Positioning method and device, vehicle, storage medium and program product

Abstract

The invention relates to the technical field of automotive electronics, and discloses a positioning method and device, a vehicle, a storage medium and a program product. The positioning method comprises the steps that the electronic equipment can obtain perception data of a vehicle at a first moment, and the perception data comprises road section perception data corresponding to at least one road section; then, based on the road section sensing data and the current pose of the vehicle, the sensing probability that the vehicle will run on each road section at a second moment can be determined, and the second moment is later than the first moment; moreover, the electronic equipment can predict a target road section on which the vehicle runs at the second moment based on the sensing probability of each road section. Furthermore, at the second moment, the condition that the vehicle runs on the target road section can be displayed in the navigation map. Therefore, the road-level positioning function can be realized, so that the vehicle is associated with the specific driving road section, the drifting phenomenon of the positioning point of the vehicle is avoided, and a more accurate navigation decision is provided for the driving of the vehicle.

Description

Technical Field

[0001] This application relates to the field of automotive electronics technology, and in particular to a positioning method, device, vehicle, storage medium, and program product. Background Technology

[0002] During vehicle operation, road-level positioning can associate the vehicle's location with specific road segments on the navigation map to ensure navigation reliability. For example, ... Figure 1 As shown, on navigation maps with numerous road segments, relying solely on isolated vehicle coordinates obtained through the Global Navigation Satellite System (GNSS) can easily lead to vehicle location drift. For example, Figure 1 If road segment A and road segment B are relatively close, and a vehicle is actually traveling on road segment A, relying solely on GNSS positioning for navigation may cause the vehicle's location point to appear to drift between adjacent road segments A and B on the navigation map. However, if electronic devices (such as in-vehicle systems) use road-level positioning to associate the vehicle with the specific road segment it is traveling on, this drifting phenomenon can be avoided, thus providing more accurate navigation decisions for the vehicle.

[0003] Currently, when electronic devices perform road-level positioning of vehicles, they still cannot accurately associate the vehicle with the actual road segment being traveled on complex road sections such as intersections or ramp merging / exiting areas. This can easily lead to association errors, such as associating the vehicle with adjacent roads of the actual road segment being traveled. Summary of the Invention

[0004] This application provides a positioning method, device, vehicle, storage medium, and program product to improve the accuracy of road-level positioning functions.

[0005] In a first aspect, this application provides a positioning method, comprising: acquiring perception data of a vehicle at a first moment, the perception data including road segment perception data corresponding to at least one road segment; determining the perception probability that the vehicle will travel on each road segment at a second moment based on the road segment perception data and the current pose of the vehicle, wherein the second moment is later than the first moment; predicting the target road segment that the vehicle will travel on at the second moment based on the perception probability of each road segment; and displaying the vehicle traveling on the target road segment on a navigation map at the second moment.

[0006] Thus, the above method enables road-level positioning, associating the vehicle with the specific road segment it travels on, avoiding vehicle positioning drift, and providing more accurate navigation decisions for vehicle travel. Furthermore, when locating the vehicle, this application can also determine the perception probability of the vehicle traveling on each road segment based on perception data (such as environmental image data captured by the vehicle's onboard camera), and then perform subsequent positioning processes based on this perception probability. In this way, by combining the method of determining the perception probability of each road segment with the vehicle's surrounding environment, the electronic device can accurately associate the vehicle with the actual road segment it is traveling on even on complex roads where adjacent road segments (such as intersections or ramps) are close in distance and have similar directions, avoiding the error of associating the vehicle with adjacent road segments of the actual travel segment.

[0007] In one possible implementation of the first aspect above, the at least one road segment includes a first road segment, and the perception probability includes a first perception probability that the vehicle will travel on the first road segment at a second moment; and the determination of the perception probability that the vehicle will travel on each road segment at a second moment based on the road segment perception data and the vehicle's current pose includes: correcting the vehicle's current pose based on the road segment perception data and the map data of each road segment in the navigation map; and in the navigation map, determining the first perception probability that the vehicle will travel on the first road segment at a second moment based on the relative distance and / or relative azimuth angle between the corrected vehicle pose and the first road segment.

[0008] In this way, by registering the perception data and the navigation map data, the gap between the navigation map and the physical world caused by mapping errors can be effectively solved, thereby improving the accuracy and success rate of road-level positioning and shortening the reconvergence time after navigation deviation.

[0009] In one possible implementation of the first aspect above, the correction of the vehicle's current pose based on road segment perception data and map data of each road segment in the navigation map includes: determining the coordinates of perception sampling points on each road segment in the vehicle coordinate system based on the road segment perception data, and determining the coordinates of map sampling points on each road segment in the world coordinate system based on the map data; performing coordinate system transformation on the coordinates of the perception sampling points or the map sampling points based on the vehicle's current pose to obtain the coordinates of the perception sampling points and the map sampling points belonging to the same coordinate system; and correcting the vehicle's pose based on the coordinates of the perception sampling points and the map sampling points located on the same road feature in the same coordinate system.

[0010] In this way, by registering the perceived data and the navigation map data, the gap between the navigation map and the physical world caused by cartographic errors can be effectively resolved.

[0011] In one possible implementation of the first aspect above, determining the coordinates of the sensing sampling points on each road segment in the vehicle coordinate system based on road segment sensing data includes: determining the road boundary of the first road segment and the road area located within the road boundary based on the road segment sensing data; obtaining the coordinates of the boundary points on the road boundary in the vehicle coordinate system; establishing a two-dimensional grid in the road area, and determining the coordinates of the sensing sampling points in each grid of the two-dimensional grid in the vehicle coordinate system based on the coordinates of the boundary points.

[0012] In one possible implementation of the first aspect above, determining the coordinates of map sampling points on each road segment in the navigation map in the world coordinate system based on map data includes: determining a first road segment in the navigation map based on map data, and determining the road width of the first road segment based on the standard lane width and the number of lanes in the first road segment indicated by the map data; determining multiple sampling centers in the first road segment, with adjacent sampling centers having a preset sampling distance; determining multiple map sampling points based on each sampling center and obtaining the coordinates of the multiple map sampling points in the world coordinate system, wherein the map sampling points are located on a circle with the sampling center as the center and a first length as the diameter, the first length being determined based on the road width.

[0013] In one possible implementation of the first aspect described above, the at least one road segment includes a second road segment, and the perception probability includes a second perception probability that the vehicle will travel on the second road segment at a second moment. The road segment perception data includes shunting point perception data corresponding to at least one road segment shunting point, which is located between the road segment where the vehicle is located at the first moment and the second road segment. Determining the perception probability that the vehicle will travel on each road segment at a second moment based on the road segment perception data and the vehicle's current pose includes: determining the position of each road segment shunting point based on the shunting point perception data; and determining the second perception probability that the vehicle will travel on the second road segment at a second moment based on the position of each road segment shunting point, the road extension direction of the second road segment, and the vehicle's current pose.

[0014] In this way, identifying vehicle driving intentions by sensing road segment divergence points provides a powerful observation source in road divergence scenarios, thereby improving the accuracy of road-level positioning. For example, in intersection scenarios, compared to traditional solutions, road matching using the method provided in this application can significantly reduce the false matching rate and increase decision lead time.

[0015] In one possible implementation of the first aspect above, the at least one road segment further includes a third road segment, the road segment diversion point is located between the road segment where the vehicle is located at the first moment and the third road segment, and the road segment diversion point is used to divert the vehicle from the road segment where it is located at the first moment to the second road segment and the third road segment; the determination of the second perception probability that the vehicle will travel on the second road segment at the second moment based on the position of each road segment diversion point, the road extension direction of the second road segment and the current pose of the vehicle includes: determining the second perception probability that the vehicle will travel on the second road segment at the second moment through a multi-round voting mechanism based on each road segment diversion point, the current pose of the vehicle, the road extension direction of the second road segment and the road extension direction of the third road segment.

[0016] In one possible implementation of the first aspect described above, the second perception probability that the vehicle will travel on the second road segment at the second moment is determined through a multi-round voting mechanism based on the diversion points of each road segment, the current pose of the vehicle, the road extension direction of the second road segment, and the road extension direction of the third road segment. This includes: determining the second road segment as a candidate road segment corresponding to the first moment based on the current pose of the vehicle, the road extension direction of the second road segment, and the road extension direction of the third road segment; calculating the first confidence value corresponding to the second road segment at the first moment based on a preset distance and the effective perception distance when acquiring perception data at the first moment; wherein the preset distance is the distance between the center point position of each road segment diversion point and the vehicle at the first moment; determining the total confidence value of the second road segment based on the first confidence value and other confidence values ​​of the second road segment calculated in previous moments; and setting corresponding second perception probabilities for the second road segment and the third road segment if the number of calculations exceeds a threshold and / or the total confidence value meets a first condition; wherein the second perception probability corresponding to the second road segment is greater than the second perception probability corresponding to the third road segment.

