware and / or software. The underground vehicle positioning device can be configured in a terminal and / or a server. Figure 1 As shown, the method includes:

[0032] S110, determining a current candidate pose set corresponding to the vehicle to be located at the current moment according to a historical candidate pose set corresponding to the previous moment of the vehicle to be located at the current moment and a predetermined historical pose change corresponding to the vehicle to be located at multiple historical moments.

[0033] Among them, the vehicle to be located can be a vehicle to be located in a mine. In this embodiment, the vehicle to be located is a vehicle located in a mine tunnel, that is, a vehicle traveling in a mine tunnel. The vehicle to be located can be any type of vehicle, optionally, an unmanned vehicle or an automatic driving vehicle. The current moment can be the moment when the vehicle is to be located. The historical candidate pose set can include multiple historical candidate poses corresponding to the vehicle to be located at the previous moment. The historical candidate pose can be used to characterize the poses that may exist in the vehicle to be located at the previous moment. The historical candidate pose can be determined based on the historical candidate pose corresponding to the vehicle to be located at the previous moment and the historical pose change amount at multiple historical moments. It should be noted that the multiple initial candidate poses corresponding to the vehicle to be located at the initial moment can be determined based on the starting position and initial speed corresponding to the vehicle to be located at the initial moment and the environmental information corresponding to the mine where the vehicle to be located is located. The historical moment can be any historical moment before the current moment. The historical pose change amount can be used to characterize the pose change information corresponding to the vehicle to be located at the historical moment. The historical pose change amount can include the historical position change amount and the historical pose change amount. The current candidate pose set may include multiple current candidate poses corresponding to the vehicle to be positioned at the current moment. The current candidate pose may be understood as a pose that the vehicle to be positioned may have at the current moment. The multiple current candidate poses may include the pose required by the vehicle to be positioned during the positioning process at the current moment.

[0034] In this embodiment, the amount of historical position change can be determined based on the vehicle speed information of the vehicle to be located, that is, the amount of historical position change corresponding to the historical moment can be determined based on the historical speed corresponding to the historical moment, the historical speed of the previous moment of the historical moment, and the time interval between the historical moment and the previous moment. More specifically, the historical speed corresponding to the historical moment and the historical speed of the previous moment of the historical moment can be integrated according to the time interval to obtain the amount of historical position change corresponding to the historical moment. The amount of historical attitude change can be determined based on the angular velocity information of the vehicle to be located, that is, the amount of historical attitude change corresponding to the historical moment can be determined based on the historical angular velocity corresponding to the historical moment, the historical angular velocity corresponding to the previous moment of the historical moment, and the time interval between the historical moment and the previous moment. More specifically, the historical angular velocity corresponding to the historical moment and the historical angular velocity of the previous moment of the historical moment can be integrated according to the time interval to obtain the amount of historical attitude change corresponding to the historical moment. It should be noted that the historical angular velocity can be obtained from the inertial measurement unit (IMU) data.

[0035] In this embodiment, in order to determine the positioning posture corresponding to the vehicle to be located at the current moment, the current candidate posture set corresponding to the vehicle to be located at the current moment can be determined first, and then the positioning posture corresponding to the vehicle to be located at the current moment can be determined based on the multiple current candidate postures included in the current candidate posture set. The current candidate posture set corresponding to the vehicle to be located at the current moment can be determined based on the historical candidate posture set corresponding to the previous moment of the vehicle to be located at the current moment and the historical posture changes corresponding to multiple historical moments.

[0036] Optionally, based on the set of historical candidate postures corresponding to the previous moment of the current moment of the vehicle to be located and the predetermined amount of change in historical postures corresponding to multiple historical moments of the vehicle to be located, the current candidate posture set corresponding to the current moment of the vehicle to be located is determined, including: obtaining the set of historical candidate postures corresponding to the previous moment of the current moment of the vehicle to be located and the amount of change in historical postures corresponding to multiple historical moments; for each historical candidate posture in the set of historical candidate postures, determining the product between the historical candidate posture and multiple historical posture transformation amounts to obtain the current candidate posture corresponding to the current moment; and determining the current candidate posture set corresponding to the current moment of the vehicle to be located based on multiple current candidate postures corresponding to the current moments.

[0037] As an optional implementation of this embodiment, a set of historical candidate poses corresponding to the previous moment of the current moment and the historical pose changes corresponding to multiple historical moments of the vehicle to be located can be obtained. Furthermore, for each historical candidate pose in the set of historical candidate poses, the product between the historical candidate pose and the multiple historical pose changes can be determined, and the obtained product is used as the current candidate pose corresponding to the current moment. Furthermore, the current pose set corresponding to the vehicle to be located at the current moment can be constructed based on the multiple current candidate poses corresponding to the current moments.

[0038] S120, obtaining the semantic features of the laneway corresponding to the vehicle to be located at the current moment, and performing semantic matching based on the semantic features of the laneway, the semantic map corresponding to the mine laneway where the vehicle to be located is located, and multiple current candidate pose sets to determine the semantic matching pose corresponding to the vehicle to be located at the current moment.

