Systems and methods for localizing vehicle using accuracy specification

Abstract

To provide systems and methods for localizing a vehicle in an environment.SOLUTION: A system for localizing a vehicle in an environment has: a first map data that defines features within an environment used to localize a vehicle within the environment; and a machine-readable instruction set. The machine-readable instruction set causes the computing device to: determine a portion of the first map data having a first type of road; determine a first accuracy specification for the first type of road, where the first accuracy specification identifies one or more features of the plurality of features defined in the first map data used to localize a vehicle traversing the first type of road within a predefined degree of accuracy; and create a second map data for the first type of road.SELECTED DRAWING: Figure 5

Description

[Technical field]

[0001] Technical Field FIELD OF THE DISCLOSURE This disclosure relates generally to systems and methods for locating a vehicle, and more particularly, to systems and methods for locating a vehicle within an environment with an accuracy specification. [Background technology]

[0002] background Autonomous driving systems, ranging from lane-keeping assistance systems to fully automated driving systems, utilize sensor inputs, map data, and other data sets to autonomously control a vehicle. To account for unpredictable and unknown variables that may occur during a driving event, autonomous driving systems utilize large amounts of sensor input data, map data, and data sets to develop control plans. This results in a need for large amounts of computational resources, which increases the complexity and cost of the autonomous driving system. However, the autonomous driving system may be able to operate in some cases by processing only a subset of the available data. Summary of the Invention

[0003] overview In one embodiment, a system for locating a vehicle within an environment includes a computing device including a processor and a non-transitory computer readable memory, first map data stored in the non-transitory computer readable memory, the first map data defining a plurality of features within the environment that are used to locate a vehicle within the environment, and a set of machine readable instructions stored in the non-transitory computer readable memory. The set of machine readable instructions, when executed by the processor, causes the computing device to at least: determine a portion of the first map data having roads of a first type; determine a first accuracy specification for the roads of the first type, the first accuracy specification identifying one or more features of the plurality of features defined in the first map data that are used to locate the vehicle passing over the roads of the first type within a predetermined accuracy; and create second map data for the roads of the first type, the second map data including the one or more features defined by the first accuracy specification, the second map data including a reduced number of features for locating the vehicle compared to the first map data.

[0004] In another embodiment, a system for localizing a vehicle in an environment includes a computing device including a processor and a non-transitory computer readable memory; first map data stored in the non-transitory computer readable memory, the first map data including one or more features defined by a first accuracy specification for locating a vehicle passing through a first type of road; second map data stored in the non-transitory computer readable memory, the second map data including one or more features defined by a second accuracy specification for locating the vehicle passing through a second type of road, the second type of road being different from the first type of road; and a set of machine readable instructions stored in the non-transitory computer readable memory. The set of machine-readable instructions, when executed by the processor, causes the computing device to at least determine whether the vehicle is deemed to be traversing the first type of road or the second type of road, locate the vehicle using the second map data when the vehicle is deemed to be traversing the first type of road, and locate the vehicle using the third map data when the vehicle is deemed to be traversing the second type of road.

[0005] In yet another embodiment, a method for localizing a vehicle within an environment includes determining a portion of first map data having roads of a first type, determining a first accuracy specification for the roads of the first type, the first accuracy specification identifying one or more features for locating the vehicle passing through the roads of the first type, creating second map data for the roads of the first type, the second map data including the one or more features defined by the first accuracy specification, determining if the vehicle is passing through the roads of the first type, and locating the vehicle using the second map data when the vehicle is deemed to be passing through the roads of the first type.

[0006] These and additional features provided by the embodiments described in the present disclosure will be more fully understood in view of the following detailed description, taken in conjunction with the drawings.

[0007] BRIEF DESCRIPTION OF THE DRAWINGS The embodiments set forth in the drawings are illustrative and exemplary in nature and are not intended to limit the subject matter defined by the claims. The following detailed description of illustrative embodiments can be understood when read in conjunction with the following drawings, in which like structure is labeled with like reference numerals, and in which: [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 illustrates generally a system for locating a vehicle within an environment according to one or more embodiments (s) shown and described in this disclosure.

[0009] [Diagram 2]FIG. 2 illustrates, in a schematic manner, various elements of a computing device of the system of FIG. 1, in accordance with one or more embodiments shown and described in this disclosure.

[0010] [Diagram 3] FIG. 3 is a top-down view of a vehicle having sensors for sensing an environment around the vehicle according to one or more embodiments shown and described in this disclosure.

[0011] [Figure 4] FIG. 4 is a diagram illustrating a vehicle equipped with a sensor for sensing an environment surrounding the vehicle, according to one or more embodiments shown and described in this disclosure.

[0012] [Diagram 5] FIG. 5 is a flow diagram illustrating a method for locating a vehicle using an accuracy specification according to one or more embodiments shown and described in this disclosure.

[0013] [Figure 6] FIG. 6 depicts an example environment of a street generated by a sensor on a vehicle, according to one or more embodiments shown and described in this disclosure.

