KR102660497B1 - System for positioning location information of car - Google Patents

Abstract

The vehicle location information positioning system according to the present invention generates dead reckoning data by performing dead reckoning based on a sensor unit including one or more sensors mounted on the vehicle and sensing data from the sensor unit, and obtains GNSS data. A first processor that generates a real-time timer using the pps signal of the GPS included in the sensor unit, and the dead recording data, GNSS data, and real-time timer are acquired, and then a local time tag is attached to perform time synchronization. , A second processor generating a fusion positioning result in which the current location of the vehicle is estimated based on the result of the time synchronization and transmitting it to the first processor, wherein the first processor generates a fusion positioning result based on the fusion positioning result. The final location of the vehicle is then output.

Description

Vehicle location information positioning system {SYSTEM FOR POSITIONING LOCATION INFORMATION OF CAR}

The present invention relates to a location information determination system.

The autonomous driving system determines the location of the vehicle based on road map information constructed using GPS and various sensors (Radar, LiDAR, cameras, etc.), and compares it with GPS, vehicle data, and sensor signal data acquired during driving. do.

In autonomous driving, stably determining the location of the vehicle is one of the most important technical features, and for this purpose, DGPS (Differential GPS) and RTK-DGPS (Real Time Kinematic-Differential GPS), which can improve the location accuracy of GPS, are used. It is also used.

In addition, in order to correct the inevitable GPS positioning error, the error is corrected using map matching technology that compares the signal input from the sensor with a pre-constructed map.

Figure 8 is a block diagram of a navigation system 800 for an unmanned autonomous vehicle according to the prior art.

The prior art includes a location measuring unit 800 that measures location information, a virtual route setting unit 820 that sets a driving route based on stored map information, and an unmanned autonomous vehicle driving along a driving path set through a lane information setting unit. A driving information detection unit 830 that acquires actual lane information, a location information correction unit 840 that corrects location information through map matching of virtual lane information and actual lane information, and a location information output unit that outputs corrected location information. It consists of (850).

Since autonomous driving positioning technology directly affects the vehicle's control output at the current time, real-time and stability must be guaranteed.

However, the autonomous driving positioning technology according to the prior art has a problem in that it is difficult to guarantee real-time and stability of the output cycle because it must process a large amount of data from various sensors, high-precision maps, GPS, etc. for positioning.

An embodiment of the present invention provides a vehicle location information positioning system that can guarantee stability while processing various data such as various sensors of the vehicle, high-precision maps, and GPS in real time.

However, the technical challenge that this embodiment aims to achieve is not limited to the technical challenges described above, and other technical challenges may exist.

As a technical means for achieving the above-mentioned technical problem, a vehicle location information positioning system according to an embodiment of the present invention includes a sensor unit including one or more sensors mounted on the vehicle, and a dead signal based on sensing data of the sensor unit. Dead reckoning is performed to generate dead reckoning data, GNSS (Global Navigation Satellite System) data is acquired, and the pps (pulse per second) signal of the GPS included in the sensor unit is used to generate dead reckoning data. After acquiring the dead reckoning data, GNSS data, and real-time timer, and attaching a local time tag, time synchronization is performed, and based on the results of the time synchronization, the vehicle's It includes a second processor that generates a fusion positioning result in which the current location is estimated and transmits it to the first processor. At this time, the first processor outputs the final location of the vehicle based on the fusion positioning result.

The first processor may operate at preset intervals, and the second processor may operate asynchronously.

The first processor may output the dead recording data and the real-time timer to the second processor at each preset period, and output the GNSS data to the second processor at less than the preset period.

The second processor may perform the time synchronization based on second trajectory data that independently accumulates dead recording data obtained from the first processor.

The first processor may compensate for the time delay of the fusion positioning result using first trajectory data independently accumulated from the generated dead recording data.

The first trajectory data may be accumulated over a preset period of time and stored in a ring buffer.

The second processor receives pre-processed sensor data from the sensor unit, performs map matching based on the pre-processed sensor data, pre-stored map data, and the second trajectory data, and includes the pre-processed sensor data and the pre-stored map data. The local time tag may be attached to each of the map data and the second trajectory data.

The second processor may perform the time synchronization by changing the coordinate system of the map data to the coordinate system of the preprocessed sensor data based on an interpolation method.

The second processor may synchronize the map data based on the local time tag of the preprocessed sensor data.

The map matching is performed for each sensor corresponding to the pre-processed sensor data, and each sensor corresponding to the pre-processed sensor data has different time information as the local time tag is attached and synchronized, and the second processor The time synchronization can be performed by compensating for the delay time for each different time information.

The first processor performs the time synchronization by compensating for the delay time while the fusion positioning result is generated and delivered, and the first processor performs the time synchronization based on the real-time timer and the first trajectory data. can do.

According to any one of the means for solving the problems of the present invention described above, it is possible to provide location information positioning results that can guarantee real-time and stability in autonomous vehicles.

