Dynamic Map Generation Focusing on the Fields of Construction and Localization Technologies

Abstract

This application relates to dynamic map generation focusing on the fields of construction and localization technology. Systems and methods for generating efficient planned routes for vehicles (including autonomous and semi-autonomous vehicles) are proposed. A route planner can generate dynamic maps and routes that efficiently reduce the uncertainty of blocker environment and behavior data. Route planning can be accomplished using statistical methods, in which a vehicle can use and rely on known data from one set of geographical or behavioral features in another geographical and behavioral context to estimate environmental and behavioral data relevant to the vehicle's current operation.

Description

Technical Field

[0001] The present disclosure relates to map generation for vehicle navigation, and more particularly to the creation of dynamic maps and planned routes for autonomous and semi-autonomous vehicles. Background Art

[0002] The behavior of drivers in a given geographical area may generally differ to some extent from the behavior of drivers in different geographical areas. For example, in most geographical areas, if drivers cannot pass through an intersection before a red light appears, they may generally avoid entering the intersection. In other geographical areas (such as large cities), drivers may enter an intersection before a red light appears, regardless of whether they will be able to pass through the intersection.

[0003] When deploying autonomous and semi-autonomous vehicles to a given geographical area, it may be important to understand the general behavior of drivers within that area. Route planning for a geographical area prior to deployment may involve collecting driving data indicating the behavior of drivers in vehicles driving within that geographical area. However, driving any route to collect such data may not be the most efficient way to collect such data. Summary of the Invention

[0004] Aspects of the present disclosure provide systems and methods for planning a route for a vehicle. According to one aspect, a method may generate a first map based on a first feature dataset in a database. The database may include multiple feature datasets. A first route may be generated based on the first map. Vehicle operation data may be collected as a second feature dataset. The second feature dataset may be compared with the multiple feature datasets in the database. Based on the similarity between the second feature dataset and a third feature dataset in the database, the first map may be updated to a second map.

[0005] According to another aspect of the present disclosure, a system for generating a vehicle route is disclosed. A database may include multiple feature datasets. A map generator may be configured to generate a first map based on a first feature dataset in the database. A planning module may be configured to generate a first route based on the first map. At least one sensor may be configured to collect vehicle operation data as a second feature dataset. A processor may be configured to compare the second feature dataset with the multiple feature datasets in the database. Based on the similarity between the second feature dataset and a third feature dataset in the database, the first map may be updated to a second map.

[0006] This has outlined the features and technical advantages of the present disclosure quite extensively so that the following detailed description can be better understood. Additional features and advantages of the present disclosure will be described below. Those skilled in the art should understand that the present disclosure can be easily used as a basis for modifying or designing other structures for performing the same purpose of the present disclosure. Those skilled in the art should also recognize that such equivalent structures do not depart from the teachings of the present disclosure as set forth in the appended claims. When considered in conjunction with the accompanying drawings, the novel features, which are considered to be characteristics of the present disclosure in terms of its organization and method of operation, as well as further purposes and advantages, will be better understood from the following description. However, it should be clearly understood that each drawing is provided for purposes of illustration and description only and is not intended as a definition of the limitations of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] In conjunction with the accompanying drawings, the features, properties, and advantages of the present disclosure will become more apparent from the following detailed description set forth below, in which like reference characters throughout the figures correspond.

[0008] Figure 1 A method of planning a route according to one aspect of the present disclosure is depicted.

[0009] Figure 2 An exemplary heat map according to one aspect of the present disclosure is depicted.

[0010] Figure 3 A method of generating a heat map according to one aspect of the present disclosure is depicted.

[0011] Figure 4 A hardware implementation for a dynamic map generation system according to aspects of the present disclosure is depicted. DETAILED DESCRIPTION

[0012] In conjunction with the accompanying drawings, the following detailed description is intended as a description of various configurations and is not intended to represent the only configuration in which the concepts described herein can be practiced. The detailed description includes specific details for providing a thorough understanding of the various concepts. However, it will be apparent to those skilled in the art that these concepts can be practiced without these specific details. In some instances, well-known structures and components are shown in block diagram form to avoid obscuring these concepts.