[0017] In one possible implementation of the first aspect above, the total confidence value satisfies the first condition, including: the total confidence value corresponding to the second road segment is greater than the confidence threshold; and the total confidence value corresponding to the second road segment is greater than the total confidence value of the third road segment calculated at previous times.

[0018] In one possible implementation of the first aspect above, predicting the target road segment for the vehicle to travel on at the second moment based on the perception probability of each road segment includes: in the navigation map, determining the emission probability that the vehicle will travel on each road segment at the second moment based on the relative distance and relative azimuth angle between the vehicle's current pose and each road segment; in the navigation map, determining the transfer probability that the vehicle will transfer from the current road segment to each road segment at the second moment based on the path connection relationship between the vehicle's current driving road segment and each road segment at the first moment; and predicting the target road segment for the vehicle to travel on at the second moment based on the first perception probability, second perception probability, emission probability, and transfer probability corresponding to each road segment.

[0019] In this way, by complementing multi-dimensional observations, the system's fault tolerance can be improved, enabling it to still function normally under conditions of single-dimensional timeliness or noise, thereby improving the system's availability in complex scenarios and the fault tolerance rate for single-frame observation anomalies.

[0020] In one possible implementation of the first aspect above, predicting the target road segment that the vehicle will travel on at the second time based on the first perception probability, second perception probability, emission probability, and transfer probability corresponding to each road segment includes: determining the predicted probability that the vehicle will travel on each road segment at the second time based on the first perception probability, second perception probability, and emission probability corresponding to each road segment; predicting the target road segment that the vehicle will travel on at the second time based on the predicted probability and transfer probability corresponding to each road segment; wherein the predicted probability corresponding to the target road segment satisfies the prediction probability condition, and the transfer probability corresponding to the target road segment satisfies the transfer probability condition.

[0021] In this way, by combining the perception probability of each road segment with the surrounding environment of the vehicle, the electronic device can still accurately associate the vehicle with the actual road segment it is traveling on in complex roads where the distance between adjacent road segments (such as intersections or ramps) is relatively short and the directions are similar, thus avoiding the error of associating the vehicle with the adjacent road segment of the actual road segment.

[0022] Secondly, this application provides a positioning system, comprising: a perception data acquisition module for acquiring perception data of a vehicle at a first moment, the perception data including road segment perception data corresponding to at least one road segment; a perception probability determination module for determining the perception probability that the vehicle will travel on each road segment at a second moment based on the road segment perception data and the vehicle's current pose; a target road segment determination module for predicting the target road segment that the vehicle will travel on at the second moment based on the perception probability of each road segment; and a navigation display module for displaying the vehicle traveling on the target road segment on a navigation map at the second moment.

[0023] Thus, the aforementioned positioning system enables road-level positioning, associating the vehicle with the specific road segment it is traveling on, preventing vehicle positioning point drift and providing more accurate navigation decisions. Furthermore, by combining the perception probability of each road segment with the surrounding environment, it is possible to accurately associate the vehicle with the actual road segment even on complex roads where adjacent road segments (such as intersections or ramps) are close in distance and have similar directions, avoiding the error of associating the vehicle with adjacent road segments.

[0024] Thirdly, this application provides an electronic device comprising: at least one memory and at least one processor, wherein the memory is coupled to the processor. The memory is used to store computer program code / instructions. When the computer program code / instructions are executed by the processor, the electronic device performs the positioning method mentioned in the first aspect and any possible implementation thereof.

[0025] Fourthly, this application provides a vehicle that includes the electronic equipment mentioned in the third aspect above.

[0026] Fifthly, this application provides a readable storage medium storing instructions. When executed on an electronic device, the instructions cause the electronic device to perform the positioning method mentioned in the first aspect and any possible implementation thereof.

[0027] Sixthly, this application provides a computer program product, including: computer instructions. When the computer instructions are executed on an electronic device, they cause the electronic device to perform the positioning method mentioned in the first aspect and any possible implementation thereof.

[0028] The beneficial effects of the third to sixth aspects mentioned above can be referred to the relevant descriptions in the first and second aspects and various possible implementations of the first aspect, and will not be repeated here. Attached Figure Description

[0029] Figure 1 A schematic diagram of a navigation map is shown according to some embodiments;

[0030] Figure 2A According to some embodiments, a schematic flowchart of a method for implementing road-level positioning function based on HMM is shown;

[0031] Figure 2B According to some embodiments, a schematic diagram is shown for calculating the relative distance and relative azimuth angle between a vehicle pose and each candidate road.

[0032] Figure 2CAccording to some embodiments, a schematic diagram is shown for calculating the transition probability corresponding to each candidate road;

[0033] Figure 3 According to some embodiments of this application, a schematic flowchart of a positioning method is shown;

[0034] Figure 4 According to some embodiments of this application, a scene diagram corresponding to sensing data is shown;

[0035] Figure 5 According to some embodiments of this application, a schematic diagram of a process for determining a first perception probability is shown;

[0036] Figure 6 According to some embodiments of this application, a schematic diagram of a scenario for determining road boundaries is shown;

[0037] Figure 7 According to some embodiments of this application, a schematic diagram of a process for determining a second perception probability is shown;

[0038] Figure 8 According to some embodiments of this application, a schematic diagram of a scenario is shown for determining the fourth road segment where a vehicle is located before passing through the divergence points of each road segment;

[0039] Figure 9 According to some embodiments of this application, a schematic diagram of a scenario for determining multiple road groups is shown;

[0040] Figure 10 According to some embodiments of this application, a schematic diagram of a multi-round voting mechanism is shown;

[0041] Figure 11 According to some embodiments of this application, a schematic diagram of a process for determining a target road segment is shown;

[0042] Figure 12 According to some embodiments of this application, a flowchart of another positioning method is shown;

[0043] Figure 13 According to some embodiments of this application, a schematic diagram of a positioning system is shown;

[0044] Figure 14 According to some embodiments of this application, a structural schematic diagram of a vehicle is shown. Detailed Implementation

[0045] The illustrative embodiments of this application include, but are not limited to, a positioning method, device, vehicle, storage medium, and program product.

[0046] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions in the embodiments of this application will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0047] As mentioned earlier, during vehicle operation, road-level positioning can associate the vehicle's location with specific road segments on the navigation map to ensure navigation reliability. For example, ... Figure 1 As shown, on navigation maps with many road segments, obtaining isolated vehicle coordinates solely through GNSS can easily lead to vehicle location drift. For example, Figure 1 If road segment A and road segment B are relatively close, and a vehicle is actually traveling on road segment A, relying solely on GNSS positioning for navigation may cause the vehicle's location point to appear to drift between adjacent road segments A and B on the navigation map. However, if electronic devices (such as in-vehicle systems) use road-level positioning to associate the vehicle with the specific road segment it is traveling on, this drifting phenomenon can be avoided, thus providing more accurate navigation decisions for the vehicle.

[0048] Currently, electronic devices can achieve road-level positioning using Hidden Markov Models (HMMs). This approach combines vehicle location points from GNSS and other sensors, road segments in navigation maps, and a probabilistic model to infer the most likely road segment the vehicle is currently on. See below for details. Figure 2A As shown.

[0049] The following is based on Figure 2A The flowchart shown provides a brief introduction to a method for implementing road-level positioning based on Hidden Markov Models (HMMs). This method can be applied to electronic devices such as in-vehicle infotainment systems. Figure 2A As shown, specifically, the method is as follows:

[0050] S201: Select candidate road segments based on vehicle locations obtained from GNSS.

[0051] For example, an electronic device can filter a set of candidate road segments from the road network of a navigation map based on the vehicle's location obtained by GNSS (or simply GNSS location). These candidate road segments are typically roads within a certain range of the vehicle's location. For instance, in the road network of the navigation map, the vehicle's location can be the center of a circle, and road segments within a certain radius can be selected as candidate road segments.

[0052] S202: Calculate the emission probability (also known as observation probability or geometric probability, etc.) between the vehicle pose (i.e., the vehicle's position and attitude) and each candidate road segment.

[0053] For example, the degree of matching between the vehicle pose and each candidate road segment can be determined based on the relative distance and relative azimuth between the vehicle pose and each candidate road segment.

[0054] For example, such as Figure 2B As shown, the electronic device can calculate the shortest relative distance L1 between the position of vehicle C1 on the navigation map and candidate road segment A1, and calculate the relative azimuth angle θ between the attitude (e.g., orientation) of vehicle C1 and the road extension direction of candidate road segment A1. Then, based on the relative distance L1 and relative azimuth angle θ between vehicle C1 and candidate road segment A1, the electronic device can calculate the emission probability between vehicle C1's pose and candidate road segment A1. The smaller the relative distance L1 and the smaller the relative azimuth angle θ, the higher the emission probability between vehicle C1's pose and candidate road segment A1. Similarly, the electronic device can also calculate the emission probability between vehicle C1's pose and other selected road segments, which will not be elaborated here.

[0055] S203: Calculate the transition probability of each candidate road segment based on historical road segments.

