Method and apparatus for determining map road link, device, and product
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2025-02-07
- Publication Date
- 2026-08-13
Smart Images

Figure CN2025076148_13082026_PF_FP_ABST
Abstract
Description
METHOD AND APPARATUS FOR DETERMINING MAP ROAD LINK, DEVICE, AND PRODUCTFIELD
[0001] Embodiments of the present disclosure generally relate to vehicle, and in particular, to a method and apparatus for determining a map road link for a vehicle, a device, and a computer program product.BACKGROUND
[0002] Research on autonomous driving and driver assistance systems has attracted widespread attention from the industry recently. Autonomous driving technology can automatically perform vehicle driving operations and achieve safe driving in an unmanned driving state by sensing the surrounding environment in real time. The application of this technology can not only significantly improve road safety and reduce traffic accidents caused by human errors, but also optimize traffic smoothness and alleviate traffic congestion problems, thereby improving the overall efficiency of road use.
[0003] In the complex road environment of cities, road network is dense and complex, especially in elevated roads, intersections and busy streets of the cities, where traffic conditions are complex and changeable. In these environments, autonomous driving systems need to have higher perception accuracy and decision-making capabilities to ensure driving safety and handle with various traffic scenarios.SUMMARY
[0004] In general, embodiments of the present disclosure provide a scheme for determining a map road link for a vehicle.
[0005] In a first aspect according to some embodiments of the present disclosure, a method for determining a map road link for a vehicle is provided. The method comprises determining a plurality of candidate map road links based on a current position of the vehicle. The method further comprises determining a plurality of confidence levels of the plurality of candidate map road links based on a traffic sign color. The method further comprises determining the map road link for the vehicle based on the plurality of confidence levels. In this way, the accuracy of choosing the map road link can be improved, and the vehicle can drive on the correct road and adjust the driving behavior according to the road type, thereby improving the user experience.
[0006] In some embodiments of the first aspect, the traffic sign color is detected by a controlled-access detector, and the controlled-access detector is configured to identify and determine whether the vehicle is on a controlled-access road based on the plurality of candidate map road link elements. In this way, the determination of lane type can be simplified and the recognition efficiency is increased.
[0007] In some embodiments of the first aspect, determining the plurality of confidence levels of the plurality of candidate map road links based on the traffic sign color comprises: adjusting the confidence level of the candidate map road link based on the traffic sign color. In this way, dynamic adjustments may be introduced in the recognition of map road links to improve accuracy.
[0008] In some embodiments of the first aspect, adjusting the confidence level of the candidate map road link based on the traffic sign color comprises in response to the traffic sign color being a first color, increasing the confidence level of the candidate map road link, and in response to the traffic sign color being a second color, decreasing the confidence level of the candidate map road link. In this way, by increasing or decreasing the confidence level, the judgment on controlled roads and ordinary roads can be more accurate.
[0009] In some embodiments of the first aspect, the traffic sign color being the first color indicates that the vehicle is on a controlled-access road; and the traffic sign color being the second color indicates that the vehicle is on a general road.
[0010] In some embodiments of the first aspect, a plurality of candidate map road link elements comprise a vehicle heading, and determining the plurality of confidence levels of the candidate map road link based on the at least one of the plurality of candidate map road link elements comprising in response to the heading deviation of the vehicle being less than a predetermined angle threshold, increasing the confidence level of the candidate map road link; and in response to the heading deviation of the vehicle being higher than a predetermined angle threshold, decreasing the confidence level of the candidate map road link. Heading data directly may help real-time and dynamic navigation, improving the vehicle rapid response capabilities.
[0011] In some embodiments of the first aspect, a plurality of candidate map road link elements comprise a slope, and determining the plurality of confidence levels of the candidate map road link based on the at least one of the plurality of candidate map road link elements comprising in response to the slope being greater than a predetermined slope threshold, increasing the confidence level of the candidate map road link; and in response to the slope being less than the predetermined slope threshold, decreasing the confidence level of the candidate map road link. In this way, the accuracy of confidence is improved.
[0012] In some embodiments of the first aspect, a plurality of candidate map road link elements comprise a tunnel element, and determining the plurality of confidence levels of the candidate map road link based on the at least one of the plurality of candidate map road link elements comprises marking a tunnel attribute of the vehicle based on environmental parameters, wherein the environmental parameters at least comprises illumination, barometer, and global positioning system (GPS) signals, and in response to the tunnel attribute of the vehicle being marked, matching the vehicle with a tunnel lane. In this way, the failure probability in signal weakening scenarios is reduced and the continuity of navigation is ensured.
[0013] In some embodiments of the first aspect, determining the map road link for the vehicle based on the plurality of confidence levels comprises: determining the state measurement results of the candidate lanes based on the plurality of confidence levels of the plurality of candidate map road link elements; inputting the state measurement results of candidate lanes into a state machine; and determining the map road link for the vehicle by the state machine. In this way, multiple confidence inputs are integrated, and decisions are more accurate and robust.
[0014] In some embodiments of the first aspect, determining the map road link for the vehicle based on the plurality of confidence levels comprises adjusting driving behaviors of the vehicle based on the determined map road link. In this way, unnecessary driving risks are reduced by dynamically adjusting driving behavior.
[0015] In some embodiments of the first aspect, adjusting driving behaviors of the vehicle based on the determined map road link comprises in response to the determined map road link being a controlled-access link, increasing speed of the vehicle and reducing need for awareness of surroundings; in response to the determined map road link being a ground road, decreasing speed of the vehicle and increasing need for awareness of surroundings to monitor a dynamic environment; and in response to the determined map road link being a tunnel, determining an exit of the tunnel and turning on lights of the vehicle. In this way, driving behavior in different scenarios are optimized, improving driving safety, efficiency and user experience.