1 is a diagram schematically explaining an autonomous driving system in an embodiment of the present invention.
Figure 2 is a block diagram of a location information determination system according to an embodiment of the present invention.
3A and 3B are functional block diagrams of first and second processors according to an embodiment of the present invention.
Figure 4 is a diagram for explaining first and second trajectory data.
Figure 5 is a diagram for explaining each process of time synchronization performed in an embodiment of the present invention.
Figure 6 is an example of time synchronizing map data.
Figure 7 is a diagram to explain the time synchronized result.
Figure 8 is a block diagram of a navigation system for an unmanned autonomous vehicle according to the prior art.

Below, with reference to the attached drawings, embodiments of the present invention will be described in detail so that those skilled in the art can easily implement the present invention. However, the present invention may be implemented in many different forms and is not limited to the embodiments described herein. In order to clearly explain the present invention in the drawings, parts unrelated to the description are omitted.

Throughout the specification, when a part "includes" a certain element, this does not mean excluding other elements, but may further include other elements, unless specifically stated to the contrary.

The present invention relates to a vehicle location information determination system 100.

According to an embodiment of the present invention, it is possible to process various data such as various sensors, high-precision maps, and GPS in real time and at the same time ensure stability.

1 is a diagram schematically illustrating an autonomous driving system 1 according to an embodiment of the present invention.

The autonomous driving system 1 according to an embodiment of the present invention includes a location information determination system 100, a surrounding environment recognition system 10, a driving path creation system 20, and a vehicle control system 30.

The location information positioning system 100 can estimate accurate positioning information of the own vehicle using various sensors and a pre-built map.

The surrounding environment recognition system 10 can detect surrounding environment information such as vehicles, pedestrians, and obstacles, and the driving path creation system 20 fuses the positioning information and surrounding environment information to create a driving path.

The vehicle control system 30 controls the vehicle based on the generated path.

The present invention relates to the location information determination system 100 among the components of such an autonomous driving system.

The positioning technology for autonomous driving applied to the location information positioning system 100 according to an embodiment of the present invention will be described as follows.

First, satellite positioning technology is a positioning method based on GNSS (Global Navigation Satellite System) such as GPS, DGPS, and Network-RTK. Absolute coordinates can be received through satellite, and the error is variable at 5-~50m.

This satellite positioning technology has the disadvantage that the information is unreliable in areas where multi-paths occur, such as urban areas.

In order to compensate for these shortcomings, the location information positioning system 100 according to an embodiment of the present invention can correct the location information obtained from satellite positioning technology based on dead reckoning based on vehicle behavior.

In other words, the location information measured by satellite technology can be corrected by utilizing vehicle sensors and an inertial measurement unit (IMU) that measures vehicle speed, steering angle, wheel odometer, yaw rate, acceleration, etc.

Dead reckoning based on vehicle behavior is calculated by accumulating the movement of the own vehicle, and the error accumulates over time. Satellite positioning can be corrected to an error of about 1 to 10 m, but error accumulation continues to occur.

To this end, an embodiment of the present invention can correct location information by dead-reckoning based on vehicle behavior based on a map matching technique that uses a pre-stored precision map for autonomous driving.

The map matching technique determines the vehicle's location relatively based on the results of comparison between a precision map for autonomous driving and data acquired through one or more sensors installed on the vehicle (e.g., camera, stereo camera, AVM camera, lidar, etc.). This is a method of obtaining estimated location information.

Here, a precision map refers to a map constructed with three-dimensional coordinates of lanes, road surface information, sign information, and traffic light information as similar to the real world as possible.

Through this, it is possible to secure a level of accuracy that enables autonomous driving, but the price of the sensor is expensive and the error can be variable depending on the amount of information to be matched to the surroundings.

In order to implement such a location information positioning system 100, an embodiment of the present invention combines the above technologies with a technology (safety core, i.e. first processor) and processing in which the processing logic is relatively simple and real-time and stability must be guaranteed. Although the logic is complex and the amount of data handled is enormous, location information can be determined through technology (performance core, i.e. second processor) that does not require real-time guarantee.

Hereinafter, it will be described with reference to FIGS. 2 to 8.

Figure 2 is a block diagram of a location information determination system 100 according to an embodiment of the present invention. 3A and 3B are functional block diagrams of the first and second processors 120 and 130 according to an embodiment of the present invention.

Referring to FIG. 2, the vehicle location information positioning system 100 according to an embodiment of the present invention includes a sensor unit 110, a first processor 120, and a second processor 130.

The sensor unit 110 includes one or more sensors mounted on the vehicle. This sensor unit 110 may include a yaw sensor, direction sensor, wheel speed sensor, shift detection sensor, GNSS module, AVM, LiDAR, FCAM, etc.

The first processor 120 is a hard real time hardware platform such as a real time ECU and micro autobox, and corresponds to a platform whose real time and stability have been verified.

Technologies implemented in the first processor 120 include dead reckoning technology based on vehicle behavior and current location estimation technology that can output the current vehicle location to the recognition/planning/control module 140.

