Lane level positioning method, device, equipment, vehicle and medium

Abstract

A lane level positioning method, a lane level positioning device, an electronic device, a vehicle, a computer-readable storage medium, and a computer program product are provided. [Solution] The method includes obtaining map road information and visually sensed road information around the vehicle based on the vehicle's positioning information, determining a plurality of candidate lanes based on the positioning information, using the map road information to determine a topological recursion probability that the vehicle is located in each candidate lane, using the visually sensed road information to determine a sensed observation probability that the vehicle is located in each candidate lane, using the positioning information to determine a positioning probability that the vehicle is located in each candidate lane, and identifying a target lane in which the vehicle is located from the plurality of candidate lanes based on the topological recursion probability, sensed observation probability, and positioning probability that the vehicle is located in each candidate lane.

Description

[Technical Field]

[0001] The present disclosure relates to the field of computer technology, particularly to the field of artificial intelligence, computer vision, intelligent vehicles, and autonomous vehicles, and in particular to a lane level positioning method, a lane level positioning device, an electronic device, a vehicle, a computer-readable storage medium, and a computer program product. [Background technology]

[0002] Due to its wide range of potential applications, driver assistance technology has attracted widespread attention in recent years within the industry, especially the automotive industry, and has been the subject of in-depth research and exploration. Driver assistance technology is a concentrated embodiment of current automated and intelligent technology, and is the result of the integration of a large number of advanced technologies. Lane-level positioning technology is an essential component of this technology, playing a crucial role and directly affecting the reliability and safety of subsequent decision-making and control.

[0003] The methods described in this section are not necessarily methods that have been previously conceived or used. Unless otherwise noted, any methods described in this section should not be considered prior art merely because they are included in this section. Similarly, unless otherwise noted, the problems addressed in this section should not be considered an admission of any prior art. Summary of the Invention

[0004] The present disclosure provides a lane level positioning method, a lane level positioning device, an electronic device, a vehicle, a computer-readable storage medium, and a computer program product.

[0005] According to one aspect of the present disclosure, there is provided a lane-level positioning method, the method including: acquiring map road information and visual sensory road information around a vehicle based on positioning information of the vehicle; determining a plurality of candidate lanes based on the positioning information; using the map road information to determine a topology recursion probability that the vehicle is located in each candidate lane; using the visual sensory road information to determine a sensory observation probability that the vehicle is located in each candidate lane; using the positioning information to determine a positioning probability that the vehicle is located in each candidate lane; and identifying a target lane in which the vehicle is located from the plurality of candidate lanes based on the topology recursion probability, the sensory observation probability, and the positioning probability that the vehicle is located in each candidate lane.

[0006] According to another aspect of the present disclosure, there is provided a lane-level positioning device, the device including: an acquisition unit configured to acquire map road information and visually sensed road information around a vehicle based on positioning information of the vehicle; a candidate lane determination unit configured to determine a plurality of candidate lanes based on the positioning information; a topology recursion probability determination unit configured to determine a topology recursion probability that the vehicle is located in each candidate lane using the map road information; a sensed observation probability determination unit configured to determine a sensed observation probability that the vehicle is located in each candidate lane using the visually sensed road information; a positioning probability determination unit configured to determine a positioning probability that the vehicle is located in each candidate lane using the positioning information; and a first target lane identification unit configured to identify a target lane in which the vehicle is located from the plurality of candidate lanes based on the topology recursion probability, the sensed observation probability, and the positioning probability that the vehicle is located in each candidate lane.

[0007] According to another aspect of the present disclosure, there is provided an electronic device including at least one processor and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to cause the at least one processor to perform the methods described above.

[0008] According to another aspect of the present disclosure, there is provided a vehicle including the electronic device described above.

[0009] According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium having stored thereon computer instructions for causing a computer to perform the method described above.

[0010] According to another aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the above method.

[0011] According to one or more embodiments of the present disclosure, the present disclosure obtains map road information and visually sensed road information around the vehicle based on the positioning information of the vehicle, determines multiple candidate lanes, and further determines the probability that the vehicle will be located in each candidate lane from three dimensions using the map road information, the visually sensed road information, and the positioning information, respectively, and finally obtains the target lane in which the vehicle is located based on these probabilities, thereby realizing more accurate lane-level positioning.

[0012] It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will be readily apparent from the following specification. [Brief explanation of the drawings]

[0013] The drawings illustratively illustrate examples, constitute a part of the specification, and together with the written description serve to explain exemplary embodiments of the examples. The illustrated examples are for illustrative purposes only and do not limit the scope of the claims. In all drawings, the same reference numerals refer to similar, but not necessarily identical, elements. [Figure 1] FIG. 1 is a schematic diagram of an exemplary system capable of implementing the methods described herein, according to an embodiment of the present disclosure. [Figure 2] 1 illustrates a flowchart of a lane-level positioning method according to an exemplary embodiment of the present disclosure. [Figure 3] 10 illustrates a flowchart for determining a topology recursion probability that a vehicle is located in each candidate lane using map road information according to an exemplary embodiment of the present disclosure. [Figure 4] 1 shows a schematic diagram of a filtering process according to an exemplary embodiment of the present disclosure. [Figure 5] 1 illustrates a flowchart for determining a sensed observation probability that a vehicle is located in each candidate lane using visually sensed road information according to an exemplary embodiment of the present disclosure. [Figure 6] 10 illustrates a flowchart for determining a positioning probability that a vehicle is located in each candidate lane using positioning information according to an exemplary embodiment of the present disclosure. [Figure 7] 1 illustrates a flowchart for identifying a target lane in which a vehicle is located from a plurality of candidate lanes according to an exemplary embodiment of the present disclosure. [Figure 8] 10 illustrates a flowchart for determining topology recursion weights, sensing observation weights, and positioning weights for each of a plurality of candidate lanes according to an exemplary embodiment of the present disclosure. [Figure 9] 1 illustrates a schematic diagram of a Hidden Markov Model according to an exemplary embodiment of the present disclosure; [Figure 10] 1 illustrates a flowchart of a lane-level positioning method according to an exemplary embodiment of the present disclosure. [Figure 11] 1 illustrates an overall technical flowchart according to an exemplary embodiment of the present disclosure. [Figure 12] FIG. 1 shows a schematic diagram of lane-level positioning according to an exemplary embodiment of the present disclosure. [Figure 13] FIG. 1 illustrates a structural block diagram of a lane level positioning device according to an exemplary embodiment of the present disclosure. [Figure 14] FIG. 1 is a block diagram illustrating the structure of an exemplary electronic device that can be used to implement embodiments of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0014]

[0023] The following describes exemplary embodiments of the present disclosure in conjunction with the drawings. For ease of understanding, various details of the embodiments of the present disclosure are included therein, but they should be considered merely exemplary. Therefore, those skilled in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for clarity and conciseness, the following description omits descriptions of known functions and structures.

[0015] In this disclosure, unless otherwise specified, the use of terms such as "first," "second," etc. to describe various elements is not intended to limit the location, timing, or importance of these elements. Such terms are used only to distinguish one element from another. In some instances, a first element and a second element may refer to the same instance of the element, or in some cases, may refer to different instances based on the context.