[0016] In some embodiments of the first aspect, adjusting driving guidance of the vehicle based on the determined map road link further comprises: in response to the determined map road link being a controlled-access link, providing on-ramp and off-ramp guidance based on the entrances and exits of the determined map road link; in response to the determined map road link being a ground road, providing guidance related to intersections, traffic lights, and dynamic traffic; and in response to the determined map road link being a tunnel, providing guidance related to ground identification and mark of the tunnel. In this way, customized guidance solutions for different lane types are provided, enabling vehicles to adapt to complex and changing traffic environments
[0017] In a second aspect according to some embodiments of the present disclosure, an apparatus for generating a quality score for an image is provided. The apparatus comprises a first determination module, configured to determine a plurality of candidate map road links based on a current position of the vehicle. The apparatus further comprises a second determination module, configured to determine a plurality of confidence levels of the plurality of candidate map road links based on a traffic sign color. In addition, the apparatus further comprises a third determination module, configured to determine the map road link for the vehicle based on the plurality of confidence levels.
[0018] In a third aspect according to some embodiments of the present disclosure, an electronic device is provided. The device comprises at least one processor and a memory coupled to the at least one processor. The memory has instructions stored therein which, when executed by the processor, cause the device to perform the method according to the first aspect of the present disclosure.
[0019] In a fourth aspect according to some embodiments of the present disclosure, a computer program product is provided. The computer program product is stored on a computer-readable medium and comprises machine-executable instructions. The machine-executable instructions, when executed by a processor, cause a machine to perform the method according to the first aspect of the present disclosure.
[0020] This Summary is provided to introduce a selection of concepts in a simplified form, which is further described below in the Detailed Description. This Summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter. Additional aspects, features, and / or advantages of examples will be set forth in part in the following description and, in part, will be apparent from the description, or may be learned by practice of the disclosure.BRIEF DESCRIPTION OF THE DRAWINGS
[0021] Embodiments of the present disclosure may be understood from the following Detailed Description when read with the accompanying figures. In accordance with the standard practice in the industry, various features are not drawn to scale. In fact, the dimensions of the various features may be arbitrarily increased or reduced for clarity of discussion. Some examples of the present disclosure are described with reference to the following figures.
[0022] FIG. 1 illustrates an example environment in which example embodiments of the present disclosure may be implemented;
[0023] FIG. 2 is a flow chart illustrating an example process of determining a map road link for a vehicle according to some embodiments of the present disclosure;
[0024] FIG. 3 is a schematic diagram illustrating an example of a determination process for choosing a candidate lane according to some embodiments of the present disclosure;
[0025] FIG. 4 is a schematic diagram illustrating an example of determining driving behavior based on the determination of map matching according to some embodiments of the present disclosure;
[0026] FIG. 5 is a schematic diagram illustrating an example of determining guidance based on the determination of map matching according to some embodiments of the present disclosure;
[0027] FIG. 6 is a block diagram illustrating an example apparatus for a map road link for a vehicle according to some embodiments of the present disclosure; and
[0028] FIG. 7 is a block diagram illustrating physical components (for example hardware) of a device with which aspects of the present disclosure may be practiced.
[0029] Throughout all the drawings, the same or similar reference numerals represent the same or similar elements. It is to be understood that the drawings are provided only for illustration and may not be drawn to scale.DETAILED DESCRIPTION
[0030] The principle of the present disclosure will now be described with reference to some embodiments. It is to be understood that these embodiments are described only for the purpose of illustration and to help those skilled in the art to understand and implement the present disclosure, without suggesting any limitation as to the scope of the disclosure. The disclosure described herein can be implemented in various manners other than the ones described below.
[0031] In the following description and claims, unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of the ordinary skills in the art to which this disclosure belongs.
[0032] References in the present disclosure to “one embodiment, ” “some embodiments, ” “an embodiment, ” and the like indicate that the embodiment described may include a particular feature, structure, or characteristic, but it is not necessary that every embodiment includes the particular feature, structure, or characteristic. Moreover, such phrases are not necessarily referring to the same embodiment. Further, when a particular feature, structure, or characteristic is described in connection with some embodiments, it is submitted that it is within the knowledge of one skilled in the art to affect such feature, structure, or characteristic in connection with other embodiments, whether or not explicitly described.
[0033] It shall be understood that although the terms “first” and “second” etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first element could be termed a second element, and similarly, a second element could be termed a first element, without departing from the scope of embodiments. As used herein, the term “and / or” includes any and all combinations of one or more of the listed terms.
[0034] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting to embodiments. As used herein, the singular forms “a, ” “an, ” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises, ” “comprising, ” “has, ” “having, ” “includes, ” and / or “including, ” when used herein, specify the presence of stated features, elements, and / or components, etc., but do not preclude the presence or addition of one or more other features, elements, components and / or combinations thereof.
[0035] As used herein, a value that “satisfies a threshold” may mean, depending on the context, that the value is greater than the threshold, greater than or equal to the threshold, equal to the threshold, less than or equal to the threshold, less than the threshold, etc.
[0036] With the development of urbanization, the road network is extremely dense and complex, especially in those megacities and this makes the vehicle localization and positioning challenging. With the elevated road in the city, which do not have altitude information in the map, the vehicle cannot identify if it is located on or under the elevated road, simply by matching the (latitude, longitude, heading) with the map. Quite often times in the map, the elevated road is digitalized couple meters next to the parallel map link. A method for identifying a correct map road link or link is needed.