[0013] In accordance with aspects of the present disclosure, systems and methods are provided for generating an efficient planned route for a vehicle, including an autonomous vehicle and a semi-autonomous vehicle. A route planner can generate a dynamic map and route that efficiently reduces the uncertainty of road-agent environmental and behavioral data. Traditional route planning may be implemented based only on known data obtained from previously acquired precise environmental and behavioral data. This approach may be impractical and costly because it requires a census-type method to explore and collect data for numerous feature sets. Alternatively, and as described herein, route planning can be accomplished using statistical methods in which a vehicle can use and rely on known data from one geographic or behavioral feature set in another geographic and behavioral context to estimate environmental and behavioral data relevant to the vehicle's current operation. Using this representative information can reduce the need for direct empirical data and save time and costs associated with collecting, storing, and analyzing large amounts of information.

[0014] Figure 1 An illustrative method 100 for planning a route in accordance with an aspect of the present disclosure is depicted. As shown in block 102, a route planner can approximate initial map information based on a first feature (such as environmental or behavioral data) selected from a database 104. The feature can take the form of, for example, a geographic region (or other geographic data set), time of day, weather conditions, demographic information, population density, or a given spatio-temporal feature. The data in the first feature can be obtained from the database 104, which can include or be linked to additional publicly available sources, including the Internet or database resources for images, maps, business records, social media sites, data from the crowd, deed registries, drones, or UAV data, etc.

[0015] Although the following description may sometimes describe a geographic region as a feature, those skilled in the art will understand that any one or more other features can alternatively be used. As described herein, the route planner can take the form of a computing device in a vehicle, a cloud server, a mobile device, or any other device (or combination of devices) capable of performing the route planning functions described herein.

[0016] The route planner can generate an initial route based on the approximated map information, as shown in block 106. As shown in block 108, the vehicle can operate along the initial route. As shown in block 110, the vehicle can generate map information of the vehicle's environment. According to one aspect, generating the map information can include, for example, using sensors to collect sensor inputs from one or more sensors and using the sensor inputs (possibly in combination with other data) to generate the map information. The sensors can take the form of LIDAR, RADAR, cameras, optoelectronic sensors, or any combination of these or other sensors, as described in more detail below.

[0017] According to one example, a vehicle can operate based on a feature configured to reduce the uncertainty of the behavior of blockers on a one-way street that is congested in a particular environment. Thus, a route planner can approximate map information based on behavior information selected from a database for a congested one-way street. The route planner can generate an initial route based on the approximated map information to provide a vehicle operating along the initial route with a maximum degree of exposure to the congested one-way street.

[0018] As shown in block 112, while operating along the initial route, the vehicle can also record its own behavior data and obtain the behavior data of blockers (e.g., other vehicles) around the vehicle. Obtaining a dataset of the behavior of other blockers may involve using sensor inputs and other associated data. As the vehicle travels along the route, the obtained behavior and environment datasets can be recorded and transmitted back to the database 104. Due to the increase in the empirical data obtained by the vehicle, the uncertainty level regarding the feature (congested one-way street) may be reduced. Thus, the route planner can reduce the uncertainty of the behavior of other blockers in the geographical area.

[0019] As shown in block 114, the route planner can define a threshold amount of behavior data to be obtained and recorded. If the threshold level of data has not been obtained, then the route planning process can continue to collect environmental and behavior data until the threshold is reached. As shown in block 116, once the threshold is reached, the route planner can select a set of environmental / behavior data (or information having any one or more given features) for a given geographical area from the database 104 such that the data in the selected set generally resembles the environmental / behavior data obtained by the vehicle. For example, the route planner can determine that the driving behavior of blockers in Austin, Texas is similar to the driving behavior of blockers in the vehicle's current geographical area. Example sets of behavioral characteristics that the vehicle can identify include, but are not limited to, behavior at stop signs in the current geographical area, behavior on a given type of road in the current geographical area, behavior on a given type of road anywhere, etc.

[0020] As shown in block 118, the route planner can update the map information based on a dataset selected from the database and a behavioral dataset obtained by the vehicle. The route planner can use the data obtained from the environment / behavior database 104 to update the map information to include a known feature dataset that is very similar to the dataset of the current environment or behavior profile. As shown in block 120, the route planner can also update the current route based on the updated map information. When the vehicle is operating on the updated route, the vehicle can continue to generate map information and obtain the environmental and behavioral information of the environment around the vehicle and the roadblock. Therefore, the iterative process of the route planner allows the vehicle to repeatedly obtain environmental and behavioral information while continuously operating along a more efficient route. Thus, compared with the vehicle continuing to operate on the initial route, the route planner can reduce the uncertainty of the behavior of roadblocks in a geographical area in a more efficient manner (e.g., faster).