[0016] The terms used in the description of various examples of the present disclosure are intended only to describe particular examples and are not intended to be limiting. Unless the context clearly indicates otherwise, and unless the number of elements is specifically limited, the element may be one or more. Furthermore, as used in this disclosure, the term "and / or" covers any and all possible combinations of the listed items.

[0017] In the related art, the accuracy of existing lane-level positioning is low.

[0018] To solve the above problems, the present disclosure obtains map road information and visually sensed road information around the vehicle based on the vehicle's positioning information, determines multiple candidate lanes, and then uses the map road information, visually sensed road information, and positioning information to determine the probability that the vehicle will be located in each candidate lane from three dimensions. Finally, based on these probabilities, it obtains the target lane in which the vehicle is located, thereby realizing more accurate lane-level positioning.

[0019] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings.

[0020] 1 illustrates a schematic diagram of an exemplary system 100 in which various methods and apparatus described herein may be implemented, according to embodiments of the present disclosure. Referring to FIG. 1, the system 100 includes a vehicle 110, a server 120, and one or more communication networks 130 coupling the vehicle 110 to the server 120.

[0021] In an embodiment of the present disclosure, the automobile 110 may include a computing device according to an embodiment of the present disclosure and may be configured to perform a method according to an embodiment of the present disclosure.

[0022] Server 120 may execute one or more services or software applications of the lane-level positioning method. In some embodiments, server 120 may also provide other services or software applications, which may include non-virtual and virtual environments. In the configuration shown in FIG. 1 , server 120 may include one or more assemblies that implement the functionality performed by server 120. These assemblies may include software assemblies, hardware assemblies, or a combination thereof, executable by one or more processors. A user of vehicle 110 may, in turn, utilize one or more client application programs to interact with server 120 to utilize the services provided by these components. It should be understood that a variety of different system configurations are possible and may differ from system 100. Accordingly, FIG. 1 is intended to be an example of a system for implementing various methods described herein and is not intended to be limiting.

[0023] Server 120 may include one or more general-purpose computers, dedicated server computers (e.g., PC (personal computer) servers, UNIX servers, mid-range servers), blade servers, mainframes, server clusters, or any other suitable arrangement and / or combination. Server 120 may also include one or more virtual machines running virtual operating systems or other computing architectures involving virtualization (e.g., one or more flexible pools of virtualizable logical storage devices to maintain virtual storage devices for the server). In various embodiments, server 120 may run one or more services or software applications that provide the functionality described below.

[0024] The computing units in server 120 may run one or more operating systems, including any of the operating systems listed above and any commercial server operating system. Server 120 may also run any one of a variety of additional server and / or middle-tier application programs, such as an HTTP server, an FTP server, a CGI server, a JAVA server, a database server, etc.

[0025] In some embodiments, server 120 may include one or more application programs for analyzing and merging data feeds and / or event updates received from vehicle 110. Server 120 may further include one or more application programs for displaying data feeds and / or real-time events via one or more display devices of vehicle 110.

[0026] Network 130 may be any type of network known to those skilled in the art, which may use any one of several available protocols to support data communications (including, but not limited to, TCP / IP, SNA, IPX, etc.) By way of example, one or more networks 130 may be a satellite communications network, a local area network (LAN), an Ethernet-based network, a token ring, a wide area network (WAN), the Internet, a virtual network, a virtual private network (VPN), an intranet, an extranet, a blockchain network, a public switched telephone network (PSTN), an infrared network, a wireless network (e.g., Bluetooth, WiFi), and / or any combination of these and other networks.

[0027] System 100 may include one or more databases 150. In some embodiments, these databases may be used to store data or other information. For example, one or more of databases 150 may be used to store information such as audio files or video files. Databases 150 may be located in a variety of locations. For example, a database used by server 120 may be local to server 120 or may be remote from server 120 and in communication with server 120 via a network or dedicated connection. Databases 150 may be of a variety of types. In some embodiments, a database used by server 120 may be a database, such as a relational database. One or more of these databases may store, update, and retrieve data from the database in response to instructions.

[0028] In some embodiments, one or more of databases 150 may be used by an application program to store data for the application program. The databases used by the application programs may be different types of databases, such as a key-value repository, an object repository, or a general-purpose repository supported by a file system.

[0029] The automobile 110 may include sensors 111 for sensing the surrounding environment. The sensors 111 may include one or more of the following sensors: a visual camera, an infrared camera, an ultrasonic sensor, a millimeter-wave radar, and a laser radar (LiDAR). Different sensors can provide different detection accuracy and range. The cameras can be mounted on the front, rear, or other locations of the vehicle. The visual camera can capture the situation inside and outside the vehicle in real time and present it to the driver and / or passengers. Furthermore, by analyzing the screen captured by the visual camera, information such as traffic light indications, intersection conditions, and the driving status of other vehicles can be obtained. The infrared camera can capture objects at night. Ultrasonic sensors can be mounted around the vehicle and are used to measure the distance of external objects from the vehicle using characteristics such as strong ultrasonic directionality. Millimeter-wave radar can be mounted on the front, rear, or other locations of the vehicle and is used to measure the distance of external objects from the vehicle using the properties of electromagnetic waves. Laser radar can be mounted on the front, rear, or other locations of a vehicle to detect edges, shape information, and identify and track objects. Due to the Doppler effect, radar devices can also measure changes in the speed of vehicles and moving objects.

[0030] The automobile 110 may further include a communication device 112. The communication device 112 may include a satellite positioning module capable of receiving satellite positioning signals (e.g., Beidou, GPS, GLONASS, and GALILEO) from satellites 141 and generating coordinates based on these signals. The communication device 112 may further include a module for communicating with a mobile communication base station 142, which may implement any suitable communication technology, such as GSM / GPRS, CDMA, LTE, or other current or evolving wireless communication technologies (e.g., 5G technology). The communication device 112 may also include a vehicular network or vehicle-to-everything (V2X) module configured to enable vehicle-to-external communication, e.g., vehicle-to-vehicle (V2V) communication with other vehicles 143 and vehicle-to-infrastructure (V2I) communication with infrastructure 144. Additionally, communication device 112 may include a module configured to communicate with user terminal 145 (including, but not limited to, a smartphone, a tablet computer, or a wearable device such as a wristwatch), for example, using an IEEE 802.11 standard wireless local area network or Bluetooth. Motor vehicle 110 may also use communication device 112 to access server 120 over network 130.

[0031] The automobile 110 may further include a control device 113. The control device 113 may include a processor, such as a central processing unit (CPU), a graphics processing unit (GPU), or other dedicated processor, in communication with various types of computer-readable storage devices or media. The control device 113 may include an autonomous driving system that automatically controls various actuators in the vehicle. The autonomous driving system is configured to control the power assemblies, steering system, braking system, etc. of the automobile 110 (not shown) via multiple actuators in response to inputs from multiple sensors 111 or other input devices to control acceleration, steering, and braking, respectively, without requiring human intervention or limited human intervention. Some of the processing functions of the control device 113 may be implemented by cloud computing. For example, some processes may be performed using an on-board processor, and other processes may be performed using cloud-side computing resources. The control device 113 may be configured to execute a lane-level positioning method according to the present disclosure. The control device 113 may also be implemented as an example of an automobile-side (client-side) computing device according to the present disclosure.

[0032] The system 100 of FIG. 1 can be configured and operated in a variety of ways to accommodate the various methods and apparatus described in accordance with this disclosure.

