Method and system for determining driver assistance data
By combining vehicle sensor data with map data, and comparing vehicle attitude and speed, the problem of inaccurate road shape and traffic condition recognition in existing driver assistance systems is solved, and more reliable driver assistance data is provided.
Patent Information
- Application Number
- CN202010476931.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Priority Date
- 2019-05-29
- Filing Date
- 2020-05-29
- Publication Date
- 2024-11-01
- Estimated Expiration
- 2040-05-29
AI Technical Summary
Existing driver assistance systems and methods lack reliability in recognizing road shapes and traffic conditions ahead, resulting in insufficient recognition accuracy.
By combining sensor data and map data from the vehicle, comparing the vehicle's attitude and speed, driving assistance data is determined, including identifying road patterns and traffic conditions. The reliability of the map data is adjusted through confidence values to provide more reliable driving assistance information.
It improves the accuracy of recognizing road conditions and traffic situations ahead, ensuring the reliability and effectiveness of the driver assistance system and avoiding misoperation under low confidence conditions.
Smart Images

Figure CN112009484B_ABST
Abstract
Description
[0001] CROSS-REFERENCE TO RELATED APPLICATIONS
[0002] This patent application claims priority to European Patent Application No. EP19177408.2 filed on May 29, 2019, entitled “METHODAND SYSTEM FOR DETERMINING DRIVING ASSISTING DATA”, which is hereby assigned to the assignee and is expressly incorporated herein by reference. Technical Field
[0003] The present invention relates to a method and a vehicle control system for determining driver assistance data about a vehicle based on sensor data and map data about other vehicles. Background Art
[0004] Today, many vehicles have various driving support functions in the form of advanced driver assistance systems (ADAS) features. Moreover, many of these features form the basis for current and future autonomous driving (AD) features. Examples of ADAS features or functions include lane departure warning systems, lane centering, lane keeping assistance, pilot assistance, lane change assistance, parking sensors, pedestrian protection systems, blind spot monitors, adaptive cruise control (ACC), anti-lock braking systems, etc. These features utilize one or more warnings or automated actions in response to certain scenarios to supplement the traditional driving controls of the vehicle.
[0005] An important requirement for vehicles with ADAS or AD systems or features is that they can reliably identify the road shape and / or traffic conditions ahead. To try to achieve this, currently known methods and systems include forward-looking sensors that directly sense the road shape and a map containing the road shape (often referred to as an HD map) and a module that estimates the position of the vehicle in the map. However, problems still exist with currently known methods and systems. For example, existing methods and systems lack the accuracy to reliably identify the road shape and / or traffic conditions.
[0006] Therefore, there is a need for methods and systems that can more reliably identify the road shape and / or traffic conditions ahead than currently known systems and methods. Summary of the invention
[0007] It is an object of the present disclosure to provide methods, vehicle control systems, and non-transitory computer readable storage media that endeavor to mitigate, alleviate, or eliminate one or more of the above-mentioned deficiencies in the prior art and the disadvantages of currently known systems and methods.
[0008] This object is achieved by a method, a vehicle control system and a non-transitory computer-readable storage medium as defined in the appended claims.The term exemplary in this context shall be understood as serving as an example, instance or illustration.
[0009] According to a first aspect of the present disclosure, a method for determining driving assistance data about a vehicle based on sensor data and map data about other vehicles is provided. The method includes: acquiring sensor data from a sensor system of a first vehicle, the sensor data including the attitude and speed of a second vehicle located in the surroundings of the first vehicle; and acquiring map data including the road shape of the surroundings of the first vehicle. The method further includes comparing the attitude and speed of the second vehicle with the map data and determining driving assistance data about a third vehicle based on the comparison.
[0010] The vehicle in this context may be any type of suitable road vehicle, such as, for example, a car, bus, truck, etc., but may also, at least with respect to the second vehicle, be other road users, such as motorcyclists, cyclists, pedestrians, etc.
[0011] The pose of the vehicle in this context will be interpreted as a geographic location (or map position) together with the orientation (heading) of the vehicle. In other words, the pose can be understood as a set (two or more) of the coordinates of the vehicle in the overall coordinate system and the direction of the vehicle in the coordinate system. The surrounding environment of the vehicle can be understood as the general area around the vehicle (i.e., within the sensor range of the vehicle) where objects (such as other vehicles, landmarks, obstacles, roads, etc.) can be detected and identified by the vehicle sensors (radar, LIDAR, camera, etc.).
[0012] Driver assistance data is data that assists a vehicle's AD or ADAS systems or features.
[0013] By means of the proposed method, driving assistance data are determined, which enable a more reliable identification of the road shape and / or traffic conditions compared to currently known systems and methods. In particular, the method can be applied to systems in which a vehicle is able to navigate / drive by using map data. The purpose is to compare reference data in the form of map data of a geographical area with sensor data about the geographical area. In addition to sensor data about surrounding vehicles, the map data may relate to a variety of other reference data describing the geographical area, such as the surroundings of a first vehicle, and may include data about lighting conditions, road conditions, distances between vehicles, types of vehicles, road shape, weather conditions, and the like. In more detail, the method enables the use of sensor data about the surrounding vehicles and the environment and the comparison of the sensor data with the map data in order to provide driving assistance data.