[0014] [Figure 7] FIG. 7 depicts an example environment of a highway generated by sensors on a vehicle, according to one or more embodiments shown and described in this disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0015] Detailed Description The embodiments disclosed in this disclosure include systems and methods for locating a vehicle in an environment with accuracy specifications. Locating a vehicle in an environment is an important feature for many autonomous driving systems. Typically, a global positioning system (GPS) is implemented to locate the vehicle. However, GPS may be prone to errors, for example, in urban environments, or may lack the granularity required to provide precise vehicle control. To improve vehicle location, many autonomous driving systems, which may include systems ranging from collision avoidance and driver assistance systems to fully autonomous controlled vehicles, utilize many sensors and many types of sensors positioned to detect features in the environment around the vehicle. To provide a high level of accuracy and precision in locating the vehicle in the environment, the detected features may be analyzed, categorized, and / or compared to known features from map data. To achieve these high levels of accuracy and precision, complex and computationally intensive systems may be required. However, autonomous vehicles do not always require the same high levels of accuracy and precision to locate the vehicle in all environments. For example, when an autonomous vehicle is traveling or driving along a highway, there may be less need to precisely locate the longitudinal progress of the vehicle, but it may be necessary to precisely and precisely locate the lateral activity of the vehicle to keep the vehicle from straying from its travel lane. Thus, the systems and methods described and illustrated in this disclosure provide systems and methods that can better utilize and reduce computational resource consumption for locating the vehicle by implementing accuracy specifications for vehicles that may be traversing particular types of roads, performing particular driving actions, etc. By better utilizing and reducing computational resource consumption for locating the vehicle as defined within the accuracy specifications, system resources may be utilized for other tasks, or may even be eliminated, thereby reducing the cost and complexity of the autonomous driving system.

[0016] With general reference to the figures, the systems and methods include one or more sensors, including, for example, one or more cameras, a GPS system, a LIDAR system, and a RADAR system, coupled to a computing device having a processor, a non-transitory computer-readable memory, and a machine-readable instruction set. In some embodiments, the machine-readable instruction set causes the processor to at least determine one or more types of roads in the map data and determine an accuracy specification for the one or more types of roads. Based on the accuracy specification, a portion of the map data for the type of road may be refined, or new map data for the type of road may be created, thereby reducing the number of features and / or sensor inputs required to locate a vehicle passing through the type of road. The systems and methods disclosed herein may then implement the new map data for locating the vehicle as it passes through a particular type of road. Thus, the system may transition between different map data stored in the non-transitory computer-readable memory as the vehicle passes through different types of roads and / or performs various driving actions. Various systems and methods for locating a vehicle within an environment with accuracy specifications will be described in more detail herein with specific reference to the corresponding drawings.

[0017] Referring now to the drawings, in particular to FIG. 1 , where like numbers indicate like structure, a system 100 for locating a vehicle 110 is depicted. The system 100 generally includes a communication path 120, a computing device 130 including a processor 132 and non-transitory computer readable memory 134, one or more cameras 140, a global positioning system (GPS) 150, a LIDAR system 152, a RADAR system 154, and network interface hardware 160. The vehicle 110 is communicatively coupled to a network 170 via the network interface hardware 160. The components of the system 100 may be stored within or assembled to the vehicle 110. The various components of the system 100 and their interactions are described in more detail below.

[0018] The communication path 120 may be formed of any medium capable of transmitting a signal, such as, for example, a conductor, a conductive trace, an optical waveguide, etc. The communication path 120 may also refer to an expanse through which electromagnetic radiation and its corresponding electromagnetic waves pass. Furthermore, the communication path 120 may be formed of a combination of media capable of transmitting a signal. In one embodiment, the communication path 120 includes a combination of conductive traces, conductors, connectors, and buses that cooperate to enable transmission of electrical data signals to components such as processors, memories, sensors, input devices, output devices, and communication devices. Thus, the communication path 120 may include a bus. Furthermore, it is pointed out that the term "signal" refers to a waveform (e.g., electrical, optical, magnetic, mechanical, or electromagnetic), such as DC, AC, sine wave, triangle wave, square wave, vibration, etc., capable of traveling through a medium. The communication path 120 communicatively couples the various components of the system 100. As used in this disclosure, the term "communicatively coupled" means that the coupled components have the ability to exchange signals with each other, such as, for example, electrical signals through a conductive medium, electromagnetic signals through the air, optical signals through an optical waveguide, etc.

[0019] 1, computing device 130 may be any device or combination of components including processor 132 and non-transitory computer-readable memory 134. Processor 132 of system 100 may be any device capable of executing a set of machine-readable instructions stored in non-transitory computer-readable memory 134. Thus, processor 132 may be an electrical controller, an integrated circuit, a microchip, a computer, or any other computing device. Processor 132 is communicatively coupled to other components of system 100 by communication path 120. Thus, communication path 120 may communicatively couple any number of processors 132 to each other as well as enable components coupled to communication path 120 to operate in a distributed computing environment. In particular, each component may operate as a node that may transmit and / or receive data. Although the embodiment depicted in FIG. 1 includes a single processor 132, other embodiments may include two or more processors 132.

[0020] The non-transitory computer readable memory 134 of the system 100 is coupled to the communication path 120 and communicatively coupled to the processor 132. The non-transitory computer readable memory 134 may include RAM, ROM, flash memory, a hard drive, or any non-transitory memory device capable of storing machine readable instructions such that the processor 132 can access and execute the machine readable instructions. The machine readable instruction set may include logic or algorithm(s) written in any programming language of any generation (e.g., 1GL, 2GL, 3GL, 4GL, or 5GL), such as a machine language that may be directly executed by the processor 132, or an assembly language, object oriented programming (OOP), scripting language, microcode, etc. that may be compiled or assembled into machine readable instructions and stored in the non-transitory computer readable memory 134. Alternatively, the machine-readable instruction set may be written in a hardware description language (HDL), such as logic implemented via either a field programmable gate array (FPGA) configuration or an application specific integrated circuit (ASIC) or their equivalents. Thus, the functionality described in this disclosure may be implemented in any conventional computer programming language, as pre-programmed hardware elements, or as a combination of hardware and software components. Although the embodiment depicted in FIG. 1 includes a single non-transitory computer-readable memory 134, other embodiments may include two or more memory modules.