[0033] According to one aspect of the present disclosure, there is provided a lane-level positioning method. As shown in Figure 2, the lane-level positioning method includes the following steps: step S201: obtain map road information and visual sensory road information around the vehicle based on the vehicle's positioning information; step S202: determine a plurality of candidate lanes based on the positioning information; step S203: determine a topology recursion probability that the vehicle is located in each candidate lane based on the map road information; step S204: determine a sensory observation probability that the vehicle is located in each candidate lane based on the visual sensory road information; step S205: determine a positioning probability that the vehicle is located in each candidate lane based on the positioning information; and step S206: identify a target lane in which the vehicle is located from the plurality of candidate lanes based on the topology recursion probability, the sensory observation probability, and the positioning probability that the vehicle is located in each candidate lane.

[0034] As a result, the present disclosure obtains map road information and visually sensed road information around the vehicle based on the vehicle's positioning information, determines multiple candidate lanes, and then uses the map road information, visually sensed road information, and positioning information to determine the probability that the vehicle will be located in each candidate lane from three dimensions, and finally obtains the target lane in which the vehicle is located based on these probabilities, thereby realizing more accurate lane-level positioning.

[0035] The method proposed in this disclosure may be used for accurate and comprehensive lane-level positioning in conditions of poor map quality.

[0036] Before step S201, vehicle positioning information may be acquired.

[0037] This disclosure relates to two levels of positioning: road-level positioning and lane-level positioning. Road-level positioning obtains the approximate position of a vehicle from the vehicle's own positioning results, which may be derived from the position after fusing a positioning system or a navigation positioning system with an inertial measurement unit. The positioning information used in steps S201, S202, and S205 may all refer to road-level positioning results. By implementing the method of this disclosure, a lane-level positioning result, i.e., the target lane in which the vehicle is located, can be obtained.

[0038] In one exemplary embodiment, the vehicle's position information can be constantly obtained by fusion positioning using a Kalman filter, using an inertial measurement unit, a navigation positioning system, wheel speed sensors, and map matching information. In step S201, the vehicle's position can be used to obtain high-precision map data within a certain area nearby. The obtained high-precision map data is mainly provided in the form of lanes, thereby providing initial road-level positioning information. The road-level positioning result is provided as a link identifier (ID).

[0039] In step S202, a plurality of candidate lanes may be determined on the high precision map based on the positioning information.

[0040] In some embodiments, the map road information may include road topology information, such as lane edge lines, center lines, road edges, and lane / road predecessor / successor relationships of multiple map lanes, and the visually sensed road information may include lane edge lines, road edges, and sensed lane / road predecessor / successor relationships of multiple sensed lanes. Note that the candidate lanes determined in step S202 are lanes in the high-precision map.

[0041] After obtaining multiple candidate lanes, in steps S203 to S205, the probability that the vehicle will be located in each candidate lane may be predicted from three levels: topology recursion, sensing observation, and positioning. In step S206, the lane-level positioning may be completed by determining the target lane in which the vehicle is most likely to be located based on these probabilities.

[0042] According to some embodiments, as shown in FIG. 3 , step S203, using map road information to determine a topological recursion probability that the vehicle is located in each candidate lane, may include: step S301, using map road information to determine a topological recursion relationship between a plurality of historical lanes and a plurality of candidate lanes; and step S304, based on the topological recursion relationship and the topological recursion probability that the vehicle was located in each historical lane at a previous time, determine a topological recursion probability that the vehicle is located in each candidate lane.

[0043] Therefore, the above method can effectively utilize map road information to predict the topology recursion probability that the vehicle will be located in each candidate lane from the topology recursion level of the lane, thereby improving the accuracy of lane-level positioning.

[0044] In some embodiments, the topological recursion relationship may refer to a predecessor-successor relationship between a plurality of historical lanes and a plurality of candidate lanes. In step S302, for each candidate lane, a historical lane corresponding to the candidate lane may be determined based on the topological recursion relationship, and a topological recursion probability of the historical lane may be determined as a topological recursion probability that the vehicle is located in the candidate lane at the current time.

[0045] According to some embodiments, as shown in FIG. 3 , step S203, using map road information to determine a topological recursion probability that the vehicle is located in each candidate lane, may further include: step S302, calculating a lane change probability of the vehicle based on the visually sensed road information; and step S303, maintaining a state transition matrix of the topological recursion observation based on the lane change probability. The topological recursion probability that the vehicle is located in each candidate lane may be determined based on the state transition matrix, the topological recursion relationship, and the topological recursion probability that the vehicle was located in each historical lane at a previous time.

[0046] Therefore, the above method can further improve the accuracy of lane-level positioning by further introducing the possible lane-changing situations of the vehicle based on the topological recursive relationship.

[0047] In some embodiments, the lane change probability may be calculated according to the following formula:

number

[0048] In some embodiments, in step S303, the lane change probability of the vehicle may be calculated based on the lateral deviation of the main vehicle from the lane edge line, and the lateral deviation may be predicted and updated as an estimated value of a Kalman filter, and a lane change to the left or right may be determined depending on whether the lateral deviation is positive or negative, and a corresponding lane change probability may be set.

[0049] In some embodiments, the Kalman filter is used for random stationary processes. The system's measurement noise, the process noise sequence, is not the signal to be filtered out; its distribution is the key information used in the estimation process. The processed signal does not distinguish between interference and useful signals; the filter's task is to extract all processed signals. Therefore, the Kalman filter is based on an optimal estimation method.

[0050] The discrete-time system is as follows:

[0051] Equation of state:

number

number

[0052] At the same time, W k and V k satisfies the following:

number

[0053] In the formula, Q k is the process noise matrix and is non-negative definite, and R k is the measurement noise matrix, and is assumed to be positive definite, and the posterior probability distributions of each step are all normal distributions.

[0054] State one-step prediction: One-step prediction is the state estimator at time k-1.

number

number

number

[0055] State estimation: Measurement quantity Z obtained at time k k One-step predicted value in the state

number

number

number

number

[0056] Filter Gain: State estimator at time k

number

number

number

number

[0057] One-step prediction mean squared error: Definition expression

number

number

[0058] Estimated mean squared error: Definition expression

number

number

[0059] The above five equations are the process of the discrete Kalman filter, that is, the initial value

number

number

[0060] A filter essentially has two parts: prediction and update. The prediction part uses equations that describe the dynamic characteristics of the system to calculate the transition probability density of the predicted state from the previous time to the current time. Because unpredictable random noise affects the state estimation, the prediction process generally needs to be modified to propagate the state probability distribution. The update part uses newly acquired measurements to modify the probability distribution of the prediction stage.

[0061] According to some embodiments, the visually sensed road information may include a plurality of sensed lanes, and the plurality of sensed lanes may include a main lane in which the vehicle is located and an adjacent lane. As shown in FIG. 5 , step S204, using the visually sensed road information to determine a sensed observation probability that the vehicle is located in each candidate lane, may include: step S501, using the visually sensed road information to determine a first distance between the vehicle and the left and right edge lines of the main lane; and step S502, based on the first distance, determine a sensed observation probability that the vehicle is located in the candidate lane corresponding to the main lane and the candidate lane corresponding to the adjacent lane.