[0037] Therefore, the embodiments of the present disclosure provide a scheme for determining a map road link for the vehicle. For example, the vehicle firstly determine a plurality of candidate map road links based on a current position of the vehicle. The vehicle may obtain data of candidate map road links based on its global positioning system (GPS) signals from a map application. The vehicle may then determine a plurality of confidence levels of the plurality of candidate map road links based on traffic sign colors of the plurality of candidate map road links.
[0038] The vehicle may then determine the map road link for the vehicle based on the plurality of confidence levels. For example, the vehicle may select a candidate map road link with the highest confidence level from the plurality of candidate map road links as a correct map road link. In this way, the accuracy of choosing the map road link can be improved, the vehicle may drive on the correct road and adjust the driving behavior and related information according to the road type, thereby improving the user experience.
[0039] FIG. 1 illustrates an example environment 100 in which example embodiments of the present disclosure may be implemented. As shown in FIG. 1, in some scenarios, such as in megacities, elevated roads are often parallel to or even overlap with ground roads, which increases the difficulty of navigation. The elevated road 104 extends above the ground road 102, but the vehicle’s navigation map lacks clear altitude markings, which may cause positioning problems. For example, the vehicle is located above the elevated road 104, but the navigation system of the vehicle may mistakenly identify it as ground road 102. It should be understood that in the present disclosure, elevated road, controlled-access highway, or controlled-access road can be the same type of road.
[0040] Relying solely on the vehicle’s GPS coordinates (such as latitude, longitude, and other information) is not sufficient to determine the specific road level where the vehicle is located. For example, in a scenario associated with embodiments of the present disclosure, it can be determined that the elevated road 104 is only a few meters away from the ground road 102. Without other information, the navigation system may not accurately determine the location of the vehicle, resulting in incorrect navigation suggestions. The speed limit or function activation of the vehicle’s automatic driving, assisted driving system or advanced driver assistance system (ADAS) is different when the vehicle is on or off the elevated road 104. For example, when the vehicle is driving on the elevated road 104, the vehicle’s navigation system may mistakenly determine that the current vehicle is driving on the ground road 102 due to inaccurate positioning information. The assisted driving system of the vehicle may then make incorrect actions based on the determination that the vehicle is driving on the ground road 102.
[0041] For example, in some scenarios, the automatic driving or assisted driving system of the vehicle may set the vehicle’s speed limit to the speed of the ground road 102 (such as 60 km / h) to limit the vehicle’s driving speed. On the elevated road 104, if the vehicle suddenly reduces its speed, the vehicles behind may not be able to react in time, causing a rear-end collision. In some scenarios, when driving on the elevated road, the vehicle, that does not enable the automatic driving or assisted driving mode based on the elevated road 104, may not turn on functions such as lane keeping and high-speed adaptive cruise, which increases the burden on the driver and increases the risk of operational errors.
[0042] For example, in some scenarios, when the vehicle is driving on the ground road 102, the navigation system of vehicle may mistakenly determine that the current vehicle is driving on the elevated road 104. Subsequently, the assisted driving system of the vehicle may make incorrect actions based on the determination that the vehicle is driving on the elevated road 104. For example, the automatic driving or assisted driving system of the vehicle may allow the vehicle to travel at a higher speed (such as 100 km / h) , while the actual environment may not be suitable for high-speed driving. This leads to collision accidents due to the high-speed driving of the vehicle in congested or complex ground traffic environments.
[0043] In some scenarios, the automatic driving or assisted driving mode (such as automatic lane change, ramp identification) designed based on the elevated road 104 is activated on the ground road 102, and the automatic driving or assisted driving system of the vehicle may misidentify the ground intersection or traffic light. Therefore, this may cause the vehicle, that enables the automatic driving or assisted driving mode based on the elevated road 104, to fail to correctly identify the traffic light or pedestrian.
[0044] In some scenarios, due to the wrong determination of the elevated road 104 and the ground road 102, the navigation system of the vehicle may plan an incorrect path, such as guiding the vehicle to enter the wrong ramp, turn to the ground road, suddenly stop in a high-speed driving environment, or repeatedly go up the elevated road. In some scenarios, due to the inconsistent determination of the navigation and assisted driving systems, the driver may be confused, which may cause the driver to fail to take over the vehicle in time, thereby exacerbating the danger.
[0045] According to an embodiment of the present disclosure, the automatic driving or assisted driving system of the vehicle may identify the color of the traffic sign (such as the traffic sign 106 and the traffic sign 108 in the FIG. 1) by the on-board camera to determine the type of road the vehicle is currently on. For example, the color of the traffic sign 108 may correspond to a fast-travel road such as an elevated road 104, highway or an elevated bridge. These roads are usually closed, with high speeds and relatively low traffic complexity. In some embodiments, the color of the traffic sign 108 may be a first color, such as, but not limited to, green.
[0046] When the vehicle’s automatic driving or assisted driving system determines that the vehicle is traveling on the elevated road 104 based on the color of the traffic sign 108, it can switch to a high-speed driving mode, optimize the vehicle’s speed and path planning, and the vehicle may pass through the fast section more efficiently.
[0047] In some embodiments, the color of the traffic sign 106 may be a second color (such as, but not limited to, blue) . The second color corresponds to the ground road 102 or an ordinary urban road. On these roads, the speed of the vehicle is low, and more dynamic elements such as pedestrians and traffic lights need to be continuously identified. The vehicle’s automatic driving or assisted driving system may determine that the vehicle is traveling on the ground road 102 based on the color of the traffic sign 106. The vehicle may enable a more cautious driving strategy, such as slowing down, monitoring pedestrians and traffic lights more frequently, and adapting to complex traffic conditions. Through this real-time adjustment, the vehicle may implement optimal driving performance on different types of roads, thereby improving driving safety and efficiency.
