Self-motion position enhancement using sensed feature measurements

Abstract

Systems and methods for determining a location of a vehicle are provided. The method includes obtaining a first location of the vehicle at a first time. A dead reckoning position of the vehicle at a second time is determined. Additionally, feature information at the second time is obtained. The feature information may be provided by a digital map or database that includes records of at least some of the surrounding objects of the vehicle. These records may include, for example, relative positioning attributes in addition to conventional absolute positioning. Position measurements of one or more features that can be identified based on the feature information are obtained. The dead reckoning position of the vehicle is corrected based on the position measurements.

Description

Technical Field

[0001] The present disclosure relates to determining a position of a vehicle, and more particularly to determining a position of a vehicle based on dead reckoning, and correcting errors in the dead reckoning position by using sensed feature measurements. Background Art

[0002] When a vehicle moves along a street or other terrain, it typically requires information about its current location. To achieve this, the vehicle may receive and utilize a Global Positioning System (GPS) signal to determine the vehicle's current location, and then use this current location information as input for a navigation application. GPS is an example of a Global Navigation Satellite System (GNSS) navigation system, in which a receiver determines its location by accurately measuring the arrival time of signaling events received from multiple satellites. However, GPS signals are not always reliably received by the vehicle. For example, in weak signal conditions, such as when the line of sight (LOS) to the satellite (S) is blocked by natural or man-made objects such as high-rise buildings, mountains, or canyons, GPS accuracy may be significantly reduced. Depending on the environment, the vehicle may not even be able to receive a GPS signal, or the accuracy of GPS may result in positioning errors on the order of tens of meters (e.g., up to 50 meters).

[0003] Another navigation system that vehicles can employ is called "dead reckoning." Various sensors employed on the vehicle are used to determine the vehicle's distance traveled and heading, which are then processed to calculate the vehicle's position. One issue with dead reckoning can be the accuracy of the sensors. Errors caused by this lack of accuracy over long periods of time can result in significant errors in the vehicle's distance traveled or deviations in its heading.

[0004] Due to increasing demands from the automotive industry, future consumer navigation systems will require greater accuracy than currently employed systems. Summary of the Invention

[0005] A method for determining a vehicle's position according to the present disclosure includes obtaining a first position of the vehicle, for example, at a first time. Determining a dead-reckoned position of the vehicle at a second time. Additionally, obtaining feature information at the second time. The feature information may be provided by a digital map or database that includes records of at least some of the vehicle's surrounding objects. These records may include, for example, relative positioning attributes in addition to traditional absolute positioning. Obtaining position measurements of one or more features identifiable based on the feature information. Correcting the dead-reckoned position of the vehicle based on the position measurements.

[0006] Specific implementations of this method may include one or more of the following features. The first position may be set as a corrected dead reckoning position. A second dead reckoning position of the vehicle at a third time may be determined. Second feature information at the third time may be obtained. A second position measurement of one or more features identifiable based on the second feature information may be obtained. The second dead reckoning position of the vehicle may be corrected based on the second position measurement. Obtaining the first position may include obtaining a position calculated by a satellite positioning system. The vehicle may include one or more sensors, such that obtaining position measurements of the one or more features may include obtaining sensor information from the one or more sensors. The one or more sensors may be lidar devices, camera devices, radar devices, or a combination thereof. The one or more features may include intersections, crosswalks, geographic landmarks, buildings, road widths, road signs, traffic lights, telephone poles, lampposts, or a combination thereof. Obtaining feature information may include obtaining a distance and / or orientation of at least one of the one or more features relative to the vehicle. Correcting the dead reckoning position of the vehicle may include triangulation and / or trilateration. Obtaining position measurements of the one or more features may include sensor fusion. The method may also include compiling correction data related to the position of the vehicle over time; predicting errors in dead reckoning using statistical bias and / or a neural network; and correcting the current position of the vehicle using the predicted errors in dead reckoning.

[0007] An example system for determining a position of a vehicle according to the present disclosure includes a memory, at least one processor communicatively coupled to the memory and configured to obtain a first position of the vehicle at a first time, determine a dead reckoning position of the vehicle at a second time, obtain feature information at the second time, obtain position measurements of one or more features identifiable based on the feature information, and correct the dead reckoning position of the vehicle based on the position measurements.

[0008] Specific implementations of such a system may include one or more of the following features. The at least one processor may be further configured to set the first position as a corrected dead reckoning position, determine a second dead reckoning position of the vehicle at a third time, obtain second feature information at the third time, obtain a second position measurement of one or more features identifiable based on the second feature information, and correct the second dead reckoning position of the vehicle based on the second position measurement. The at least one processor may be configured to obtain the first position in part using a position calculated by a satellite positioning system. The vehicle may include one or more sensors, and the at least one processor may be configured to obtain the first position using sensor information from the one or more sensors. The one or more sensors may include a lidar device, a camera device, a radar device, or a combination thereof. The one or more features may be an intersection, a crosswalk, a geographic landmark, a building, a road width, a road sign, a traffic light, a telephone pole, a lamppost, or a combination thereof. The at least one processor may be configured to obtain feature information including a distance and / or orientation of at least one of the one or more features relative to the vehicle. The at least one processor may be configured to correct the dead reckoning position at least in part using triangulation and / or trilateration. The at least one processor may be configured to obtain position measurements of the one or more features using, at least in part, sensor fusion. The at least one processor may also be configured to: compile correction data related to the position of the vehicle over time; predict errors in dead reckoning using statistical bias and / or neural networks; and correct the current position of the vehicle using the predicted errors in dead reckoning.

[0009] An example system for determining a position of a vehicle according to the present disclosure includes: means for obtaining a first position of the vehicle at a first time; means for determining a dead reckoning position of the vehicle at a second time; means for obtaining feature information at the second time; means for obtaining position measurements of one or more features identifiable based on the feature information; and means for correcting the dead reckoning position of the vehicle based on the position measurements.

[0010] Specific implementations of such a system may include one or more of the following features. The system may also include: means for setting the first position as a corrected dead reckoning position; means for determining a second dead reckoning position of the vehicle at a third time; means for obtaining second feature information at the third time; means for obtaining a second position measurement of one or more features identifiable based on the second feature information; and means for correcting the second dead reckoning position of the vehicle based on the second position measurement. The means for obtaining the first position may include obtaining a position calculated by a satellite positioning system. The vehicle may include one or more sensors, and obtaining position measurements of the one or more features may include means for obtaining sensor information from the one or more sensors. The sensors may include using a lidar device, a camera device, a radar device, or a combination thereof. The one or more features may include an intersection, a crosswalk, a geographic landmark, a building, a road width, a road sign, a traffic light, a telephone pole, a lamppost, or a combination thereof. The means for obtaining the feature information may include obtaining a distance and / or a bearing of at least one of the one or more features relative to the vehicle. The means for correcting the dead reckoning position of the vehicle may include triangulation and / or trilateration. The means for obtaining the position measurements of the one or more features may include sensor fusion. The system may also include means for compiling correction data related to the vehicle's position over time, means for predicting errors in dead reckoning using statistical bias and / or neural networks, and means for correcting the vehicle's current position using the predicted errors in dead reckoning.