[0062] As a result, the above method can effectively utilize visually sensed road information to predict the topology recurrence probability that a vehicle will be located in each candidate lane from the road sensed level, thereby improving the accuracy of lane-level positioning.

[0063] In some embodiments, in step S502, in response to determining that the first distance indicates that the vehicle is not approaching any adjacent lane, the process may set a sensed observation probability for the candidate lane corresponding to the primary lane that exceeds a first probability value and a sensed observation probability for the candidate lane corresponding to the adjacent lane that is less than a second probability value. In response to determining that the first distance indicates that the vehicle is approaching an adjacent lane, the process may set a sensed observation probability for the candidate lane corresponding to the adjacent lane that exceeds a second probability value and a sensed observation probability for the candidate lane corresponding to the primary lane that is less than the first probability value.

[0064] According to some embodiments, as shown in FIG. 6 , step S205, using the positioning information to determine the positioning probability that the vehicle is located in each candidate lane, may include: step S601, using the positioning information to determine a second distance between the vehicle and the center line of each candidate lane; and step S602, determining the positioning probability that the vehicle is located in each candidate lane based on the second distance between the vehicle and each candidate lane.

[0065] Therefore, the method can effectively utilize the positioning information to predict the positioning probability that the vehicle will be located in each candidate lane from the positioning level, thereby improving the accuracy of lane-level positioning.

[0066] In some embodiments, the centerline of the candidate lane may be obtained from map road information. In step S602, the determined positioning probability may be negatively correlated with the second distance. That is, the closer the vehicle is to the centerline of the candidate lane, the higher the positioning probability corresponding to the candidate lane.

[0067] In step S206, the topology recursion probability, the sensing observation probability, and the positioning probability corresponding to each candidate lane may be combined to obtain a target probability corresponding to the candidate lane. Further, based on the target probability of each candidate lane, the target lane in which the vehicle is most likely located may be identified.

[0068] In some embodiments, the above steps S203 to S206 may be considered as a process of assigning probability confidence.

[0069] According to some embodiments, as shown in FIG. 7 , step S206, identifying a target lane in which the vehicle is located from the plurality of candidate lanes based on the topology recursion probability, the sensing observation probability, and the positioning probability that the vehicle is located in each candidate lane, may include: step S701, determining a topology recursion weight, a sensing observation weight, and a positioning weight for each of the plurality of candidate lanes; step S702, for each candidate lane among the plurality of candidate lanes, normalizing the topology recursion probability, the sensing observation probability, and the positioning probability that the vehicle is located in the candidate lane using the topology recursion weight, the sensing observation weight, and the positioning weight of the candidate lane to obtain a target probability that the vehicle is located in the candidate lane; and step S703, determining a target lane based on the target probability that the vehicle is located in each candidate lane.

[0070] This allows the method to more effectively combine the topology recursion weights, the sensing observation weights and the positioning weights, and more accurately identify the target road from multiple candidate lanes.

[0071] In some embodiments, the target probability may be expressed as:

number

[0072] In some embodiments, the topology recursion weights, sensing observation weights, and positioning weights may be set based on prior knowledge or may be dynamically adjusted.

[0073] According to some embodiments, as shown in Fig. 8 , step S701, determining a topology recursion weight, a sensing observation weight, and a positioning weight for each of a plurality of candidate lanes may include: step S801, in response to determining that a topology recursion probability that the vehicle was located in one historical lane at a previous time is greater than a preset threshold, setting a topology recursion weight for the vehicle to be located in a candidate lane corresponding to the one historical lane to be equal to or greater than a first preset value.

[0074] If the topology recursion probability corresponding to a historical lane is greater than a predetermined threshold, the weight of the topology recursion-based method may be set to a high value in subsequent predictions to account for the high reliability of the topology recursion-based method when performing lane-level positioning on the historical lane, thereby enabling greater reliance on lane-level positioning using topology recursion information.

[0075] In some embodiments, in response to determining that the topology recursion probability that the vehicle was located in one of the historical lanes at a previous time point is less than a preset threshold, a topology recursion weight for the vehicle being located in a candidate lane corresponding to the one of the historical lanes is set to be less than a first preset value. In other words, when performing lane-level positioning in the historical lanes, if the reliability of the topology recursion-based method is low, the corresponding weight can be reduced in subsequent predictions to reduce the use of topology recursion information.

[0076] According to some embodiments, as shown in Figure 8, step S701, determining the topology recursion weight, the sensing observation weight, and the positioning weight for each of the plurality of candidate lanes may include: step S802, in response to determining that the number of lanes in the visual sensing road information and the map road information are the same and in response to determining that the visual sensing road information indicates that left and right shoulders have been detected, set the sensing observation weight for each candidate lane where the vehicle is located to be equal to or greater than a second preset value.

[0077] If the visual sensing result is the same as the number of lanes in the high-precision map and the left and right edges of the current road are successfully detected, the reliability of the current visual sensing road information is high. Therefore, the accuracy of lane-level positioning can be improved by setting a high weight for the method of performing lane-level positioning based on sensing observation.

[0078] According to some embodiments, as shown in FIG. 8 , step S701, determining a topology recursion weight, a sensing observation weight, and a positioning weight for each of a plurality of candidate lanes, may include: step S803, determining a positioning weight based on a time length for which the vehicle enters a lane-level positioning recursion mode, where the lane-level positioning recursion mode indicates a mode for performing lane-level positioning using a topology recursion probability, a sensing observation probability, and a positioning probability, and the positioning weight is negatively correlated with the time length.

[0079] The lane-level positioning recursive mode is a mode that performs lane-level positioning using topology recursion probability, sensing observation probability, and positioning probability. This mode does not rely entirely on positioning information and map information, but performs comprehensive inference based on various information. The description of steps S201 to S206 in Figure 2 is the lane-level positioning recursion mode. Since this mode is less dependent on positioning information and map information, the longer the mode is in place, the lower the reliability of the recursion information becomes. Therefore, by setting a smaller weight, the overall accuracy of lane-level positioning can be ensured.

[0080] After step S206, a post-processing operation may be performed. In some embodiments, the post-processing operation may use the multi-frame inter-timing results to maintain a Hidden Markov Model (HMM), realize timing information transition, and realize spatial alignment of multi-source information (positioning information, map road information, and visual sensing road information) through a candidate link road topology structure, thereby improving the safety attributes of lane-level positioning post-processing.

[0081] Hidden Markov Model map matching has already established itself as a state-of-the-art method for both offline and online map matching. A first-order hidden Markov model describes the behavior of a system over time as a sequence of system states.

number

number

number

number

number

number

number

number

[0082] First-order hmm makes the following assumptions about state transitions and estimation:

[0083] ·Markov state assumption: time

number

number

number

number

[0084] Markov sensor assumption: time

number

number

number

number

[0085] In the context of map matching, states are the map positions of the vehicle and estimates are the position measurements. Transitions between system states correspond to paths between map positions. The solution to the online map matching problem follows a recursive method of state filtering.

[0086] Maximum Likelihood Location Probability

number

number

[0087] By definition,

number

number

number

number

number

number

number

number

number

number

number

number

number

number

[0088] According to some embodiments, as shown in FIG. 10, the lane-level positioning method may further include: step S1002: matching the visually sensed road information with the map road information. Determining a plurality of candidate lanes and their corresponding topology recursion probabilities, sensed observation probabilities, and positioning probabilities may be performed in response to determining that the visually sensed road information does not match the map road information. The operations and effects of steps S1001 and S1005 to S1009 in FIG. 10 may refer to steps S201 to S206 in FIG. 2, and will not be described further here.