[0048] FIG. 2 is a flow chart illustrating an example process 200 of determining a map road link for a vehicle according to some embodiments of the present disclosure. The process 200 may be implemented by a controller of a vehicle. As shown in Fig. 2, at block 202, a plurality of candidate map road links may be determined based on the current position of the vehicle.
[0049] For example, in some embodiments, the current position of the vehicle may be determined by GPS, IMU (inertial measurement unit) , laser radar (LIDAR) or other sensors. These sensors may provide information related to the position and posture of the vehicle in three-dimensional space. The position of the vehicle may be then mapped as high-precision map data. The high-precision map may include information such as the geometry, position, markings, traffic signs, etc. of the lane. The current position of the vehicle may be compared with this information to determine the possible range of lanes that the vehicle may be in. All lanes around the current position of the vehicle may be determined as candidate lanes.
[0050] At block 204, a plurality of confidence levels of the plurality of candidate map road links may be determined based on traffic sign color. In some embodiments, the controller of the vehicle may identify traffic signs on the road by image recognition (such as, including but not limited to, computer vision and deep learning) . In some embodiments, these signs may include speed limit signs, no parking signs, lane change instructions, etc.
[0051] The color and shape of the sign provide important information related to the lane attributes. In some embodiments, for example, in some regions or environments, elevated roads, highways, or expressways usually have green traffic signs. In some regions or environments, the road, except for elevated roads, highways, or expressways, usually have blue traffic signs.
[0052] In some further embodiments, from the camera detection, the information that dominant background color of the traffic signs may be obtained. This characteristic may be used to identify if the vehicle is driving on or under the elevated road.
[0053] At block 206, the map road link for the vehicle may be determined based on the plurality of confidence levels. The confidence of each candidate lane may be synthesized based on its position, the color of the traffic sign, and other factors, etc. Different factors may be given different weights based on the needs of the vehicle.
[0054] In some embodiments, for example, the weight of the color of the traffic sign may be more important than the impact of a map-matched position, or vice versa. After synthesizing the confidence levels of multiple candidate lanes, the controller of the vehicle may select the lane with the highest confidence as the target driving lane for the vehicle.
[0055] FIG. 3 is a schematic diagram illustrating an example 300 of a determination process for choosing a candidate lane according to some embodiments of the present disclosure. At block 302, a link matcher of a vehicle may be initiated for execution steps. The link matcher may combine vehicle sensor data, map data, and traffic environment to determine current position or link of the vehicle. In some embodiments, the link matcher may initialize the matching process and prepare required input data including the current location information of the vehicle (such as GPS coordinates, inertial sensor data, boundary line information, etc. ) and environment data (including road geometry, traffic signs, lane information, etc. ) .
[0056] At block 304, the controller of the vehicle may receive and identify those input data. For example, in some embodiments, the controller of the vehicle may pre-process those input data, such as integrating those input data into a unified input format for use in subsequent steps. This step may provide sufficient data support so that candidate lane generation and subsequent confidence calculations may be analyzed based on complete environmental information.
[0057] At block 306, the controller of the vehicle may use GetLinksAroundPose function to extract all possible lane links around the current position vehicle based on map data. In some embodiments, these lane links may be determined by spatial range, such as lanes within a certain radius centered on the vehicle. For example, in some embodiments, the controller of the vehicle may perform spatial matching based on GPS coordinates and lane geometry information in the map to screen out all lanes that intersect or are close to the position of the vehicle. This step may ensure that these candidate lanes are highly reliable to avoid omissions or incorrect screening.
[0058] At block 308, the controller of the vehicle may determine the generated lane links (link_candidates) as candidate lanes. In some embodiments, these candidate lanes are lanes that the vehicle may be traveling or will enter, and include multiple types, such as the current lane, adjacent lanes, etc. According to the embodiments of this disclosure, the selecting of these lanes requires a combination of map geometry information and vehicle dynamic information, such as speed and direction of the vehicle. According to the embodiments of this disclosure, the controller of the vehicle may further optimize the candidate set based on lane attributes, such as excluding lanes in the opposite direction of the vehicle's driving, to improve matching efficiency.
[0059] At block 310, the controller of the vehicle may construct a tunnel detector to determine whether the vehicle is in a tunnel. In some embodiments, the input data to the tunnel detector may include vehicle position, IMU data (such as acceleration and gyroscope) , GPS signal quality, and the location and length of tunnels marked in the map.
[0060] At block 312, in some embodiments, the tunnel detector of the vehicle may be executed to confirm whether the vehicle is in a tunnel. For example, in some embodiments, the tunnel detector of the vehicle may make preliminary judgment by comparing the current position of the vehicle with the range of the tunnel in the map. In some further embodiments, the tunnel detector of the vehicle may combine the quality of the GPS signals (such as whether it is lost or weakened) and the changes in the IMU data (such as continuous linear acceleration or constant heading angle) for further confirmation.
[0061] At block 316, in some embodiments, the tunnel detector of the vehicle may convert the detection results into a probability value, i.e. "likelihood in tunnel” . The numerical range of this confidence level may be between 0 and 1, wherein 1 means that the vehicle is completely confirmed to be in the tunnel and 0 means that the vehicle is not in the tunnel. The higher the confidence level is, the higher the credibility of the candidate lanes related to the tunnel.
[0062] At block 318, in some embodiments, a controlled-access detector of the vehicle may be constructed to confirm that whether the vehicle is on a controlled-access road. According to embodiments of the disclosure, the input data to the control access detector may include traffic sign data (such as, color, shape, size of traffic signs) , location of the vehicle, controlled-access information marked by the maps.
[0063] At block 320, the controlled-access detector of the vehicle may be executed to confirm whether the vehicle is on a controlled-access road by identify connected vehicles (CV) -based traffic signals. For example, in some embodiments, when the controlled-access detector of the vehicle detects that the color of traffic sign is a first color, the controlled-access detector may determine current lanes that the vehicle is driving is a controlled-access road.