[0021] According to one aspect of the present disclosure, the route planner may initially have selected a set of environmental and behavioral information for a city such as Austin, Texas. Although the vehicle is located at another geographical location, the route planner may still estimate that the current environmental and behavioral profile of the roadblock is very similar to the known environmental and behavioral data of the geographical area and roadblock from Austin, Texas. In subsequent iterations, after obtaining additional environmental and behavioral data while the vehicle is operating on the updated route, the route planner can determine that the driving environment and behavior of roadblocks in the current geographical area are actually more similar to the driving behavior of roadblocks in San Diego, California, compared to Austin, Texas. Therefore, the route planner can select the environmental and behavioral dataset of San Diego and can generate an updated route based on the selected data and the behavioral data obtained by the vehicle. The route planner can also split the feature data across multiple known environmental and behavioral datasets. For example, the route planner can determine that the driving behavior of roadblocks in Austin at a stop sign is more similar to that in San Diego, so it can retain the dataset related to "the behavior of roadblocks at a stop sign" from the Austin dataset while updating with respect to other feature sets of San Diego. That is, the datasets for the identified features can be discretely split and applied based on each feature.

[0022] According to one aspect of the present disclosure, the route planner can generate a heat map or a prioritization list that approximately estimates the amount of information obtained by the vehicle from various regions of the map for behavioral information. Therefore, the route planner can subsequently generate a route based on the generated heat map. Figure 2 An illustrative heat map 200 according to one aspect of the present disclosure is depicted. The heat map 200 can be in the form of a geographical area, such as Figure 2The map shown in , or it can be a prioritized list, grid, or other representations known in the art. The heat map 200 can include identified regions, routes, or other objects and locations where the system has a deterministic or non-deterministic level.

[0023] If the vehicle travels along the route or region, assuming a certain amount of known environmental and behavioral information has been obtained, the heat map 200 can approximate the amount of information to be obtained. For example, the heat map 200 can include a route or region identified as the first information gain 202. The region identified or classified according to the first information gain 202 can, for example, indicate that little information is known about the route or region. As described herein, the route planner can utilize this information to avoid such routes or regions due to lack of information. Conversely, given the lack of information in the first information gain 202, the route planner can choose to search for such regions to obtain additional information about the route or region. Similarly, the route planner can use regions identified at other gain levels (including the second information gain 204, the third information gain 206, and the fourth information gain 208) to identify information regions based on the level or amount of information to be obtained by observing the region using the system sensors.

[0024] Although Figure 2 the heat map 200 of is shown as a geographical map with superimposed gain levels, those skilled in the art will recognize that other prioritization and classification mechanisms can be implemented without departing from the scope of the present disclosure.

[0025] Depending on the operating mode of the vehicle, the route planner can choose to search for regions containing known and favorable data to provide a more efficient and convenient route. Alternatively, the route planner can implement a route that avoids regions where the data is known, either because the known data presents adverse route conditions with more uncertainty than regions with unknown data, or because the vehicle is operating in a learning mode to explore and collect additional environmental and behavioral information, regardless of whether the route is favorable.

[0026] Figure 3Illustrative method 300 for generating and using a heat map in accordance with one aspect of the present disclosure is depicted. As shown in block 302, an initial heat map can be generated based on known data from an environment and behavior database 304. The initial heat map and route planning can identify one or more features for which, if additional data were collected, the uncertainty associated with the data for those features would be reduced. For example, the initial heat map can indicate that obtaining loiterer behavior on certain crowded one-way streets can significantly reduce the uncertainty of loiterer behavior in a given environment. By obtaining loiterer behavior on certain bridges at night, a large amount of other uncertainty can also be reduced, but to a lesser extent than for the crowded one-way street feature. As shown in block 306, a route planner can generate an initial route along the crowded one-way street. As shown in block 308, a vehicle can be traveling along the route. As shown in blocks 310 and 312, based on the environment and behavior data obtained from the vehicle operating along the initial route, the route planner can update the heat map, as shown in block 314, to reflect the collection of that data. The route planner can include a threshold determination, as shown in block 316, which determines whether the amount of data collected for a prioritized feature (e.g., a crowded one-way street) is sufficient to reduce the uncertainty associated with that feature below a desired level. If there is not enough data, the vehicle can continue to collect data along the route. The route planner can determine that the amount of data collected for a first feature is sufficient. Thus, since behavioral information has been collected from these areas, the amount of information to be obtained by traveling the crowded one-way street has been significantly reduced. As shown in block 318, the route planner can update the heat map to reflect this reduction in uncertainty. The updated heat map can now indicate that obtaining loiterer behavior on the identified bridges will minimize the uncertainty of loiterer behavior, and the route planner can generate an updated planned route along those bridges, as shown in block 320.