[0089] After obtaining the visual sensory road information and map road information, the map matching module can be used to first match the two. If the matching fails, the map matching module can trigger the determination of candidate lanes and calculate the topology recursion probability, the sensory observation probability, and the positioning probability, and then use these probabilities to perform lane-level positioning. In other words, if the matching between the visual sensory road information and the map road information is not successful, the lane-level positioning recursion mode can be entered.

[0090] In some embodiments, the visually sensed road information includes visually sensed lane lines, and the map road information includes map lane lines. In step S1002, the visually sensed road information and the map road information may be subjected to a histogram filter to provide matching point pairs, and high-precision availability information may be generated based on the matching point pairs. The high-precision availability information may include: 1) whether the visually sensed lane lines are successfully matched with the map lane lines; 2) whether the deviation between the visually sensed lane lines and the map lane lines is less than a threshold; 3) whether the main vehicle has left the road boundary; and 4) whether the intersection is a Y-shaped intersection.

[0091] In response to determining that at least one of the following four conditions is not met: 1) the visually sensed lane boundary line is successfully matched with the map lane boundary line; 2) the deviation is less than a preset deviation threshold; 3) the road boundary is not exceeded; and 4) the intersection is not a Y-shaped intersection, steps S1005 to S1009 may be executed by determining that the visually sensed road information and the map road information do not match, i.e., recursive lane-level positioning may be performed using a multi-source sensor.

[0092] In response to determining that all four of the above conditions are met, it may be determined that the visually sensed road information and the map road information match, and lane positioning may be performed using the high-precision map.

[0093] According to some embodiments, the visually sensed road information may include a plurality of sensed lanes, and the plurality of sensed lanes may include a main lane in which the vehicle is located and an adjacent lane. As shown in FIG. 10 , the lane-level positioning method may further include: in step S1003, in response to determining that the visually sensed road information matches the map road information, using the visually sensed road information to determine a first distance between the vehicle and left and right side lines of the main lane and a second distance between the vehicle and a center line of at least one candidate lane among the plurality of candidate lanes, the second distance including at least the candidate lane corresponding to the main lane; and in step S1004, identifying a target lane in which the vehicle is located from the candidate lane corresponding to the main lane and the candidate lanes corresponding to the adjacent lane based on the first distance and the second distance.

[0094] In some embodiments, road-level positioning requires a large amount of calculation and is performed infrequently. However, downstream requirements for lane-level positioning output are frequent. Therefore, there may be delays in the link information provided by road-level positioning. Therefore, it is necessary to perform a subsequent lane update determination. This involves using the lane topology relationship provided by the high-precision map and the position information provided by the fusion positioning to determine whether the main vehicle is in a subsequent lane, and further confirming the main lane in which the main vehicle is currently located. This prevents lane determination errors caused by delays in road-level positioning and improves the robustness of lane calculation.

[0095] In some embodiments, the following lane update determination may include calculating left and right intercepts from the following lane edge line of the main vehicle, determining possible main lanes based on the opposite signs of the left and right intercepts, calculating the angle between the main vehicle and the lane center line, and if the angle is acute, determining that the main vehicle has already entered the following lane, and further updating the road information.

[0096] FIG. 11 illustrates an overall technical flowchart according to an exemplary embodiment of the present disclosure. The input layer 1102 may include a high-precision map 1104, positioning information 1106, map matching information 1108, and visually sensed road information 1110. Here, the visually sensed road information may further include lane boundary lines 1112 and road shoulders 1114. Based on the map matching information 1108, scene control 1116 may be performed, i.e., whether to perform high-precision map lane-level positioning 1110 or recursive lane-level positioning 1118 is determined based on the matching situation. The recursive lane-level positioning 1118 further requires calculating a topology recursion probability 1120, a sensed observation probability 1122, and a positioning probability 1124, and then performing normalization and post-processing 1126 on the three. Finally, a result output 1128 is performed after the high-precision map lane-level positioning 1110 or the recursive lane-level positioning 1118.

[0097] The method of the present disclosure will now be introduced in conjunction with one exemplary embodiment.

[0098] FIG. 12 shows a schematic diagram of lane-level positioning according to an exemplary embodiment of the present disclosure. The white lane boundaries are high-precision map lane boundaries, the green lane centerlines are high-precision map lane boundaries, the yellow lane boundaries are visually sensed lane boundaries, and the pink arcs are respectively at radii of 5 m, 10 m, and 50 m from the main vehicle. As can be seen from the diagram, there is a clear deviation phenomenon (high offset) between the yellow and white lines, which indicates poor quality of the high-precision map. The map matching module outputs high-precision unavailability information accordingly, and lane-level positioning enters recursive mode.

[0099] In some embodiments, map road information may be acquired from a high-precision map based on positioning information output from road-level positioning, including all lane information banded under the link, i.e., lane_seq 1 to 3 in the figure. These lanes may be determined as multiple candidate lanes. The preceding and succeeding lane relationships may also be obtained based on a high-precision map near the main vehicle.

[0100] In some embodiments, current visually sensed road information may be acquired, including multiple sensed lanes, i.e., yellow percep_seq 1 to 3 in the figure. The lane change probability can be calculated, and the left / right lane change probability at the location shown in the figure is 0.

[0101] In some embodiments, topology recursion information may be obtained through the link output from road-level positioning, and lane topology relationships, i.e., lane_topo, may be maintained by taking into account the hysteresis of road-level positioning, i.e., cur_lane (candidate lane) and last_lane (history lane) in the figure. Furthermore, probability confidence assignment may be performed to obtain topology recursion probabilities, sensed observation probabilities, and fusion positioning probabilities.

[0102] In some embodiments, for topology recursion probability and weight calculation, since the lane change probability is 0, the probability state transition matrix is ​​an identity matrix, and the weights are set based on the topology recursion probability used at the previous time. The lane change probability is calculated by the above formula.

[0103] In some embodiments, for the sensing observation probability and weight calculation, if the current sensing is the same as the number of lanes in the high-precision map and the left and right shoulders are detected, the sensing observation weight is set to a relatively large value, the main vehicle distance is in the center of the lane, and the distance from the left and right edge lines is large, the given main lane probability is 1, and the left and right lane probabilities are 0.

[0104] In some embodiments, for the fused positioning probability and weight calculation, since the main vehicle has not left the map, the road-level positioning does not enter the recursive mode, and the weight of the fused positioning probability is set based only on the time of entering the lane-level positioning recursive mode, the longer the time, the lower the weight, and the probability of the fused positioning is set based on the distance from the lane centerline.

[0105] In some embodiments, the probabilities of all candidate lanes can be obtained by normalizing the target probability formula above, and the lane marking with the highest probability is given as the final lane-level positioning output. Since the regional road-level positioning is not in recursive mode and is not a ramp or tunnel scene, no special post-processing is required.