[0064] In some further embodiments, when the controlled-access detector of the vehicle detects that the color of traffic sign is a second color, the controlled-access detector may determine current lanes that the vehicle is driving is a ground road. In some further embodiments, the first color may be green, and the second color may be blue. For example, the confidence level of the candidate map road link may be increased in response to the traffic sign color being a first color, and the confidence level of the candidate map road link may be decreased in response to the traffic sign color being a second color.
[0065] In the context of this disclosure, a map road link may be a linear spatial object of a map that defines the geometry and connectivity of a road network between two points in the network. In some embodiments, for example, a map road link may be an elevated road, a ground road, a single carriageway, a dual carriageway, a slip road, a roundabout, and indicative trajectory across a traffic square, etc. on the map.
[0066] It is noted that The traffic sign colors of road listed in this disclosure are merely exemplary. In other areas or locations, the traffic sign colors of road may be other colors, and this disclosure does not impose any limitation on this.
[0067] At block 322, in some embodiments, the controlled-access detector of the vehicle may convert the detection results into a probability value, i.e. "likelihood_in_ca” . The numerical range of this confidence level may be between 0 and 1, wherein 1 means that the vehicle is completely confirmed to be in the controlled-access road and 0 means that the vehicle is not in the controlled-access road. The higher the confidence level is, the higher the credibility of the candidate lanes related to the controlled-access road.
[0068] At block 324, in some embodiments, the controller of the vehicle may combine all the results into a unified input data format (MatchingInput) , which may include complete information related to the candidate lanes (such as lane geometry, position, tunnel confidence, controlled area confidence, and other sensor data etc. ) . The matching process may be performed by a link matcher of the vehicle.
[0069] At block 326, in some embodiments, the controller of the vehicle may determine whether all the candidate link is checked to ensure that all candidate paths are inputted into the matching process to avoid omissions. At block 328, in some embodiments, if there are still unchecked candidate links or lanes, the controller of the vehicle may process this unchecked link.
[0070] At block 330, in some embodiments, the controller of the vehicle may determine emission probability of the hidden markov model (HMM) for the candidate link. For example, the matching degree between measurement (such as GPS position) of the vehicle and the candidate road link may be determined. A higher emission probability indicates that the vehicle is more likely to be located on a target candidate road link.
[0071] At block 332, in some embodiments, the controller of the vehicle may determine whether the vehicle’s current driving direction is consistent with the direction of the candidate road link with a heading influence. For example, the controller of the vehicle may obtain the current driving direction from vehicle sensors (such as track points provided by an inertial navigation system or GPS) . Then the controller of the vehicle may determine an angle between the vehicle direction and the road direction and convert it into a probability value. In some embodiments, when the angle is less than a predetermined threshold, the matching probability is higher. In some embodiments, when the angle is higher than a predetermined threshold, the matching probability is lower.
[0072] At block 334, in some embodiments, the controller of the vehicle may determine the influence of matching between the slope of the candidate road link and the current driving slope of the vehicle with the slope influence. For example, the slope of the vehicle may be measured by sensors (such as accelerometers) to reflect whether the vehicle is currently uphill, downhill, or level. Then the measured slope of the vehicle may be compared with the slope of the candidate road link. In some embodiments, if the measured slope or difference between both is greater than a predetermined slope threshold, the confidence level of the candidate road link may be increased. In some further embodiments, if the slope or difference between both being less than the predetermined slope threshold, the confidence level of the candidate road link may be decreased.
[0073] At block 336, in some embodiments, the controller of the vehicle may determine whether the candidate road link is in a tunnel with a tunnel influence. For example, the controller of the vehicle may mark the candidate road link as a tunnel when the outside illumination is dark, barometer is high, and the GPS signals of the vehicle are interrupted.
[0074] At block 338, in some embodiments, the controller of the vehicle may determine a controlled-access influence with the controlled-access detector. For example, in some embodiments, when the controlled-access detector detects that the traffic sign color is a first color, the confidence level of the candidate map road link may be increased. In some further embodiments, when the traffic sign color is a second color, the confidence level of the candidate map road link may be decreased.
[0075] At block 340, in some embodiments, all the above influencing elements (such as emission probability, direction influence, slope influence, tunnel influence, controlled-access influence) may be considered to calculate the comprehensive probability of each candidate road link. At block 344, the controller of the vehicle may determine the transition probability between the current candidate road link and each previous the candidate road link. In some embodiments, the transition probability may be influenced by elements such as road topology, turning angle, diving distance, etc. At block 346, the current candidate road link and its comprehensive probability and transition probability may be added to the state set for later calculation.
[0076] At block 342, in some embodiments, when all the candidate road links are checked, the controller of the vehicle may determine the optimal path based on the comprehensive probability and state transition probability. In some further embodiments, at block 348, a list of candidate states may be generated. These results will be passed to the navigation module of the vehicle or used to generate map matching results. At block 350, the match process is ended. In this way, the current link matcher of the vehicle may find ambiguity in all possible candidates, the CV signals will add this factor to the state machine (viterbi) and based on the detected color, the correct link candidate will quickly dominate and be selected.
[0077] FIG. 4 is a schematic diagram illustrating an example 400 of determining driving behavior based on the determination of map matching according to some embodiments of the present disclosure. At block 402, the process may be started. At block 404, the vehicle may obtain the candidate map links or lanes around the vehicle.
[0078] At block 406, the vehicle may determine a type of the map road link based on the method disclosed in the FIG. 3, which will not be repeated here. At block 408, the vehicle may determine that the vehicle is driving on a controlled-access link, and the controlled-access link requires the vehicle to drive at a high speed with large spacing between vehicles.