[0027] A set of environment and behavior information (selected from databases 104, 304) having one or more given features need not be data for any discrete concept having those features. For example, the behavioral information can be represented by a feature vector x = [f0, f1, f2, f3, …, f n , where f0 - f n are values for corresponding features—e.g., city, road type, loiterer type, time, weather, etc.—. A difference function f(x1, x2) can output the difference between a first data set (represented by vector x1) and a second data set (represented by vector x2). The difference function can be trained based on previously labeled similarities between corresponding environment and behavior data sets. The difference function can also be used to determine the similarity between an environment and behavior data set in the database and an environment and behavior data set obtained by the vehicle.

[0028] Figure 4FIG. is a diagram illustrating an example of a hardware implementation of a map generation system 400 according to aspects of the present disclosure. The map generation system 400 may be a component of a vehicle, a robotic device, or other device. For example, as Figure 4 shown, the map generation system 400 may be a component of an automobile 428. Aspects of the present disclosure are not limited to the map generation system 400 being a component of the automobile 428, as other devices such as buses, boats, drones, simulators, or robots are also contemplated to use the map generation system 400. The automobile 428 may be autonomous or semi-autonomous.

[0029] The map generation system 400 may be implemented with a bus architecture generally represented by bus 430. The bus 430 may include any number of interconnecting buses and bridges, depending on the specific application of the map generation system 400 and overall design constraints. The bus 430 may link together various circuits including one or more processors and / or hardware modules represented by processor 420, communication module 422, positioning module 418, sensor module 402, locomotion module 426, planning module 424, computer-readable medium 414. The bus 430 may also link together various other circuits such as a timing source, peripherals, voltage regulators, and power management circuits, which are well known in the art and will not be described further herein.

[0030] The map generation system 400 may include a transceiver 416, sensor module 402, map generator 408, environment and behavior (E / B) database 412, communication module 422, positioning module 418, locomotion module 426, planning module 424, and computer-readable medium 414 coupled to processor 420. The transceiver 416 is coupled to antenna 434. The transceiver 416 communicates with various other devices via a transmission medium. For example, the transceiver 416 may receive commands via transmissions from a user or a remote device. As another example, the transceiver 416 may transmit driving statistics and information from the map generator 408 to a server (not shown).

[0031] The map generator 408 may include a processor 420 coupled to the computer-readable medium 414. The processor 420 may perform processing, including executing software stored on the computer-readable medium 414 that provides functions in accordance with the present disclosure. The software, when executed by the processor 420, causes the map generation system 400 to perform various functions described for a particular device such as the automobile 428 or any one of the modules 402, 408, 414, 416, 418, 420, 422, 424, 426. The computer-readable medium 414 may also be used to store data manipulated by the processor 420 when executing the software.

[0032] The sensor module 402 can be used to obtain measurement values via different sensors such as the first sensor 406, the second sensor 404, and the third sensor 410. The first sensor 406 can be a vision sensor for capturing 2D images, such as a stereo camera or a red-green-blue (RGB) camera. The second sensor 404 can be a range sensor, such as a light detection and ranging (LIDAR) sensor or a radio detection and ranging (RADAR) sensor. The third sensor 410 can include an in-cabin camera for capturing raw video or images of the interior environment of the vehicle 428. Of course, aspects of the present disclosure are not limited to the above sensors, as other types of sensors can also be contemplated for either of the sensors 404, 406, such as, for example, thermal, sonar, and / or laser. The measurement values of the sensors 404, 406, 410, 406 can be processed by the processor 420, the sensor module 402, the map generator 408, the communication module 422, the positioning module 418, the motion module 426, the planning module 424 in conjunction with the computer-readable medium 414 to implement the functions described herein. In one configuration, the data captured by the first sensor 406 and the second sensor 404 can be transmitted to an external device via the transceiver 416. The sensors 404, 406, 410 can be coupled to the vehicle 428 or can communicate with the vehicle 428.