[0011] An example non-transitory processor-readable storage medium according to the present disclosure includes processor-readable instructions configured to cause one or more processors to determine a position of a vehicle. The non-transitory processor-readable storage medium may include code for obtaining a first position of the vehicle at a first time; code for determining a dead reckoning position of the vehicle at a second time; code for obtaining feature information at the second time; code for obtaining position measurements of one or more features identifiable based on the feature information; and code for correcting the dead reckoning position of the vehicle based on the position measurements.

[0012] Specific implementations of such a storage medium may include one or more of the following features. The non-transitory processor-readable storage medium may include: code for setting a first position as a corrected dead reckoning position; code for determining a second dead reckoning position of the vehicle at a third time; code for obtaining second feature information at the third time; code for obtaining a second position measurement of one or more features identifiable based on the second feature information; and code for correcting the second dead reckoning position of the vehicle based on the second position measurement. The non-transitory processor-readable storage medium may include code for obtaining a position calculated by a satellite positioning system. The vehicle may include one or more sensors, and the code for obtaining position measurements of the one or more features may include code for obtaining sensor information from the one or more sensors. The one or more sensors may include a lidar device, a camera device, a radar device, or a combination thereof. The one or more features may include an intersection, a crosswalk, a geographic landmark, a building, a road width, a road sign, a traffic light, a telephone pole, a lamppost, or a combination thereof. The code for obtaining feature information may also include code for obtaining a distance and / or bearing of at least one of the one or more features relative to the vehicle. The code for correcting the dead reckoning position of the vehicle may include code for performing triangulation and / or trilateration. The code for obtaining position measurements of one or more features may include code for performing sensor fusion. The non-transitory processor-readable storage medium may also include code for compiling correction data related to the position of the vehicle over time; code for predicting errors in dead reckoning using statistical bias and / or neural networks; and code for correcting the current position of the vehicle using the predicted errors in dead reckoning. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Non-limiting and non-exhaustive aspects are described with reference to the following figures, wherein like reference numerals refer to like parts throughout the various figures unless otherwise specified.

[0014] Figure 1 Block diagrams illustrating example components and / or systems implemented in a vehicle are illustrated.

[0015] Figure 2 Illustrations of an example vehicle configured with various sensor and communication components and / or systems are shown.

[0016] Figure 3 is a functional block-level diagram of an example vehicle.

[0017] Figure 4 is a process flow diagram of an example method for providing a correction to a dead reckoning position of a vehicle.

[0018] Figure 5is a diagram of example errors that may occur when performing dead reckoning (DR) and their corrections.

[0019] Figure 6 is an illustration of an example triangulation to determine a vehicle's position based on feature position measurements.

[0020] Figure 7 is an example of fusion of map and sensor information. DETAILED DESCRIPTION

[0021] Techniques for determining the position of a vehicle are provided. Dead reckoning can be used to determine the position of the vehicle. Errors in the dead reckoned position can be corrected by using position measurements of features that can be identified in the surrounding area. These techniques and configurations are examples, and other configurations and techniques can be used.

[0022] Figure 1 is a block diagram of various components and / or systems implemented in an example vehicle, such as an automobile. Vehicle 100 may include one or more cameras 135. A camera may include a camera sensor and a mounting assembly. Different mounting assemblies may be used for different cameras on vehicle 100. For example, a forward-facing camera may be mounted in the front bumper, in the stalk of a rearview mirror assembly, or in other forward-facing areas of vehicle 100. A rear-facing camera may be mounted in the rear bumper / fender, on the rear windshield, in the trunk, or in other rear-facing areas of the vehicle. Side mirrors may be mounted on the sides of the vehicle, such as integrated into the mirror assembly or door assembly. The camera can provide object detection and distance estimation, particularly for objects of known size and / or shape (e.g., stop signs and license plates both have standardized sizes and shapes), and can also provide information about rotational motion relative to the vehicle's axes (such as during cornering). When used in conjunction with other sensors, the camera can be calibrated using other systems (such as lidar, wheel tick / distance sensors, and / or GNSS) to verify travel distance and angular orientation. Cameras can similarly be used to verify and calibrate other systems to verify that distance measurements are correct (e.g., by calibrating against known distances between known objects (landmarks, roadside markings, road mile markers, etc.)), and also to verify that object detection is being performed accurately so that objects are mapped accordingly by the lidar and other systems to the correct position relative to the car. Similarly, when combined with, for example, accelerometers, the time to impact with a road hazard can be estimated (e.g., the time elapsed before hitting a pothole), which can be verified against the actual impact time and / or against a parking model (e.g., compared to an estimated stopping distance if stopping is attempted before impacting the object) and / or against a maneuvering model (verifying that the current estimate of the turning radius at the current speed and / or the maneuverability measurement at the current speed is accurate under the current conditions and modified accordingly based on the camera and other sensor measurements to update the estimated parameters).

[0023] The accelerometer, gyroscope, and magnetometer 140 may be used to provide and / or verify motion and direction information. The accelerometer and gyroscope may be used to monitor wheel and drivetrain performance. The accelerometer may also be used to verify the actual time of impact of road hazards (such as potholes) relative to the predicted time based on existing braking and acceleration models and steering models. In one embodiment, the gyroscope and magnetometer may be used to measure the rotational state of the vehicle and the orientation relative to magnetic north, respectively, and to measure and calibrate an estimate and / or model of the turning radius at the current speed and / or a maneuverability measurement at the current speed (especially when used in conjunction with measurements from other external and internal sensors such as other sensors 145, such as speed sensors, wheel tick sensors, and / or odometer measurements).

[0024] The light detection and ranging (LiDAR) 150 subsystem uses pulsed lasers to measure the distance to objects. While cameras can be used for object detection, LiDAR 150 provides a means to more confidently detect the distance (and orientation) of objects, especially for objects of unknown size and shape. LiDAR 150 measurements can also be used to estimate travel speed, vector direction, relative positioning, and stopping distance by providing accurate and incremental distance measurements.

[0025] The memory 160 may be used with the processor 110 and / or the DSP 120 and may include flash memory, RAM, ROM, a disk drive, or a flash memory card or other memory device, or various combinations thereof. In one embodiment, the memory 160 may contain instructions for implementing the various methods described throughout this description, including, for example, processes for implementing the use of relative positioning between vehicles and between vehicles and external reference objects (such as roadside units). In one embodiment, the memory may contain instructions for operating and calibrating sensors, and receiving map, weather, vehicle (both vehicle 100 and surrounding vehicles), and other data, and determining driving parameters (such as relative positioning, absolute positioning, stopping distance, acceleration and turning radius at current speed and / or maneuverability at current speed, vehicle-to-vehicle distances, turn initiation / timing and execution, and initiation / timing of driving maneuvers) using various internal and external sensor measurements and the received data and measurements.