[0021] Still referring to FIG. 1 , one or more cameras 140 are coupled to the communication path 120 and communicatively coupled to the processor 132. The one or more cameras 140 may be any device having an array of sensing devices capable of detecting radiation in the ultraviolet, visible, and / or infrared wavelength ranges. The one or more cameras 140 may have any resolution. The one or more cameras 140 may be omnidirectional or panoramic cameras. In some embodiments, one or more optical components, such as mirrors, fisheye lenses, or any other type of lens, may be optically coupled to each of the one or more cameras 140. In embodiments described in this disclosure, the one or more cameras 140 may capture image data of the environment outside the vehicle 110 and provide the images to the computing device 130. The one or more cameras 140 may be positioned inside or on the vehicle 110 to view the environment outside the vehicle 110. For example, without limitation, the one or more cameras 140 may be positioned on the dashboard of the vehicle 110 to capture images of the surroundings in front of the vehicle 110 during operation. The location of the one or more cameras 140 is not limited to the dashboard of the vehicle 110. The one or more cameras 140 may be positioned anywhere on or within the vehicle 110 to capture images of the surroundings of the vehicle 110 during operation.

[0022] During operation, one or more cameras 140 capture image data and transmit the image data to the computing device 130. The image data may be received by the processor 132, which may process the image data using one or more image processing algorithms. Any known or yet to be developed video and image processing algorithms may be applied to the image data to identify an item in the environment and determine the location of an item relative to other items. Exemplary video and image processing algorithms include, without limitation, kernel-based tracking (mean shift tracking) and contour processing algorithms. In general, the video and image processing algorithms may detect objects and motion from consecutive or separate frames of image data. One or more object recognition algorithms may be applied to the image data to estimate three-dimensional objects and determine their relative locations to each other. For example, structure from motion (SfM), a photogrammetric range imaging technique for estimating three-dimensional structures from image sequences, may be used. Additionally, any known or yet to be developed object recognition algorithms may be used to extract objects, edges, dots, bright spots, gray spots, and even optical properties and / or image fragments from the image data. For example, object recognition algorithms include, but are not limited to, scale invariant feature transform ("SIFT"), speed up robust features ("SURF"), and edge detection algorithms.

[0023] 1, a Global Positioning System, GPS system 150 is coupled to the communication path 120 and communicatively coupled to the computing device 130. The GPS system 150 has the capability of generating location information representative of the location of the vehicle 110 by receiving one or more GPS signals from one or more GPS satellites. The GPS signals communicated to the computing device 130 via the communication path 120 may include location information including National Marine Electronics Association (NMEA) messages, latitude and longitude data sets, street addresses, names of known places based on a place database, and the like. Additionally, the GPS system 150 may be compatible with any other system capable of generating an output representative of a location. For example, a local positioning system that provides location based on cellular signals and broadcast towers, or a radio signal detection device that has the capability of triangulating a location via radio signals received from one or more radio signal antennas.

[0024] In some embodiments, the system 100 can include a light detection and ranging (LIDAR) system 152. The LIDAR system 152 is communicatively coupled to the communication path 120 and the computing device 130. The LIDAR system 152 uses pulsed laser light to measure distances from the LIDAR system 152 to objects that reflect the pulsed laser light. The LIDAR system 152 can be fabricated as a solid-state device with few or no moving parts, including those configured as optical phased array devices whose prism-like action allows for a wide field of view without the weight and size complexities associated with conventional rotating LIDAR systems 152. The LIDAR system 152 is highly suitable for time-of-flight measurements that can be correlated with distance measurements to objects within the field of view of the LIDAR system 152. A digital 3D representation (e.g., a point cloud representation) of a target or environment can be generated by calculating the difference in return times of various wavelengths of pulsed laser light emitted by the LIDAR system 152. The pulsed laser light emitted by the LIDAR system 152, in one form, may operate in or near the infrared range of the electromagnetic spectrum, emitting radiation at approximately 905 nanometers in one example. Using sensors such as the LIDAR system 152, the vehicle 110 can provide detailed 3D spatial information for identification of objects near the vehicle 110, and such information can be used in the service of the system for vehicle mapping, navigation and autonomous operation, particularly when coupled with a georeferencing device, such as a GPS system 150 or a gyroscope-based inertial navigation unit (INU, not shown) or related dead reckoning system, and non-transitory computer readable memory 134 (itself or the memory 130 of a computing device).

[0025] In some embodiments, the one or more sensors of the system 100 may include a RADAR system 154. The RADAR system 154 is communicatively coupled to the communication path 120 and the computing device 130. A RADAR system is a system that employs a method of using radio waves to determine the range, angle, and relative speed of an object. The RADAR system 154 may be used in conjunction with one or more cameras 140, ultrasonic, LIDAR system 152, or other sensors to obtain information about the vehicle's surrounding environment. Data from the RADAR system 154 may be processed to improve the level of object identification and decision-making, allowing an autonomous system within the vehicle to determine or distinguish, for example, whether a driver is drifting into an adjacent lane or intentionally leaving space. The need for this information has led to a significant increase in the number of automobiles manufactured with one or more radar systems. For example, autonomous driving systems such as blind spot detection, lane change assistance, front / rear cross traffic alert, autonomous emergency braking, and adaptive cruise control may rely on data from the RADAR system 154.

[0026] RADAR systems 154 generally utilize frequencies within the 24 GHz band in both narrowband and ultra-wideband unregulated spectrum. However, new spectrum regulations are inhibiting the use of the 24 GHz band, and thus some systems may currently utilize frequencies within the 77-81 GHz band. While these bands are typically used in automotive RADAR systems, the scope of the systems and methods described in this disclosure is not limited to these frequency ranges. Generally, RADAR systems 154 emit a high energy ping and measure the time it takes to receive a reflection. However, some systems implement a frequency modulated continuous wave that transmits a "chirp," a frequency sweep that passes through the bandwidth of the system. Objects in the signal path then reflect this chirp back. The difference between the frequency of the chirp coming from the transmitter and the frequency of the received reflected signal is linearly related to the distance from the transmitter to the object at any one time.