[0056] Here, "historical road segment" refers to the actual road segment on which a vehicle traveled at a previous time. "Transfer probability" refers to the probability of transferring from a historical road segment to one of the current candidate road segments. For example, if a historical road segment is directly connected to a current candidate road segment, the transfer probability of that candidate road segment is higher. Conversely, if a historical road segment is far from or not connected to a current candidate road segment, the transfer probability of that candidate road segment is lower.

[0057] For example, such as Figure 2C As shown, candidate road segments can be A1, A2, and A3, where road segment A1 is connected to road segment A2, and road segment A3 is an adjacent road segment of road segments A1 and A2. Figure 2CAs shown, if the historical road segment is A1, the probability of transitioning to candidate road segment A1 (i.e., the probability of continuing on candidate road segment A1) is the highest (e.g., probability 1.0). The probability of transitioning to candidate road segment A2 (i.e., the probability of turning from historical road segment A1 to candidate road segment A2) is also relatively high (e.g., probability 0.75), while the probability of transitioning to candidate road segment A3 (i.e., the probability of jumping from historical road segment A1 to candidate road segment A3) is 0.0. Similarly, if the historical road segment is A2, the probability of transitioning to candidate road segment A2 is the highest (e.g., probability 1.0), the probability of transitioning to candidate road segment A1 is also relatively high (e.g., probability 0.75), while the probability of transitioning to candidate road segment A3 is 0.0. If the historical road segment is A3, the probability of transitioning to candidate road segment A3 is the highest (e.g., probability 1.0), the probability of transitioning to candidate road segment A1 is 0.0, and the probability of transitioning to candidate road segment A2 is also 0.0.

[0058] S204: Using the Viterbi algorithm, the optimal road segment sequence is calculated based on the launch probability and the transition probability.

[0059] The optimal road sequence refers to the road segments that a vehicle actually traveled on at previous and current times. For example, the optimal road segment sequence {…road segment at time t1, road segment at time t2, road segment at time t3, road segment at time t4} can represent the road segments where the vehicle was located at the previous time t1, time t2, time t3, and the current time t4, respectively.

[0060] For example, the electronic device can comprehensively consider the transmission probability determined in S202 and the transition probability determined in S203 to calculate the actual driving road segment at the current time in the optimal road segment sequence. For instance, if the transmission probability corresponding to a candidate road segment A1 is high, but the transition probability corresponding to candidate road segment A1 is 0, it indicates that the position information output by the GNSS may have a large error, and the vehicle will not be in candidate road segment A1. As another example, if the transition probability corresponding to a candidate road segment A2 is high, but the transmission probability corresponding to candidate road segment A2 is low, it may indicate that the vehicle has not yet reached candidate road segment A2. Furthermore, if the transition probability corresponding to a candidate road segment A3 is high, and the transmission probability corresponding to candidate road segment A3 is also high, it can be indicated that the vehicle's current actual driving road segment is candidate road segment A3. Furthermore, the electronic device can determine the vehicle's optimal road segment sequence {…road segment at time t1, road segment at time t2, road segment at time t3, candidate road segment A3 at time t4}.

[0061] S205: Output road-level positioning results.

[0062] In other words, the actual road segment being driven at the current moment in the optimal road segment sequence obtained in S204 is output as the road-level positioning result.

[0063] S206: The next round of calculations will begin as the vehicle moves forward.

[0064] For example, when the GNSS outputs a new vehicle location, the electronic equipment can repeatedly execute S201 to 205 above to calculate the new actual driving road segment.

[0065] Thus, through the above Figure 2A The method shown can achieve road-level positioning of the vehicle, thereby associating the vehicle with the specific road segment it is traveling on, avoiding the phenomenon of vehicle positioning point drift, and providing more accurate navigation decisions for vehicle driving.

[0066] It is understandable that in the aforementioned method for achieving road-level positioning based on Hidden Markov Models (HMMs), the electronic device determines the road-level positioning result based on the transmission and transition probabilities of each candidate road segment. Furthermore, the transmission probability of each candidate road segment is determined solely based on the relative position and relative azimuth between the vehicle and each candidate road segment. However, when adjacent road segments (such as intersections or ramps) are close in distance and have similar directions, the electronic device, relying only on relative position and relative azimuth, struggles to distinguish the vehicle's location at the elevated level or intersection. Consequently, the electronic device cannot accurately associate the vehicle with the actual road segment it is traveling on, easily leading to association errors, such as incorrectly associating the vehicle with a neighboring road segment of the actual road segment.

[0067] To address the aforementioned problems, this application provides a positioning method. Specifically, an electronic device can acquire vehicle perception data at a first moment (such as environmental image data captured by an onboard camera), wherein the perception data includes road segment perception data corresponding to at least one road segment. Then, based on the road segment perception data and the vehicle's current pose, the electronic device can determine the perception probability that the vehicle will travel on each road segment at a second moment, wherein the second moment is later than the first moment. Furthermore, based on the perception probability of each road segment, the electronic device can predict the target road segment that the vehicle will travel on at the second moment. Then, at the second moment, the location of the vehicle traveling on the target road segment can be displayed on the navigation map.

[0068] Thus, the above method enables road-level positioning, associating the vehicle with the specific road segment it travels on, avoiding vehicle positioning drift, and providing more accurate navigation decisions for vehicle travel. Furthermore, when locating the vehicle, this application can also determine the perception probability of the vehicle traveling on each road segment based on perception data (such as environmental image data captured by the vehicle's onboard camera), and then perform subsequent positioning processes based on this perception probability. In this way, by combining the method of determining the perception probability of each road segment with the vehicle's surrounding environment, the electronic device can accurately associate the vehicle with the actual road segment it is traveling on even on complex roads where adjacent road segments (such as intersections or ramps) are close in distance and have similar directions, avoiding the error of associating the vehicle with adjacent road segments of the actual travel segment.

[0069] It should be noted that the electronic device mentioned in this application can be any vehicle equipment such as an in-vehicle computer, vehicle infotainment system, or in-vehicle electronic device. Alternatively, the electronic device mentioned in this application can also be any terminal device capable of data interaction with the vehicle, such as a mobile phone, wearable device, tablet computer, or terminal in self-driving vehicles. This application does not limit the specific form of the electronic device in its embodiments.

[0070] The following is combined Figure 3 The flowchart shown illustrates the positioning method provided in this application. This method can be applied to electronic devices, such as the aforementioned in-vehicle infotainment system. Figure 3 As shown, specifically, the method is as follows:

[0071] S301: Acquire the vehicle's perception data at the first moment.

[0072] In some embodiments, the sensing data may include road segment sensing data corresponding to at least one road segment. For example, such as Figure 4 As shown, the road segment perception data may include lane line perception data, road boundary (such as guardrails) perception data, road segment divergence point perception data, and divergence guide strip perception data, etc., and this application does not limit these.

[0073] In some embodiments, the vehicle's perception data may be sensor data collected by sensors such as cameras or radar, for example, image data of the surrounding environment captured by a camera. Furthermore, the vehicle sensors may also transmit the collected perception data to electronic devices.

[0074] S302: Based on the road segment perception data and the vehicle's current pose in the perception data, determine the perception probability that the vehicle will travel on each road segment at the second moment, wherein the second moment is later than the first moment.

[0075] In some embodiments, the vehicle’s current pose may include the vehicle’s position and / or orientation.

[0076] In some embodiments, the electronic device may determine the first sensing data corresponding to each road segment based on the magnitude of the relative distance between the vehicle and each road segment, and / or based on the magnitude of the relative direction between the vehicle and each road segment.

[0077] Specifically, when determining the initial probability of a vehicle traveling on various road segments, the electronic device can first perform coordinate system transformation on the coordinates of the sensing sampling points in the road segment sensing data or the coordinates of the map sampling points in the map data, thereby obtaining the coordinates of the sensing sampling points and the map sampling points belonging to the same coordinate system. Then, the electronic device can determine a coordinate correction amount (also called a pose correction amount) based on the coordinates of the sensing sampling points and the map sampling points located in the same coordinate system and belonging to the same actual road point, and correct the vehicle's current pose based on this coordinate correction amount to obtain the corrected vehicle pose. Then, the electronic device can determine the initial probability of the vehicle traveling on road segment A in the navigation map based on the relative position and / or relative azimuth angle between the corrected vehicle pose and a certain road segment A (as an example of the first road segment). The specific process for determining the initial probability of the vehicle can be found later in the text. Figure 5 As shown, details will not be elaborated here.

[0078] In other embodiments, when there is a diversion road segment on the road segment in front of the vehicle, such as the one described above. Figure 4 The electronic equipment can also sense data from the diversion points of the road segments 401 and 402 as shown above. Figure 4 Using the perception data corresponding to the road segment divergence point 405 shown, the road extension direction of the divergence road segment (as an example of the second road segment), and the vehicle pose, a second perception probability that the vehicle will travel on a certain divergence road segment is determined. The specific process for determining the second perception probability can be found later. Figure 7 As shown, details will not be elaborated here.

[0079] Thus, by using the above method, the first perception probability and / or the second perception probability that the vehicle will travel on each road segment at the second moment can be determined.