[0026] The power and drive system (generator, battery, transmission, engine) and related systems 175 and systems (brakes, actuators, throttle control, steering and electrical) 155 can be controlled by a processor and / or hardware or software or by the operator of the vehicle or by some combination thereof. The systems (brakes, actuators, throttle control, steering and electrical, etc.) 155 and power and drive or other systems 175 can be used in conjunction with performance parameters and operating parameters to enable autonomous (and manual, with respect to alerts and emergency overrides / braking / stopping) safe and accurate driving and operation of the vehicle 100, such as to merge into traffic, stop, accelerate and otherwise operate the vehicle 100 safely, effectively and efficiently. Inputs from various sensor systems (such as cameras 135, accelerometers, gyroscopes and magnetometers 140, lidar 150, GNSS receiver 170, radar 153), inputs from wireless transceiver 130 and / or other sensors 145, or various combinations thereof, messaging and / or measurements may be used by the processor 110 and / or DSP 120 or other processing system to control the power and drive system 175 and systems (brakes, actuators, throttle control, steering and electrical, etc.) 155.

[0027] A Global Navigation Satellite System (GNSS) receiver can be used to determine positioning relative to the ground (absolute positioning) and, when used with other information (such as measurements and / or mapping data from other objects), can be used to determine positioning relative to other objects (such as relative to other cars and / or relative to the road).

[0028] The GNSS receiver 170 may support one or more GNSS constellations and other satellite-based navigation systems. For example, the GNSS receiver 170 may support global navigation satellite systems such as the Global Positioning System (GPS), Russia's Global Navigation Satellite System (GLONASS), Galileo, and / or BeiDou, or any combination thereof. In one embodiment, the GNSS receiver 170 may support regional navigation satellite systems (such as NAVIC or QZSS or a combination thereof) and various augmentation systems (e.g., satellite-based augmentation systems (SBAS) or ground-based augmentation systems (GBAS)) such as Doppler Orbits and Radiolocation Integrated by Satellite (DORIS) or Wide Area Augmentation System (WAAS) or European Geostationary Navigation Overlay Service (EGNOS) or Multipurpose Satellite Augmentation System (MSAS) or Local Area Augmentation System (LAAS). In one embodiment, the GNSS receiver 130 and antenna 132 may support multiple frequency bands and sub-bands, such as the GPS L1, L2, and L5 bands, the Galileo E1, E5, and E6 bands, the Compass (Beidou) B1, B3, and B2 bands, the GLONASS G1, G2, and G3 bands, and the QZSS L1C, L2C, and L5-Q bands.

[0029] The GNSS receiver 170 can be used to determine position and relative position that can be used for positioning, navigation, and to calibrate other sensors when appropriate, such as for determining the distance between two points in time under clear sky conditions and using the distance data to calibrate other sensors (such as odometers and / or lidar). In one embodiment, GNSS-based relative position based on, for example, shared Doppler and / or pseudorange measurements between vehicles can be used to determine a highly accurate distance between two vehicles and, when combined with vehicle information such as shape and model information and GNSS antenna position, can be used to calibrate, validate, and / or influence the confidence level associated with information from lidar, cameras, radar, sonar, and other distance estimation technologies. GNSS Doppler measurements can also be used to determine the linear and rotational motion of a vehicle or a vehicle relative to another vehicle, which can be used in conjunction with gyroscopes and / or magnetometers and other sensor systems to maintain the calibration of those systems based on the measured position data. Relative GNSS positioning data can also be combined with high-confidence absolute position from roadside equipment 425 (also known as roadside units or RSUs) to determine a high-confidence absolute position of the vehicle. Furthermore, during periods of inclement weather that may obscure lidar and / or camera-based data sources, relative GNSS positioning data may be used to avoid other vehicles and remain within lanes or other assigned road areas. For example, using an RSU equipped with a GNSS receiver and V2X capabilities, GNSS measurement data may be provided to the vehicle, which, when provided along with the absolute position of the RSU, may be used to navigate the vehicle relative to a map, thereby keeping the vehicle in a lane and / or road despite a lack of visibility.

[0030] Radio detection and ranging (radar 153) uses transmitted radio waves that reflect off objects. The reflected radio waves are analyzed based on the time it takes for the reflections to arrive and other signal characteristics of the reflected waves to determine the location of nearby objects. Radar 153 can be used to detect the location of nearby cars, roadside objects (signs, other vehicles, pedestrians, etc.), and is often capable of detecting objects even in obscuring weather conditions such as snow, rain, or hail. Therefore, radar 153 can be used to supplement the lidar 150 system and camera 135 system by providing ranging and distance measurements and information to other objects, where vision-based systems would typically fail. Furthermore, radar 153 can be used to calibrate and / or perform sanity checks on other systems, such as lidar 150 and camera 135. Ranging measurements from radar 153 can be used to determine / measure braking distance at the current speed, acceleration, maneuverability at the current speed, and / or turning radius at the current speed and / or maneuverability measurements at the current speed. In some systems, ground-penetrating radar can also be used to track the road surface, for example, via radar-reflecting markings on the road surface or terrain features such as ditches.

[0031] The vehicle 100 may also include multiple wireless transceivers, including WAN, WLAN, and / or PAN transceivers. In one embodiment, the radio technology that can support one or more wireless communication links also includes wireless local area network (e.g., WLAN, such as IEEE 802.11), Bluetooth (BT), and / or ZigBee.

[0032] Figure 2 A diagram of a vehicle configured with example sensor and communication components and / or systems is illustrated. Figure 2 As shown in , the vehicle 100 may have, for example, cameras such as a rearview mirror-mounted camera 206, a front fender-mounted camera (not shown), a side mirror-mounted camera (not shown), and a rear camera (not shown, but typically on the trunk, hatch, or rear bumper). The vehicle 100 may also have a lidar subsystem 204 for detecting objects and measuring distances to those objects; the lidar system 204 is typically mounted on the roof, however, if there are multiple lidar units 204, they can be oriented around the front, rear, and sides of the vehicle. The vehicle 100 may have various other location-related systems, such as a GNSS receiver 170 (typically located in a shark fin unit on the rear of the roof), various wireless transceivers (such as WAN, WLAN, V2X; typically but not necessarily located in the shark fin) 202, a radar system 208 (typically in the front bumper), and sonar 210 (typically located on both sides of the vehicle, if present). There may also be various wheel 212 and driveline sensors such as tire pressure sensors, accelerometers, gyroscopes, and wheel rotation detection and / or counters. It is recognized that this list is not intended to be limiting, and Figure 2 This section is intended to provide example locations of various sensors in an embodiment of the vehicle 100. Additionally, further details regarding specific sensors are provided with respect to Figure 1 Described.