[0079] In some embodiments, the controller of the vehicle may increase the target speed of the vehicle, but keep it within the speed limit prescribed by regulation. In some further embodiments, the controller of the vehicle may limit unnecessary lane changes and comply with the rules of highways. In some other embodiments, the controller of the vehicle may also prioritize staying in the current lane. In some other embodiments, the controller of the vehicle may reduce need for awareness of surroundings.
[0080] At block 410, the vehicle may determine that the vehicle is driving on a ground link. The ground link allows slow speeds and frequent lane changes. In some embodiments, the controller of the vehicle may allow more flexible speed changes to adapt to different road conditions (such as traffic lights, obstacles in front of the vehicle) . In some further embodiments, the controller of the vehicle may adjust the safe distance between the vehicle and the vehicle in front in dense traffic. In some other embodiments, the controller of the vehicle may increase need for awareness of surroundings.
[0081] At block 412, the vehicle may determine that the vehicle is driving on a tunnel lane. The tunnel land usually prohibits lane changes or parking. In some embodiments, the controller of the vehicle may reduce the target speed and comply with tunnel speed limits. In some embodiments, the controller of the vehicle may strictly limit lane changes and stay in the current lane. In some further embodiments, the controller of the vehicle may use inertial navigation or CV signals to supplement GPS data to ensure high-precision vehicle positioning. In some other embodiments, the controller of the vehicle may turn on the lights during the tunnel lane.
[0082] FIG. 5 is a schematic diagram illustrating an example 500 of determining guidance based on the determination of map matching according to some embodiments of the present disclosure. At block 502, the process may be started. At block 504, the vehicle may obtain the candidate map links or lanes around the vehicle.
[0083] At block 506, the vehicle may determine a type of the map road link based on the method disclosed in the FIG. 3, which will not be repeated here. At block 508, the vehicle may determine that the vehicle is driving on a controlled-access link, and the controlled-access link requires the vehicle to drive at a high speed with large spacing between vehicles.
[0084] In some embodiments, the controller of the vehicle may inform the the vehicle to stay in the current lane, switch lanes in advance to enter a designated exit, or warn the driver not to enter a restricted lane. At the same time, the controller of the vehicle may monitor the real-time status of the controlled lane (such as closure, congestion) to provide guidance for dynamic adjustments (such as, on-ramp and off-ramp guidance) .
[0085] At block 510, the vehicle may determine that the vehicle is driving on a ground link. In some embodiments, the vehicle may guide vehicles to drive in a specific direction at complex intersections, remind vehicles to comply with speed limits or avoid construction sections. In some embodiments, the vehicle may provide guidance related to intersections, traffic lights, and dynamic traffic. In some further embodiments, the vehicle may also provide turn reminders, road priority instructions, etc., to help drivers drive more safely.
[0086] At block 512, the vehicle may determine that the vehicle is driving on a tunnel lane. In some embodiments, the controller of the vehicle may provide corresponding speed limit reminders, safe distance warnings and the exit location of the tunnel (such as ground identification and mark of the tunnel) . In this way, the controller of the vehicle may accurately identify lane types and provide customized navigation guidance for different scenarios, improving driving safety and efficiency.
[0087] Fig. 6 is a block diagram illustrating an example apparatus 600 for a map road link for a vehicle according to some embodiments of the present disclosure. The apparatus 600 comprises a first determination module 602, a second determination module 604, and a third determination module 606. In some embodiments, the first determination module 602 is configured to determine a plurality of candidate map road links based on a current position of the vehicle. The second determination module 604 is configured to determine a plurality of confidence levels of the plurality of candidate map road links based on a traffic sign color. The third determination module 604 is configured to determine the map road link for the vehicle based on the plurality of confidence levels.
[0088] In some embodiments, the traffic sign color is detected by a controlled-access detector, and the controlled-access detector is configured to identify and determine whether the vehicle is on a controlled-access road based on a plurality of candidate map road link elements.
[0089] In some further embodiments, the second determination module 604 comprises an adjusting module configured to adjust the confidence level of the candidate map road link based on the traffic sign color. In some further embodiments, the adjusting module is further configured to increase the confidence level of the candidate map road link in response to the traffic sign color being a first color, and decrease the confidence level of the candidate map road link in response to the traffic sign color being a second color.
[0090] In some further embodiments, the traffic sign color being the first color indicates that the vehicle is on a controlled-access road, and the traffic sign color being the second color indicates that the vehicle is on a general road.
[0091] In some embodiments, the second determination module 604 comprises an adjusting module configured to adjust the confidence level of the candidate map road link based on the vehicle heading. The adjusting module is further configured to increase the confidence level of the candidate map road link in response to the heading deviation of the vehicle being less than a predetermined angle threshold. The adjusting module is further configured to decrease the confidence level of the candidate map road link in response to the heading deviation of the vehicle being higher than a predetermined angle threshold.
[0092] In some further embodiments, the second determination module 604 comprises an adjusting module configured to adjust the confidence level of the candidate map road link based on the slope. The adjusting module is further configured to increase the confidence level of the candidate map road link in response to the slope being greater than a predetermined slope threshold. The adjusting module is further configured to decreasing the confidence level of the candidate map road link in response to the slope being less than the predetermined slope threshold.
[0093] In some further embodiments, the second determination module 604 comprises an adjusting module configured to adjust the confidence level of the candidate map road link based on the tunnel element. The adjusting module is further configured to mark a tunnel attribute of the vehicle based on environmental parameters, and the environmental parameters at least comprises illumination, barometer, and global positioning system (GPS) signals. In some further embodiments, when the tunnel attribute of the vehicle is marked, the vehicle with a tunnel lane may be matched.