[0080] S303: Based on the perception probability of each road segment, predict the target road segment that the vehicle will travel on at the second time.

[0081] In some embodiments, the electronic device can determine the probability of the vehicle traversing each road segment at a second moment based on the relative distance and relative azimuth angle between the vehicle's current pose and each road segment in the navigation map. For example, as described above. Figure 2B The electronic device shown can determine the transmission probability of road segment A1 based on the relative distance and relative azimuth between the location of vehicle C1 on the navigation map and road segment A1. See below for details. Figure 11 As shown in S111, details will not be elaborated here.

[0082] Additionally, electronic devices can also determine the probability of a vehicle transferring from its current road segment to other road segments in a second moment, based on the path connections between the vehicle's current road segment and other road segments in the first moment, within the navigation map. For example, as described above. Figure 2C As shown, if the current road segment is A1, the transition probability for road segment A2 is 0.75, and the transition probability for road segment A3 is 0.0. See below for details. Figure 11 As shown in S112, details will not be elaborated here.

[0083] Thus, after calculating the first and second perception probabilities of each road segment through S302 above, and the emission and transfer probabilities of each road segment through S303 above, the electronic device can predict the target road segment the vehicle will travel on at the second moment based on the first perception probability, second perception probability, emission probability, and transfer probability corresponding to the road segment. See below for details. Figure 11 As shown in S113, details will not be elaborated here.

[0084] S304: At the second moment, the vehicle is displayed on the navigation map as traveling on the target road segment.

[0085] In some embodiments, after determining the target road segment that the vehicle will travel on in the next moment, the electronic device can associate the target road segment on the navigation map with the vehicle in the next moment to achieve road-level positioning of the vehicle.

[0086] Thus, by using the above method, the vehicle can be associated with the specific road segment it is traveling on, avoiding vehicle positioning drift and providing more accurate navigation decisions for vehicle travel. Furthermore, when locating the vehicle, this application can also determine the perception probability of the vehicle traveling on each road segment based on perception data (such as environmental image data captured by the vehicle's onboard camera), and then perform subsequent positioning processes based on this perception probability. In this way, by combining the method of determining the perception probability of each road segment with the vehicle's surrounding environment, the electronic device can accurately associate the vehicle with the actual road segment it is traveling on even on complex roads where adjacent road segments (such as intersections or ramps) are close in distance and have similar directions, avoiding the error of associating the vehicle with adjacent road segments of the actual road segment.

[0087] The following is combined Figure 5 The flowchart shown illustrates the process of determining the initial probability of a vehicle traveling on various road segments, as mentioned above. This method can be applied to electronic devices, such as the aforementioned in-vehicle infotainment systems. Figure 5 As shown, specifically, the method is as follows:

[0088] S51: Based on road segment perception data and map data of each road segment in the navigation map, the current position and pose of the vehicle are corrected.

[0089] In this way, by registering the perceived data and the navigation map data, the discrepancy between the navigation map and the physical world caused by mapping errors can be effectively resolved. Specifically, the process of correcting the vehicle's current pose can be referred to as follows: S511 to S514:

[0090] S511: Based on road segment perception data, determine the coordinates of perception sampling points on each road segment in the vehicle coordinate system.

[0091] In some embodiments, the electronic device can determine the coordinates of each sensing sampling point in the vehicle coordinate system (VCS) based on the distance of each sensing sampling point in the road segment sensing data relative to the vehicle.

[0092] For example, the electronic device can first determine the road boundaries (also called road geometric boundaries) of each road segment (taking the first road segment as an example) and the road area within the road boundaries based on road segment perception data. For example, as Figure 6 As shown, the electronic device can determine the road boundary 601 and the road area 602 located within the road boundary. The road boundary may include the edges of impassable areas such as curbs, guardrails, median strip edges, or green belt edges.

[0093] Then, after determining the road boundaries, the electronic device can obtain the coordinates of each boundary point on the road boundary in the vehicle coordinate system. For example, the coordinates of each boundary point in the vehicle coordinate system can be... Where i refers to the i-th boundary point, N refers to all N boundary points, and bx i It is the x-coordinate of the i-th boundary point, by i It is the ordinate of the i-th boundary point.

[0094] Next, the electronic device can create a two-dimensional grid within the road area of ​​the road boundary, for example, in Figure 6 The road area 602 shown is divided into multiple two-dimensional grids. The electronic device can then determine the coordinates of the sensing sampling points within each grid in the vehicle coordinate system based on the coordinates of each boundary point. When determining the coordinates of each sensing sampling point, it is also necessary to first determine whether each sensing sampling point is within the road boundary. If it is within the road boundary, its coordinates in the vehicle coordinate system can be calculated. For example, the sensing sampling point within each grid can refer to the center point of each grid. The coordinates of the sensing sampling points within each grid (i.e., the center point of each grid) can be determined by... To obtain it. Among them, Let x be the minimum x-coordinate among the coordinates of each road boundary. Let be the minimum ordinate among the coordinates of each road boundary, i be the i-th horizontal grid cell in the road area, and j be the j-th vertical grid cell in the road area. It is the grid side length.

[0095] In this way, the coordinates of the sensing sampling points on each road segment in the vehicle coordinate system can be determined using the above method.

[0096] S512: Based on map data, determine the coordinates of map sampling points on each road segment in the navigation map in the world coordinate system.

[0097] In some embodiments, the electronic device may first determine the map sampling points on the navigation map, and then read the coordinates of the map sampling points recorded on the navigation map in the world coordinate system.

[0098] For example, an electronic device can determine multiple connected road segments near a vehicle (as an example of a first road segment) in a navigation map based on map data. For road segments that overlap in two-dimensional space, such as ground-level roads and elevated roads, the electronic device can acquire data for each road segment separately. Then, the electronic device can determine the road width of each road segment based on standard lane widths (such as lane widths specified in national standards) and the number of lanes in each road segment indicated by the map data. For example, if a road segment A (as an example of a first road segment) has three lanes, the electronic device can determine the road width of road segment A based on 3*L1, where L1 is the lane width specified in national standards. It should be understood that the lane width specified in national standards may not be uniform; for example, highways, national roads, or provincial roads may have different lane widths. Therefore, the electronic device can determine the lane width L1 of a road segment A based on its road classification attribute (such as highway or provincial road) in the navigation map, and this application does not limit this determination.

[0099] Next, the electronic device can sample each road segment at equal intervals (also known as preset sampling distances) to determine multiple sampling centers on each road segment. That is, adjacent sampling centers are spaced apart by a preset sampling distance. Then, the electronic device can determine multiple map sampling points based on each sampling center and obtain the coordinates of these map sampling points in the world coordinate system. For example, the electronic device can determine multiple map sampling points on a circle centered at the sampling center and with a first diameter. The first diameter can be determined based on the road width, such as the road width itself or half of the road width.

[0100] In this way, the coordinates of the map sampling points on each road segment in the world coordinate system can be determined using the above method.

[0101] S513: Based on the vehicle's current pose, perform coordinate system transformation on the coordinates of the perception sampling points or the map sampling points to obtain the coordinates of the perception sampling points and the map sampling points belonging to the same coordinate system.

[0102] In some embodiments, the electronic device can convert the coordinates of the sensing sampling points in the vehicle coordinate system to the coordinates of the sensing sampling points in the world coordinate system based on the current pose of the vehicle. Alternatively, the electronic device can also convert the coordinates of the map sampling points in the world coordinate system to the coordinates of the map sampling points in the vehicle coordinate system based on the current pose of the vehicle.

[0103] S514: Based on the coordinates of perception sampling points and map sampling points located on the same road features in the same coordinate system, the vehicle's pose is corrected.

[0104] In some embodiments, after registering the perceived data and map data using the method described in S513 above, the electronic device can determine a coordinate correction amount based on the corresponding perceived sampling point coordinates and map sampling point coordinates. The corresponding perceived sampling point coordinates and map sampling point coordinates located on the same road feature indicate that they represent the same actual road point. Then, after determining the coordinate correction amount, the electronic device can superimpose the coordinate correction amount onto the vehicle's current pose to obtain the corrected vehicle pose.

[0105] Thus, the vehicle's position and posture can be corrected through the above steps S511 to S514.

[0106] S52: In the navigation map, based on the corrected vehicle pose and the relative distance and / or relative azimuth between each road segment, determine the first perception probability that the vehicle will travel on each road segment at the second moment.

[0107] In some embodiments, after correcting the vehicle's pose, the electronic device can determine, on a navigation map, the shortest relative distance between the corrected vehicle position and each road segment (such as a first road segment), and the relative azimuth angle between the corrected vehicle attitude (such as orientation) and the road extension direction of each road segment. Then, based on the relative distance and relative azimuth angle between the vehicle's pose and each road segment, the electronic device can determine the first perception probability corresponding to each road segment. For example, the smaller the relative distance and the smaller the relative azimuth angle, the greater the first perception probability corresponding to that road segment.