[0014] The present disclosure is based at least in part on the following implementation, which will advantageously provide additional data for improving the robustness of currently known systems by providing driving assistance data, which can provide more reliable identification of the road shape and / or traffic conditions ahead. The identified road shape and / or traffic conditions must be reliable in order to apply AD or ADAS systems or features. Thus, the inventors recognized that sensor data about the first vehicle of the second vehicle and map data about the surrounding environment of the first vehicle can be used to determine driving assistance data about a third vehicle.
[0015] According to an exemplary embodiment of the present disclosure, it is determined whether the driving assistance data indicates inconsistency based on the comparison. By indicating any inconsistency, the driving assistance data can make a more reliable identification of the road shape and / or traffic conditions ahead, because the situation in which the inconsistency is indicated can be separated from the situation in which the inconsistency is not indicated. The situation in which the inconsistency is not indicated typically indicates that any identification of the road shape and / or traffic conditions ahead is more reliable. Therefore, it is possible to identify the situation in which the identification of the road shape and / or traffic conditions ahead is more reliable.
[0016] According to a further exemplary embodiment of the present disclosure, the driving assistance data includes a confidence level of the map data. For example, determining the driving assistance data may include increasing the confidence level of the map data if the comparison does not indicate an inconsistency. Furthermore, determining the driving assistance data may include decreasing the confidence level of the map data if the comparison indicates an inconsistency. Thus, a situation in which the recognition of the road shape and / or traffic conditions ahead is more reliable can be identified as a situation in which the confidence level of the map data is high according to the driving assistance data.
[0017] According to another exemplary embodiment of the present disclosure, the driving assistance data includes a traffic condition, which may be one of a risk scenario, traffic density, and a temporary traffic change.
[0018] In another exemplary embodiment of the present disclosure, additional sensor data can be obtained. For example, additional sensor data can be obtained from the sensor system of the first vehicle, wherein the additional sensor data includes the posture and speed of the additional vehicle located in the surrounding environment of the first vehicle. The posture and speed of the additional vehicle are then compared with the map data, and the driving assistance data is determined based on the comparison with respect to the third vehicle. Additionally or alternatively, additional sensor data can be obtained from the sensor systems of multiple additional vehicles, and the additional sensor data is located in the posture and speed of the surrounding vehicles in the corresponding surrounding environment of multiple additional vehicles. Additional map data is also obtained, and the additional map data includes the road shape of the corresponding surrounding environment of multiple vehicles. The posture and speed of the surrounding vehicles are then compared with the additional map data, and the driving assistance data is determined based on the comparison with respect to the third vehicle. By obtaining additional sensor data, based on a larger amount of sensor data compared with the map data, and based on the driving assistance data determined by the comparison, a more reliable identification of the road shape and / or traffic conditions is made.
[0019] According to an exemplary embodiment of the present disclosure, the method further includes transmitting the determined driving assistance data to a third vehicle.
[0020] According to a second aspect of the present disclosure, a central control system is provided. The central control system includes at least one processor, and at least one memory. One or more processors are configured to execute instructions stored in the memory, and the instructions cause the vehicle control system to execute a method for determining driving assistance data about a vehicle based on sensor data about other vehicles. The method includes acquiring sensor data from a sensor system of a first vehicle, the sensor data including the posture and speed of a second vehicle located in the surroundings of the first vehicle and acquiring map data including the road shape of the surroundings of the first vehicle. The method further includes comparing the posture and speed of the second vehicle with the map data and determining driving assistance data about a third vehicle based on the comparison. With respect to this aspect of the present disclosure, similar advantages and preferred features are proposed as in the first aspect of the present disclosure discussed previously.
[0021] By central control system is meant a central control system that is remote from the vehicle and within range of which sensor data can be acquired from several vehicles. The central control system may be included in a cloud service. One central control system may serve a geographical area or multiple vehicles.
[0022] According to a third aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing one or more programs configured to be executed by one or more processors of a central control system, the one or more programs comprising instructions for executing a method according to any one of the embodiments disclosed herein. With respect to this aspect of the present disclosure, similar advantages and preferred features are proposed as in the first aspect of the present disclosure discussed previously.
[0023] Further embodiments of the invention are defined in the appended claims. It should be emphasized that when used in this specification, the term "comprising / including" is adopted to specify the presence of stated features, integers, steps, or components. It does not prevent the presence or addition of one or more other features, integers, steps, components, or groups thereof.
[0024] These and other features and advantages of the invention will be further clarified hereinafter with reference to the embodiments described hereinafter. BRIEF DESCRIPTION OF THE DRAWINGS
[0025] Additional objects, features and advantages of the embodiments of the present disclosure will be apparent from the following detailed description, with reference to the accompanying drawings, in which:
[0026] Figure 1 is a schematic top view representation of a vehicle and surrounding vehicles in accordance with an embodiment of the present disclosure.