[0039] Among them, the tunnel semantic feature is used to indicate the tunnel traffic objects existing in the tunnel. The tunnel semantic feature can be understood as a feature that can reflect the basic attributes of the tunnel, which can help to subjectively understand and recognize the tunnel. Optionally, the tunnel semantic feature can include tunnel markings, traffic signs, tunnel boundaries, signal lights, etc. Mine tunnels are a general term for various underground spaces that are excavated in different rocks along different directions, at different inclinations, in different sections and lengths, and serve different ranges and are used for different purposes. Semantic maps can usually be a high-level map representation. Semantic maps not only contain geometric information of geographic spatial locations, but also contain semantic information of various objects, tunnels, traffic rules, etc. in the environment. In general, the environmental data of the mine tunnel can be collected by sensors installed on the vehicle to obtain three-dimensional data, image data, and location data of tunnel traffic objects of the mine tunnel. Furthermore, the acquired environmental data of the mine tunnel can be used to construct a semantic map, and the constructed semantic map can be annotated with semantic features to mark the tunnel traffic objects in the mine tunnel on the map. Furthermore, the annotated semantic map can be used as a semantic map corresponding to the mine tunnel. The semantic matching pose can be understood as a matching pose determined by a semantic matching operation. It should be noted that the semantic matching pose can be one of the multiple current candidate poses included in the current candidate pose set.

[0040] In this embodiment, the lane semantic features corresponding to the vehicle to be positioned at the current moment can be determined based on the lane image of the mine lane where the vehicle to be positioned is located at the current moment.

[0041] Optionally, obtaining the semantic features of the laneway corresponding to the vehicle to be located at the current moment includes: acquiring images of the mine laneway where the vehicle to be located is located by a camera device pre-installed on the vehicle to be located, so as to obtain the laneway image corresponding to the vehicle to be located at the current moment; and extracting semantic features of the laneway image to obtain the semantic features of the laneway corresponding to the vehicle to be located at the current moment.

[0042] The camera device may be a vehicle-mounted camera. The lane image may be an image reflecting the surrounding environment of the vehicle to be located. In this embodiment, the semantic feature extraction of the lane image may include multiple implementations. Optionally, the semantic feature extraction of the lane image is performed according to a visual semantic segmentation algorithm; the semantic feature extraction of the lane image is performed according to a semantic segmentation model, etc.

[0043] As an optional implementation of this embodiment, during the driving process of the vehicle to be positioned, the image of the mine tunnel where the vehicle to be positioned is located can be collected by a camera device pre-installed on the vehicle to be positioned. Then, the tunnel image corresponding to the vehicle to be positioned at the current moment can be obtained. Furthermore, the tunnel image can be input into a pre-trained semantic segmentation model to extract features of the tunnel image based on the semantic segmentation model to obtain the semantic features of the tunnel corresponding to the vehicle to be positioned at the current moment.

[0044] In this embodiment, when the semantic features of the lane corresponding to the vehicle to be located at the current moment are obtained, the semantic map corresponding to the mine lane where the vehicle to be located is located can be obtained. Then, semantic matching can be performed based on the semantic features of the lane, the semantic feature elements in the semantic map, and the current candidate pose set. Then, the semantic matching pose corresponding to the vehicle to be located at the current moment can be determined from multiple current candidate poses in the current candidate pose set based on the semantic matching results.

[0045] S130, performing point cloud matching according to the semantic matching posture, the scanning point cloud data corresponding to the vehicle to be positioned at the current moment, and the point cloud map corresponding to the mine tunnel, so as to determine the point cloud matching posture corresponding to the vehicle to be positioned at the current moment.

[0046] Among them, the scanning point cloud data can be understood as the point cloud data obtained after scanning the surrounding environment of the vehicle through the vehicle-mounted radar device. In this embodiment, the scanning point cloud data can be the point cloud data obtained after scanning the surrounding environment of the vehicle to be positioned by the vehicle-mounted radar device pre-set on the vehicle to be positioned. In general, when the vehicle to be positioned equipped with the vehicle-mounted radar device is driving in the mine tunnel, the surrounding environment of the vehicle to be positioned can be scanned by the vehicle-mounted radar device. Then, the point cloud data of the surrounding environment of the vehicle to be positioned can be obtained, and the scanned point cloud data can be used as the scanning point cloud data. The point cloud map can be a pre-constructed three-dimensional point cloud map of the mine tunnel. In general, the environmental point cloud data of the mine tunnel can be obtained, and the feature information in the environmental point cloud data can be extracted in time through SLAM. Then, a three-dimensional point cloud map of the mine tunnel is constructed based on the feature information. Among them, the environmental point cloud data is the sensor (such as laser radar, camera, inertial measurement unit, etc.) mounted on the mobile device or robot to obtain the perception information of the surrounding environment. The point cloud matching posture can be understood as the matching posture determined by the point cloud matching operation.

[0047] In this embodiment, when the semantic matching posture is obtained, the semantic matching posture can be used as an input parameter in the point cloud matching operation. Further, the scanning point cloud data corresponding to the vehicle to be located at the current moment and the point cloud map corresponding to the mine tunnel where the vehicle to be located is located can be obtained. Furthermore, point cloud matching can be performed based on the semantic matching posture, the scanning point cloud data and the point cloud map to obtain the point cloud matching posture corresponding to the vehicle to be located at the current moment.