[0108] In this way, the first probability of the vehicle traveling on each road segment can be determined using the above method. Furthermore, by registering the perception data and navigation map data, the discrepancy between the navigation map and the physical world caused by mapping errors can be effectively resolved, thereby improving the accuracy and success rate of road-level positioning, and also shortening the reconvergence time after navigation deviation.

[0109] The following is combined Figure 7 The flowchart shown illustrates the process of determining the second perception probability of the vehicle traveling on various road segments, as mentioned above. Among these, [the process is related to the above...]. Figure 5 Compared to the process of determining the first perception probability shown, the embodiments of this application combine the perception data of the diversion points of the road segment when determining the second perception probability, thereby improving the positioning accuracy in the road segment diversion scenario. This method can be applied to electronic devices, such as the aforementioned in-vehicle infotainment systems. Figure 7 As shown, specifically, the method is as follows:

[0110] S71: Determine the location of the diversion points for each road segment based on the diversion point sensing data.

[0111] In some embodiments, the road segment perception data includes at least one shunting point perception data corresponding to a road segment shunting point, wherein the road segment shunting point is located between the road segment where the vehicle is located at the first moment and a second road segment ahead of the vehicle. For example, as described above. Figure 4 As shown, road segment diversion point 405 is located between the current road segment 404 and the road segment 402 (or road segment 401) ahead of the vehicle, and road segment diversion point 406 is located between the current road segment 404 and the road segment 402 (or road segment 403) ahead of the vehicle. Furthermore, road segment diversion point 405 is also used to divert the vehicle's current road segment 404 into road segments 401 and 402, and road segment diversion point 406 is also used to divert the vehicle's current road segment 404 into road segments 402 and 403.

[0112] In some embodiments, since the sensing accuracy of sensors such as vehicle cameras changes with the sensing distance, and the distance that needs to be sensed in advance also changes dynamically at different vehicle speeds, the electronic device can also dynamically adjust the effective longitudinal sensing range (also known as the effective sensing distance) according to the vehicle speed. Only road segment divergence points within the effective sensing range will be considered effective road segment divergence points. For example, the electronic device can determine the effective sensing range of the vehicle according to the following formula (1):

[0113] (1);

[0114] in, Indicates the vehicle's effective sensing range. This represents the vehicle's basic perception range, determined based on experiments or experience; v represents the vehicle speed; k represents the vehicle's speed. speed This refers to a coefficient determined based on experiments or experience.

[0115] Thus, through the above formula (1), the electronic device can determine the effective perception range of the vehicle and use the diversion point perception data within the effective perception range as the effective diversion point perception data.

[0116] S72: Based on the location of the diversion points of each road segment, the road extension direction of the second road segment, and the current pose of the vehicle, determine the second perception probability that the vehicle will travel on the second road segment at the second moment.

[0117] In some embodiments, the road segment ahead of the vehicle may include a second road segment for diversion (as described above). Figure 4 Section 401 of the road and the third road section (as described above) Figure 4 Road section 402), road section diversion point (as mentioned above) Figure 4 The road segment diversion point 405 is located between the road segment where the vehicle is located at the first moment and the third road segment (or the second road segment). Furthermore, the road segment diversion point is also used to divert vehicles from the road segment where they are located at the first moment to the second and third road segments.

[0118] In some embodiments, before determining the second perceived probability that the vehicle will travel on the second and third road segments, the electronic device may first determine on the navigation map the fourth road segment where the vehicle will be located before passing the branch points of each road segment. The process of determining the fourth road segment is described below.

[0119] For example, electronic devices can Determine the x-coordinate of the center position of the diversion point of each road segment. c , where x i This represents the x-coordinate (e.g., the coordinate of the vehicle's direction of travel) of the i-th road segment divergence point in the vehicle coordinate system, and N represents the total number of road segment divergence points. Additionally, it can be determined by... Determine the y-coordinate of the center position of the diversion point of each road segment. c , where y i The ordinate of the i-th road segment divergence point in the vehicle coordinate system (e.g., the coordinates of the left and right sides of the vehicle) is represented by N, and N represents the total number of road segment divergence points.

[0120] Then, electronic devices can... Determine the center location of each road divergence point and the distance d between the vehicles. c , where x c It is the x-coordinate of the center position of each road divergence point in the vehicle coordinate system, y c This is the ordinate of the center position of each road divergence point in the vehicle coordinate system. Next, as... Figure 8 As shown, the electronic device can determine the distance d from the vehicle on the navigation map. c At point A, a distance is specified, and multiple fifth road segments are found within a certain radius centered at point A. The endpoints of each found fifth road segment lie within a circle centered at point A, and each fifth road segment has multiple subsequent road segments. For example, ... Figure 8 As shown, the found fifth road segments are road segments L3 and L7. Next, the electronic equipment selects the fifth road segment with the smallest relative azimuth angle based on the vehicle's position and the road extension direction of each fifth road segment. This fifth road segment is the fourth road segment the vehicle is in before passing the branching points of each road segment (e.g., L3 and L7). Figure 8 Road section L3 in the middle.

[0121] In this way, the fourth road segment where the vehicle is located before passing the branching points of each road segment can be determined using the above method. Then, the electronic equipment can determine the second road segment, the third road segment (or other road segments) into which the fourth road segment branches off, based on the branching points of each road segment.

[0122] Next, the electronic device can determine the second perception probability that the vehicle will travel on the second road segment at the second moment through a multi-round voting mechanism, based on the diversion points of each road segment, the vehicle's current position, the road extension direction of the second road segment, and the road extension direction of the third road segment (or may also include the road extension directions of other road segments). See S721 to S724 below for details.

[0123] S721: Based on the vehicle's current pose, the road extension direction of the second road segment, and the road extension direction of the third road segment, the second road segment is determined as the candidate road segment corresponding to the first moment.

[0124] For example, the electronic device can select a candidate road segment corresponding to the vehicle's direction of travel from multiple road segments, such as the second road segment and the third road segment.

[0125] In some embodiments, such as Figure 9 As shown, the electronic device can also divide the road segments after each road segment divergence point into road groups (e.g., road group A1, road group A2, and road group A3) based on the location of each road segment divergence point (e.g., road segment divergence point 901 and road segment divergence point 902) and the road extension direction of each road segment after the road segment divergence point. Then, the electronic device can also select a candidate road group corresponding to the vehicle's direction of travel from each road group, wherein the first road segment in the candidate road group is the aforementioned candidate road segment.

[0126] S722: Based on the preset distance and the effective sensing distance when acquiring sensing data at the first moment, calculate the first confidence value corresponding to the second road segment at the first moment.

[0127] The effective sensing distance is the effective sensing range calculated by the formula (1) above. The preset distance is the distance between the center point of each road segment divergence point and the vehicle at the first moment, which is the distance d calculated in S72 above. c Furthermore, the first confidence value can be calculated using the following formula (2).

[0128] (2);

[0129] in, It is the effective sensing distance, d cThe distance between the center point of each road segment divergence point and the vehicles at the first moment. Conf is the confidence value, where the distance d is the distance between the divergence points. c The closer the two are, the higher the confidence value (Conf).

[0130] S723: Based on the first confidence value and other confidence values ​​of the second road segment calculated at previous times, determine the total confidence value of the second road segment.

[0131] In other words, the total confidence value of each road segment is obtained by summing them up.

[0132] In some embodiments, such as Figure 10 As shown, the electronic device can determine a candidate road segment at each time point (T0, T1, T2, T3, T4, or T5) and calculate the confidence value at that time. For example, Figure 10 As shown, at time T0, if vehicle 100 does not find a road segment diversion point or there are no road segments nearby that can match the road segment diversion point, the electronic device can set the voting mechanism at the current time to an invalid state. At time T1, when the electronic device selects road segment L3 as a candidate road segment based on the direction of travel of vehicle 100, the electronic device can determine the confidence value Conf_31 of road segment L3 at time T1 according to the above formula (2). At time T2, when the electronic device determines road segment L2 as a candidate road segment based on the direction of travel of vehicle 100, the electronic device can determine the confidence value Conf_22 of road segment L2 at time T2 according to the above formula (2). At time T3, when the electronic device determines road segment L2 as a candidate road segment based on the direction of travel of vehicle 100, the electronic device can determine the confidence value Conf_23 of road segment L2 at time T3 and the total confidence value Conf_22+Conf_23 according to the above formula (2). At time T4, when the electronic device determines road segment L2 as a candidate road segment based on the direction of travel of vehicle 100, the electronic device can determine the confidence value Conf_24 and the total confidence value Conf_22+Conf_23+Conf_24 of road segment L2 at time T4 according to the above formula (2). At time T5, if vehicle 100 does not find a road segment diversion point or there is no road segment around it that can match the road segment diversion point, the electronic device can set the voting mechanism at the current time to an invalid state.

[0133] In summary, in a multi-round voting mechanism, electronic devices can accumulate the confidence values ​​of each road segment calculated each time to obtain the total confidence value of each road segment.