[0033] refer to Figure 3 , shows a functional block-level diagram of an example vehicle that determines its position via dead reckoning and corrects errors in the dead reckoning position based on external feature measurements. Vehicle 100 may receive vehicle information from vehicle external sensors 302 and vehicle internal sensors 304. The received vehicle sensor information may then be processed in a vehicle position determination module 312. Vehicle position determination module 312, which may include one or more processors that execute code, may also include modules such as external feature identification and position measurement module 308 and current dead reckoning position module 306. Based on the position measurements of the identified external features, the vehicle's dead reckoning position may be corrected 310.

[0034] Vehicle external sensors 302 may include, but are not limited to, cameras 206, lidar system 204, radar system 208, proximity sensors, rain sensors, weather sensors, GNSS receiver 170, and data received therewith, such as map data, environmental data, location, route, and / or other vehicle or external feature information (see also FIG. Figure 1 and Figure 2 and accompanying text). Vehicle interior sensors 304 may include: wheel sensors 212, such as tire pressure sensors, brake pad sensors, brake status sensors, speedometers, and other speed sensors; heading and / or orientation sensors, such as magnetometers and geomagnetic compasses; distance sensors, such as odometers and wheel tick sensors; inertial sensors, such as accelerometers and gyroscopes, and inertial positioning results using the aforementioned sensors; and yaw, pitch, and / or roll sensors, such as may be determined individually or using other sensor systems (such as accelerometers, gyroscopes, and / or tilt sensors).

[0035] Both vehicle interior sensor 304 and vehicle exterior sensor 302 may have shared or dedicated processing capabilities. For example, a sensor system or subsystem may have one or more sensor processing cores that determine vehicle state values ​​(such as yaw, pitch, roll, heading, speed, acceleration capability and / or distance, and / or stopping distance) based on measurements and other inputs from accelerometers, gyroscopes, magnetometers and / or other sensing systems. Different sensing systems may communicate with each other to determine measurements. The vehicle state values ​​derived from the measurements of interior and exterior sensors may be further combined with vehicle state values ​​and / or measurements from other sensor systems using general-purpose or application processors. In one embodiment, sensors may be segmented into related systems (e.g., lidar, radar, motion, wheel systems, etc.), which are operated by dedicated core processing for raw results to output vehicle state values ​​from each core, which are combined and interpreted to derive combined vehicle state values, including capability data elements and state data elements, which may be used to control or otherwise influence vehicle operation.

[0036] refer to Figure 4 And further reference Figures 1 to 3 , shows an example method 400 for determining a dead reckoning position of a vehicle and correcting associated errors. However, the method 400 is an example and not limiting. The method 400 can be modified, for example, by splitting a single stage into multiple stages.

[0037] At stage 402, the method includes obtaining a first location of the vehicle at a first time. GNSS receiver 170 and processor 110 are components for obtaining the first location. In one example, processor 110 and accelerometer, gyroscope, and magnetometer 140 may be components for obtaining the first location. For example, the first location may be provided, but is not limited to, by utilizing GPS / GNSS, or may be a previously determined dead reckoning location.

[0038] At stage 404, the method includes determining a dead reckoning position of the vehicle at a second time. The dead reckoning position module 306 is a component for determining a dead reckoning position. In one example, the dead reckoning position module 306 may be configured to receive various measurements from vehicle interior sensors 304 and vehicle exterior sensors 304 to determine a dead reckoning position at the second time. Dead reckoning, or DR, as it is commonly referred to, is the process of calculating a current position based on a previously acquired position fix. Generally, as is known in the art, the dead reckoning position of the vehicle at the second time may be determined by advancing a first position based on sensor information that provides, but is not limited to, heading, speed, and time. For example, the vehicle 100 may be equipped with sensors 145 and corresponding vehicle dimensions, such as wheel circumference measurements, and may be configured to record wheel rotation and steering direction. Other sensors, such as one or more inertial sensors (e.g., accelerometers, gyroscopes, solid-state compasses), may also be used.

[0039] Errors may accumulate based on sensor instabilities or other nonlinearities associated with the sensor input. In one example, reference Figure 5 , illustrates the errors that may be generated when performing dead reckoning (DR). The first position 502 determined at stage 402 may be obtained, but is not limited to, via GNSS receiver 170 and may include a certain amount of error (e.g., uncertainty value). Consequently, subsequent dead reckoning (DR) estimates may also include initial errors and other accumulated sensor errors. For example, the sensor information provided to the dead reckoning position module 306 may be slightly inaccurate and may result in right or left deviations and / or erroneous distances, as shown in path 504. The corresponding DR position of the vehicle determined at stage 404 may include such errors.

[0040] Return Reference Figure 4, errors in the dead reckoning position estimate can be corrected. To achieve this, initially, at stage 406, the method includes obtaining feature information at the second time. Processor 110 and wireless transceiver 130 are components for obtaining the feature information at the second time. In one example, obtaining the feature information may include retrieving from memory 160 or other sources those features in the surrounding area that can be identified via various vehicle sensors. These features may include, but are not limited to, intersections, crosswalks, geographic landmarks, buildings, road widths, road signs, road widths, traffic lights, telephone poles, highway exits, and / or lampposts. The feature information may include records of at least some of the objects surrounding the vehicle, which may be included in, for example, a digital map or database. These records may include relative positioning attributes in addition to traditional absolute positioning. These records may also include identification data sufficient to identify features in the received sensor data. GNSS receiver 170 and / or wireless transceiver 130 may be used to obtain the feature information. Vehicle 100 may be configured to provide location coordinates (e.g., latitude / longitude) to a third-party service provider to obtain information about those features in the area near the vehicle's coarse position. The coarse position of the vehicle 100 may be based on the determined dead reckoning position at the second time, and / or based on other positioning technologies such as, for example, GPS. The extent of the area surrounding the vehicle 100 to be searched (for features) may be based on configuration options or other application criteria (e.g., a positioning uncertainty value), and may include, but is not limited to, distances of 100, 200, 500, or 1000 yards around the coarse position of the vehicle 100. In one example, the vehicle 100 may have feature / coarse map information stored in local memory 160, and the vehicle 100 may parse the feature / coarse map information to determine those features near the vehicle 100.