[0027] Locating a vehicle using a RADAR system 154 depends in part on the resolution and accuracy of this distance measurement. Resolution determines how far apart objects need to be before they are distinguishable as two objects. Accuracy is just the accuracy of the distance measurement. Distance measurement error and minimum resolvable distance are inversely proportional to the bandwidth of the chirp. Due to the width of available frequencies, for example, moving from 24 GHz to 77 GHz can achieve 20 times better performance in range resolution and accuracy. The range resolution of a 77 GHz system can be 4 cm compared to 75 cm for a 24 GHz radar, which can allow for better detection of multiple objects close together.

[0028] 1 depicts a RADAR system 154, some systems 100 described in this disclosure may not include a RADAR system 154. Alternatively, the system 100 may include multiple RADAR systems 154 positioned at various locations on the vehicle to detect objects in the vehicle's environment at various fields of view. Additionally, it should be understood that references in this disclosure to a "sensor" may refer to any one of the sensors discussed above, one or more cameras 140, a GPS system 150, a LIDAR system 152, a RADAR system 154, or any other sensor known to one of ordinary skill in the art for implementing an autonomous driving system.

[0029] 1, system 100 may include network interface hardware 160 coupled to communication path 120 and communicatively coupled to computing device 130. Network interface hardware 160 may be any device capable of transmitting and / or receiving data over network 170. Thus, network interface hardware 160 may include a communication transceiver for transmitting and / or receiving any wired or wireless communication. For example, network interface hardware 160 may include an antenna, a modem, a LAN port, a Wi-Fi card, a WiMax card, mobile communication hardware, near-field communication hardware, satellite communication hardware, and / or any wired or wireless hardware for communicating with other networks and / or devices. In one embodiment, network interface hardware 160 includes hardware configured to operate according to the Bluetooth® wireless communication protocol. In another embodiment, network interface hardware 160 may include a Bluetooth® transmit / receive module for transmitting and receiving Bluetooth® communications to network 170. Network interface hardware 160 may also include a radio frequency identification ("RFID") reader configured to interrogate and read RFID tags.

[0030] In some embodiments, system 100 may be communicatively coupled to nearby vehicles and / or other computing devices via network 170. In some embodiments, network 170 is a personal area network utilizing Bluetooth technology to communicatively couple system 100 and nearby vehicles. In other embodiments, network 170 may include one or more computer networks (e.g., personal area networks, local area networks, or wide area networks), cellular networks, satellite networks, and / or global positioning systems, and combinations thereof. Thus, system 100 may be communicatively coupled to network 170 via wires, wide area networks, local area networks, personal area networks, cellular networks, satellite networks, and the like. Suitable local area networks may include wired Ethernet and / or wireless technologies, such as Wi-Fi. Suitable personal area networks may include wireless technologies, such as IrDA, Bluetooth, wireless USB, Z-Wave, ZigBee, and / or other short-range wireless communication protocols. Suitable personal area networks may also include wired computer buses, such as USB and Fire Wire. Suitable cellular networks include, but are not limited to, technologies such as LTE, WiMAX, UMTS, CDMA, and GSM.

[0031] 1 , as discussed above, a network 170 may be utilized to communicatively couple the system 100 with nearby vehicles. The nearby vehicles may include a computing device 130 having a non-transitory computer-readable memory 134 and a processor 132, as well as network interface hardware 160, capable of being communicatively coupled with the system 100. The processor 132 of the nearby vehicle may execute a set of machine-readable instructions stored in the non-transitory computer-readable memory 134 to communicate with the system 100.

[0032] Referring now to FIG. 2, elements of a computing device 130 are depicted. As illustrated, the computing device 130 includes a processor 132 and a non-transitory computer-readable memory 134. Additionally, the processor 132 and the non-transitory computer-readable memory 134 communicate over a local communication interface 139 within the computing device 130. In some embodiments, the computing device 130 may include additional elements not illustrated in FIG. 2, such as, without limitation, input / output hardware, network interface hardware, and / or other data storage components. The non-transitory computer-readable memory 134 may store map data 135, accuracy specifications 136, feature libraries 137, and logic 138. The map data 135 may include one or more sets of map data 135. The map data 135 may be a compilation of feature-based maps and / or point cloud data of an environment, such as a city, town, state, country, or part of a road, or a region of a country. Map data 135 may include a data representation of an environment in which vehicle 110 may navigate. For example, one particular map data 135 may include a road map for a particular city. The map may include features that may be detectable by one or more sensors provided on vehicle 110. Analysis of data from one or more sensors on vehicle 110 and comparison to features within map data 135 may be used to locate vehicle 110 within the environment.

[0033] The non-transitory computer-readable memory 134 may also include an accuracy specification 136. The accuracy specification 136 defines features to include in the particular map data 135 for a particular type of road and / or driving action that the system may require to locate the vehicle in the environment. For example, the accuracy specification 136 may determine that the map data 135 for a certain type of road, e.g., a highway, includes lane boundary and sign features to adequately locate the vehicle 110 passing through the highway. That is, features such as vegetation, buildings, and curbs may not need to be identified using sensors to locate a vehicle traveling on the highway. Thus, the non-transitory computer-readable memory 134 may include a feature library that defines one or more feature classes. The feature library 137 may include feature definitions such that they can be semantically segmented from the sensor data and labeled in the map data to locate the vehicle 110. For example, a feature library may include definitions for features such as, but not limited to, signs, lane boundary lines, buildings, traffic lights and stop lines, parking spaces, curbs and barriers, vegetation, street markings (e.g., passing footpaths, railroad crossings, or turn arrows), etc.

[0034] Additionally, the non-transitory computer-readable memory 134 may include logic 138 that, when executed, causes the processor 132 of the computing device or other components of the system 100 to perform steps of the methods described in this disclosure. For example, the non-transitory computer-readable memory 134 may include one or more sets of machine-readable instructions for performing the methods, which are described in more detail in this disclosure.