[0033] The positioning module 418 can be used to determine the position of the vehicle 428. For example, the positioning module 418 can use the Global Positioning System (GPS) to determine the position of the vehicle 428. The communication module 422 can be used to facilitate communication via the transceiver 416. For example, the communication module 422 can be configured to provide communication capabilities via different wireless protocols such as WiFi, Long Term Evolution (LTE), 3G, etc. The communication module 422 can also be used to communicate with other components of the vehicle 428 that are not the map generator 408.

[0034] The motion module 426 can be used to facilitate the movement of the vehicle 428. As an example, the motion module 426 can control the movement of the wheels. As another example, the motion module 426 can communicate with the power source of the vehicle 428, such as an engine or a battery. Of course, aspects of the present disclosure are not limited to providing movement via wheels, and other types of components for providing movement are contemplated, such as propellers, pedals, fins, and / or jet engines.

[0035] The map generation system 400 may also include a planning module 424 that plans a route or controls the movement of the vehicle 428 via the movement module 426 based on the analysis performed by the map generator 408. In one configuration, the planning module 424 overrides user input when the user input is expected (e.g., predicted) to cause a collision. These modules may be software modules running in the processor 420, residing / stored in the computer-readable medium 414, one or more hardware modules coupled to the processor 420, or some combination thereof.

[0036] The map generator 408 may communicate with the sensor module 402, transceiver 416, processor 420, communication module 422, positioning module 418, movement module 426, planning module 424, and computer-readable medium 414. In one configuration, the map generator 408 may receive sensor data from the sensor module 402. The sensor module 402 may receive sensor data from sensors 404, 406, 410. In accordance with aspects of the present disclosure, the sensor module 402 may filter data to remove noise, encode data, decode data, merge data, extract frames, or perform other functions. In an alternative configuration, the map generator 408 may receive sensor data directly from sensors 404, 406, 410.

[0037] As Figure 4 shown, the map generator 408 may communicate with the planning module 424 and the movement module 426 to generate a roadmap, plan a route, and operate the vehicle 428 based on the generated map. As described herein, the map generator 408 may rely on known environment and behavior data from the E / B database 412 to generate an initial map based on one or more features in the database. As the vehicle 428 progresses along the route, additional environment and behavior data may be obtained from the sensor module 402, movement module 426, etc. The additional data may be used to refine or change the map on which the vehicle 428 is currently operating. The map generator may use the newly obtained information to adapt or update the initial map and, together with the planning module 424, update the route on which the vehicle 428 is operating.

[0038] In accordance with one aspect of the present disclosure, the map generator 408 may also generate a heat map representing one or more levels of uncertainty of the feature data. The heat map may represent various levels of feature data based on how much (or little) data is known about the feature. The planning module 424 may use the heat map generated by the map generator 408 to prescribe a route for the vehicle 428. The planning module 424 may implement the heat map in a variety of ways, as described herein. The planning module 424 may generate a route based on the heat map to avoid areas of high uncertainty when an alternative route through more well-known (low uncertainty) areas is more efficient (i.e., less traffic, faster travel time, etc.).

[0039] Alternatively, the planning module 424 can choose to generate a route to find the areas of high uncertainty identified in the heat map to obtain additional environmental and behavioral data, thereby reducing uncertainty. The planning module 424 can also plan a route through areas of higher uncertainty and avoid areas of low uncertainty, because the feature data in well-known areas is undesirable for an efficient route. For example, a given geographical area may have a low level of uncertainty in terms of traffic congestion and, given other environmental parameters, is likely to indicate traffic congestion. Thus, the planning module 424 can determine a route along and through an area of higher uncertainty (despite the high uncertainty), because the resulting route is estimated to be more efficient than a route through a known area with traffic congestion.

[0040] Based on these teachings, those skilled in the art should recognize that the scope of the present disclosure is intended to cover any aspect of the present disclosure, whether implemented independently of any other aspect of the present disclosure or in combination with any other aspect of the present disclosure. For example, any number of the described aspects can be used to implement a device or practice a method. Additionally, the scope of the present disclosure is intended to cover the use of other structures, functions, or structures and functions including or other than the described aspects of the present disclosure to practice such a device or method. It should be understood that any aspect of the present disclosure can be implemented by one or more elements of the claims.