[0048] Optionally, point cloud matching is performed based on the semantic matching posture, the scanning point cloud data corresponding to the vehicle to be located at the current moment, and the point cloud map corresponding to the mine tunnel to determine the point cloud matching posture corresponding to the vehicle to be located, including: determining the product between the semantic matching posture and a predetermined transformation parameter matrix to obtain the point cloud posture to be processed; determining the matching error based on the point cloud posture to be processed, the scanning point cloud data, and the actual point cloud data on the point cloud map corresponding to the scanning point cloud data; adjusting the point cloud posture to be processed with the minimum matching error as the optimization goal, and taking the point cloud posture to be processed corresponding to the minimum matching error as the point cloud matching posture corresponding to the vehicle to be located.

[0049] Among them, the transformation parameter matrix can be used to characterize the conversion relationship between the laser radar coordinate system and the camera coordinate system. The transformation parameter matrix can generally describe how to transform a point in one coordinate system into another coordinate system, thereby realizing data fusion between the laser radar and the camera. The transformation parameter matrix may include rotation transformation parameters and translation transformation parameters. In general, the transformation parameter matrix can be calibrated by the external parameters of the laser radar and the camera. Furthermore, the transformation parameter matrix can be determined according to the external parameter calibration result. In this embodiment, the semantic matching posture is obtained by matching the lane image and the semantic map collected by the vehicle-mounted camera device, and is the posture information corresponding to the camera coordinate system. Furthermore, the posture of the point cloud to be processed obtained by multiplying the semantic matching posture with the transformation parameter matrix can be understood as converting the posture in the camera coordinate system to the posture in the laser radar coordinate system. The matching error can be used to characterize the degree of matching difference between the scanned point cloud data and the point cloud map. The point cloud matching algorithm is mainly used to align two or more frames of point cloud data to obtain the relative posture or transformation matrix between them. Optionally, the point cloud matching algorithm includes a point-to-plane point cloud matching algorithm (Iterative Closest Point, ICP), a normal vector iterative closest point algorithm (Normal Iterative Closest Point, NICP), etc.

[0050] As an optional implementation of this embodiment, the on-board radar equipment and the on-board camera device of the vehicle to be located can be calibrated with external parameters to obtain a transformation parameter matrix for characterizing the conversion relationship between the laser radar coordinate system and the camera coordinate system. Further, when the semantic matching posture is obtained, the product between the semantic matching posture and the transformation parameter matrix can be determined, and the obtained product can be used as the point cloud posture to be processed corresponding to the vehicle to be located at the current moment. Further, the point cloud posture to be processed, the scanned point cloud data, and the actual point cloud data corresponding to the scanned point cloud data on the point cloud map can be processed according to the error function corresponding to the preset point cloud matching algorithm to obtain the matching error. Further, the point cloud data to be processed can be adjusted with the minimum matching error as the optimization goal. Furthermore, the point cloud posture to be processed corresponding to the minimum matching error can be used as the point cloud matching posture corresponding to the vehicle to be located at the current moment.

[0051] Exemplarily, the matching error may be expressed based on the following formula:

[0052]

[0053] Where E represents the matching error; p i represents the i-th point in the scanned point cloud data; T lm Indicates the pose of the point cloud to be processed; q i Indicates the actual scan data on the point cloud map and pi Corresponding points; λ represents the regularization coefficient, optional, λ∈[0.35,0.55].

[0054] S140, performing posture fusion on the point cloud matching posture and the predetermined trajectory prediction posture corresponding to the current moment of the vehicle to be positioned, so as to obtain the target positioning posture corresponding to the current moment of the vehicle to be positioned.

[0055] Among them, the trajectory prediction posture can be understood as the vehicle posture calculated by trajectory extrapolation. The target positioning posture can be used to characterize the positioning information corresponding to the vehicle to be positioned at the current moment. In general, the vehicle to be positioned can be positioned by the target positioning posture, so as to obtain the vehicle position and vehicle driving status of the vehicle to be positioned in time. The target positioning posture can at least include the vehicle position and vehicle driving status.

[0056] In this embodiment, the trajectory prediction posture corresponding to the current moment of the vehicle to be located can be determined based on the historical actual posture corresponding to the vehicle to be located at the previous moment. Optionally, the trajectory prediction posture is determined by: obtaining the historical actual posture corresponding to the vehicle to be located at the previous moment and the current posture change corresponding to the current moment; determining the product between the historical actual posture and the current posture change to obtain the trajectory prediction posture corresponding to the vehicle to be located at the current moment.

[0057] The historical actual position and posture may be the actual vehicle position and posture of the vehicle to be positioned at the previous moment before the current moment. The current position and posture change amount may be used to characterize the position and posture change from the previous moment to the current moment. The current position and posture change amount may include the current position change amount and the current posture change amount.