[0134] S724: If the number of calculations exceeds the number threshold and / or the total confidence value meets the first condition, set the corresponding second perception probability for the second road segment and the third road segment.

[0135] In some embodiments, the total confidence value satisfying the first condition may include: the total confidence value corresponding to the second road segment is greater than a confidence threshold; and the total confidence value corresponding to the second road segment is greater than the total confidence value of the third road segment (or may also include other road segments) calculated at previous time points. Additionally, the second perception probability corresponding to the second road segment is greater than the second perception probability corresponding to the third road segment (or may also include other road segments).

[0136] In some embodiments, when the voting mechanism is in an invalid state, the second perception probability corresponding to each road segment can be set to 1.0 to indicate that it will not affect the determination of the target road segment. Additionally, when the number of calculations is less than a threshold and / or the total confidence value does not meet the first condition, the voting mechanism is in a selection state. At this time, the second perception probability corresponding to each road segment can also be set to 1.0 to indicate that it will not affect the determination of the target road segment. Furthermore, when the number of calculations is greater than a threshold and / or the total confidence value meets the first condition, the voting mechanism is in a confirmation state. At this time, the electronic device can set different second perception probabilities for each road segment.

[0137] Thus, the second perception probability of a vehicle traveling on each road segment can be determined using the above method. Furthermore, identifying vehicle driving intentions by perceiving road segment divergence points provides a powerful observation source in road divergence scenarios, thereby improving the accuracy of road-level localization. For example, in intersection scenarios, compared to traditional solutions, the method provided in this application can significantly reduce the false matching rate and increase decision lead time.

[0138] The following is combined Figure 11 The flowchart shown describes the process of determining the target road segment by combining the first perception probability and the second perception probability of each road segment. This method can be applied to electronic devices, such as the aforementioned in-vehicle infotainment systems. Figure 11 As shown, specifically, the method is as follows:

[0139] S111: In the navigation map, based on the vehicle's current pose and the relative distance and relative azimuth angle between it and each road segment, the probability of the vehicle traversing each road segment at the second moment is determined.

[0140] In some embodiments, the electronic device can calculate the shortest relative distance between the vehicle's position on the navigation map and each road segment, and calculate the relative azimuth angle between the vehicle's posture (e.g., orientation) and the road extension direction of each road segment. Then, based on the relative distance and relative azimuth angle between the vehicle's posture and each road segment, the electronic device can determine the corresponding transmission probability for each road segment. The smaller the relative distance and the smaller the relative azimuth angle, the higher the degree of matching between the vehicle's posture and that road segment, and the greater the corresponding transmission probability.

[0141] S112: In the navigation map, based on the path connection relationship between the vehicle's current driving road segment and other road segments at the first moment, determine the transfer probability of the vehicle moving from the current driving road segment to other road segments at the second moment.

[0142] For example, if the current road segment is directly connected to another road segment, the probability of switching to that road is higher. Conversely, if the current road segment is far from or not connected to another road segment, the probability of switching to that road is lower.

[0143] S113: Based on the first perception probability, second perception probability, emission probability and transfer probability corresponding to each road segment, predict the target road segment that the vehicle will travel on at the second time.

[0144] In some embodiments, the electronic device can first determine the predicted probability (also known as the observation probability) that the vehicle will travel on each road segment at the second moment based on the first perception probability, the second perception probability, and the transmission probability corresponding to each road segment. For example, the calculation process of the predicted probability can be referred to the following formula (3).

[0145] (3);

[0146] in, This represents the predicted probability for each road segment. This represents the first perception probability for each road segment. This represents the second perception probability corresponding to each road segment. This represents the emission probability corresponding to each road segment.

[0147] It is understandable that in practical applications, in order to facilitate calculation, the probability values ​​on both sides of the above formula (3) can be logarithmic and addition can be used instead of multiplication to obtain the predicted probability of each road segment.

[0148] Then, after determining the predicted probability corresponding to each road segment based on the above formula (3), the electronic device can predict the target road segment that the vehicle will travel on at the second time point based on the predicted probability and transition probability corresponding to each road segment. The predicted probability corresponding to the target road segment satisfies the prediction probability condition, for example, the predicted probability corresponding to the target road segment is greater than the predicted probability corresponding to other road segments, and / or, the predicted probability corresponding to the target road segment is greater than the prediction probability threshold. Furthermore, the transition probability corresponding to the target road segment satisfies the transition probability condition, for example, the transition probability corresponding to the target road segment is greater than the transition probability corresponding to other road segments, and / or, the transition probability corresponding to the target road segment is greater than the transition probability threshold.

[0149] Thus, the above method enables road-level positioning, associating the vehicle with the specific road segment it travels on, preventing vehicle positioning drift, and providing more accurate navigation decisions. Furthermore, multi-dimensional observation complementarity improves system fault tolerance, allowing it to function normally even under conditions of single-dimensional time-sensitive or noisy states. This, in turn, improves system availability in complex scenarios and increases fault tolerance for single-frame observation anomalies. Additionally, compared to end-to-end deep learning solutions, the method provided in this application reduces memory usage, thereby meeting the real-time requirements of mass-produced automotive platforms.

[0150] The following is combined Figure 12 The overall process of the positioning method provided in this application is described.

[0151] like Figure 12 As shown, the electronic device can acquire vehicle perception data and determine features such as road boundaries and road segment divergence points through a perception model. Then, the electronic device can determine the first perception probability (also known as the road boundary geometric registration observation probability) for each road segment based on features such as road boundaries, and the second perception probability (also known as the road divergence point semantic observation probability) for each road segment based on features such as road segment divergence points. Additionally, the electronic device can determine the transmission probability (also known as the relative distance geometric observation probability) for each road segment based on the vehicle pose acquired by GNSS. Next, the electronic device can determine the predicted probability for each road segment based on the first perception probability, second perception probability, and transmission probability. Furthermore, the electronic device can determine the transfer probability for each road segment based on the vehicle's historical travel routes. In this way, the electronic device can determine the target road segment based on the predicted and transfer probabilities of each road segment, thereby achieving road-level positioning.

[0152] Thus, by employing the methods described above, road-level positioning can be achieved, thereby associating the vehicle with the specific road segment it is traveling on, preventing vehicle positioning point drift, and providing more accurate navigation decisions for vehicle travel. Furthermore, through multi-dimensional observation complementarity, the system's fault tolerance can be improved, allowing it to function normally even under conditions of single-dimensional time-sensitive or noisy conditions.

[0153] Furthermore, in some embodiments, corresponding to the above-described positioning method, this application also provides a positioning system. For example, such as... Figure 13 As shown, the positioning system 1300 may include a perception data acquisition module 1301, a perception probability determination module 1302, a target road segment determination module 1303, and a navigation display module 1304.

[0154] The perception data acquisition module 1301 is used to acquire the perception data of the vehicle at the first moment, and the perception data includes road segment perception data corresponding to at least one road segment.

[0155] The perception probability determination module 1302 is used to determine the perception probability that the vehicle will travel on each road segment at the second moment based on the road segment perception data and the vehicle's current pose.

[0156] The target road segment determination module 1303 is used to predict the target road segment that the vehicle will travel on at the second time point based on the perception probability of each road segment.

[0157] The navigation display module 1304 is used to display the vehicle's travel on the target road segment on the navigation map at a second moment.

[0158] Thus, the above positioning system can achieve road-level positioning, thereby associating the vehicle with the specific road segment it is traveling on, avoiding vehicle positioning drift, and providing more accurate navigation decisions for vehicle driving.

[0159] Furthermore, in some embodiments, the perception probability determination module 1302 may include a first perception probability submodule. The first perception probability submodule is used to correct the vehicle's current pose based on road segment perception data and map data of each road segment in the navigation map. Furthermore, the first perception probability submodule is also used to determine, in the navigation map, a first perception probability that the vehicle will travel on each road segment at a second time, based on the relative distance and / or relative azimuth angle between the corrected vehicle pose and each road segment.

[0160] Furthermore, in some embodiments, the perception probability determination module 1302 may include a second perception probability submodule. The second perception probability submodule is used to determine the location of each road segment's diversion point based on the diversion point perception data. Furthermore, the second perception probability submodule is also used to determine a second perception probability that the vehicle will travel on each road segment at a second time, based on the location of each road segment's diversion point, the road extension direction of each road segment, and the vehicle's current pose.

[0161] Furthermore, in some embodiments, the positioning system may also include a transmission probability determination module, which is used to determine, in the navigation map, the transmission probability that the vehicle will travel on each road segment at a second moment, based on the relative distance and relative azimuth angle between the vehicle's current pose and each road segment.

[0162] Furthermore, in some embodiments, the positioning system may also include a transition probability determination module, which is used to determine, in the navigation map, the transition probability that the vehicle will transfer from the current driving road segment to each road segment at a second moment, based on the path connection relationship between the vehicle's current driving road segment and each road segment at a first moment.

[0163] Furthermore, in some embodiments, the target road segment determination module 1303 is also used to predict the target road segment in which the vehicle travels at the second time point based on the first perception probability, the second perception probability, the emission probability, and the transfer probability corresponding to each road segment.