[0027] Figure 2 is a schematic side view illustration of a vehicle including vehicle control equipment in communication with the central control system of the present disclosure.
[0028] Figure 3 The flowchart of the method for determining driving assistance data according to an embodiment of the present disclosure is shown.
[0029] Figure 4 The flowchart of a method for determining driving assistance data according to another embodiment of the present disclosure is shown.
[0030] Figure 5 is a schematic diagram of a central control system for determining driving assistance data according to an embodiment of the present disclosure. DETAILED DESCRIPTION
[0031] Those skilled in the art will appreciate that the steps, services, and functions explained herein may be implemented using stand-alone hardware circuits, using software running in conjunction with a programmed microprocessor or general purpose computer, using one or more application specific integrated circuits (ASICs), and / or using one or more digital signal processors (DSPs). It will also be appreciated that when the present disclosure is described in terms of methods, it may also be embodied in one or more processors and one or more memories coupled to the one or more processors, wherein the one or more memories store one or more programs that, when executed by the one or more processors, perform the steps, services, and functions disclosed herein.
[0032] In the following description of exemplary embodiments, the same reference numerals denote the same or similar components.
[0033] Figure 1 A device having a structure arranged to be associated with an embodiment of the present disclosure and relating to Figure 2 and Figure 5 A schematic top view of a vehicle 1 of a vehicle control system 10 communicating with a disclosed central control system (not shown). The vehicle 1 will be referred to as the first vehicle 1 below. The schematic diagram shows a first vehicle on a road with four separate lanes and three surrounding second vehicles 2a, 2b, 2c. Two of the surrounding second vehicles 2a, 2b travel in the same direction as the first vehicle (i.e., on the same side of the road) but in different lanes, while one of the surrounding second vehicles 2c travels on the opposite side of the road.
[0034] The vehicle control system 10 includes a positioning system 11 configured to determine a set of geographic coordinates (i.e., map position) of the first vehicle 1 and an orientation of the first vehicle 1. The orientation of the first vehicle is the orientation of the vehicle toward which it is traveling, i.e., the vehicle orientation (heading orientation). The geographic coordinates and orientation are also referred to together as attitude in this article. The vehicle control system 10 has a sensor system 12 including at least one sensor (not shown) for detecting and identifying objects outside the first vehicle 1, thereby generating sensor data. The sensor system 12 can, for example, include one or more radar (RADAR) arrangements, laser radar (LIDAR) arrangements, and one or more cameras, or any other suitable sensor.
[0035] In addition, the vehicle control system 10 has a vehicle control device 13 connected to the positioning system 11 and the sensor system 12. In more detail, the vehicle control device 13 is configured to obtain map data including the road shape of the surrounding environment of the first vehicle. The road shape includes a representation of the position road map data (for example, the center of the road or the center of the lane) and / or a representation of the road shape (that is, the curvature and / or the heading). It should be understood that the vehicle control device 13 may include a digital signal processor arranged and configured for digital communication with a server outside the site or a cloud-based server. Therefore, data can be sent to and from the vehicle control device 13. Then, the geographic location of the first vehicle is determined with the help of the positioning system 11, which can determine the geographic location with the help of a GNSS system, IMU data and road shape and / or by the use of fixed landmarks, as has been demonstrated above.
[0036] Therefore, depending on the functionality provided in the control circuitry, one or more communication interfaces (not shown) and / or one or more antenna interfaces may be provided, and in addition, one or more sensor interfaces (not shown) may also be provided for obtaining data from sensors within the vehicle.
[0037] Next, the vehicle control device 13 is configured to measure 22a, 22b, 22c the position and speed of the first vehicle 1 for each of one or more surrounding second vehicles 2a, 2b, 2c located in the surrounding environment by means of the vehicle perception system 12. The vehicle control device 13 is further configured to determine the map position of each of the one or more surrounding second vehicles 2a, 2b, 2c by means of the sensor system 12 based on the geographical location of the first vehicle 1 and the measured position of each of the one or more surrounding second vehicles 2a, 2b, 2c.
[0038] In other words, the vehicle control device 13 is configured to first determine the position of one or more surrounding second vehicles 2a, 2b, 2c in a local coordinate system of the first vehicle 1 and then transform that position into a global coordinate system.
[0039] The vehicle control device 13 is further configured to determine the orientation of each of the one or more surrounding second vehicles 2a, 2b, 2c with the aid of the vehicle perception system 12, which orientation together with the map position of each of the one or more surrounding second vehicles 2a, 2b, 2c forms the posture of each of the one or more surrounding second vehicles 2a, 2b, 2c.
[0040] Figure 2Such as including vehicle control equipment 13 and positioning system 11 about Figure 1 A schematic side view of a vehicle 1 such as the first vehicle 1 of FIG. 1 is shown. The vehicle control device 13 has a processor 14 , a memory 15 , a sensor interface 16 and a communication / antenna interface 17 .