[0106] This disclosure proposes an active lane-level positioning method, which serves as an important supplement to high-precision map-based lane-level positioning systems in driver assistance systems. It incorporates recursive lane-level positioning calculations based on the original framework, adapting to scenes with poor high-precision map quality and improving effectiveness in bend angles and reality-changing scenes. As a result, this lane-level positioning technology, as an important component of driver assistance technology, provides important technical support for the implementation of driver assistance technology, achieving benefits such as tunnel bend angle closure, no map convex hull closure, no longitudinal error map output closure, and maintaining unexpired positioning in reality-changing scenes. Furthermore, the use of the method disclosed herein increases the availability of intelligent driving by 50% and the positioning effectiveness rate by 42.9% in tunnel scenes, and the availability of intelligent driving by 58.8% and the positioning effectiveness rate by 70.6% in reality-changing scenes. It also solves the lane-level positioning closure and jump problems at railroad crossings in normal scenes and the layer misalignment problem on multi-layered roads.

[0107] 13 , the lane-level positioning device 1300 includes: an acquisition unit 1310 configured to acquire map road information and visually sensed road information around the vehicle based on positioning information of the vehicle; a candidate lane determination unit 1320 configured to determine a plurality of candidate lanes based on the positioning information; a topology recursion probability determination unit 1330 configured to determine a topology recursion probability that the vehicle is located in each candidate lane using the map road information; a sensed observation probability determination unit 1340 configured to determine a sensed observation probability that the vehicle is located in each candidate lane using the visually sensed road information; a positioning probability determination unit 1350 configured to determine a positioning probability that the vehicle is located in each candidate lane using the positioning information; and a first target lane identification unit 1360 configured to identify a target lane in which the vehicle is located from the plurality of candidate lanes based on the topology recursion probability, the sensed observation probability, and the positioning probability that the vehicle is located in each candidate lane.

[0108] According to some embodiments, the topological recursion probability determination unit may include a first determination subunit configured to determine a topological recursion relationship between a plurality of historical lanes and a plurality of candidate lanes using map road information, and a second determination subunit configured to determine a topological recursion probability that the vehicle will be located in each candidate lane based on the topological recursion relationship and a topological recursion probability that the vehicle will be located in each candidate lane at a previous time.

[0109] According to some embodiments, the topology recurrence probability determination unit may further include a calculation subunit configured to calculate a lane change probability of the vehicle based on the visually sensed road information, and a matrix maintenance subunit configured to maintain a state transition matrix of the topology recurrence observation based on the lane change probability. The topology recurrence probability that the vehicle will be located in each candidate lane may be determined based on the state transition matrix, the topology recurrence relation, and the topology recurrence probability that the vehicle was located in each historical lane at a previous time.

[0110] According to some embodiments, the visually sensed road information includes a plurality of sensed lanes, and the plurality of sensed lanes includes a main lane in which the vehicle is located and an adjacent lane. The sensed observation probability determining unit may include a third determining subunit configured to determine a first distance between the vehicle and a left and right edge line of the main lane using the visually sensed road information, and a fourth determining subunit configured to determine a sensed observation probability that the vehicle is located in a candidate lane corresponding to the main lane and a candidate lane corresponding to the adjacent lane based on the first distance.

[0111] According to some embodiments, the positioning probability determination unit may include a fifth determination subunit configured to determine a second distance between the vehicle and a center line of each candidate lane using the positioning information, and a sixth determination subunit configured to determine a positioning probability that the vehicle is located in a candidate lane corresponding to the main lane based on the second distance between the vehicle and each candidate lane.

[0112] According to some embodiments, the target lane determination unit may include: a weight determination subunit configured to determine a topology recursion weight, a sensing observation weight, and a positioning weight for each of a plurality of candidate lanes; a target probability determination subunit configured, for each candidate lane among the plurality of candidate lanes, to normalize the topology recursion probability, the sensing observation probability, and the positioning probability that the vehicle is located in the candidate lane using the topology recursion weight, the sensing observation weight, and the positioning weight of the candidate lane to obtain a target probability that the vehicle is located in the candidate lane; and a target lane determination subunit configured to determine a target lane based on the target probability that the vehicle is located in each candidate lane.

[0113] According to some embodiments, the weight determination subunit may include a topology recursion weight determination subunit configured to set a topology recursion weight for the vehicle to be located in a candidate lane corresponding to the one historical lane to a first preset value or greater in response to determining that a topology recursion probability for the vehicle to be located in the one historical lane at a previous time is greater than a preset threshold.

[0114] According to some embodiments, the weight determination subunit may include a sensing observation weight determination subunit configured to set a sensing observation weight for the vehicle located in each candidate lane to a second preset value or greater in response to determining that the number of lanes in the visually sensed road information and the map road information are the same and in response to determining that the visually sensed road information indicates that left and right shoulders have been detected.

[0115] According to some embodiments, the weight determination subunit may include a positioning weight determination subunit configured to determine a positioning weight based on a length of time that the vehicle enters a lane-level positioning recursion mode, where the lane-level positioning recursion mode indicates a mode in which lane-level positioning is performed using topology recursion probability, sensing observation probability, and positioning probability, and the positioning weight is negatively correlated with the length of time.

[0116] According to some embodiments, the lane-level positioning device may further include a matching unit configured to match the visually sensed road information with the map road information. Determining a plurality of candidate lanes and their corresponding topology recursion probabilities, sensed observation probabilities, and positioning probabilities may be performed in response to determining that the visually sensed road information does not match the map road information.

[0117] According to some embodiments, the visually sensed road information may include a plurality of sensed lanes, and the plurality of sensed lanes may include a main lane in which the vehicle is located and an adjacent lane. The lane-level positioning device may further include: a distance determination unit configured to, in response to determining that the visually sensed road information matches the map road information, determine a first distance between the vehicle and left and right side lines of the main lane and a second distance between the vehicle and a center line of at least one candidate lane among the plurality of candidate lanes, the candidate lane including at least the candidate lane corresponding to the main lane, using the visually sensed road information; and a second identification unit configured to identify a target lane in which the vehicle is located from the candidate lane corresponding to the main lane and the candidate lanes corresponding to the adjacent lane based on the first distance and the second distance.

[0118] In the technical solution disclosed herein, the collection, storage, use, processing, transmission, provision and disclosure of relevant user personal information shall all comply with the provisions of relevant laws and regulations and shall not violate public order and morals.

[0119] According to embodiments of the present disclosure, an electronic device, a readable storage medium, and a computer program product are further provided.

[0120] As shown in FIG. 14 , a structural block diagram of an electronic device 1400 that can be used as a server or client of the present disclosure is described herein as an example of a hardware device applicable to various aspects of the present disclosure. The electronic device represents various forms of digital electronic computing devices, such as laptop computers, desktop computers, stage computers, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components, their connections, and their functions shown herein are merely exemplary and do not limit the implementation of the present disclosure as described and / or claimed herein.

[0121] 14, the device 1400 includes a computing unit 1401 and can perform various appropriate operations and processes by means of a computer program stored in a read-only memory (ROM) 1402 or loaded from a storage unit 1408 into a random access memory (RAM) 1403. The RAM 1403 can further store various programs and data necessary for operating the device 1400. The computing unit 1401, the ROM 1402, and the RAM 1403 are connected to each other by a bus 1404. An input / output (I / O) interface 1405 is also connected to the bus 1404.