[0035] The following sections describe embodiments of the operation of system 100 for locating vehicle 110 within an environment. In some embodiments of system 100, system 100 includes a computing device 130 having a processor 132 and non-transitory computer-readable memory 134, one or more cameras 140 communicatively coupled to computing device 130, a GPS system 150, a LIDAR system 152, and a RADAR system 154. In some embodiments, system 100 includes additional sensors and systems described in this disclosure.

[0036] Referring now to FIG. 3, a top-down view of a vehicle 110 equipped with multiple sensors is illustrated. The vehicle 110 is an exemplary embodiment of a vehicle 110 having sensors from the system 100. The vehicle 110 includes cameras 140a, 140b, 140c, 140d, and 140e (each of which is one of the one or more cameras 140), each illustrated with an exemplary field of view. The vehicle 110 includes a GPS system 150 and a LIDAR system 152 positioned on the roof of the vehicle 110. By positioning the LIDAR system 152 on the roof of the vehicle 110, for example as illustrated in FIG. 3, the LIDAR system 152 may have up to a 360 degree field of view 252' of the environment around the vehicle 110. However, in some embodiments, one or more LIDAR systems 152 may be positioned at various locations on the vehicle 110 to capture different perspectives of the environment. Additionally, the vehicle 110 includes a RADAR system with RADAR sensors 154a, 154b, 154c, 154d, 154e, and 154f (each of which is part of the RADAR system 154) positioned at various locations on the vehicle 110. The RADAR sensors 154a-154f are also depicted with fields of view to depict example detection areas for each RADAR sensor 154a-154f. However, in some embodiments, the vehicle 110 may not include a RADAR system.

[0037] As illustrated in FIG. 3, an exemplary deployment of sensors on the vehicle 110 includes many sensors with overlapping fields of view. Thus, in some embodiments, the autonomous driving system may receive more than one signal from more than one sensor for the same region of the environment around the vehicle 110. In some cases, redundancy of data and signals from more than one sensor covering the same region of an environment may not improve the accuracy of the autonomous driving system or may not be necessary for certain driving actions and / or traversal of certain types of roads. In fact, analysis of data from sensors covering the same region may increase the computational load required by the system 100 to locate the vehicle 110 within the environment. To address this computational load, the system 100 may suppress data from one or more sensors through the accuracy specification 136, or the system 100 may not use data from one or more sensors to determine the location of the vehicle 110 within the environment.

[0038] 4, an exemplary embodiment is depicted in which the system 100 constrains the number of sensors used to locate the vehicle 110 in the environment. The vehicle 110 is depicted, for example, passing through a road. For example, the road may be a highway along which the vehicle 110 is to travel in the same lane. As a result, the location of the vehicle 110 may be determined based on lane boundary features captured by a camera 140a having a field of view 140a′ of the highway in front of the vehicle 110, including image data of the lane boundary lines 402 and 404. Thus, although the camera 140b also includes a field of view 140b′ in front of the vehicle 110, the image data from the camera 140b may not include the lane boundary lines 402 and 404 and thus may not be required to locate the lateral position and motion of the vehicle 110. The accuracy specification 136 may define which features in the environment are required to locate the vehicle traveling along the highway. For example, because locating a vehicle 110 traveling along a highway requires high accuracy for lateral position and movement (i.e., staying in a particular lane on the highway) and relatively low accuracy for longitudinal position and movement (e.g., how far the vehicle has traveled along the highway), accuracy specifications 136 may be defined to reduce or eliminate dependency on sensors to provide signals and data for locating the longitudinal position and movement of the vehicle 110. For example, to locate the vehicle 110 passing along the highway, it may only be necessary to receive and / or analyze image data from camera 140a. In some embodiments, until high accuracy is required for locating the vehicle 110 in its longitudinal position, data from GPS system 150 may be sufficient to provide a location of the longitudinal position and movement of the vehicle 110.

[0039] While FIG. 4 and the above example depict and describe an embodiment in which the vehicle 110 traverses a highway, it should be understood that other types of roads and / or driving actions may have accuracy specifications 136 defined to reduce dependency on one or more sensors and the associated signals and data provided by those sensors to locate the vehicle 110 within the environment.

[0040] In some embodiments, the system 100 may reduce the computational load used to locate the vehicle by creating or adjusting the map data 135 to have a reduced number of features based on the accuracy specification 136. The accuracy specification 136 determines which features in the map data are necessary to locate the vehicle while traveling on a particular type of road and / or during a particular driving action, such as finding an exit ramp and exiting a highway. For example, a sensor may detect a sign and provide a signal and data to the computing device 130 indicating the detection of the sign, however, if the map data that the computing device is currently utilizing to locate the vehicle does not include the sign feature, the sign may be ignored as irrelevant to the location process. Thus, computational resources that might have been used to identify signs in the map data and update the vehicle's location based on the detection of the sign may be preserved for other processes.

[0041] Turning now to Figure 5, a flow chart 500 is depicted illustrating a method for locating a vehicle using an accuracy specification. The flow chart 500 depicted in Figure 5 is a representation of a set of machine readable instructions stored in non-transitory computer readable memory 134 and executed by processor 132 of computing device 130. The process of flow chart 500 of Figure 5 may be executed at various times and / or in response to a determination that the vehicle is traversing a particular type of road.

[0042] At step 510, the computing device 130 receives map data. The computing device 130 may receive the map data from a variety of sources. In some embodiments, the map data 135 may be stored in a non-transitory computer-readable memory 134 and accessed by the system 100. In some embodiments, the map data 135 may be generated by one or more sensors coupled to the vehicle or transmitted to the computing device 130 from a remote computing device via the network 170. Once the map data is received, at step 512, the computing device 130 may determine a portion of the first map data that has a first type of road. The first map data may be a comprehensive feature-based map set. The first map data may be compiled using a point cloud representation of the environment, an image-based representation of the environment, or a combination of the two to define one or more features in the environment.