[0058] In this embodiment, the current vehicle speed of the vehicle to be located at the current moment and the historical vehicle speed at the previous moment can be obtained. Further, the time interval between the current moment and the previous moment can be determined, and the current vehicle speed and the historical vehicle speed can be integrated according to the time interval to obtain the current position change corresponding to the current moment. And, the current vehicle angular velocity of the vehicle to be located at the current moment and the historical vehicle angular velocity at the previous moment can be obtained according to the inertial measurement unit. Further, the time interval between the current moment and the previous moment can be determined, and the current vehicle angular velocity and the historical vehicle angular velocity can be integrated according to the time interval to obtain the current posture change corresponding to the current moment.

[0059] As an optional implementation of this embodiment, the current vehicle speed of the vehicle to be located at the current moment and the historical vehicle speed at the previous moment can be obtained, and the current position change corresponding to the vehicle to be located at the current moment can be determined based on the current vehicle speed and the historical vehicle speed; and the current vehicle angular velocity of the vehicle to be located at the current moment and the historical vehicle angular velocity of the vehicle to be located at the previous moment can be obtained, and the current posture change corresponding to the vehicle to be located at the current moment can be determined based on the current vehicle angular velocity and the historical vehicle angular velocity. Furthermore, the current position change and the current posture change can be used as the current posture change corresponding to the vehicle to be located at the current moment. Further, the historical actual posture corresponding to the vehicle to be located at the previous moment and the current posture change corresponding to the current moment can be obtained. Further, the product between the historical actual posture and the current posture change can be determined, and the product can be used as the trajectory prediction posture corresponding to the vehicle to be located at the current moment.

[0060] In practical applications, the trajectory prediction pose can usually be directly used as the vehicle positioning pose. However, the trajectory prediction pose may have a low pose information accuracy, which in turn leads to a low positioning accuracy of the vehicle positioning pose.

[0061] In view of the above situation, in this embodiment, the corresponding matching postures in various situations can be fused by fusion positioning. Then, the fused posture can be used as the target positioning posture corresponding to the vehicle to be positioned at the current moment.

[0062] Optionally, the point cloud matching posture and the predetermined trajectory prediction posture corresponding to the vehicle to be located at the current moment are posture fused to obtain the target positioning posture corresponding to the vehicle to be located at the current moment, including: interpolating and fusing the point cloud matching posture and the trajectory prediction posture according to a fusion positioning algorithm, and using the fused posture as the target positioning posture corresponding to the vehicle to be located at the current moment.

[0063] The fusion positioning algorithm may be an algorithm for fusing at least two postures to obtain a final positioning posture.

[0064] As an optional implementation of this embodiment, the point cloud matching pose and trajectory prediction pose corresponding to the current moment of the vehicle to be positioned can be interpolated and fused according to the fusion positioning algorithm, and the fused pose can be output. Furthermore, the fused pose can be used as the target positioning pose corresponding to the current moment of the vehicle to be positioned.

[0065] The technical solution of the embodiment of the present invention determines the current candidate pose set corresponding to the vehicle to be positioned at the current moment according to the historical candidate pose set corresponding to the previous moment of the vehicle to be positioned at the current moment and the predetermined historical pose change corresponding to multiple historical moments of the vehicle to be positioned; further, obtains the semantic features of the laneway corresponding to the vehicle to be positioned at the current moment, and performs semantic matching according to the laneway semantic features, the semantic map corresponding to the mine laneway where the vehicle to be positioned is located, and the current candidate pose set to determine the semantic matching pose corresponding to the vehicle to be positioned at the current moment; further, according to the semantic matching pose, the scanning point cloud data corresponding to the vehicle to be positioned at the current moment and the change amount of the historical pose corresponding to the mine laneway where the vehicle to be positioned is located, the semantic matching pose is determined. Point cloud matching is performed on the point cloud map corresponding to the mine tunnel to determine the point cloud matching posture corresponding to the vehicle to be positioned at the current moment; further, the point cloud matching posture and the predetermined trajectory prediction posture corresponding to the vehicle to be positioned at the current moment are fused to obtain the target positioning posture corresponding to the vehicle to be positioned at the current moment, which solves the problems of complicated operation process, time-consuming and labor-intensive, high cost and low positioning accuracy in the underground vehicle positioning method in the related technology, realizes the effect of accurately positioning the underground vehicle based on the integration and collaborative work of multiple on-board sensors, and realizes the effect of improving the vehicle positioning accuracy, positioning stability and reliability on the basis of reducing the positioning cost.

[0066] Embodiment 2

[0067] Figure 2 It is a flow chart of an underground vehicle positioning method provided by the second embodiment of the present invention. On the basis of the above-mentioned embodiment, the method for determining the semantic matching posture is further refined. Optionally, semantic matching is performed according to the semantic features of the tunnel, the semantic map corresponding to the mine tunnel where the vehicle to be positioned is located, and the current candidate posture set to determine the semantic matching posture corresponding to the vehicle to be positioned at the current moment, including: for each current candidate posture in the current candidate posture set, according to the target candidate posture, the semantic features of the tunnel and the semantic map, determine the target weight corresponding to the target candidate posture; according to the target weights corresponding to multiple current candidate postures, determine the semantic matching posture corresponding to the vehicle to be positioned at the current moment from multiple current candidate postures. The specific implementation method can refer to the technical solution of this embodiment. Among them, the technical terms that are the same or similar to those in the above-mentioned embodiments are not repeated here.