[0164] Thus, the aforementioned positioning system enables road-level positioning, associating vehicles with specific road segments and preventing vehicle location drift, thereby providing more accurate navigation decisions. Furthermore, multi-dimensional observation complementarity enhances system fault tolerance, allowing it to function normally even under conditions of single-dimensional time-sensitive or noisy conditions.

[0165] In some embodiments, this application also provides a readable storage medium. The readable storage medium stores instructions that, when executed on an electronic device, cause the electronic device to perform the positioning method mentioned in this application.

[0166] In other embodiments, this application also provides a computer program product, wherein the computer program product includes computer instructions. When the computer instructions are executed on an electronic device, the electronic device enables the electronic device to implement the positioning method mentioned in this application.

[0167] In other embodiments, this application also provides an electronic device. The electronic device includes at least one memory and at least one processor, the memory being coupled to the processor. The memory stores computer program code / instructions. When the computer program code / instructions are executed by the processor, the electronic device can implement the positioning method mentioned in this application.

[0168] Furthermore, in some embodiments, this application also provides a vehicle, which may include the aforementioned electronic equipment. For example, taking a computer system 50 as an example, refer to... Figure 14 The diagram illustrates, by way of example, the structural schematic of the vehicle 100 proposed in this application.

[0169] like Figure 14 As shown, the functional framework of vehicle 100 may include various subsystems, such as the sensor system 10, control system 20, one or more peripheral devices 30 (one is shown as an example), power supply 40, and computer system 50. Optionally, vehicle 100 may also include other functional systems, such as an engine system that provides power to vehicle 100, etc., which are not limited herein.

[0170] The sensor system 10 may include several detection devices that can sense the measured information and convert the sensed information into electrical signals or other desired forms of information output according to a certain rule. For example... Figure 14 As shown, these detection devices may include a global navigation satellite system (GNSS), a vehicle speed sensor (12), an inertial measurement unit (IMU), etc., and this application does not limit them.

[0171] The Global Navigation Satellite System 11 can be used for real-time positioning and navigation globally. In this application, the Global Navigation Satellite System 11 can be used to achieve real-time positioning of the vehicle 100, providing the geographical location information of the vehicle 100. Exemplarily, the Global Navigation Satellite System 11 may include the Global Positioning System (GPS), BeiDou satellite navigation system, or Galileo system, etc. The vehicle speed sensor 12 is used to detect the vehicle speed of the vehicle 100. The inertial measurement unit 13 may include a combination of an accelerometer and a gyroscope, and is a device for measuring the angular rate and acceleration of the vehicle 100. For example, during vehicle operation, the inertial measurement unit 13 can measure the position and angular changes of the vehicle body based on the inertial acceleration of the vehicle 100, such as measuring the acceleration and angular rate of the vehicle 100.

[0172] The control system 20 may include a steering unit 21, a braking unit 22, etc.

[0173] Steering unit 21 can represent a system for adjusting the direction of travel of vehicle 100, which may include, but is not limited to, a steering wheel or other structural device for adjusting or controlling the direction of travel of vehicle 100. Braking unit 22 can represent a system for slowing down the speed of vehicle 100, and may also be called a vehicle braking system. It may include, but is not limited to, a brake controller, a reducer, or other structural device for slowing down the vehicle. In practical applications, braking unit 22 can use friction to slow down the vehicle tires, thereby slowing down the speed of vehicle 100.

[0174] Peripheral device 30 may include several components, such as the communication system 31, touch screen 32, user interface 33, etc., as shown in the figure. The communication system 31 is used to enable network communication between vehicle 100 and other devices besides vehicle 100. In practical applications, the communication system 31 can employ wireless communication technology or wired communication technology to achieve network communication between vehicle 100 and other devices. This wired communication technology can refer to communication between vehicle 100 and other devices via network cable or fiber optic cable, etc. This wireless communication technology includes, but is not limited to, Global System for Mobile Communications (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Time Division Code Division Multiple Access (TD-SCDMA), Long Term Evolution (LTE), Wireless Local Area Networks (WLAN) (such as Wireless Fidelity (Wi-Fi) networks), Bluetooth (BT), Global Navigation Satellite System (GNSS), Frequency Modulation (FM), Near Field Communication (NFC), and Infrared (IR) technology, etc.

[0175] The touchscreen 32 can be used to detect operation commands on the touchscreen 32. For example, the user can perform touch operations on the content data displayed on the touchscreen 32 according to actual needs to achieve the corresponding function, such as playing music, video, or other multimedia files. The user interface 33 can specifically be a touch panel, used to detect operation commands on the touch panel. The user interface 33 can also be a physical button or a mouse. The user interface 33 can also be a display screen, used to output data and display images or data. Optionally, the user interface 33 can also be at least one device belonging to the category of peripheral devices, such as a touchscreen, microphone, and speaker.

[0176] Several functions of vehicle 100 are controlled and implemented by computer system 50. Computer system 50 may include multiple processing systems, such as processor 51, continuous damping control (CDC) 52, mobile device control (MDC) 53, telematics-BOX (T-BOX) 54, as well as memory 55 (also referred to as a storage device) and gateway 56. In practical applications, memory 55 can be located inside or outside computer system 50, for example, as a cache within vehicle 100; this application does not impose limitations. Processor 51 may be, for example, a graphics processing unit (GPU). Processor 51, CDC 52, MDC 53, and T-BOX 54 can be used to run relevant programs or corresponding instructions stored in memory 55 to implement the corresponding functions of vehicle 100.

[0177] The memory 55 may include volatile memory; it may also include non-volatile memory, such as read-only memory (ROM), flash memory, or solid-state drive; or it may include a combination of the above types of memory. The memory 55 can be used to store a set of program code or instructions corresponding to the program code, so that the processor 51 can call the program code or instructions stored in the memory 55 to implement the corresponding functions of the vehicle 100. In this application, the memory 55 may store a set of program code for vehicle control, which the processor 51, CDC 52, MDC 53, and T-BOX 54 can call to control the vehicle.

[0178] Optionally, in addition to storing program code or instructions, memory 55 may also store information such as navigation maps, driving routes, and sensor data. Computer system 50 can be combined with other components in the vehicle functional framework diagram, such as the sensors in sensor system 10, to realize the relevant functions of vehicle 100. For example, computer system 50 can control the driving direction or speed of vehicle 100 based on data input from sensor system 10; this application does not impose limitations on this.

[0179] It should be noted that the above Figure 14 This is merely a schematic diagram of one possible functional framework for vehicle 100. In practical applications, vehicle 100 may include more or fewer systems or components, and this application does not impose any limitations.

[0180] The embodiments disclosed herein can be implemented in hardware, software, firmware, or a combination of these implementations. The embodiments herein can be implemented as computer programs or program code executable on a programmable system including at least one processor, a storage system (including volatile and non-volatile memory and / or storage elements), at least one input device, and at least one output device.

[0181] Program code can be applied to input instructions to perform the functions described herein and generate output information. The output information can be applied to one or more output devices in a known manner. For the purposes of this document, the processing system includes any system having a processor such as, for example, a digital signal processor, a microcontroller, an application-specific integrated circuit, or a microprocessor.

[0182] The program code can be implemented using a high-level procedural language or an object-oriented programming language to communicate with the processing system. Assembly language or machine language can also be used when needed. In fact, the mechanisms described in this paper are not limited to any particular programming language. In either case, the language can be a compiled language or an interpreted language.

[0183] In some cases, the disclosed embodiments may be implemented in hardware, firmware, software, or any combination thereof. The disclosed embodiments may also be implemented as instructions carried or stored thereon on one or more temporary or non-temporary machine-readable (e.g., computer-readable) storage media, which may be read and executed by one or more processors. For example, the instructions may be distributed via a network or through other computer-readable media. Therefore, machine-readable media may include any mechanism for storing or transmitting information in a machine-readable (e.g., computer-readable) form, including but not limited to floppy disks, optical disks, optical discs, magneto-optical disks, read-only memory (ROM), random access memory (RAM), magnetic cards or optical cards, erasable programmable read-only memory (EPROM), flash memory, electrically erasable programmable read-only memory (EEPROM), or tangible machine-readable storage for transmitting information (e.g., carrier waves, infrared signals, digital signals, etc.) using the Internet in the form of electrical, optical, acoustic, or other propagation signals. Therefore, machine-readable media includes any type of machine-readable medium suitable for storing or transmitting electronic instructions or information in a machine-readable (e.g., computer-readable) form.

[0184] In the accompanying drawings, some structural or methodological features may be shown in a specific arrangement and / or order. However, it should be understood that such a specific arrangement and / or order may not be necessary. Rather, in some embodiments, these features may be arranged in a manner and / or order different from that shown in the illustrative drawings. Furthermore, the inclusion of structural or methodological features in a particular figure does not imply that such features are required in all embodiments, and in some embodiments, these features may be omitted or may be combined with other features.