[0041] At stage 408, the method includes obtaining position measurements of one or more features identified based on the feature information. External feature identification and location module 308 is a component for obtaining position measurements. Stage 408 may include obtaining sensor information from one or more sensors 302 and 303 (as described above). The obtained sensor information is provided to external feature identification and location module 308, which may then utilize various recognition techniques known in the art to identify one or more features in the surrounding area. For example, a visual / optical sensor (e.g., camera 135) may be configured to obtain images of the vicinity of vehicle 100. A recognition process may be performed on the obtained images, in part using the feature information obtained in stage 406, to thereby identify one or more features. Once the features are identified, a radar or lidar system (or other sensor) may obtain the range and / or orientation of the identified features relative to vehicle 100. Other sensors may be configured to provide additional information. Sensor information may be obtained on demand or periodically (e.g., based on a sensor duty cycle). The one or more position measurements may include, but are not limited to, temporal separation measurements in addition to spatial separation measurements. A distance sensor, such as included in vehicle external sensors 302 , may be used in conjunction with an inertial measurement device (eg, gyroscope, accelerometer 140 ) to determine the orientation and height of an object based on a coordinate system and the orientation of the distance sensor.

[0042] At stage 410, the method includes correcting the dead reckoning position of the vehicle based on the position measurements, such as Figure 5 illustratively shown in the path 508 depicted in FIG. The dead reckoning position correction module 310 is a component for correcting the dead reckoning position. The known positions of the identifiable features and the sensed distances and / or bearings to the identifiable features can be used to improve the accuracy of the dead reckoning position. For example, based on the number of identified features and their known absolute positions, and using spatial separation (e.g., distance and / or bearing) and / or temporal separation, a corrected position of the vehicle 100 can be determined using positioning techniques known in the art. Illustratively, as Figure 6 The triangulation and / or trilateration shown may be used to determine a corrected position of the vehicle.

[0043] refer to Figure 6, a diagram 600 is shown illustrating an example triangulation for determining a vehicle's position based on feature position measurements. Diagram 600 includes a vehicle 602 and a plurality of roadside features, including a first feature 604, a second feature 606, a third feature 608, and a fourth feature 610. Vehicle 602 may include some or all of the features of vehicle 100, and vehicle 100 may be an example of vehicle 602. Features 604, 606, 608, 610 may be one or more of an intersection, a crosswalk, a geographic landmark, a building, road width, a road sign, road width, a traffic light, a telephone pole, a highway exit, a lamppost, or other objects detectable by one or more of the vehicle's external sensors 302. Feature information detectable by external sensors 302, such as corresponding locations and other distinguishing aspects (e.g., text, expected return signal, color configuration, etc.), may be provided at stage 406, and external feature identification and location module 308 may be configured to utilize the sensor input to determine the location of the features. The vehicle position determination module 312 can be configured to perform triangulation or multilateration calculations using the spatial separation and relative positioning of features. In a first example, the vehicle 602 can use the positions of the first feature 604 and the second feature 606 and the corresponding distances to the first feature and the second feature to determine a first position estimate. In a second example, the vehicle 602 can use the positions of the third feature 608 and the fourth feature 610 and the corresponding distances to the third feature and the fourth feature to determine a second position estimate. Temporal separation between feature detection and distance measurement can also be used. For example, longitudinal and lateral corrections can be separated by projection on the XY axis. In this way, a single feature can be used to determine a position estimate for the vehicle (e.g., heading position). Other electronic measurement techniques such as Doppler, departure angle (of a transmitted signal), arrival angle (of a reflected signal), and signal strength information can be used to determine the vehicle's position.

[0044] Return Reference Figure 5 As vehicle 100 continues to move, the first position may be set as a corrected dead reckoning position of the vehicle, and the dead reckoning process may be repeated. More specifically, a second dead reckoning position fix at a third time may be determined, and second feature information may be obtained. A second position measurement of one or more features that can be identified based on the second feature information is obtained, and the dead reckoning position of the vehicle is corrected based on the second position measurement. Figure 6 The triangulation / multilateration techniques described in may be applied to correct the position estimate of the vehicle 100 at various correction points 506 to determine the position measurement and correct the dead reckoning position of the vehicle at stage 410 .

[0045] Obtaining a position measurement of one or more features may include sensor fusion. Using sensor fusion, inputs from multiple sources / sensors (such as GPS / maps, lidar sensors, radar sensors, and / or cameras) may be combined using software algorithms, as known in the art, to determine a position measurement. The resulting measurement is more accurate because it balances the strengths of the different sensors. Each type of sensor has various advantages and / or disadvantages. Radar accurately determines distance and speed—even in challenging weather conditions—but cannot read street signs or “see” the color of traffic lights. Cameras can read signs or classify objects, however, they may be easily blinded by weather conditions, dirt, etc. Lidars can accurately detect objects, but they typically do not have the range or affordability of cameras or radars. Vehicles may also use sensor fusion to fuse information from multiple sensors of the same type to take advantage of, for example, partially overlapping fields of view.

[0046] refer to Figure 7 , shows a diagram 700 of an example of fusion of map and sensor information. Diagram 700 includes a road segment 701 having multiple features and corresponding positions based on map information and sensor measurements. In one example, a vehicle may be at an assumed location 702a and may receive feature information including a first map location 704a of a first feature and a second map location 706a of a second feature. The vehicle's measured location 702b may be based on measurements of the first and second features. In one example, the measured location 702b may also be based on external measurements, such as GNSS or other terrestrial measurements. As a result of calculating the measured location 702b and the corresponding measurements of the first and second features, the first feature may be determined to be at a first measured location 704b, and the second feature may be determined to be at a second measured location 706b. The vehicle may be configured to generate fused positions of the features based on the corresponding map locations 704a, 706a and the measured locations 704b, 706b. For example, the first fused position 708 may be based on an average of the first map position 704a and the first measured position 704b, and the second fused position 710 may be based on an average of the second map position 706a and the second measured position 706b. In one example, the average position may be determined based on averaging the corresponding coordinate measurements (e.g., latitude / longitude / altitude) of each feature and each corresponding measurement and map data. Figure 7 One measurement for each of the features is illustrated, but additional measurements for each feature based on different sensors may also be obtained. In one example, correcting the DR position at stage 410 may be based on applying measurements obtained by the vehicle (e.g., measured distance, angle of arrival, etc.) to the corresponding fused positions of the features.

[0047] In one example, the measured position 702b of the vehicle can be based on a machine learning method or algorithm. For example, training data including detection of known features can be associated with the known location. Distance measurements and other signal analysis (e.g., reflected signal strength, channel response at a location, etc.) can also be used as training data associated with the known location of the vehicle. In one example, correcting errors in dead reckoning can also be achieved by compiling correction data related to the vehicle's position over time. Other machine learning, artificial intelligence, and / or neural network methods and algorithms can be used with the compiled correction data to predict errors in the dead reckoning position estimate and determine the vehicle's current location.