[0068] like Figure 2 As shown, the method includes:

[0069] S210, determining a current candidate pose set corresponding to the vehicle to be located at the current moment according to a historical candidate pose set corresponding to the previous moment of the vehicle to be located at the current moment and a predetermined historical pose change corresponding to the vehicle to be located at multiple historical moments.

[0070] S220, obtaining the lane semantic features corresponding to the vehicle to be positioned at the current moment, and for each current candidate posture in the current candidate posture set, determining the target weight corresponding to the current candidate posture according to the current candidate posture, the lane semantic features and the semantic map.

[0071] The target weight may be a value representing the likelihood of the current candidate pose. Generally, the higher the target weight, the higher the likelihood that the candidate pose corresponding to the target weight is the final desired matching pose.

[0072] In this embodiment, after obtaining the current candidate pose set corresponding to the vehicle to be positioned at the current moment and obtaining the lane semantic features corresponding to the vehicle to be positioned at the current moment, for each current candidate pose in the current candidate pose set, the matching distance between the lane semantic features and the semantic feature elements corresponding to the lane semantic features in the semantic map is determined according to the current candidate pose, the lane semantic features and the semantic map. Further, the target weight corresponding to the current candidate pose can be determined according to the matching distance.

[0073] Optionally, a target weight corresponding to the current candidate posture is determined based on the current candidate posture, the lane semantic features and the semantic map, including: determining the product between the current candidate posture and the lane semantic features to obtain the visual detection features corresponding to the current candidate posture; determining the distance between the visual detection features and the semantic feature elements corresponding to the lane semantic features in the semantic map to obtain the semantic matching distance corresponding to the current candidate posture; and determining the target weight corresponding to the current candidate posture based on the semantic matching distance.

[0074] As an optional implementation of the first embodiment of this embodiment, for each current candidate pose in the current candidate pose set, the product between the current candidate pose and the lane semantic feature can be determined, and the obtained product can be used as the visual detection feature corresponding to the current candidate pose. Further, the semantic feature element corresponding to the lane semantic feature in the semantic map can be determined, and the distance between the visual detection feature and the semantic feature element can be determined, and the obtained distance can be used as the semantic matching distance corresponding to the current candidate pose. Furthermore, the semantic matching distance can be processed according to a Gaussian function to obtain a target weight corresponding to the current candidate pose.

[0075] Exemplarily, the semantic matching distance may be determined based on the following formula:

[0076]

[0077] Among them, dist i represents the semantic matching distance corresponding to the i-th current candidate pose; T cm represents the current candidate pose; s jrepresents the semantic feature of the jth lane; m j Indicates the semantic map with s j Corresponding semantic feature elements.

[0078] Exemplarily, the target weight may be expressed based on the following formula:

[0079]

[0080] in, represents the target weight corresponding to the i-th current candidate pose; μ represents the mean of the semantic matching distance; σ represents the standard deviation of the semantic matching distance; dist i Represents the semantic matching distance corresponding to the i-th current candidate pose.

[0081] S230. Determine, according to the target weights corresponding to the multiple current candidate postures, a semantic matching posture corresponding to the vehicle to be located at the current moment from the multiple current candidate postures.

[0082] In this embodiment, when the target weight corresponding to each current candidate posture is obtained, the semantic matching posture corresponding to the vehicle to be positioned at the current moment can be determined from the multiple current candidate postures according to the multiple target weights.

[0083] Optionally, based on the target weights corresponding to multiple current candidate postures, the semantic matching posture corresponding to the vehicle to be located at the current moment is determined from the multiple current candidate postures, including: determining the target weight with the largest weight value based on the multiple target weights, and using the current candidate posture corresponding to the determined target weight as the semantic matching posture corresponding to the vehicle to be located at the current moment.

[0084] As an optional implementation of this embodiment, the target weight with the largest weight value can be determined from multiple target weights. Further, the current candidate posture corresponding to the determined target weight can be used as the semantic matching posture corresponding to the vehicle to be located at the current moment.

[0085] S240, performing point cloud matching according to the semantic matching posture, the scanning point cloud data corresponding to the vehicle to be positioned at the current moment, and the point cloud map corresponding to the mine tunnel, so as to determine the point cloud matching posture corresponding to the vehicle to be positioned at the current moment.

[0086] S250, performing posture fusion on the point cloud matching posture and the predetermined trajectory prediction posture corresponding to the current moment of the vehicle to be positioned, so as to obtain the target positioning posture corresponding to the current moment of the vehicle to be positioned.

[0087] The technical solution of the embodiment of the present invention obtains the lane semantic features corresponding to the vehicle to be located at the current moment, and for each current candidate posture in the current candidate posture set, determines the target weight corresponding to the current candidate posture according to the target candidate posture, the lane semantic features and the semantic map; further, according to the target weights corresponding to multiple current candidate postures, the semantic matching posture corresponding to the vehicle to be located at the current moment is determined from multiple current candidate postures, thereby achieving the effect of accurately positioning the underground vehicle by extracting and matching the semantic features in the image. These semantic features are relatively stable in the underground mining environment and are not easily disturbed by environmental changes, so the stability and accuracy of positioning can be improved.