[0041] The first vehicle 1 has a sensor system including a plurality of sensors 24 (e.g., cameras, lidars, radars, ultrasonic transducers, etc.). The sensors 24 are configured to obtain information representing the surrounding environment of the vehicle. In more detail, the perception system 12 includes sensors 24 adapted to track one or more road references (e.g., lane markings, road edges, other vehicles, landmarks, etc.) in order to estimate the road shape and, in particular, the road boundaries of the road being traveled.
[0042] In addition, the processor 14 of the vehicle control device 13 is configured to receive sensor data including information about the surrounding environment of the first vehicle 1. It should be understood that the sensor interface 16 can also provide the possibility of obtaining sensor data directly (not shown) or via a dedicated sensor control circuit 23 in the vehicle. The communication / antenna interface 17 can additionally provide the possibility of sending output to a remote location by means of an antenna 25. Moreover, some sensors 24 in the vehicle can communicate with the control device 10 using a local network setting (director CAN bus, I2C, Ethernet, optical fiber, etc.). The communication / antenna interface 17 can be arranged to communicate with other control functions of the vehicle and can therefore also be regarded as a control interface. However, a separate control interface (not shown) can be provided. Local communication within the vehicle can also be a wireless type using protocols such as WiFi, LoRa, ZigBee, Bluetooth, or similar intermediate / short-range technologies, etc.
[0043] In addition, the first vehicle 1 is connected to the central control system 50 according to an embodiment of the present disclosure and is related to Figure 5Further disclosed. The central control system 50 is located in the external network 20. The connection from the first vehicle to the external network 20 can be, for example, via a wireless link, for example, via an antenna 25 (for example, for executing part or all of a computing instruction with the aid of a remote resource). The same or some other wireless links can be used to communicate with other vehicles or local infrastructure elements in the vicinity of the vehicle. Cellular communication technology can be used for remote communication to the external network, and if the cellular communication technology used has low latency, it can also be used for communication between vehicles, vehicle to vehicle (V2V), and / or vehicle to infrastructure V2X. Examples of cellular radio technologies are GSM, GPRS, EDGE, LTE, 5G, 5G NR, etc., also including future cellular solutions. However, in some solutions, medium-range to short-range communication technology is used, and the director wireless local area (LAN), for example, a solution based on IEEE 802.11. ETSI is working on cellular standards for vehicle communications and considers 5G as a suitable solution due to the low latency and high bandwidth and efficient handling of communication channels.
[0044] Figure 3 3 is a flow chart of a method 300 for determining driving assistance according to an embodiment of the present disclosure. The method may be executed in a central control system (eg, in a central control system 50 according to an embodiment of the present disclosure) and is related to Figure 2 and Figure 5 Further disclosed. By central control system is meant a central control system that is remote from the vehicle and within the range where sensor data can be acquired from several vehicles. The central control system may be included in a cloud service. A central control system may, for example, serve a specific geographic area or a specific plurality of vehicles.
[0045] In method 300, sensor data is acquired 310 from a sensor system of a first vehicle. The first vehicle and the sensor system may be, for example, as described with respect to Figure 1 and Figure 2 The disclosed first vehicle 1 and the sensor system 12 including the sensor 24 can acquire sensor data from the first vehicle 1 via the communication / antenna interface 17 and the antenna 25. The sensor data includes the attitude and speed of the second vehicle located in the surrounding environment of the first vehicle. The second vehicle can be, for example, Figure 1 One of the one or more surrounding second vehicles 2a, 2b, 2c disclosed. The second vehicle can travel in the same direction, the opposite direction with respect to the first vehicle. If the second vehicle travels in the same direction as the first vehicle, it can travel in the same lane or a different lane compared to the first vehicle.
[0046] In addition, map data is obtained 320. The map data includes a road shape of the surroundings of the first vehicle. The map data can be obtained from a local memory of a device or system in which the map data is executed or can be obtained from a memory in a remote site. The road shape of the surroundings of the first vehicle may include non-drivable areas and drivable areas of the surroundings of the first vehicle. The road shape may additionally include a representation of the position road map data (e.g., the center of the road or the center of the lane), and / or a representation of the shape of the road (i.e., curvature and / or heading). The attitude and speed of the second vehicle are compared 330 with the map data and driving assistance data about the third vehicle is determined 340 based on the comparison. Driving assistance data is data that assists the AD or ADAS system or feature of the vehicle.
[0047] The driving assistance data may then be sent to a third vehicle.
[0048] An advantage of the method is that one vehicle can observe many other vehicles and in particular vehicles with ADAS features can help provide data for use in AD vehicles, for example regarding positioning and trajectory planning. In addition, an advantage with respect to acquiring sensor data relating to the attitude and speed of another (second) vehicle from the sensor system of a (first) vehicle is that sensor data relating to the (second) vehicle itself which may not include a sensor system can be acquired. Thus, sensor data relating to the attitude and speed of a larger number of vehicles can be acquired which can be compared with map data and driving assistance data determined. This enables a more reliable identification of road shape and / or traffic conditions compared to currently known systems and methods.