[0048] Other examples and implementations are within the scope of this disclosure and the appended claims. For example, due to the nature of software and computers, the functions described above can be implemented using software executed by a processor, hardware, firmware, hardwiring, or any combination thereof. Features that implement the functions can also be physically located in various locations, including being distributed so that various parts of the functions are implemented in different physical locations.

[0049] As used herein, the singular forms "a," "an," and "the" include the plural forms as well, unless the context clearly indicates otherwise. As used herein, the term "comprising" specifies the presence of recited features, integers, steps, operations, elements, and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0050] Furthermore, as used herein, “or” used in a list of items (possibly followed by “at least one of” or “one or more of”) indicates a disjunctive list, so that, for example, a list of “at least one of A, B, or C,” or a list of “one or more of A, B, or C,” or a list of “A or B or C” means A or B or C or AB (A and B) or AC (A and C) or BC (B and C) or ABC (i.e., A and B and C), or a combination having more than one feature (e.g., AA, AAB, ABBC, etc.). Thus, a statement that an item (e.g., a processor) is configured to perform a function with respect to at least one of A or B, or a statement that an item is configured to perform function A or function B, means that the item may be configured to perform the function with respect to A, or may be configured to perform the function with respect to B, or may be configured to perform the functions with respect to both A and B. For example, the phrase "a processor configured to measure at least one of A or B" or "a processor configured to measure A or B" means that the processor may be configured to measure A (and may or may not be configured to measure B), or may be configured to measure B (and may or may not be configured to measure A), or may be configured to measure A and B (and may be configured to select which one or both of A and B to measure). Similarly, a statement about a component for measuring at least one of A or B includes a component for measuring A (which may or may not be able to measure B), or a component for measuring B (and may or may not be configured to measure A), or a component for measuring A and B (which may be able to select which one or both of A and B to measure). As another example, a statement that an item (e.g., a processor) is configured to perform at least one of function X or function Y means that the item may be configured to perform function X, or may be configured to perform function Y, or may be configured to perform function X and function Y. For example, the phrase “a processor configured to measure at least one of X or Y” means that the processor may be configured to measure X (and may or may not be configured to measure Y), or may be configured to measure Y (and may or may not be configured to measure X), or may be configured to measure X and measure Y (and may be configured to select which or both of X and Y to measure).

[0051] As used herein, unless otherwise stated, a statement that a function or operation is "based on" an item or condition means that the function or operation is based on the stated item or condition, and may be based on one or more items and / or conditions other than the stated item or condition.

[0052] Substantial changes may be made according to specific requirements. For example, customized hardware may also be used, and / or specific elements may be implemented in hardware, in software executed by a processor (including portable software, such as applets, etc.), or in both. In addition, connections to other computing devices such as network input / output devices may be employed. Unless otherwise indicated, components (functional or otherwise) shown in the figures and / or discussed herein as being connected or communicating with each other are communicatively coupled. That is, these components may be connected directly or indirectly to enable communication therebetween.

[0053] The systems and devices discussed above are examples. Various configurations may omit, substitute, or add various processes or components as appropriate. For example, features described with respect to certain configurations may be combined in various other configurations. Different aspects and elements of the configurations may be combined in similar ways. Furthermore, technology is constantly evolving, and therefore many of the elements are examples and do not limit the scope of this disclosure or the claims.

[0054] A wireless communication system is a system in which communications are transmitted wirelessly between wireless communication devices, i.e., by electromagnetic and / or acoustic waves propagating through air space rather than through wires or other physical connections. A wireless communication system (also referred to as a wireless communication system or wireless communication network) may not cause all communications to be transmitted wirelessly, but may be configured so that at least some communications are transmitted wirelessly. Furthermore, the term "wireless communication device" or similar terms does not require that the functionality of the device be used exclusively or even primarily for communication, that communications using the wireless communication device be exclusively or even primarily wireless, or that the device be a mobile device. Rather, it indicates that the device includes wireless communication capabilities (unidirectional or bidirectional), for example, including at least one radio component (each radio component being part of a transmitter, receiver, or transceiver) for wireless communication.

[0055] Specific details are given in this description to provide a thorough understanding of example configurations (including specific implementations). However, configurations can be practiced without these specific details. For example, well-known circuits, processes, algorithms, structures, and techniques have been shown without unnecessary details to avoid confusing these configurations. This description provides example configurations without limiting the scope, applicability, or configuration of the claims. On the contrary, the previous description of the configuration provides a description for implementing the described technology. Various changes can be made to the function and arrangement of the elements.

[0056] As used herein, the terms "processor-readable medium," "machine-readable medium," and "computer-readable medium" refer to any medium that participates in providing data that causes a machine to operate in a particular manner. Using a computing platform, various processor-readable media may be involved in providing instructions / code to a processor for execution, and / or may be used to store and / or carry such instructions / code (e.g., as signals). In many specific implementations, processor-readable media are physical and / or tangible storage media. Such media may take many forms, including, but not limited to, non-volatile media and volatile media. Non-volatile media include, for example, optical disks and / or magnetic disks. Volatile media include, but are not limited to, dynamic memory.

[0057] After describing several example configurations, various modifications, alternative configurations, and equivalents can be used. For example, the above elements can be components of a larger system, wherein other rules can take precedence over the application of the present disclosure or otherwise modify the application of the present disclosure. In addition, several operations can be taken before, during, or after considering the above elements. Accordingly, the above description does not limit the scope of the claims.

[0058] Specific implementation examples are described in the following numbered clauses:

[0059] Clause 1. A method of determining a position of a vehicle, the method comprising: obtaining a first position of the vehicle at a first time; determining a dead reckoning position of the vehicle at a second time; obtaining feature information at the second time; obtaining position measurements of one or more features identifiable based on the feature information; and correcting the dead reckoning position of the vehicle based on the position measurements.

[0060] Clause 2. The method of clause 1, further comprising: setting the first position as the corrected dead reckoning position; determining a second dead reckoning position of the vehicle at a third time; obtaining second feature information at the third time; obtaining a second position measurement of one or more features identifiable based on the second feature information; and correcting the second dead reckoning position of the vehicle based on the second position measurement.

[0061] Clause 3. The method of clause 1, wherein obtaining the first position comprises obtaining a position calculated by a satellite positioning system.

[0062] Clause 4. The method of clause 1, wherein the vehicle comprises one or more sensors, and wherein obtaining position measurements of the one or more features comprises obtaining sensor information from the one or more sensors.

[0063] Clause 5. The method of clause 4, wherein the one or more sensors comprise a lidar device, a camera device, a radar device, or a combination thereof.

[0064] Clause 6. The method of clause 1, wherein the one or more features include an intersection, a crosswalk, a geographic landmark, a building, a road width, a road sign, a traffic light, a telephone pole, a lamppost, or a combination thereof.

[0065] Clause 7. The method of clause 1, wherein obtaining feature information further comprises obtaining a distance and / or orientation of at least one of the one or more features relative to the vehicle.