[0088] Embodiment 3

[0089] Figure 3 Schematic diagram of the structure of an underground vehicle positioning device provided by the third embodiment of the present invention. Figure 3 As shown, the device includes: a candidate pose set determination module 310, a semantic matching pose determination module 320, a point cloud matching pose determination module 330 and a positioning pose determination module 340.

[0090] Among them, the candidate pose set determination module 310 is used to determine the current candidate pose set corresponding to the vehicle to be located at the current moment according to the historical candidate pose set corresponding to the previous moment of the current moment and the predetermined historical pose change corresponding to the vehicle to be located at multiple historical moments; the semantic matching pose determination module 320 is used to obtain the lane semantic features corresponding to the vehicle to be located at the current moment, and perform semantic matching according to the lane semantic features, the semantic map corresponding to the mine lane where the vehicle to be located is located, and the current candidate pose set to determine the vehicle to be located at the current moment. Semantic matching posture; wherein the lane semantic features are used to indicate lane traffic objects existing in the lane; a point cloud matching posture determination module 330 is used to perform point cloud matching according to the semantic matching posture, the scanning point cloud data corresponding to the vehicle to be located at the current moment and the point cloud map corresponding to the mine lane, so as to determine the point cloud matching posture corresponding to the vehicle to be located at the current moment; a positioning posture determination module 340 is used to perform posture fusion of the point cloud matching posture and the predetermined trajectory prediction posture corresponding to the vehicle to be located at the current moment, so as to obtain the target positioning posture corresponding to the vehicle to be located at the current moment.

[0091] The technical solution of the embodiment of the present invention determines the current candidate pose set corresponding to the vehicle to be positioned at the current moment according to the historical candidate pose set corresponding to the previous moment of the vehicle to be positioned at the current moment and the predetermined historical pose change corresponding to multiple historical moments of the vehicle to be positioned; further, obtains the semantic features of the laneway corresponding to the vehicle to be positioned at the current moment, and performs semantic matching according to the laneway semantic features, the semantic map corresponding to the mine laneway where the vehicle to be positioned is located, and the current candidate pose set to determine the semantic matching pose corresponding to the vehicle to be positioned at the current moment; further, according to the semantic matching pose, the scanning point cloud data corresponding to the vehicle to be positioned at the current moment and the change amount of the historical pose corresponding to the mine laneway where the vehicle to be positioned is located, the semantic matching pose is determined. Point cloud matching is performed on the point cloud map corresponding to the mine tunnel to determine the point cloud matching posture corresponding to the vehicle to be positioned at the current moment; further, the point cloud matching posture and the predetermined trajectory prediction posture corresponding to the vehicle to be positioned at the current moment are fused to obtain the target positioning posture corresponding to the vehicle to be positioned at the current moment, which solves the problems of complicated operation process, time-consuming and labor-intensive, high cost and low positioning accuracy in the underground vehicle positioning method in the related technology, realizes the effect of accurately positioning the underground vehicle based on the integration and collaborative work of multiple on-board sensors, and realizes the effect of improving the vehicle positioning accuracy, positioning stability and reliability on the basis of reducing the positioning cost.

[0092] Optionally, the historical candidate pose set includes multiple historical candidate poses corresponding to the vehicle to be positioned at the previous moment; the candidate pose set determination module 310 includes: a historical pose acquisition unit, a current candidate pose determination unit and a candidate pose set determination unit.

[0093] A historical posture acquisition unit is used to obtain a set of historical candidate postures corresponding to the previous moment of the current moment and a historical posture change amount corresponding to multiple historical moments of the vehicle to be positioned;

[0094] a current candidate posture determination unit, configured to determine, for each of the historical candidate postures in the historical candidate posture set, a product between the historical candidate posture and a plurality of the historical posture transformation amounts, so as to obtain a current candidate posture corresponding to the current moment;

[0095] The candidate posture set determination unit is used to determine the current candidate posture set corresponding to the vehicle to be positioned at the current moment according to multiple current candidate postures corresponding to the current moment.

[0096] Optionally, the semantic matching posture determination module 320 includes: a lane image acquisition unit and a semantic feature extraction unit.

[0097] A lane image acquisition unit, used to acquire images of the mine lane where the vehicle to be positioned is located by using a camera device pre-installed on the vehicle to be positioned, so as to obtain a lane image corresponding to the vehicle to be positioned at the current moment;

[0098] The semantic feature extraction unit is used to extract semantic features from the lane image to obtain the lane semantic features corresponding to the vehicle to be located at the current moment.

[0099] Optionally, the semantic matching posture determination module 320 includes: a posture weight determination unit and a semantic matching posture determination unit.