[0094] In some further embodiments, the apparatus 600 may comprise: a determination module configured to determine the state measurement results of the candidate lanes based on the plurality of confidence levels of the plurality of candidate map road link elements; an inputting module configured to input the state measurement results of candidate lanes into a state machine; and a determination module configured to determine the map road link for the vehicle by the state machine.
[0095] In some further embodiments, the apparatus 600 may comprise: an adjusting module configured to adjust driving behaviors of the vehicle based on the determined map road link. In some further embodiments, the apparatus 600 may comprise: an adjusting module configured to increase speed of the vehicle and reducing need for awareness of surroundings in response to the determined map road link being a controlled-access link. In some embodiments, the adjusting module is configured to decrease speed of the vehicle and increase need for awareness of surroundings to monitor a dynamic environment in response to the determined map road link being a ground road. In some embodiments, the adjusting module is configured to determine an exit of the tunnel and turning on lights of the vehicle in response to the determined map road link being a tunnel.
[0096] In some further embodiments, the apparatus 600 may comprise: an adjusting module configured to adjusting driving guidance of the vehicle based on the determined map road link. In some embodiments, the adjusting module is configured to provide on-ramp and off-ramp guidance based on the entrances and exits of the determined map road link in response to the determined map road link being a controlled-access link. In some embodiments, the adjusting module is configured to providing guidance related to intersections, traffic lights, and dynamic traffic in response to the determined map road link being a ground road. In some embodiments, the adjusting module is configured to providing guidance related to ground identification and mark of the tunnel in response to the determined map road link being a tunnel.
[0097] FIG. 7 is a block diagram illustrating physical components (for example hardware) of a device 700 with which aspects of the present disclosure may be practiced. The device 700 may be the device or apparatus described in the embodiments of the present disclosure, such as the computing device 72 in Fig. 1. As shown in Fig. 7, the device 700 includes a processor 701, which may be configured to execute various appropriate actions and processing to perform the methods (e.g., the method 200) of the present disclosure. The processor 701 is implemented in hardware, firmware, or a combination of hardware and software. In addition, although not shown in Fig. 7, the device 700 may also include a co-processor.
[0098] The processor 701 may execute actions and processing to perform the methods of the present disclosure according to computer program instructions. The computer program instructions for performing the operations of the present disclosure may be assembly instructions, Instruction Set Architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, status setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages as well as conventional procedural programming languages. In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA) , or a programmable logic array (PLA) , is customized by utilizing status information of the computer-readable program instructions. The electronic circuit may execute the computer-readable program instructions so as to implement various aspects of the present disclosure.
[0099] These computer-readable program instructions may be provided to a processing unit of a general-purpose computer, a special-purpose computer, or a further programmable data processing apparatus, thereby producing a machine, such that these instructions, when executed by the processing unit of the computer or the further programmable data processing apparatus, produce means for implementing functions / actions specified in one or more blocks in the flow charts and / or block diagrams. These computer-readable program instructions may also be stored in a non-transitory computer-readable storage medium, and these instructions cause a computer, a programmable data processing apparatus, and / or other devices to operate in a specific manner; and thus the computer-readable medium having instructions stored includes an article of manufacture that includes instructions that implement various aspects of the functions / actions specified in one or more blocks in the flow charts and / or block diagrams.
[0100] The computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatuses, or other devices, such that a series of operating steps may be executed on the computer, the other programmable data processing apparatuses, or the other devices to produce a computer-implemented process, such that the instructions executed on the computer, the other programmable data processing apparatuses, or the other devices may implement the functions / actions specified in one or more blocks in the flow charts and / or block diagrams.
[0101] The computer program instructions may be stored in a Read-Only Memory (ROM) 702 or be loaded onto a Random Access Memory (RAM) 703 from a storage unit 708, for example. The processor 701, the ROM 702, and the RAM 703 are connected to each other via bus 704. An input / output (I / O) interface 705 is also connected to bus 704. The various methods or processes described above may be performed by the processor 701.
[0102] A plurality of components in device 700 are connected to the I / O interface 705, including: an input unit 706, such as a keyboard and a mouse; an output unit 707, such as various types of displays and speakers; the storage unit 708, such as a magnetic disk and an optical disc; and a communication unit 709, such as a network card, a modem, and a wireless communication transceiver. The communication unit 709 allows the device 700 to exchange information / data with other devices via a computer network, such as the Internet, and / or various telecommunication networks.
[0103] In some embodiments, the methods and processes described above may be implemented as a computer program product. The computer program product may include a computer-readable storage medium on which computer-readable program instructions for performing various aspects of the present disclosure are loaded.
[0104] The computer-readable storage medium may be a tangible device that may retain and store instructions used by an instruction-executing device. For example, the computer-readable storage medium may be, but is not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the above. More specific examples (a non-exhaustive list) of the computer-readable storage medium include: a portable computer disk, a hard disk, a random access memory (RAM) , a read-only memory (ROM) , an erasable programmable read-only memory (EPROM or flash memory) , a static random access memory (SRAM) , a portable compact disc read-only memory (CD-ROM) , a digital versatile disc (DVD) , a memory stick, a floppy disk, a mechanical coding device, for example, a punch card or a raised structure in a groove with instructions stored thereon, and any suitable combination of the foregoing. The computer-readable storage medium used herein is not to be interpreted as transient signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber-optic cables) , or electrical signals transmitted through electrical wires.
[0105] The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to various computing / processing devices, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives computer-readable program instructions from a network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in each computing / processing device.