[0122] The components of device 1400 are connected to I / O interface 1405 and include input unit 1406, output unit 1407, storage unit 1408, and communication unit 1409. Input unit 1406 may be any type of device capable of inputting information into device 1400. Input unit 1406 can receive input numeric or character information and generate key signal input for user settings and / or function control of the electronic device, and may include, but is not limited to, a mouse, keyboard, touchscreen, trackboard, trackball, joystick, microphone, and / or remote control. Output unit 1407 may be any type of device capable of presenting information, and may include, but is not limited to, a display, speaker, video / audio output terminal, vibrator, and / or printer. Storage unit 1408 may include, but is not limited to, a magnetic disk or an optical disk. The communication unit 1409 enables the device 1400 to exchange information / data with other devices via a computer network, e.g., the Internet, and / or various telecommunications networks, and may include, but is not limited to, a modem, a network card, an infrared communication device, a wireless communication transceiver, and / or a chipset, e.g., a Bluetooth device, an 802.11 device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0123] The computing unit 1401 may be any of a variety of general-purpose and / or special-purpose processing components having processing and computing capabilities. Some examples of the computing unit 1401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units that execute machine learning network algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 1401 performs the methods and processes described above, such as the lane-level positioning method. For example, in some embodiments, the lane-level positioning method may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 1408. In some embodiments, some or all of the computer program may be loaded and / or installed into the device 1400 via the ROM 1402 and / or the communication unit 1409. When the computer program is loaded into the RAM 1403 and executed by the computing unit 1401, it may perform one or more steps of the lane-level positioning method described above. Optionally, in other embodiments, the computing unit 1401 may be configured to perform the lane-level positioning method in any other suitable manner (eg, by firmware).

[0124] Various embodiments of the systems and techniques described herein may be realized 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 a chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being embodied in one or more computer programs that may be executed and / or interpreted by a programmable system including at least one programmable processor, which may be a special purpose or general purpose programmable processor, and which may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device;

[0125] Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, so that when executed by the processor or controller, the program code performs the functions / operations specified in the flowcharts and / or block diagrams. The program code may be entirely executed on a machine, partially executed on a machine, partially executed on a machine and partially executed on a remote machine as a separate software package, or entirely executed on a remote machine or server.

[0126] In the context of this disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in connection with an instruction execution system, device, or apparatus. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or apparatus, or any suitable combination of the above. More specific examples of machine-readable storage media include an electrical connection with one or more leads, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0127] To provide for interaction with a user, the systems and techniques described herein may be implemented in a computer having a display device (e.g., a cathode ray tube (CRT) or liquid crystal display (LCD) monitor) for displaying information to a user, and a keyboard and pointing device (e.g., a mouse or trackball) by which a user may provide input to the computer. Other types of devices may also be used to provide for interaction with a user; for example, 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 audio input, voice input, and tactile input).

[0128] The systems and techniques described herein may be implemented in a computing system that includes backstage components (e.g., as a data server), a computing system that includes middleware components (e.g., as an application server), a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with the system or technique implementation), or any combination of backstage components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communications network). Examples of communications networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0129] The computer system may include a client and a server. The client and server are generally remote from each other and typically interact via a communication network. The client-server relationship is created by executing computer programs on the corresponding computers that have 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 a cloud computing service system and solves the problems of traditional physical hosts and VPS services (also known as "Virtual Private Servers" or "VPSs"), such as high management difficulty and poor business scalability. The server may be a distributed system server or a blockchain-connected server.

[0130] It should be understood that the various forms of flow described above may be used, and steps may be rearranged, added, or deleted. For example, the steps described in this disclosure may be performed in parallel, sequentially, or in a different order, and the present disclosure is not limited thereto as long as the technical solution disclosed in this disclosure achieves the desired results.

[0131] Although the embodiments or examples of the present disclosure have been described with reference to the drawings, it should be understood that the above-described methods, systems, and devices are merely exemplary embodiments or examples, and that the scope of the present invention is not limited by these embodiments or examples, but only by the appended claims and their equivalents. Various elements in the embodiments or examples may be omitted or replaced by their equivalents. Furthermore, steps may be performed in a different order from that described in this disclosure. Furthermore, various elements in the embodiments or examples may be combined in various ways. Importantly, with the evolution of technology, many elements described herein may be replaced by equivalent elements that appear later in this disclosure.

Claims

1. 1. A computer-implemented lane level positioning method, comprising: Obtaining map road information and visually sensed road information around the vehicle based on the positioning information of the vehicle; determining a plurality of candidate lanes based on the positioning information; determining a topology recursion probability that the vehicle is located in each candidate lane using the map road information; utilizing the visually sensed road information to determine a sensed observation probability that the vehicle is located in each candidate lane; determining a positioning probability that the vehicle is located in each candidate lane using the positioning information; and identifying a target lane in which the vehicle is located from the plurality of candidate lanes based on a topology recursion probability, a sensing observation probability, and a positioning probability that the vehicle is located in each candidate lane.

2. Determining a topology recursion probability that the vehicle is located in each candidate lane using the map road information includes: determining a topological recursion relationship between a plurality of historical lanes and the plurality of candidate lanes using the map road information; and determining a topological recurrence probability that the vehicle will be located in each candidate lane based on the topological recurrence relationship and a topological recurrence probability that the vehicle was located in each historical lane at a previous time.

3. Determining a topology recursion probability that the vehicle is located in each candidate lane using the map road information includes: calculating a lane change probability for the vehicle based on the visually sensed road information; maintaining a state transition matrix of a topology recursive observation based on the lane change probabilities; 3. The method of claim 2, wherein the topological recurrence probability that the vehicle will be located in each candidate lane is determined based on the state transition matrix, the topological recurrence relation, and the topological recurrence probability that the vehicle will be located in each historical lane at a previous time.

4. The visually sensed road information includes a plurality of sensed lanes, the plurality of sensed lanes including a main lane in which the vehicle is located and an adjacent lane, and determining a sensed observation probability that the vehicle is located in each candidate lane using the visually sensed road information includes: determining a first distance between the vehicle and left and right marginal lines of the main lane using the visually sensed road information; and determining a sensed observation probability that the vehicle is located in a candidate lane corresponding to the primary lane and a candidate lane corresponding to the adjacent lane based on the first distance.

5. Determining a positioning probability that the vehicle is located in each candidate lane using the positioning information includes: determining a second distance between the vehicle and a centerline of each candidate lane using the positioning information; and determining a positioning probability that the vehicle is located in each candidate lane based on a second distance between the vehicle and each candidate lane.

6. Identifying a target lane in which the vehicle is located from the plurality of candidate lanes based on a topology recursion probability, a sensing observation probability, and a positioning probability that the vehicle is located in each candidate lane, determining a topology recursion weight, a sensing observation weight, and a positioning weight for each of the plurality of candidate lanes; For each candidate lane among the plurality of candidate lanes, normalize the topology recursion weight, the sensing observation weight, and the positioning probability that the vehicle is located in the candidate lane using the topology recursion weight, the sensing observation weight, and the positioning weight of the candidate lane to obtain a target probability that the vehicle is located in the candidate lane; and determining the target lane based on a target probability that the vehicle is located in each candidate lane.

7. Determining a topology recursion weight, a sensing observation weight, and a positioning weight for each of the plurality of candidate lanes includes:

7. The method of claim 6, further comprising: in response to determining that a topology recursion probability that the vehicle was located in a historical lane at a previous time is greater than a preset threshold, setting a topology recursion weight that the vehicle is located in a candidate lane corresponding to the historical lane to a first preset value or greater.