[0041] The word "exemplary" is used herein to mean "serving as an example, instance, or illustration". Any aspect described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other aspects.

[0042] Although specific aspects are described herein, many variations and permutations of these aspects fall within the scope of the present disclosure. Although some benefits and advantages of the preferred aspects are mentioned, the scope of the present disclosure is not intended to be limited to specific benefits, uses, or purposes. Instead, the aspects of the present disclosure are intended to be widely applicable to different technologies, system configurations, networks, and protocols, some of which are shown by way of example in the following description of the figures and preferred aspects. The detailed description and the drawings are merely illustrative of the present disclosure and not limiting, and the scope of the present disclosure is defined by the appended claims and their equivalents.

[0043] As used herein, the term "determining" encompasses a variety of actions. For example, "determining" can include calculating, computing, processing, deriving, investigating, looking up (e.g., looking up in a table, database, or another data structure), ascertaining, etc. Additionally, "determining" can include receiving (e.g., receiving information), accessing (e.g., accessing data in a memory), etc. Further, "determining" can include parsing, selecting, choosing, establishing, etc.

[0044] As used herein, a phrase referring to "at least one" in a list of items means any combination of those items, including a single member. For example, "at least one of a, b, or c" is intended to cover: a, b, c, a - b, a - c, b - c, and a - b - c.

[0045] The various illustrative logical blocks, modules, and circuits described in connection with the present disclosure can be implemented or performed with a processor specifically configured to perform the functions discussed in the present disclosure. The processor can be a neural network processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array signal (FPGA) or other programmable logic device (PLD), discrete gate or transistor logic, discrete hardware components designed to perform the functions described herein, or any combination thereof. Alternatively, the processing system can include one or more neuromorphic processors for implementing the neuron models and nervous system models described herein. The processor can be a microprocessor, a controller, a microcontroller, or a state machine specifically configured as described herein. The processor can also be implemented as a combination of computing devices, e.g., a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors in conjunction with a DSP core, or such other special configurations as described herein.

[0046] The steps of the methods or algorithms described in connection with the present disclosure may be implemented directly in hardware, in a software module executed by a processor, or in a combination of both. The software modules may reside in a storage or machine-readable medium, including random access memory (RAM), read-only memory (ROM), flash memory, erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disk, removable disk, CD-ROM, or other optical disk storage devices, magnetic disk storage devices, or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and that can be accessed by a computer. The software modules may include a single instruction or multiple instructions and may be distributed over several different code segments, different programs, and across multiple storage media. The storage medium may be coupled to the processor such that the processor can read information from, and write information to, the storage medium. Alternatively, the storage medium may be integral to the processor.

[0047] The methods disclosed herein include one or more steps or acts for implementing the described methods. Without departing from the scope of the claims, the method steps and / or acts may be interchanged with one another. In other words, unless a specific order of steps or acts is specified, the order and / or use of specific steps and / or acts may be modified without departing from the scope of the claims.

[0048] The described functionality may be implemented in hardware, software, firmware, or any combination thereof. If implemented in hardware, then an example hardware configuration may include a processing system in a device. The processing system may be implemented with a bus architecture. The bus may include any number of interconnected buses and bridges, depending on the specific application of the processing system and overall design constraints. The bus may link together various circuits including a processor, a machine-readable medium, and a bus interface. The bus interface may be used to connect, via the bus, a network adapter, among other things, to the processing system. The network adapter may be used to implement signal processing functions. For certain aspects, a user interface (e.g., keypad, display, mouse, joystick, etc.) may also be connected to the bus. The bus may also link together various other circuits, such as a timing source, peripheral devices, voltage regulators, power management circuits, etc., which are well known in the art and will not be described further herein.

[0049] The processor may be responsible for managing the bus and for processing, including the execution of software stored on the machine-readable medium. The software shall be construed to mean instructions, data, or any combination thereof, whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise.

[0050] In a hardware implementation, the machine-readable medium can be part of a processing system separate from the processor. However, as will be readily understood by those skilled in the art, the machine-readable medium or any part thereof can be external to the processing system. For example, the machine-readable medium can include transmission lines, carrier waves modulated by data, and / or computer products separate from the device, all of which can be accessed by the processor via a bus interface. Alternatively or additionally, the machine-readable medium or any part thereof can be integrated into the processor, which can be the case with a cache and / or a dedicated register file. Although the various components discussed may be described as having a specific location, such as local components, they can also be configured in various ways, such as some components being configured as part of a distributed computing system.