[0100] A posture weight determination unit, for determining, for each current candidate posture in the current candidate posture set, a target weight corresponding to the current candidate posture according to the target candidate posture, the lane semantic feature and the semantic map;

[0101] The semantic matching posture determination unit is used to determine the semantic matching posture corresponding to the vehicle to be positioned at the current moment from the multiple current candidate postures according to the target weights corresponding to the multiple current candidate postures.

[0102] Optionally, the posture weight determination unit includes: a visual feature determination subunit, a semantic matching distance determination subunit and a posture weight determination subunit.

[0103] A visual feature determination subunit, used to determine the product between the current candidate pose and the lane semantic feature to obtain a visual detection feature corresponding to the current candidate pose;

[0104] A semantic matching distance determination subunit, used to determine the distance between the visual detection feature and the semantic feature element corresponding to the lane semantic feature in the semantic map, so as to obtain a semantic matching distance corresponding to the current candidate pose;

[0105] The posture weight determination subunit is used to determine the target weight corresponding to the current candidate posture according to the semantic matching distance.

[0106] Optionally, the semantic matching posture determination unit is specifically used to determine the target weight with the largest weight value based on the multiple target weights, and use the current candidate posture corresponding to the determined target weight as the semantic matching posture corresponding to the vehicle to be located.

[0107] Optionally, the point cloud matching pose determination module 330 includes: a point cloud pose determination unit, a matching error determination unit and a point cloud matching pose determination unit.

[0108] A point cloud pose determination unit, used to determine the product between the semantic matching pose and a predetermined transformation parameter matrix to obtain a point cloud pose to be processed;

[0109] A matching error determination unit, configured to process the point cloud pose to be processed, the scanned point cloud data, and actual point cloud data on the point cloud map corresponding to the scanned point cloud data according to a preset point cloud matching algorithm to obtain a matching error;

[0110] The point cloud matching posture determination unit is used to adjust the point cloud posture to be processed by taking the minimum matching error as the optimization target, and take the point cloud posture to be processed corresponding to the minimum matching error as the point cloud matching posture corresponding to the vehicle to be positioned.

[0111] Optionally, the positioning posture determination module 340 is specifically used to interpolate and fuse the point cloud matching posture and the trajectory prediction posture according to a fusion positioning algorithm, and use the fused posture as the target positioning posture corresponding to the vehicle to be positioned at the current moment.

[0112] Optionally, the device further includes: a historical posture acquisition module and a trajectory prediction posture determination module.

[0113] The historical posture acquisition module is used to obtain the historical actual posture of the vehicle to be positioned at the previous moment and the current posture change corresponding to the current moment;

[0114] The trajectory prediction posture determination module is used to determine the product between the historical actual posture and the current posture change amount to obtain the trajectory prediction posture corresponding to the vehicle to be positioned at the current moment.

[0115] The underground vehicle positioning device provided in the embodiment of the present invention can execute the underground vehicle positioning method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0116] Embodiment 4

[0117] Figure 4 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0118] like Figure 4 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0119] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0120] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as an underground vehicle positioning method.

[0121] In some embodiments, the underground vehicle positioning method can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the underground vehicle positioning method described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform the underground vehicle positioning method in any other appropriate manner (for example, by means of firmware).

[0122] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0123] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0124] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, 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), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0125] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0126] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a target blockchain network, and the Internet.

[0127] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0128] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0129] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for positioning an underground vehicle, characterized in that: include: Determine a current candidate pose set corresponding to the vehicle to be positioned at the current moment according to a historical candidate pose set corresponding to the last moment of the vehicle to be positioned at the current moment and a predetermined historical pose change corresponding to the vehicle to be positioned at multiple historical moments; Acquire the lane semantic features corresponding to the vehicle to be located at the current moment, and perform semantic matching according to the lane semantic features, the semantic map corresponding to the mine lane where the vehicle to be located is located, and the current candidate pose set, so as to determine the semantic matching pose corresponding to the vehicle to be located at the current moment; wherein the lane semantic features are used to indicate lane traffic objects existing in the lane; Performing point cloud matching according to the semantic matching posture, the scanning point cloud data corresponding to the vehicle to be positioned at the current moment, and the point cloud map corresponding to the mine tunnel to determine the point cloud matching posture corresponding to the vehicle to be positioned at the current moment; The point cloud matching posture and the predetermined trajectory prediction posture corresponding to the vehicle to be positioned at the current moment are fused to obtain the target positioning posture corresponding to the vehicle to be positioned at the current moment.

2. The underground vehicle positioning method according to claim 1, characterized in that: The historical candidate pose set includes a plurality of historical candidate poses corresponding to the vehicle to be positioned at the previous moment; determining the current candidate pose set corresponding to the vehicle to be positioned at the current moment according to the historical candidate pose set corresponding to the vehicle to be positioned at the previous moment at the current moment and the predetermined historical pose changes corresponding to the vehicle to be positioned at multiple historical moments, including: Obtain a set of historical candidate poses corresponding to the previous moment of the current moment and a change amount of historical poses corresponding to multiple historical moments of the vehicle to be positioned; For each of the historical candidate poses in the historical candidate pose set, determine the product of the historical candidate pose and a plurality of historical pose transformation amounts to obtain a current candidate pose corresponding to the current moment; A current candidate pose set corresponding to the current moment of the vehicle to be positioned is determined according to the multiple current candidate poses corresponding to the current moment.