[0043] In step 514, an accuracy specification is determined. The accuracy specification may define one or more features required to locate a vehicle in an environment having a first type of road. In some embodiments, the first type of road may be a highway, a street, a parking lot, a country road, or any other type of road that a vehicle may traverse. The one or more features in the map data may include signs, lane boundaries, buildings, traffic lights and stop lines, parking spaces, curbs and barriers, vegetation, road level markings (e.g., sidewalks, railroad crossings, or turn arrows), and the like. Signs may include anything posted along a road that indicates information to a vehicle or driver. For example, signs may include stop signs, mileposts, road signs, highway bulletin boards, and the like. The accuracy specification may be defined by a user who enters the details of this specification into the memory of the computing device 130. However, in some embodiments, the accuracy specification may be developed from empirical rules gained through driving events along a certain type of road. In some embodiments, for example, in step 516, computing device 130 may further determine accuracy specifications to correspond to learned or upcoming driving actions associated with a particular type of road. For example, if a driver has a tendency to make turns along a particular type of road, the accuracy specifications may include features to improve the accuracy of the location location should the driver decide to make a turn.

[0044] As another example, in a fully autonomous vehicle, route directions including a starting location and a destination may be input. Based on the map data, the computing device 130 may determine a route, and then one or more accuracy specifications for portions of the route may be determined based on one or more driving actions (e.g., vehicle operations required to traverse a portion of the route) and one or more types of roads that the vehicle will traverse during the route. In other embodiments where the route may be unknown, driving actions that bind to accuracy specifications for a type of road may be determined based on commonly performed vehicle operations that are associated with that type of road, and even from past driving history. For example, the computing device 130 may determine that the current route is from home to work, and then the computing device 130 may predict driving actions that will occur along the route and update or generate the accuracy specifications in response.

[0045] In step 518, the computing device 130 creates new map data (e.g., second map data) or updates the portion of the first map data having the first type of road based on the accuracy specification. For example, the second map data includes one or more features defined by the accuracy specification for the first type of road. In step 520, the computing device 130 determines whether there are additional types of roads in the first map data. For example, when there are additional portions of the first map data having another type of road that can be improved to reduce the computational load in locating a vehicle passing through that type of road, the computing device 130 identifies the next type of road in step 522 and then determines the accuracy specification for that type of road in step 514. However, when there are no additional types of roads that can be improved to reduce the computational load in locating a vehicle passing through that type of road, the process continues to step 524. However, in some embodiments, the process may end until the vehicle begins to actively use the map data for location. In step 524, computing device 130 may determine the type of road the vehicle is traversing. For example, computing device 130 may determine when the vehicle transitions from one type of road to another type of road, such as from an exit ramp from a highway to a street. For each type of road that the vehicle traverses, computing device 130 may select and utilize map data corresponding to that type of road to locate the vehicle in step 526. As a result, computing device 130 may reduce the computational burden in locating the vehicle because the map data for a given type of road may include a reduced or improved set of features specific to locating a vehicle along that type of road.

[0046] Referring to FIG. 6 as an example, a computing device 130 may utilize first map data for a vehicle passing through a street. FIG. 6 illustrates an example of image data captured by one or more cameras 140 on the vehicle 110 with features defined in the first map data. Because lateral and longitudinal positions and movements within a city need to be determined with high accuracy, the first map data may include many features for locating the vehicle. For example, accuracy specifications for a street-type road may include signs 608, lane boundaries 612, buildings 614, traffic lights and stop lines 604 and 606, parking spaces (not depicted), curbs and barriers 610, vegetation 616 and 618, and road-level markings (e.g., sidewalks, turn arrows, etc.). However, features such as vegetation 616 and 618 may be unnecessary. This is because the environment along the street may not include a lot of vegetation 616 and 618, or the vegetation 616 and 618 may not be distinctive enough to facilitate localization of a vehicle on the street based on the vegetation 616 and 618, such as trees and bushes.

[0047] In some embodiments, the system 100 may capture image data from one or more cameras 140 while the vehicle 110 passes through a street, such as that depicted in FIG. 6. The system may further identify features in the image data using the first map data. The identification of the features may be used to locate the vehicle 110 within the environment. If the first map data does not include definitions for features such as vegetation 616 and 618, the system 100 may not identify or associate such features to reduce consumption of computational resources.

[0048] However, when the vehicle leaves a street and enters, for example, a highway, the computing device 130 transitions the system 100 from relying on the first map data to relying on the second map data defined by a different accuracy specification for locating the vehicle along the highway. FIG. 7 illustrates an example of image data captured by one or more cameras 140 on the vehicle 110 with features defined in the second map data. The second map data may include fewer features for locating the vehicle than the first map data, since the accuracy for longitudinal position and motion may be reduced. For example, the accuracy specification defining the second map data for a highway type road may include only features such as lane boundaries 702, 704, 706 and 708, curbs and barriers 710, and milepost markers 712. That is, some features, such as buildings, may no longer be relevant for locating the vehicle on the highway. Although these features may be captured by sensors on the vehicle 110, they may not provide relevant information for locating the vehicle passing along the highway. Thus, rather than wasting computational resources to calculate a vehicle localization that takes the detection of a building by one of the sensors and combines it with the map data, the accuracy specification may state that the building should be excluded from the second map data.

[0049] In some embodiments, the system 100 may capture image data from one or more cameras 140 while the vehicle 110 passes along a highway, such as the one depicted in FIG. 7. The system may further identify features in the image data using the second map data. The identification of the features may be used to locate the vehicle 110 within the environment. If the second map data does not include definitions for features such as buildings, traffic lights and stop lines, parking spaces, vegetation, and road level markings, the system 100 may not identify or associate those features to reduce consumption of computational resources.