[0051] The machine-readable medium can include multiple software modules. The software modules can include a transmission module and a reception module. Each software module can reside in a single storage device or be distributed across multiple storage devices. For example, when a triggering event occurs, the software module can be loaded from a hard disk drive into RAM. During the execution of the software module, the processor can load some instructions into the cache to improve access speed. Then one or more cache lines can be loaded into the dedicated register file for the processor to execute. When referring to the functions of the software modules below, it will be understood that such functions are implemented by the processor when executing instructions from the software module. Additionally, it should be recognized that aspects of the present disclosure improve the functions of the processors, computers, machines, or other systems implementing these aspects.

[0052] If implemented in software, the functions can be stored on or transmitted through a computer-readable medium as one or more instructions or code. The computer-readable medium includes computer storage media and communication media, and the communication media includes any storage media that facilitates the transfer of a computer program from one place to another.

[0053] Furthermore, it should be recognized that modules and / or other suitable components for performing the methods and techniques described herein can be downloaded and / or otherwise obtained by a user terminal and / or a base station as appropriate. For example, such a device can be coupled to a server to facilitate the transfer of components for performing the methods described herein. Alternatively, the various methods described herein can be provided via a storage component such that the user terminal and / or the base station can obtain the various methods when the storage component is coupled or provided to the device. Moreover, any other suitable techniques for providing the methods and techniques described herein to the device can be utilized.

[0054] It should be understood that the claims are not limited to the exact configurations and components shown above. Various modifications, changes, and variations can be made to the arrangements, operations, and details of the above methods and apparatuses without departing from the scope of the claims.

Claims

1. A method for planning a route of a vehicle, the method comprising: Generating a first map based on a first dataset of features in a database, the first map being a heat map representing the uncertainty level of the first dataset of features, the database including multiple datasets of features; Generating a first route based on the first map; Collecting vehicle operation data as a second dataset of features; Comparing the second dataset of features with the multiple datasets of features in the database; And Updating the first map to a second map based on the similarity between the second dataset of features and a third dataset of features in the database.

2. The method according to claim 1, wherein the multiple datasets of features include environmental data, and the environmental data includes a dataset associated with a geographical area.

3. The method according to claim 1, wherein the feature The multiple datasets include roadblocker behavior data.

4. The method according to claim 1, wherein the vehicle operation data includes environmental data.

5. The method according to claim 1, further comprising updating the first route to a second route based on the second map.

6. The method according to claim 1, further comprising collecting vehicle operation data until a threshold is met, and once the collected vehicle operation data exceeds the threshold, the first map is updated to the second map.

7. The method according to claim 1, wherein the method further comprises: Collecting vehicle operation data until an uncertainty threshold is met, and once the collected vehicle operation data exceeds the uncertainty threshold, the heat map is updated to the second map; Updating the first route to a second route based on the uncertainty level of the second dataset of features.

8. A system for generating a vehicle route, the system comprising: A database including multiple datasets of features; A map generator configured to generate a first map based on a first dataset of features in the database, the first map being a heat map representing the uncertainty level of the first dataset of features; A planning module configured to generate a first route based on the first map, and At least one sensor configured to collect vehicle operation data as a second dataset of features; A processor configured to: Compare the second dataset of features with the multiple datasets of features in the database; and Update the first map to a second map based on the similarity between the second dataset of features and a third dataset of features in the database.

9. The system according to claim 8, wherein the system includes an autonomous vehicle.

10. The system according to claim 8, wherein the feature The multiple datasets include environmental data, and the environmental data includes a dataset associated with at least one of a geographical area, a time of day, and weather.

11. The system according to claim 8, wherein the feature The multiple datasets include roadblocker behavior data.

12. The system according to claim 8, wherein the vehicle operation data includes environmental data.

13. The system according to claim 8, wherein the processor is further configured to update the first route to a second route based on the second map.

14. The system according to claim 8, wherein the at least one sensor is configured to collect vehicle operation data until a threshold is met, and once the collected vehicle operation data exceeds the threshold, the first map is updated to the second map.

15. The system according to claim 8, wherein the at least one sensor is configured to collect vehicle operation data until an uncertainty threshold is met, and once the collected vehicle operation data exceeds the uncertainty threshold, the heat map is updated to the second map.

Images