[0049] The driving assistance data may include a confidence value for the map data. The confidence value for the map data may be indicated or determined by comparison. For example, if the comparison indicates that the confidence of the map data is low, the driving assistance data may indicate a low confidence value for the map data. The driving assistance data indicating the low confidence value for the map data may then be sent to a third vehicle that is located or is likely to be located at a location related to the map data. This makes it possible to avoid the use of map data that has a low confidence value and that is therefore not effective in the third vehicle, for example to assist an AD or ADAS system or feature of the third vehicle. In a scenario where the map data has a low confidence value, the AD or ADAS system or feature will then be disabled and the vehicle may be switched to manual mode with respect to such AD or ADAS system or feature.
[0050] If not, the comparison indicates that the confidence of the map data is high, then the driving assistance data can indicate a high confidence value for the map data. The driving assistance data indicating a high confidence value for the map data can then be sent to a third vehicle that is located or is likely to be located at the location to which the map data relates. This makes it possible to validate the map data to enable use of the map data, for example, to assist an AD or ADAS system or feature of the third vehicle. In the scenario that the map data has, then an AD or ADAS system or feature can be implemented.
[0051] Determining the driver assistance data may be based on whether the comparison indicates an inconsistency 342 , ie, whether the sensor data and the map data are inconsistent in some way.
[0052] The comparison may indicate, for example, that the vehicle is travelling in a location where it is not allowed to travel according to the map data. This may be due, for example, to temporary traffic changes.
[0053] The inconsistency may further indicate that the map data is not valid, or that the map data has a low confidence or at least there may be issues with the validity and / or confidence of the map data. Similarly, if there are no inconsistencies, this may indicate that the map data is valid or that the map data has a high confidence or at least there is no indication of any issues with the validity and / or confidence of the map data.
[0054] For example, determining the driving assistance data may include decreasing 344 a confidence value of the map data if the comparison indicates an inconsistency. Similarly, determining the driving assistance data may include increasing 346 a confidence value of the map data if the comparison does not indicate an inconsistency.
[0055] The method 300 may be used in map validation, for example using the determined confidence value for the map data. In general, map validation may include:
[0056] ·Collection and monitoring,
[0057] Correction and anonymization
[0058] · Map creation
[0059] ·alignment
[0060] ·verify
[0061] ·polymerization
[0062] Assessment with optional reporting
[0063] The purpose of map validation is to keep the HD maps up to date. The maps will typically be located in the cloud and the map data can be acquired by a central control system. Both ADAS and AD vehicles are used as probes and sensor data from the sensor systems of ADAS and AD vehicles are acquired in the central control system.
[0064] In the collection, detection data including, for example, sensor data is collected (acquired) in the central control system and converted into an appropriate format. Features of method 300 can be used to collect (acquire) sensor data from one or more first vehicles, the sensor data including the attitude and speed of one or more second vehicles in the surrounding environment of a corresponding one of the one or more first vehicles.
[0065] In rectification and anonymization, the sensor data are cleaned, anonymized and aligned. The sensor data are filtered and sorted in strict chronological order within anonymous observation batches.
[0066] Local map creation operates on a stream of anonymized sensor data and creates a local map. This involves converting the sensor data to local coordinates relative to a reference point in a global coordinate system (typically corresponding to the middle of the vehicle's rear axle) and finally delimiting the output into a local sub-map. Features of method 300 can be used by considering sensor data including the attitude and velocity of one or more second vehicles in the surroundings of a corresponding one of the one or more first vehicles.
[0067] In the alignment, a local partial map is input, rotated, translated, and matching points between the local map and the HD map are output.
[0068] Verification receives matching points between the local map and the HD map from the alignment and outputs verified metrics (i.e., type, distance, etc.) for the individual sub-maps along with the HD map object identifications. Portions of the local map are verified for each of the HD map objects within the coverage area (bounding box) and any differences (metrics / inconsistencies) are noted. These metrics / inconsistencies are input to the aggregation. Features of method 300 can be used by considering sensor data including the attitude and velocity of one or more second vehicles located in the surroundings of a corresponding one of the one or more first vehicles and any inconsistencies indicated by comparison of the sensor data with the map data.
[0069] When you query the HD map for map objects (map data) within a certain area (bounding box), it will return map objects like traffic signs, lane markings, and center lanes. Each map object contains at least one geographic location (shape point) which contains latitude, longitude, and altitude. A traffic sign, for example, contains only one shape point and metadata (e.g., sign type), while a lane marking contains a collection of shape points and metadata.
[0070] Aggregation receives as input HD map object identifications with corresponding validation metrics / inconsistencies for many sub-maps. Aggregate sensor data for locations over time.
[0071] After aggregation, there is an evaluation where a decision is made whether to act on any deviations (metrics / inconsistencies).
[0072] For example, reports may be sent to map stakeholders for any deviations (metrics / inconsistencies).Features of method 300 can be used by determining a confidence value for the map data based on the inconsistency and providing the confidence value to a third vehicle.