[0185] It should be noted that the units / modules mentioned in the device embodiments of this paper are logical units / modules. Physically, a logical unit / module can be a physical unit / module, a part of a physical unit / module, or a combination of multiple physical units / modules. The physical implementation of these logical units / modules is not the most important factor; rather, the combination of functions implemented by these logical units / modules is the key to solving the technical problem proposed in this paper. Furthermore, to highlight the innovative aspects of this paper, the device embodiments described above have not introduced units / modules that are not closely related to solving the technical problem proposed in this paper. This does not mean that the device embodiments do not contain other units / modules.

[0186] It should be noted that in the examples and description of this patent, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one" does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0187] While this document has been illustrated and described with reference to certain preferred embodiments thereof, those skilled in the art will understand that various changes in form and detail may be made therein without departing from the scope of this document.

Claims

1. A positioning method, characterized in that, include: Acquire the vehicle's perception data at the first moment, the perception data including road segment perception data corresponding to at least one road segment; Based on the road segment perception data and the vehicle's current pose, the perception probability that the vehicle will travel on each of the road segments at a second moment is determined, wherein the second moment is later than the first moment; Based on the perception probability of each road segment, the target road segment in which the vehicle travels at the second time moment is predicted; At the second moment, the vehicle is displayed on the navigation map as traveling on the target road segment.

2. The positioning method according to claim 1, characterized in that, The at least one road segment includes a first road segment, and the perception probability includes a first perception probability that the vehicle will travel on the first road segment at a second moment; and... The step of determining the probability that the vehicle will travel on each of the road segments at the second moment based on the road segment perception data and the vehicle's current pose includes: Based on the road segment perception data and the map data of each road segment in the navigation map, the current pose of the vehicle is corrected; In the navigation map, based on the relative distance and / or relative azimuth angle between the corrected vehicle pose and the first road segment, a first perception probability that the vehicle will travel on the first road segment at a second moment is determined.

3. The positioning method according to claim 2, characterized in that, The step of correcting the vehicle's current pose based on the road segment perception data and the map data of each road segment in the navigation map includes: Based on the road segment perception data, the coordinates of the perception sampling points on each road segment in the vehicle coordinate system are determined, and based on the map data, the coordinates of the map sampling points on each road segment in the navigation map in the world coordinate system are determined. Based on the current pose of the vehicle, the coordinates of the sensing sampling points or the map sampling points are transformed to obtain the coordinates of the sensing sampling points and the map sampling points belonging to the same coordinate system. The vehicle's pose is corrected based on the coordinates of the sensing sampling points and map sampling points located on the same road features within the same coordinate system.

4. The positioning method according to claim 3, characterized in that, The step of determining the coordinates of the sensing sampling points on each road segment in the vehicle coordinate system based on the road segment sensing data includes: Based on the road segment perception data, the road boundary of the first road segment and the road area within the road boundary are determined; Obtain the coordinates of the boundary points on the road boundary in the vehicle coordinate system; A two-dimensional grid is established in the road area, and the coordinates of the sensing sampling points in each grid of the two-dimensional grid in the vehicle coordinate system are determined based on the coordinates of the boundary points.

5. The positioning method according to claim 3, characterized in that, The step of determining the coordinates of map sampling points in the world coordinate system for each road segment in the navigation map based on the map data includes: Based on the map data, the first road segment is determined in the navigation map, and the road width of the first road segment is determined based on the standard lane width and the number of lanes in the first road segment indicated by the map data. Multiple sampling centers are identified in the first road segment, and adjacent sampling centers have a preset sampling distance; Based on each of the sampling centers, multiple map sampling points are determined and the coordinates of the multiple map sampling points in the world coordinate system are obtained. The map sampling points are located on a circle with the sampling center as the center and a first length as the diameter, and the first length is determined according to the road width.

6. The positioning method according to claim 2, characterized in that, The at least one road segment includes a second road segment, and the perception probability includes a second perception probability that the vehicle will travel on the second road segment at a second moment; The road segment perception data includes at least one road segment diversion point perception data, wherein the road segment diversion point is located between the road segment where the vehicle is located at the first moment and the second road segment. The step of determining the probability that the vehicle will travel on each of the road segments at the second moment based on the road segment perception data and the vehicle's current pose includes: The location of the diversion point for each road segment is determined based on the diversion point sensing data. Based on the location of the diversion points of each road segment, the road extension direction of the second road segment, and the current pose of the vehicle, a second perception probability is determined that the vehicle will travel on the second road segment at the second moment.

7. The positioning method according to claim 6, characterized in that, The at least one road segment further includes a third road segment, the road segment diversion point being located between the road segment where the vehicle is located at the first moment and the third road segment, and the road segment diversion point being used to divert the vehicle from the road segment where it is located at the first moment to the second road segment and the third road segment; The determination of the second perception probability that the vehicle will travel on the second road segment at a second moment, based on the location of the diversion points of each road segment, the road extension direction of the second road segment, and the current pose of the vehicle, includes: Based on the location of the diversion points of each road segment, the current position of the vehicle, the road extension direction of the second road segment, and the road extension direction of the third road segment, the second perception probability that the vehicle will travel on the second road segment at the second moment is determined through a multi-round voting mechanism.

8. The positioning method according to claim 7, characterized in that, The second perception probability that the vehicle will travel on the second road segment at the second moment is determined through a multi-round voting mechanism based on the diversion points of each road segment, the current pose of the vehicle, the road extension direction of the second road segment, and the road extension direction of the third road segment, including: Based on the vehicle's current pose, the road extension direction of the second road segment, and the road extension direction of the third road segment, the second road segment is determined to be the candidate road segment corresponding to the first moment. Based on a preset distance and the effective sensing distance when the sensing data is acquired at the first moment, a first confidence value corresponding to the second road segment at the first moment is calculated; wherein, the preset distance is the distance between the center point of each road segment divergence point and the vehicle at the first moment; Based on the first confidence value and other confidence values ​​of the second road segment calculated at previous times, the total confidence value of the second road segment is determined; If the number of calculations exceeds a threshold and / or the total confidence value meets a first condition, a corresponding second perception probability is set for the second road segment and the third road segment; wherein... The second perception probability corresponding to the second road segment is greater than the second perception probability corresponding to the third road segment.

9. The positioning method according to claim 8, characterized in that, The total confidence value satisfies the first condition, including: The total confidence value corresponding to the second road segment is greater than the confidence threshold; and, The total confidence value corresponding to the second road segment is greater than the total confidence value of the third road segment calculated at the previous time points.

10. The positioning method according to claim 6, characterized in that, The step of predicting the target road segment that the vehicle will travel on at the second time moment based on the perceived probability of each road segment includes: In the navigation map, based on the relative distance and relative azimuth angle between the vehicle's current pose and each of the road segments, the probability of the vehicle traveling on each of the road segments at the second moment is determined; In the navigation map, based on the path connection relationship between the vehicle's current driving road segment and each of the road segments at the first moment, the probability of the vehicle transferring from the current driving road segment to each of the road segments at the second moment is determined; Based on the first perception probability, the second perception probability, the emission probability, and the transfer probability corresponding to each road segment, the target road segment in which the vehicle travels at the second time moment is predicted.

11. The positioning method according to claim 10, characterized in that, The step of predicting the target road segment in which the vehicle travels at the second time moment based on the first perception probability, the second perception probability, the emission probability, and the transfer probability corresponding to each of the road segments includes: Based on the first perception probability, the second perception probability, and the emission probability corresponding to each road segment, the predicted probability that the vehicle will travel on each road segment at the second moment is determined. Based on the predicted probability and the transition probability corresponding to each road segment, the target road segment in which the vehicle travels at the second time moment is predicted; Wherein, the predicted probability corresponding to the target road segment satisfies the prediction probability condition, and the transition probability corresponding to the target road segment satisfies the transition probability condition.

12. A positioning system, characterized in that, include: The perception data acquisition module is used to acquire the perception data of the vehicle at the first moment, and the perception data includes road segment perception data corresponding to at least one road segment. The perception probability determination module is used to determine the perception probability that the vehicle will travel on each of the road segments at the second moment based on the road segment perception data and the current pose of the vehicle. The target road segment determination module is used to predict the target road segment in which the vehicle travels at the second time moment based on the perception probability of each road segment. The navigation display module is used to display the vehicle traveling on the target road segment in the navigation map at a second moment.

13. An electronic device, characterized in that, include: At least one memory and at least one processor, the memory being coupled to the processor; the memory being used to store computer program code / instructions; when the computer program code / instructions are executed by the processor, causing the electronic device to perform the positioning method as described in any one of claims 1 to 11.

14. A vehicle, characterized in that, Including the electronic device as described in claim 13.

15. A readable storage medium, characterized in that, The readable storage medium stores instructions that, when executed on an electronic device, cause the electronic device to perform the positioning method as described in any one of claims 1 to 11.

16. A computer program product, characterized in that, include: Computer instructions, when executed on an electronic device, cause the electronic device to perform the positioning method as described in any one of claims 1 to 11.

Images