8. Determining a topology recursion weight, a sensing observation weight, and a positioning weight for each of the plurality of candidate lanes includes:

7. The method of claim 6, further comprising: in response to determining that the number of lanes in the visually sensed road information and the map-road information are the same, and in response to determining that the visually sensed road information indicates that left and right shoulders have been detected, setting a sensing observation weight for each candidate lane in which the vehicle is located to greater than or equal to a second preset value.

9. Determining a topology recursion weight, a sensing observation weight, and a positioning weight for each of the plurality of candidate lanes includes:

7. The method of claim 6, further comprising determining the positioning weight based on a length of time the vehicle is in a lane-level positioning recursion mode, the lane-level positioning recursion mode indicating a mode for performing lane-level positioning using topology recursion probability, sensing observation probability, and positioning probability, and the positioning weight is negatively correlated with the length of time.

10. 6. The method of claim 1, further comprising matching the visually sensed road information with the map-road information, wherein determining the plurality of candidate lanes and their corresponding topology recursion probabilities, sensed observation probabilities and positioning probabilities is performed in response to determining that the visually sensed road information does not match the map-road information.

11. The visually sensed road information includes a plurality of sensed lanes, the plurality of sensed lanes including a main lane in which the vehicle is located and an adjacent lane, and the method includes: In response to determining that the visual-sensing road information matches the map-road information, using the visual-sensing road information to determine a first distance between the vehicle and left and right border lines of the primary lane and a second distance between the vehicle and a center line of at least one candidate lane among the plurality of candidate lanes, the center line including at least the candidate lane corresponding to the primary lane; and identifying a target lane in which the vehicle is located from the candidate lanes corresponding to the main lane and the candidate lanes corresponding to the adjacent lanes based on the first distance and the second distance.

12. A lane level positioning device, comprising: an acquisition unit configured to acquire map road information and visual sensing road information around the vehicle based on the positioning information of the vehicle; a candidate lane determination unit configured to determine a plurality of candidate lanes based on the positioning information; a topology recursion probability determination unit configured to utilize the map road information to determine a topology recursion probability that the vehicle is located in each candidate lane; a sensed observation probability determination unit configured to utilize the visual sensed road information to determine a sensed observation probability that the vehicle is located in each candidate lane; a positioning probability determination unit configured to utilize the positioning information to determine a positioning probability that the vehicle is located in each candidate lane; and a first target lane identification unit configured to identify a target lane in which the vehicle is located from the plurality of candidate lanes based on a topology recursion probability, a sensing observation probability, and a positioning probability that the vehicle is located in each candidate lane.

13. The topology recursion probability determination unit: a first determination subunit configured to determine a topological recursive relationship between a plurality of historical lanes and the plurality of candidate lanes using the map road information; and a second determination subunit configured to determine a topological recursion probability that the vehicle will be located in each candidate lane based on the topological recursion relationship and a topological recursion probability that the vehicle was located in each historical lane at a previous time.

14. The topology recursion probability determination unit: a calculation subunit configured to calculate a lane change probability of the vehicle based on the visually sensed road information; a matrix maintaining subunit configured to maintain a state transition matrix of a topology recursive observation based on the lane change probability; 14. The apparatus of claim 13, wherein a topological recurrence probability that the vehicle will be located in each candidate lane is determined based on the state transition matrix, the topological recurrence relation, and a topological recurrence probability that the vehicle was located in each historical lane at a previous time.

15. The visually sensed road information includes a plurality of sensed lanes, the plurality of sensed lanes including a main lane where the vehicle is located and an adjacent lane, and the sensed observation probability determination unit: a third determination subunit configured to determine a first distance between the vehicle and the left and right edge lines of the main lane using the visually sensed road information; and a fourth determination subunit configured to determine, based on the first distance, a sensed observation probability that the vehicle is located in a candidate lane corresponding to the main lane and a candidate lane corresponding to the adjacent lane.

16. The positioning probability determination unit: a fifth determination subunit configured to determine a second distance between the vehicle and a center line of each candidate lane using the positioning information; and a sixth determination subunit configured to determine a positioning probability that the vehicle is located in each candidate lane based on a second distance between the vehicle and each candidate lane.

17. The target lane determination unit: a weight determination subunit configured to determine a topology recursion weight, a sensing observation weight, and a positioning weight for each of the plurality of candidate lanes; a target probability determination subunit configured to, for each candidate lane among the plurality of candidate lanes, normalize a topology recursion probability, a sensing observation probability, and a positioning probability that the vehicle is located in the candidate lane using a topology recursion weight, a sensing observation weight, and a positioning weight of the candidate lane to obtain a target probability that the vehicle is located in the candidate lane; and a target lane determination subunit configured to determine the target lane based on a target probability that the vehicle is located in each candidate lane.

18. The weight determination subunit:

18. The apparatus of claim 17, further comprising: a topology recursion weight determination subunit configured to set a topology recursion weight for the vehicle to be located in a candidate lane corresponding to the one historical lane to a first preset value or greater in response to determining that a topology recursion probability for the vehicle to be located in the one historical lane at a previous time is greater than a preset threshold.

19. The weight determination subunit:

18. The apparatus of claim 17, further comprising a sensing observation weight determination subunit configured to set a sensing observation weight for each candidate lane in which the vehicle is located to a second predetermined value or greater in response to determining that the number of lanes in the visually sensed road information and the map road information are the same and in response to determining that the visually sensed road information indicates that left and right shoulders have been detected.

20. The weight determination subunit:

18. The apparatus of claim 17, further comprising: a positioning weight determination subunit configured to determine the positioning weight based on a length of time the vehicle enters a lane-level positioning recursion mode, the lane-level positioning recursion mode indicating a mode for performing lane-level positioning using a topology recursion probability, a sensed observation probability, and a positioning probability, and the positioning weight is negatively correlated with the length of time.

21. Further comprising a matching unit configured to match the visually sensed road information with the map road information; 17. The apparatus of claim 12, wherein determining the plurality of candidate lanes and their corresponding topology recursion probabilities, sensory observation probabilities, and positioning probabilities is performed in response to determining that the visually sensed road information does not match the map road information.

22. The visually sensed road information includes a plurality of sensed lanes, the plurality of sensed lanes including a main lane in which the vehicle is located and an adjacent lane, and the device: a distance determination unit configured to, in response to determining that the visual-sensing road information matches the map-road information, determine a first distance between the vehicle and left and right edge lines of the main lane using the visual-sensing road information and a second distance between the vehicle and a center line of at least one candidate lane among the plurality of candidate lanes, the candidate lane including at least the candidate lane corresponding to the main lane; and a second identification unit configured to identify a target lane in which the vehicle is located from the candidate lanes corresponding to the main lane and the candidate lanes corresponding to the adjacent lanes based on the first distance and the second distance.

23. at least one processor; a memory communicatively coupled to the at least one processor, An electronic device, wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to cause the at least one processor to perform the method of any one of claims 1 to 5.

24. A vehicle comprising the electronic device of claim 23.

25. A non-transitory computer readable storage medium having stored thereon computer instructions, the computer instructions being used to cause the computer to perform the method of any one of claims 1 to 5.

26. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 5.

Images