[0050] In some embodiments, the system 100 may continue to define new types of roads and accuracy specifications for the types of roads traversed by the vehicle throughout the driving event, and the system 100 transitions between dependencies on one or more different map data defined by one or more accuracy specifications as the vehicle proceeds from one type of road to another.

[0051] It should be appreciated that the embodiments described in this disclosure are directed to systems and methods for locating a vehicle based on map data defined by an accuracy specification. The accuracy specification defines the map data for a particular type of road based on the sensors and accuracy required to locate a vehicle passing through that type of road. As a result, when high accuracy or a particular sensor system does not improve or is not utilized to locate the vehicle, the accuracy specification reduces or eliminates the dependency on that element, thereby reducing the computational resources required for location.

[0052] It is noted that the terms "substantially" and "about" may be used in this disclosure to express the inherent degree of uncertainty that may result from any quantitative comparison, value, measurement or other expression. These terms are also used in this disclosure to express the degree to which a quantitative expression may vary from the stated basis without resulting in a change in the basic functionality of the subject matter discussed.

[0053] While particular embodiments have been illustrated and described in this disclosure, it should be understood that various other changes and modifications can be made without departing from the spirit and scope of the claimed subject matter. Moreover, although various aspects of the claimed subject matter have been described in this disclosure, such aspects need not be used in combination. It is therefore intended that the appended claims cover all such changes and modifications that fall within the scope of the claimed subject matter. [Example 1] 1. A system for locating a vehicle within an environment, comprising: a computing device including a processor and a non-transitory computer readable memory; first map data stored in the non-transitory computer readable memory, the first map data defining a plurality of features within an environment that are used to locate a vehicle within the environment; A set of machine readable instructions stored in the non-transitory computer readable memory that, when executed by the processor, causes the computing device to at least: determining a portion of the first map data having roads of a first type; determining a first accuracy specification for the first type of road, the first accuracy specification identifying one or more features of the plurality of features defined in the first map data that are used to locate the vehicle traversing the first type of road within a predetermined accuracy; generating second map data for the first type of road, the second map data including the one or more features defined by the first accuracy specification, the second map data including a reduced number of features for locating the vehicle compared to the first map data; a set of machine readable instructions for causing the A system including: [Example 2] The set of machine readable instructions, when executed, further cause the computing device to: determining whether the vehicle is traversing a road of the first type; locating the vehicle utilizing the second map data as the vehicle traverses the first type of road; The system of Example 1, [Example 3] The set of machine readable instructions, when executed, further cause the computing device to: determining a second type of road within the first map data, the second type of road being different from the first type of road; determining a second accuracy specification for the second type of road, the second accuracy specification defining one or more features of the plurality of features defined in the first map data that are used to locate the vehicle passing over the second type of road; generating third map data for the second type of road, the third map data including the one or more features defined according to the second accuracy specification; The system described in Example 1. [Example 4] 4. The system of example 3, wherein the second map data includes at least one feature that is different from the one or more features included in the third map data. [Example 5] The set of machine readable instructions, when executed, further cause the computing device to: determining whether the vehicle is traversing a road of the first type or a road of the second type; locating the vehicle using the first map data when the vehicle is deemed to be traversing the first type of road; locating the vehicle using the second map data when the vehicle is deemed to be traversing the second type of road; The system of Example 3, [Example 6] 2. The system of example 1, wherein the first map data includes a point cloud representation of the environment. [Example 7] 2. The system of example 1, wherein the first map data includes an image-based representation of the environment. [Example 8] The system of Example 1, wherein the first map data includes a point cloud representation and an image-based representation of the environment. [Example 9] The system of Example 1, wherein the first accuracy specification is based on the first type of road and one or more driving actions. [Example 10] 2. The system of example 1, wherein the first type of road comprises a street. [Example 11] 2. The system of example 1, wherein the first type of road comprises a highway. [Example 12] The plurality of features in the environment include: sign, lane boundaries, building, Signals and stop lines, Parking space, Curbs and barriers, and Vegetation, The system of Example 1, comprising at least one class of features selected from the group comprising: [Example 13] 1. A system for locating a vehicle within an environment, comprising: a computing device including a processor and a non-transitory computer readable memory; first map data stored in the non-transitory computer readable memory, the first map data including one or more features defined by a first accuracy specification for locating a vehicle traversing a first type of road; second map data stored in the non-transitory computer readable memory, the second map data including one or more features defined by a second accuracy specification for locating the vehicle traversing a second type of road, the second type of road being different from the first type of road; A set of machine readable instructions stored in the non-transitory computer readable memory that, when executed by the processor, causes the computing device to at least: determining whether the vehicle is traversing a road of the first type or a road of the second type; locating the vehicle using the first map data when the vehicle is deemed to be traversing the first type of road; locating the vehicle using the second map data when the vehicle is deemed to be traversing a road of the second type; a set of machine readable instructions for causing the A system including: [Example 14] 14. The system of example 13, wherein the one or more features defining the first map data include at least one feature that differs from the one or more features defining the second map data. [Example 15] 14. The system of example 13, wherein the first type of road is a city road and the second type of road is a highway. [Example 16] the one or more features of the first accuracy specification include signs, lane markings, traffic lights, and stop lines for locating the vehicle traveling on the first type of road; the one or more features of the second accuracy specification include lane boundary lines for locating the vehicle passing through the second type of road; The system of Example 13. [Example 17] The first map data and the second map data are sign, lane boundaries, building, Signals and stop lines, Parking space, Curbs and barriers, and Vegetation The system of Example 13, comprising at least one feature selected from the group comprising: [Example 18] 1. A method for localizing a vehicle within an environment, comprising: determining a portion of a first map data having roads of a first type; determining a first accuracy specification for the first type of road, the first accuracy specification identifying one or more features for locating the vehicle passing through the first type of road; generating second map data for the first type of road, the second map data including the one or more features defined according to the first accuracy specification; determining whether the vehicle is traversing a road of the first type; locating the vehicle utilizing the second map data when the vehicle is deemed to be traversing the first type of road; The method includes: [Example 19] determining a second type of road within the first map data, the second type of road being different from the first type of road; determining a second accuracy specification for the second type of road, the second accuracy specification identifying one or more features for locating the vehicle passing through the second type of road; generating third map data for the second type of road, the third map data including the one or more features defined according to the second accuracy specification; The method of Example 18, further comprising: [Example 20] determining whether the vehicle is traversing a road of the first type or a road of the second type; locating the vehicle using the second map data when the vehicle is traversing the first type of road; locating the vehicle using the third map data when the vehicle is deemed to be traversing the second type of road; The method of Example 19, further comprising: [Explanation of symbols]