[0066] Clause 8. The method of clause 1, wherein correcting the dead reckoning position of the vehicle comprises triangulation and / or trilateration.

[0067] Clause 9. The method of clause 1, wherein obtaining position measurements of one or more features comprises sensor fusion.

[0068] Clause 10. The method of clause 1, further comprising: compiling correction data related to the position of the vehicle over time; predicting errors in the dead reckoning using statistical bias and / or a neural network; and correcting the current position of the vehicle using the predicted errors in the dead reckoning.

[0069] Clause 11. A system for determining a position of a vehicle, the system comprising: a memory; at least one processor communicatively coupled to the memory and configured to: obtain a first position of the vehicle at a first time; determine a dead reckoning position of the vehicle at a second time; obtain feature information at the second time; obtain position measurements of one or more features identifiable based on the feature information; and correct the dead reckoning position of the vehicle based on the position measurements.

[0070] Clause 12. The system of clause 11, wherein the at least one processor is further configured to: set the first position as the corrected dead reckoning position; determine a second dead reckoning position of the vehicle at a third time; obtain second feature information at the third time; obtain a second position measurement of one or more features identifiable based on the second feature information; and correct the second dead reckoning position of the vehicle based on the second position measurement.

[0071] Clause 13. The system of clause 11, wherein the at least one processor is configured to obtain the first position using, in part, a position calculated by a satellite positioning system.

[0072] Clause 14. The system of clause 11, wherein the vehicle comprises one or more sensors, and wherein the at least one processor is configured to utilize sensor information from the one or more sensors to obtain the first position.

[0073] Clause 15. The system of clause 14, wherein the one or more sensors comprise a lidar device, a camera device, a radar device, or a combination thereof.

[0074] Clause 16. The system of clause 11, wherein the one or more features include an intersection, a crosswalk, a geographic landmark, a building, a road width, a road sign, a traffic light, a telephone pole, a lamppost, or a combination thereof.

[0075] Clause 17. The system of clause 11, wherein the at least one processor is configured to obtain feature information comprising a distance and / or a position of at least one of the one or more features relative to the vehicle.

[0076] Clause 18. The system of clause 11, wherein the at least one processor is configured to correct the dead reckoning position using, at least in part, triangulation and / or trilateration.

[0077] Clause 19. The system of clause 11, wherein the at least one processor is configured to obtain position measurements of one or more features using, at least in part, sensor fusion.

[0078] Clause 20. The system of clause 11, wherein the at least one processor is further configured to: compile correction data related to the position of the vehicle over time; predict errors in dead reckoning using statistical bias and / or neural networks; and correct the current position of the vehicle using the predicted errors in dead reckoning.

[0079] Clause 21. A system for determining a position of a vehicle, the system comprising: means for obtaining a first position of the vehicle at a first time; means for determining a dead reckoning position of the vehicle at a second time; means for obtaining feature information at the second time; means for obtaining position measurements of one or more features identifiable based on the feature information; and means for correcting the dead reckoning position of the vehicle based on the position measurements.

[0080] Clause 22. The system of clause 21, further comprising: means for setting the first position as a corrected dead reckoning position; means for determining a second dead reckoning position of the vehicle at a third time; means for obtaining second feature information at the third time; means for obtaining a second position measurement of one or more features identifiable based on the second feature information; and means for correcting the second dead reckoning position of the vehicle based on the second position measurement.

[0081] Clause 23. The system of clause 21, wherein the means for obtaining the first position comprises obtaining a position calculated by a satellite positioning system.

[0082] Clause 24. The system of clause 21, wherein the vehicle comprises one or more sensors, and wherein obtaining position measurements of the one or more features comprises means for obtaining sensor information from the one or more sensors.

[0083] Clause 25. The system of clause 24, wherein the one or more sensors comprise a lidar device, a camera device, a radar device, or a combination thereof.

[0084] Clause 26. The system of clause 21, wherein the one or more features include an intersection, a crosswalk, a geographic landmark, a building, a road width, a road sign, a traffic light, a telephone pole, a lamppost, or a combination thereof.

[0085] Clause 27. The system of clause 21, wherein the means for obtaining feature information comprises obtaining a distance and / or a position of at least one of the one or more features relative to the vehicle.

[0086] Clause 28. The system of clause 21, wherein the means for correcting the dead reckoning position of the vehicle comprises triangulation and / or trilateration.

[0087] Clause 29. The system of clause 21, wherein the means for obtaining position measurements of one or more features comprises sensor fusion.

[0088] Clause 30. The system of clause 21, further comprising: means for compiling correction data related to the position of the vehicle over time; means for predicting errors in the dead reckoning using statistical bias and / or a neural network; and means for correcting the current position of the vehicle using the predicted errors in the dead reckoning.

[0089] Clause 31. A non-transitory processor-readable storage medium comprising processor-readable instructions configured to cause one or more processors to determine a position of a vehicle, the non-transitory processor-readable storage medium comprising: code for obtaining a first position of the vehicle at a first time; code for determining a dead reckoning position of the vehicle at a second time; code for obtaining feature information at the second time; code for obtaining position measurements of one or more features identifiable based on the feature information; and code for correcting the dead reckoning position of the vehicle based on the position measurements.

[0090] Clause 32. The non-transitory processor-readable storage medium of clause 31, further comprising: code for setting the first position as the corrected dead reckoning position; code for determining a second dead reckoning position of the vehicle at a third time; code for obtaining second feature information at the third time; code for obtaining a position measurement of one or more features identifiable based on the second feature information; and code for correcting the second dead reckoning position of the vehicle based on the second position measurement.

[0091] Clause 33. The non-transitory processor-readable storage medium of Clause 31, wherein the code for obtaining the first location comprises code for obtaining a location calculated by a satellite positioning system.

[0092] Clause 34. A non-transitory processor-readable storage medium as described in clause 31, wherein the vehicle includes one or more sensors, and wherein the code for obtaining position measurements of the one or more features includes code for obtaining sensor information from the one or more sensors.

[0093] Clause 35. The non-transitory processor-readable storage medium of clause 34, wherein the one or more sensors comprise a lidar device, a camera device, a radar device, or a combination thereof.

[0094] Clause 36. The non-transitory processor-readable storage medium of clause 31, wherein the one or more features comprise an intersection, a crosswalk, a geographic landmark, a building, a road width, a road sign, a traffic light, a telephone pole, a lamppost, or a combination thereof.

[0095] Clause 37. The non-transitory processor-readable storage medium of clause 31, wherein the code for obtaining feature information further comprises code for obtaining a distance and / or orientation of at least one of the one or more features relative to the vehicle.

[0096] Clause 38. The non-transitory processor-readable storage medium of Clause 31 , wherein the code for correcting the dead reckoning position of the vehicle comprises code for performing triangulation and / or trilateration.