[0106] The flow charts and block diagrams in the drawings illustrate the architectures, functions, and operations of possible implementations of the devices, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flow charts or block diagrams may represent a module, a program segment, or part of an instruction, and the module, program segment, or part of an instruction includes one or more executable instructions for implementing specified logical functions. In some alternative implementations, functions marked in the blocks may also occur in an order different from those marked in the accompanying drawings. For example, two consecutive blocks may in fact be executed substantially concurrently, and sometimes they may also be executed in a reverse order, depending on the functions involved. It should be further noted that each block in the block diagrams and / or flow charts, as well as a combination of blocks in the block diagrams and / or flow charts, may be implemented using a dedicated hardware-based system that executes specified functions or actions, or using a combination of special hardware and computer instructions.
[0107] Various embodiments of the present disclosure have been described above. The foregoing description is illustrative rather than exhaustive, and is not limited to the disclosed various embodiments. Numerous modifications and alterations are apparent to persons of ordinary skill in the art without departing from the scope and spirit of the illustrated embodiments. The selection of terms as used herein is intended to best explain the principles and practical applications of the various embodiments or the technical improvements to technologies on the market, or to enable other persons of ordinary skill in the art to understand the various embodiments disclosed herein.
Claims
1.A method (200) for determining a map road link for a vehicle, comprising:determining (202) a plurality of candidate map road links based on a current position of the vehicle;determining (204) a plurality of confidence levels of the plurality of candidate map road links based on a traffic sign color; anddetermining (206) the map road link for the vehicle based on the plurality of confidence levels.2.The method (200) of claim 1, the traffic sign color is detected by a controlled-access detector, and the controlled-access detector is configured to identify and determine whether the vehicle is on a controlled-access road based on a plurality of candidate map road link elements.3.The method (200) of claim 1, wherein determining the plurality of confidence levels of the plurality of candidate map road links based on the traffic sign color comprises:adjusting the confidence level of the candidate map road link based on the traffic sign color.4.The method (200) of claim 1, wherein adjusting the confidence level of the candidate map road link based on the traffic sign color comprises:in response to the traffic sign color being a first color, increasing the confidence level of the candidate map road link; andin response to the traffic sign color being a second color, decreasing the confidence level of the candidate map road link.5.The method (200) of claim 4, wherein the traffic sign color being the first color indicates that the vehicle is on a controlled-access road; andwherein the traffic sign color being the second color indicates that the vehicle is on a general road.6.The method (200) of claim 1, wherein a plurality of candidate map road link elements comprise a vehicle heading, and determining the plurality of confidence levels of the candidate map road link based on the at least one of the plurality of candidate map road link elements comprises:in response to the heading deviation of the vehicle being less than a predetermined angle threshold, increasing the confidence level of the candidate map road link; andin response to the heading deviation of the vehicle being higher than a predetermined angle threshold, decreasing the confidence level of the candidate map road link.7.The method (200) of claim 1, wherein a plurality of candidate map road link elements comprise a slope, and determining the plurality of confidence levels of the candidate map road link based on the at least one of the plurality of candidate map road link elements comprises:in response to the slope being greater than a predetermined slope threshold, increasing the confidence level of the candidate map road link; andin response to the slope being less than the predetermined slope threshold, decreasing the confidence level of the candidate map road link.8.The method (200) of claim 1, wherein a plurality of candidate map road link elements comprise a tunnel element, and determining the plurality of confidence levels of the candidate map road link based on the at least one of the plurality of candidate map road link elements comprises:marking a tunnel attribute of the vehicle based on environmental parameters, wherein the environmental parameters at least comprises illumination, barometer, and global positioning system (GPS) signals; andin response to the tunnel attribute of the vehicle being marked, matching the vehicle with a tunnel lane.9.The method (200) of claim 1, wherein determining the map road link for the vehicle based on the plurality of confidence levels comprises:determining the state measurement results of the candidate lanes based on the plurality of confidence levels of the plurality of candidate map road link elements;inputting the state measurement results of candidate lanes into a state machine; anddetermining the map road link for the vehicle by the state machine.10.The method (200) of claim 1, wherein determining the map road link for the vehicle based on the plurality of confidence levels comprises:adjusting driving behaviors of the vehicle based on the determined map road link.11.The method (200) of claim 10, wherein adjusting driving behaviors of the vehicle based on the determined map road link comprises:in response to the determined map road link being a controlled-access link, increasing speed of the vehicle and reducing need for awareness of surroundings;in response to the determined map road link being a ground road, decreasing speed of the vehicle and increasing need for awareness of surroundings to monitor a dynamic environment; andin response to the determined map road link being a tunnel, determining an exit of the tunnel and turning on lights of the vehicle.12.The method (200) of claim 10, wherein adjusting driving guidance of the vehicle based on the determined map road link further comprises:in response to the determined map road link being a controlled-access link, providing on-ramp and off-ramp guidance based on the entrances and exits of the determined map road link;in response to the determined map road link being a ground road, providing guidance related to intersections, traffic lights, and dynamic traffic; andin response to the determined map road link being a tunnel, providing guidance related to ground identification and mark of the tunnel.13.An apparatus (600) for determining a map road link for a vehicle, comprising:a first determination module (602) , configured to determine a plurality of candidate map road links based on a current position of the vehicle;a second determination module (604) , configured to determine a plurality of confidence levels of the plurality of candidate map road links based on traffic sign color; anda third determination module (606) , configured to determine the map road link for the vehicle based on the plurality of confidence levels.14.An electric device (700) comprising:one or more processors (701) ; anda memory (702) storing computer-executable instructions, the computer-executable instructions when executed by the one or more processors (701) , cause the device (700) to implement the method (200) according to any of claims 1-12.15.A computer program product tangibly stored on a computer-readable medium and comprising machine-executable instructions, wherein the machine-executable instructions, when executed, cause a machine to perform the method (200) according to any of claims 1-12.