[0054] 100 Systems 110 Vehicle 120 Communication Path 130 Computing Devices 132 processors 134 Non-transitory computer-readable memory 135 Map Data 136 Accuracy Specifications 137 Feature Library 138 Logic 139 Local Communication Interface 140 Camera 150 Global Positioning System (GPS) 152 LIDAR system 154 RADAR system 160 Network Interface Hardware 170 Network

Claims

1. 1. A system for locating a vehicle within an environment, comprising: a computing device including a processor and a non-transitory computer readable memory; first map data stored in the non-transitory computer readable memory, the first map data defining a plurality of features within an environment that are used to locate a vehicle within the environment; A set of machine readable instructions stored in the non-transitory computer readable memory that, when executed by the processor, causes the computing device to at least: determining a portion of the first map data having roads of a first type; determining a first accuracy specification for the first type of road, the first accuracy specification identifying one or more features of the plurality of features defined in the first map data that are used to locate the vehicle traversing the first type of road within a predetermined accuracy; generating second map data for the first type of road, the second map data including the one or more features defined by the first accuracy specification, the second map data including a reduced number of features for locating the vehicle compared to the first map data; a set of machine readable instructions for causing the A system including:

2. The set of machine readable instructions, when executed, further cause the computing device to: determining whether the vehicle is traversing a road of the first type; locating the vehicle utilizing the second map data as the vehicle traverses the first type of road; The system of claim 1 .

3. The set of machine readable instructions, when executed, further cause the computing device to: determining a second type of road within the first map data, the second type of road being different from the first type of road; determining a second accuracy specification for the second type of road, the second accuracy specification defining one or more features of the plurality of features defined in the first map data that are used to locate the vehicle traversing the second type of road; generating third map data for the second type of road, the third map data including the one or more features defined according to the second accuracy specification; 3. A system according to claim 1 or 2.

4. The system of claim 3 , wherein the second map data includes at least one feature that is different from the one or more features included in the third map data.

5. The set of machine readable instructions, when executed, further cause the computing device to: determining whether the vehicle is traversing a road of the first type or a road of the second type; locating the vehicle using the first map data when the vehicle is deemed to be traversing the first type of road; locating the vehicle using the second map data when the vehicle is deemed to be traversing the second type of road; The system of claim 3 .

6. The system of claim 1 , wherein the first map data comprises a point cloud representation of the environment.

7. The system of claim 1 , wherein the first map data comprises an image-based representation of the environment.

8. The system of claim 1 , wherein the first map data includes a point cloud representation and an image-based representation of the environment.

9. 1. A system for locating a vehicle within an environment, comprising: a computing device including a processor and a non-transitory computer readable memory; first map data stored in the non-transitory computer readable memory, the first map data including one or more features defined by a first accuracy specification for locating a vehicle traversing a first type of road; second map data stored in the non-transitory computer readable memory, the second map data including one or more features defined by a second accuracy specification for locating the vehicle traversing a second type of road, the second type of road being different from the first type of road; A set of machine readable instructions stored in the non-transitory computer readable memory that, when executed by the processor, causes the computing device to at least: determining whether the vehicle is traversing a road of the first type or a road of the second type; locating the vehicle using the first map data when the vehicle is deemed to be traversing the first type of road; locating the vehicle using the second map data when the vehicle is deemed to be traversing the second type of road; a set of machine readable instructions for causing the A system including:

10. 10. The system of claim 9, wherein the one or more features defining the first map data include at least one feature that differs from the one or more features defining the second map data.

11. 11. The system according to claim 9, wherein the first type of road is a city road and the second type of road is a highway.

12. the one or more features of the first accuracy specification include signs, lane boundaries, traffic lights, and stop lines for locating the vehicle passing through the first type of road; the one or more features of the second accuracy specification include lane boundary lines for locating the vehicle passing through the second type of road; A system according to any one of claims 9 to 11.

13. 1. A method for localizing a vehicle within an environment, comprising: determining a portion of a first map data having roads of a first type; determining a first accuracy specification for the first type of road, the first accuracy specification identifying one or more features for locating the vehicle passing over the first type of road; generating second map data for the first type of road, the second map data including the one or more features defined according to the first accuracy specification; determining whether the vehicle is traversing a road of the first type; locating the vehicle utilizing the second map data when the vehicle is deemed to be traversing the first type of road; The method includes:

14. determining a second type of road within the first map data, the second type of road being different from the first type of road; determining a second accuracy specification for the second type of road, the second accuracy specification identifying one or more features for locating the vehicle passing through the second type of road; generating third map data for the second type of road, the third map data including the one or more features defined according to the second accuracy specification; The method of claim 13 further comprising:

15. determining whether the vehicle is traversing a road of the first type or a road of the second type; locating the vehicle using the second map data when the vehicle is traversing the first type of road; locating the vehicle using the third map data when the vehicle is deemed to be traversing the second type of road; and The method of claim 14 further comprising:

Images