[0097] Clause 39. The non-transitory processor-readable storage medium of clause 31, wherein the code for obtaining position measurements of one or more features comprises code for performing sensor fusion.

[0098] Clause 40. The non-transitory processor-readable storage medium of clause 31, further comprising: code for compiling correction data related to the position of the vehicle over time; code for predicting errors in the dead reckoning using statistical bias and / or a neural network; and code for correcting the current position of the vehicle using the predicted errors in the dead reckoning.

Claims

1. A method for determining a position of a vehicle, the method comprising: Obtaining a first position of the vehicle at a first time; determining a dead reckoning position of the vehicle at a second time; obtaining characteristic information at the second time; obtaining position measurements of one or more features identifiable based on the feature information; as well as The dead reckoning position of the vehicle is corrected based on the position measurement.

2. The method according to claim 1, further comprising: setting the first position as the corrected dead reckoning position; determining a second dead reckoning position of the vehicle at a third time; obtaining second feature information at the third time; obtaining a second position measurement of one or more features identifiable based on the second feature information; and The second dead reckoning position of the vehicle is corrected based on the second position measurement. The method of claim 1 , wherein obtaining the first position comprises obtaining a position calculated by a satellite positioning system. 4 . The method of claim 1 , wherein the vehicle comprises one or more sensors, and wherein obtaining position measurements of the one or more features comprises obtaining sensor information from the one or more sensors.

5. The method of claim 4, wherein the one or more sensors comprise a lidar device, a camera device, a radar device, or a combination thereof.

6. The method of claim 1, wherein the one or more features include an intersection, a crosswalk, a geographic landmark, a building, a road width, a road sign, a traffic light, a telephone pole, a lamppost, or a combination thereof. The method of claim 1 , wherein obtaining the feature information further comprises obtaining a distance or a position of at least one of the one or more features relative to the vehicle. 8 . The method of claim 1 , wherein correcting the dead reckoning position of the vehicle comprises triangulation or trilateration.

9. The method of claim 1, wherein obtaining position measurements of one or more features comprises sensor fusion.

10. The method according to claim 1, further comprising: compiling calibration data relating to the position of said vehicle over time; using statistical bias or neural networks to predict errors in the dead reckoning; as well as The predicted error in the dead reckoning is used to correct the current position of the vehicle.

11. A system for determining a position of a vehicle, the system comprising: Memory; at least one processor communicatively coupled to the memory and configured to: Obtaining a first position of the vehicle at a first time; determining a dead reckoning position of the vehicle at a second time; obtaining characteristic information at the second time; obtaining position measurements of one or more features identifiable based on the feature information; as well as The dead reckoning position of the vehicle is corrected based on the position measurement.

12. The system of claim 11, wherein the at least one processor is further configured to: setting the first position as the corrected dead reckoning position; determining a second dead reckoning position of the vehicle at a third time; obtaining second feature information at the third time; obtaining a second position measurement of one or more features identifiable based on the second feature information; and The second dead reckoning position of the vehicle is corrected based on the second position measurement.

13. The system of claim 11, wherein the at least one processor is configured to obtain the first position using, in part, a position calculated by a satellite positioning system.

14. The system of claim 11, wherein the vehicle comprises one or more sensors, and wherein the at least one processor is configured to utilize sensor information from the one or more sensors to obtain the first position.

15. The system of claim 14, wherein the one or more sensors comprise a lidar device, a camera device, a radar device, or a combination thereof.

16. The system of claim 11, wherein the one or more features include an intersection, a crosswalk, a geographic landmark, a building, a road width, a road sign, a traffic light, a telephone pole, a lamppost, or a combination thereof. 17 . The system of claim 11 , wherein the at least one processor is configured to obtain feature information comprising a distance or a position of at least one of the one or more features relative to the vehicle.

18. The system of claim 11, wherein the at least one processor is configured to correct the dead reckoning position using, at least in part, triangulation or trilateration.

19. The system of claim 11, wherein the at least one processor is configured to obtain position measurements of one or more features using, at least in part, sensor fusion.

20. The system of claim 11, wherein the at least one processor is further configured to: compiling calibration data relating to said position of said vehicle over time; using statistical bias or neural networks to predict errors in the dead reckoning; and The predicted error in the dead reckoning is used to correct the current position of the vehicle.

21. A system for determining a position of a vehicle, the system comprising: means for obtaining a first position of the vehicle at a first time; means for determining a dead reckoning position of the vehicle at a second time; means for obtaining characteristic information at the second time; means for obtaining a position measurement of one or more features identifiable based on the feature information; as well as Means for correcting the dead reckoning position of the vehicle based on the position measurement.

22. The system of claim 21, further comprising: means for setting the first position as the corrected dead reckoning position; means for determining a second dead reckoning position of the vehicle at a third time; means for obtaining second characteristic information at said third time; means for obtaining a second position measurement of one or more features identifiable based on the second feature information; as well as Means for correcting the second dead reckoning position of the vehicle based on the second position measurement.

23. The system of claim 21, wherein the vehicle includes one or more sensors, and wherein obtaining position measurements of the one or more features includes means for obtaining sensor information from the one or more sensors.

24. The system of claim 21, wherein the one or more features include an intersection, a crosswalk, a geographic landmark, a building, a road width, a road sign, a traffic light, a telephone pole, a lamppost, or a combination thereof.

25. The system of claim 21, wherein the means for obtaining feature information comprises obtaining a distance or a position of at least one of the one or more features relative to the vehicle.

26. The system of claim 21, wherein the means for correcting the dead reckoning position of the vehicle comprises triangulation or trilateration.

27. The system of claim 21, wherein the means for obtaining position measurements of one or more features comprises sensor fusion.

28. The system of claim 21, further comprising: means for compiling correction data relating to said position of said vehicle over time; means for predicting errors in said dead reckoning using statistical bias or a neural network; as well as Means for correcting a current position of the vehicle using the predicted error in dead reckoning.

29. A non-transitory processor-readable storage medium comprising processor-readable instructions configured to cause one or more processors to determine a position of a vehicle, the non-transitory processor-readable storage medium comprising: a code for obtaining a first position of the vehicle at a first time; code for determining a dead reckoning position of the vehicle at a second time; a code for obtaining feature information at the second time; code for obtaining a position measurement of one or more features identifiable based on the feature information; as well as Code for correcting the dead reckoning position of the vehicle based on the position measurement.

30. The non-transitory processor-readable storage medium of claim 29, further comprising: code for setting the first position as the corrected dead reckoning position; code for determining a second dead reckoning position of the vehicle at a third time; a code for obtaining second feature information at the third time; code for obtaining a position measurement of one or more features identifiable based on the second feature information; as well as Code for correcting the second dead reckoning position of the vehicle based on the second position measurement.

Images