[0073] Figure 4 FIG. 4 is a flow chart of a method 400 for determining driving assistance data according to another embodiment of the present disclosure. Figure 2 and Figure 5 The method 400 is performed in the disclosed central control system 50. In the method 400, sensor data is acquired 310 from a sensor system of a first vehicle. In addition, map data is acquired 320. The map data includes the road shape of the surrounding environment of the first vehicle. The attitude and speed of the second vehicle are compared 330 with the map data and driving assistance data about a third vehicle is determined 340 based on the comparison. The driving assistance data can then be sent to the third vehicle.
[0074] Typically, steps 310, 320, 330, 340, and 350 are similar to those described in connection with Figure 3 The corresponding steps in the method 300 described are the same and are related to Figure 3 The disclosure of is also valid for method 400 .
[0075] The determined driving assistance data based on the comparison may include traffic conditions 442. Traffic conditions may be determined based on the comparison 330 of the sensor data to the map data.
[0076] The traffic conditions can then be sent to the third vehicle, where they can be used to determine the operational design domain (ODD), i.e., the specific conditions under which a given driving AD or ADAS system or feature is designed to function, including but not limited to driving mode. This can incorporate various constraints, such as those in geography, traffic, speed, and roadways. This makes it possible to assist the AD system or feature of the third vehicle. In a scenario where the requirements of the ODD are not met, for example due to identified traffic conditions, the AD feature will then be disabled or not enabled, and the third vehicle can be switched to manual mode with respect to such AD or ADAS system or feature.
[0077] An advantage of the method is that one vehicle is able to observe many other vehicles and in particular vehicles with ADAS features to help provide driving assistance data including high-importance traffic conditions for positioning and trajectory planning of the AD vehicle. In addition, an advantage with respect to acquiring sensor data related to the attitude and speed of another (second) vehicle from the sensor system of the (first) vehicle is that sensor data related to the (second) vehicle itself, which may not include a sensor system, can be acquired. Therefore, sensor data related to the attitude and speed of a larger number of vehicles can be acquired, which data can be compared with map data and driving assistance data including traffic conditions can be determined. Compared with currently known systems and methods, this can further achieve more reliable identification of traffic conditions.
[0078] The driving assistance data including traffic conditions may additionally include enhanced traffic information. For example, in comparison 330, traffic conditions such as high density traffic may be identified in a particular lane, and traffic conditions such as low density traffic may be identified in other lanes. Such enhanced traffic information can be provided to a third vehicle, such as a third vehicle that is or may be located in an area related to the driving assistance information, or the like.
[0079] Determining that the driver assistance data includes traffic conditions can be based on determining 444 whether the comparison indicates an inconsistency, ie, the sensor data and the map data are inconsistent in some way. Traffic conditions can then be determined 446 based on the inconsistency.
[0080] An inconsistency that the comparison may indicate is that the vehicle is traveling where it is not allowed to travel according to the map data, for example, where the map data does not indicate a drivable area. It can also indicate that the vehicle is traveling in a direction or at a speed that is not allowed to travel according to the map data, for example, the vehicle is traveling in the wrong direction with respect to the map data or in a lane at a higher or lower speed than expected. Based on such indications, temporary traffic changes, risk scenarios or other traffic conditions may be identified.
[0081] Based on the identification of temporary traffic changes, risk scenarios or other traffic conditions, the requirements of ODD cannot be met. In such scenarios, for AD vehicles receiving driver assistance data, AD features will be disabled or not enabled, and driving can be switched to manual mode with respect to such AD features.
[0082] In addition, regarding Figures 1 to 4 , further sensor data can be acquired from the first vehicle with respect to further surrounding (second) vehicles, or from further (first) vehicles with respect to respective surrounding (second) vehicles, or from both. This is discussed below.
[0083] Additional sensor data from the sensor system of the first vehicle can be acquired. The additional sensor data includes the attitude and speed of additional vehicles in the surrounding environment of the first vehicle. The attitude and speed of the additional vehicles can then be compared with the map data and the driving assistance data can be determined based on the comparison.
[0084] For scenarios in which the additional sensor data relates to the same or overlapping surroundings (i.e., the first vehicle was located in the same or a similar location when the additional sensor data was generated) and in which the sensor data is generated within a predetermined time period, the additional sensor data from sensor systems of multiple additional vehicles may be aggregated and compared to the map data after aggregation.
[0085] An advantage of acquiring sensor data relating to the attitude and speed of further vehicles is that relevant sensor data can be received from one (first) vehicle regarding further (second) vehicles. Thus, sensor data relating to the attitude and speed of a greater number of further vehicles can be acquired, which data can be compared with map data and driver assistance data determined. This enables a more reliable identification of road shape and / or traffic conditions than currently known systems and methods.
[0086] To the extent that sensor data from a first vehicle's sensor system regarding a second vehicle is of reduced quality compared to sensor data regarding the first vehicle itself, acquiring sensor data regarding a greater number of additional vehicles will provide a greater amount of sensor data that can compensate for and be more targeted to the possible reduced quality.
[0087] The length of the predetermined period will generally depend on the application and the type of driver assistance data to be determined.