3. The underground vehicle positioning method according to claim 1, characterized in that: The obtaining of the lane semantic feature corresponding to the vehicle to be located at the current moment includes: Capturing an image of the mine tunnel where the vehicle to be located is located by using a camera device pre-installed on the vehicle to be located, so as to obtain a tunnel image corresponding to the vehicle to be located at the current moment; Semantic features are extracted from the lane image to obtain the lane semantic features corresponding to the vehicle to be located at the current moment.

4. The underground vehicle positioning method according to claim 1, characterized in that: The performing semantic matching according to the lane semantic features, the semantic map corresponding to the mine lane where the vehicle to be located is located, and the current candidate pose set to determine the semantic matching pose corresponding to the vehicle to be located at the current moment, includes: For each current candidate pose in the current candidate pose set, determining a target weight corresponding to the current candidate pose according to the current candidate pose, the lane semantic feature and the semantic map; According to the target weights corresponding to the multiple current candidate postures, the semantic matching posture corresponding to the vehicle to be located at the current moment is determined from the multiple current candidate postures.

5. The underground vehicle positioning method according to claim 4, characterized in that: The determining, according to the current candidate pose, the lane semantic feature and the semantic map, a target weight corresponding to the current candidate pose comprises: Determine the product between the current candidate pose and the lane semantic feature to obtain a visual detection feature corresponding to the current candidate pose; Determining a distance between the visual detection feature and a semantic feature element in the semantic map corresponding to the lane semantic feature to obtain a semantic matching distance corresponding to the current candidate pose; A target weight corresponding to the current candidate pose is determined according to the semantic matching distance.

6. The underground vehicle positioning method according to claim 4, characterized in that: The step of determining the semantic matching posture corresponding to the vehicle to be located from the multiple current candidate postures according to the target weights corresponding to the multiple current candidate postures includes: The target weight with the largest weight value is determined according to the multiple target weights, and the current candidate posture corresponding to the determined target weight is used as the semantic matching posture corresponding to the vehicle to be located.

7. The underground vehicle positioning method according to claim 1, characterized in that: The performing point cloud matching according to the semantic matching posture, the scanning point cloud data corresponding to the vehicle to be positioned at the current moment, and the point cloud map corresponding to the mine tunnel to determine the point cloud matching posture corresponding to the vehicle to be positioned includes: Determine the product between the semantic matching pose and a predetermined transformation parameter matrix to obtain a point cloud pose to be processed; Processing the point cloud pose to be processed, the scanned point cloud data, and actual point cloud data on the point cloud map corresponding to the scanned point cloud data according to a preset point cloud matching algorithm to obtain a matching error; The minimum matching error is taken as the optimization goal to adjust the point cloud pose to be processed, and the point cloud pose to be processed corresponding to the minimum matching error is taken as the point cloud matching pose corresponding to the vehicle to be positioned.

8. The underground vehicle positioning method according to claim 1, characterized in that: The step of fusing the point cloud matching posture with the predetermined trajectory prediction posture corresponding to the current moment of the vehicle to be positioned to obtain the target positioning posture corresponding to the current moment of the vehicle to be positioned includes: The point cloud matching posture and the trajectory prediction posture are interpolated and fused according to a fusion positioning algorithm, and the fused posture is used as the target positioning posture corresponding to the vehicle to be positioned at the current moment.

9. The underground vehicle positioning method according to claim 1, characterized in that: Also includes: Obtain the historical actual position and posture change of the vehicle to be positioned at the previous moment and the current position and posture change at the current moment; The product between the historical actual posture and the current posture change is determined to obtain the trajectory prediction posture corresponding to the vehicle to be positioned at the current moment.

10. An underground vehicle positioning device, characterized in that: include: A candidate pose set determination module is used to determine a current candidate pose set corresponding to the vehicle to be positioned at the current moment according to a historical candidate pose set corresponding to the previous moment of the vehicle to be positioned at the current moment and a predetermined historical pose change corresponding to the vehicle to be positioned at multiple historical moments; A semantic matching posture determination module is used to obtain the lane semantic features corresponding to the vehicle to be located at the current moment, and perform semantic matching based on the lane semantic features, the semantic map corresponding to the mine lane where the vehicle to be located is located, and the current candidate posture set to determine the semantic matching posture corresponding to the vehicle to be located at the current moment; wherein the lane semantic features are used to indicate lane traffic objects existing on the lane; A point cloud matching posture determination module is used to perform point cloud matching according to the semantic matching posture, the scanning point cloud data corresponding to the vehicle to be positioned at the current moment, and the point cloud map corresponding to the mine tunnel, so as to determine the point cloud matching posture corresponding to the vehicle to be positioned at the current moment; The positioning posture determination module is used to perform posture fusion on the point cloud matching posture and the predetermined trajectory prediction posture corresponding to the vehicle to be positioned at the current moment, so as to obtain the target positioning posture corresponding to the vehicle to be positioned at the current moment.

Images