[0088] Additional sensor data from sensor systems of multiple additional vehicles may be acquired. The additional sensor data includes attitudes and speeds of surrounding vehicles in the respective surroundings of the multiple additional vehicles. Furthermore, additional map data including road shapes of the respective surroundings of the multiple vehicles is acquired. The attitudes and speeds of the surrounding vehicles may then be compared with the additional map data and driving assistance data may be determined based on the comparison.
[0089] For scenarios in which the additional sensor data relates to the same or overlapping surroundings (i.e., the additional vehicles were located in the same or similar locations when the additional sensor data was generated) and in which the sensor data was generated within a predetermined time period, the additional sensor data from sensor systems of multiple additional vehicles can be aggregated and compared to the map data after aggregation.
[0090] An advantage of acquiring sensor data from further vehicles relating to the attitude and speed of further other vehicles in the respective surroundings of the further vehicles is that sensor data can be acquired also for further vehicles which do not themselves comprise a sensor system. Thus, sensor data relating to the attitude and speed of a greater number of vehicles can be acquired which can be compared with map data and driver assistance data determined. This enables a more reliable recognition of the road shape and / or traffic conditions compared to currently known systems and methods.
[0091] To the extent that sensor data from the sensor systems of each of the other vehicles regarding each of the surrounding vehicles has reduced quality compared to sensor data regarding the vehicle itself, acquiring sensor data from a greater number of vehicles and regarding a greater number of surrounding vehicles will provide a greater amount of sensor data that can compensate for and be more targeted to the possible reduced quality.
[0092] The length of the predetermined period will generally depend on the application and the type of driver assistance data to be determined.
[0093] Figure 5 is a schematic diagram of a central control system 50 for determining driving assistance data according to an embodiment of the present disclosure. The central control system includes at least one processor 52 and at least one memory 54. The processor is configured to execute instructions 56 stored in the memory, which instructions 56 cause the central control system 50 to execute the instructions according to the present disclosure and in particular according to the embodiment of the present disclosure. Figure 3 and 4 The disclosed embodiments provide methods for determining driver assistance data about a vehicle based on sensor data about other vehicles.
[0094] The central control system 50 may be identified, for example, as a general purpose processor, a special purpose processor, a circuit containing a processing component, a group of distributed processing components, a group of distributed computers configured for processing, a field programmable gate array (FPGA), etc. The central control system 50 may additionally include a microprocessor 14, a microcontroller, a programmable digital signal processor, or another programmable device. The central control system 50 may also or instead include an application specific integrated circuit (ASIC), a programmable gate array or programmable array logic, a programmable logic device, or a digital signal processor. In the case where the central control system 50 includes a programmable device such as a microprocessor, a microcontroller, or a programmable digital signal processor mentioned above, the processor may additionally include computer executable code that controls the operation of the programmable device.
[0095] The processor(s) 52 (associated with the central control system 50) may be or include any number of hardware components for performing data or signal processing or for executing computer code (instructions 56) stored in the memory 54. The memory 54 may be one or more devices for storing data and / or computer code for completing or facilitating the various methods described in this specification. The memory 54 may include volatile memory or non-volatile memory. The memory 54 may include a database component, an object code component, a script component, or any other type of information structure for supporting the various activities of the specification. According to an exemplary embodiment, any distributed or local memory device may be utilized with respect to the systems and methods of the specification. According to an exemplary embodiment, the memory 54 (e.g., via a circuit or any other wired, wireless, or network connection) is communicatively connected to the processor 52 and includes computer code for executing one or more processes described herein.
[0096] Included in the central control system 50 may be a non-transitory computer-readable storage medium 54 storing one or more programs configured to be executed by one or more processors 52 of the central control system 50, the one or more programs including instructions for causing the central control system 50 to perform operations in accordance with the present disclosure and in particular in accordance with the present disclosure. Figure 3 and 4 Instructions 56 of the method of the disclosed embodiment.
[0097] In general, computer-accessible media may include any tangible or non-transitory storage media or memory media, such as electronic, magnetic, or optical media—for example, a disk or CD / DVD-ROM coupled to a computer system via a bus. As used herein, the terms "tangible" and "non-transitory" are intended to describe computer-readable storage media (or "memory") other than propagating electromagnetic signals, but are not intended to otherwise limit the types of physical computer-readable storage devices encompassed by the phrase computer-readable media or memory. For example, the terms "non-transitory computer-readable media" or "tangible memory" are intended to include types of storage devices that do not necessarily store information permanently, including, for example, random access memory (RAM). Program instructions and data stored on a tangible computer-accessible storage medium in a non-transitory form may be further transmitted by a transmission medium or by signals such as electronic, electromagnetic, or digital signals that may be conveyed via a communication medium such as a network and / or wireless link.
[0098] The present disclosure has been presented above with reference to specific embodiments. However, other embodiments than those described above are possible and within the scope of the present disclosure. Different method steps beyond those described above for performing the method by hardware or software may be provided within the scope of the present disclosure. Therefore, according to an exemplary embodiment, a non-transitory computer-readable storage medium is provided that stores one or more programs configured to be executed by one or more processors of a vehicle control system, the one or more programs including instructions for performing a method according to any of the embodiments discussed above. Alternatively, according to another exemplary embodiment, a cloud computing system can be configured to perform any of the methods presented herein. The cloud computing system may include distributed cloud computing resources that jointly perform the methods presented herein under the control of one or more computer program products.
[0099] Thus, it should be understood that parts of the described solutions may be implemented in the vehicle, in a system external to the vehicle, or in any combination of internal and external to the vehicle; for example, in a server in communication with the vehicle, a so-called cloud solution. For example, sensor data may be sent to an external system and the system performs steps to compare the sensor data (movement of other vehicles) with predefined behavioral models. Different features and steps of the embodiments may be combined in other combinations than those described.
[0100] Exemplary methods, computer-readable storage media, control devices, vehicles, and infrastructure equipment are set forth in the following items:
[0101] It should be noted that the word "comprising" does not exclude the presence of other elements or steps than those listed and the word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. It should be further noted that any reference numerals do not limit the scope of the claims, that the invention may be at least partially implemented by means of both hardware and software and that several "means" or "units" may be represented by the same item of hardware.
[0102] Although the figure can show the specific order of method steps, the order of steps may be different from the order depicted. In addition, two or more steps can be performed in parallel or under the scenario of partial simultaneous occurrence. For example, the step of receiving the signal including the information about movement and the information about the current road scene can be interchanged based on a specific implementation. Such changes will depend on the selected software and hardware system and the designer's choice. All such changes are within the scope of the present disclosure. Similarly, software implementation can be realized to realize various connection steps, processing steps, comparison steps and decision steps by utilizing standard programming techniques with rule-based logic and other logics. Only the above-mentioned and described embodiments are given as examples and should not be limited to the present invention. For those skilled in the art, other solutions, uses, purposes, and functions within the scope of the present invention as claimed in the patent embodiments described below should be obvious.
Claims
1. A method for determining driving assistance data about a vehicle based on sensor data and map data about other vehicles, the method comprising: acquiring sensor data from a sensor system of a first vehicle, the sensor data including a posture and velocity of a second vehicle located in an environment surrounding the first vehicle; Acquiring map data including the road shape of the surrounding environment of the first vehicle; comparing the attitude and velocity of the second vehicle with the map data; determining driving assistance data regarding a third vehicle based on the comparison; and sending the determined driving assistance data to the third vehicle, Wherein the driving assistance data comprises a confidence value for the map data, and wherein determining whether the driving assistance data indicates an inconsistency is based on the comparison.
2. The method according to claim 1, wherein: Determining driving assistance data includes increasing a confidence value for the map data if the comparison does not indicate an inconsistency.
3. The method according to claim 1, wherein: Determining driving assistance data includes reducing a confidence value of the map data if the comparison indicates an inconsistency.
4. The method according to any one of claims 1 to 3, wherein: The driving assistance data includes traffic conditions.
5. The method according to claim 4, wherein: The traffic condition is one of a risk scenario, a traffic density, and a temporary traffic change.
6. The method according to claim 1, further comprising: acquiring additional sensor data from a sensor system of the first vehicle, the additional sensor data including attitudes and velocities of additional vehicles located in the surroundings of the first vehicle; and The attitude and velocity of the further vehicle are compared to the map data.
7. The method according to claim 1, wherein: The second vehicle is located in an adjacent lane or an opposite lane in the surroundings of the first vehicle.
8. The method according to claim 1, wherein: The road shape of the surrounding environment of the first vehicle includes a non-drivable area and a drivable area of the surrounding environment of the first vehicle.
9. The method according to claim 1, further comprising: acquiring additional sensor data from sensor systems of a plurality of additional vehicles, the additional sensor data including attitudes and velocities of surrounding vehicles located in respective surroundings of the plurality of additional vehicles; acquiring additional map data, the additional map data including road shapes of the surrounding environments of the plurality of additional vehicles; and The attitude and velocity of the surrounding vehicles are compared with the further map data.
10. The method according to claim 9, wherein: The road shapes of the corresponding surroundings of the plurality of other vehicles include non-drivable areas and drivable areas of the corresponding surroundings of the plurality of other vehicles.
11. A central control system, comprising: at least one processor; at least one memory; The at least one processor is configured to execute instructions stored in the memory, the instructions causing the central control system to perform a method for determining driving assistance data about a vehicle based on sensor data about other vehicles, the method comprising: acquiring sensor data from a sensor system of a first vehicle, the sensor data including a posture and velocity of a second vehicle located in an environment surrounding the first vehicle; Acquiring map data including the road shape of the surrounding environment of the first vehicle; comparing the attitude and velocity of the second vehicle with the map data; determining driving assistance data regarding a third vehicle based on the comparison; and sending the determined driving assistance data to the third vehicle, Wherein the driving assistance data comprises a confidence value for the map data, and wherein determining whether the driving assistance data indicates an inconsistency is based on the comparison.
12. A non-transitory computer-readable storage medium storing one or more programs, the one or more programs being configured to be executed by one or more processors of a computer, the one or more programs comprising instructions for causing the computer to perform the method according to any one of claims 1 to 10.