The second processor 130 is a CPU/GPU-based hardware platform and is a variety of high-performance autonomous driving platforms, including PCs. Technologies implemented by the second processor 130 include sensor data processing technology, map matching technology, and location fusion technology that fuses location coordinates estimated by satellite positioning/dead reckoning/map matching.

At this time, the logic implemented in the first processor 120 operates at preset intervals, and the logic implemented in the second processor 130 operates asynchronously (First Input First Output (FIFO), Triggered, Sampling). It is characterized by

Each function implemented by the first and second processors 120 and 130 will be described with reference to FIGS. 3A to 5.

Meanwhile, the first and second processors 120 and 130 may be driven by executing programs respectively stored in memory (not shown). The memory in which these programs are stored is a general term for non-volatile storage devices and volatile storage devices that continue to retain stored information even when power is not supplied.

For example, memory can be found in compact flash (CF) cards, secure digital (SD) cards, memory sticks, solid-state drives (SSD), and micro SD cards. It may include magnetic computer storage devices such as NAND flash memory and hard disk drives (HDD), and optical disc drives such as CD-ROM and DVD-ROM.

FIG. 3A is a functional block diagram of the first processor 120, and FIG. 3B is a functional block diagram of the second processor 130. Figure 4 is a diagram for explaining first and second trajectory data. Figure 5 is a diagram for explaining each process of time synchronization performed in an embodiment of the present invention.

First, referring to FIG. 3A, the first processor 120 generates dead accounting data by performing dead accounting based on the sensing data of the sensor unit 110 including the vehicle sensor and IMU.

At this time, the dead recording data performed is accumulated for a certain period of time in the first trajectory management unit, and this is a value accumulated over a short period of time and corresponds to reliable data.

In addition, the first processor 120 acquires GNSS data (latitude, longitude, heading, speed, quality, etc.) from GNSS and sets a real time timer in the time manager using the GPS pps (pulse per second) signal. Create.

At this time, the real-time timer is a reliable timer in ms units and is the standard time for outputting the final position of the own vehicle.

Meanwhile, the first processor 120 operates at a preset period (for example, assuming storage for 1 second at a period of 20ms, 50 vehicle location data are stored), and accordingly, the first trajectory data is stored for a preset certain time. It can be accumulated over time and stored in the ring buffer.

The first processor 120 may compensate for the delay time of the fusion positioning result received from the second processor 130 using the first trajectory data independently accumulated from the generated dead reckoning data.

The first processor 120 may output dead recording data and a real-time timer calculated at each timing to the second processor 130 at a preset period (for example, 50 times per second), and the GNSS output may be Depending on the GPS output cycle, the dead recording data may be output at a lower frequency than a preset cycle (for example, twice per second).

The first processor 120 transmits the dead reckoning data, GNSS data, and real-time timer obtained in this way to the second processor 130 (P1).

As shown in FIG. 3B, the second processor 130 receives dead recording data, GNSS data, and a real-time timer (P1) from the first processor 120 and can estimate the current location of the own vehicle.

At this time, since the second processor 130 uses data from several sensors (e.g., AVM, LIDAR, FCAM, etc.) included in the sensor unit 110, the second processor 130 operates asynchronously. , real-time processing time is also not guaranteed.

Accordingly, the result values generated by the second processor 130 have a time delay. To compensate for this time delay, the second processor 130 attaches its own local time tag to each data to achieve time synchronization. Carry out the process.

Data to which time tags are added in this way have different time information, meaning that they are data acquired from different vehicle locations. Therefore, in order to compensate for this, the second processor 130 receives the dead recording data obtained from the first processor 120 and performs time synchronization based on the second trajectory data accumulated by itself through the second trajectory management unit. can do.

At this time, the second trajectory data is generated completely independently from the first trajectory data generated by the first processor 120, and corresponds to a very reliable value acquired over a short period of time.

That is, the first trajectory data generated by the first processor 120 is accurate for a short time as described above, but since error accumulation over time is unavoidable, it has a different value from the current vehicle trajectory.

Accordingly, the second processor 130 rotates or moves the dead reckoning data (first trajectory data, P3) acquired from the first processor 120 as shown in FIG. 4 to the current position through the second trajectory management unit. The second trajectory data (P4) can be generated by modifying through .

The second processor 130 may perform time synchronization using the second trajectory data generated in this way, and generate a fusion positioning result (P2) in which the current location of the vehicle is estimated based on the time synchronization result. This is transmitted to the first processor 120, and the first processor 120 can output the final location of the vehicle by replacing it with the current coordinates based on the fusion positioning result (P2).

Meanwhile, since the fusion positioning result (P2) received by the first processor 120 reflects delay depending on data processing time, communication time, etc., the first processor 120 uses the first trajectory data generated from the first trajectory management unit. You can compensate for this by using .

Based on this, the recognition/planning/control module 140 can determine the current location of the vehicle and make a future driving plan.

Hereinafter, time synchronization performed in the first and second processors 120 and 130 according to an embodiment of the present invention will be described in more detail with reference to FIG. 5.

The second processor 130 may receive pre-processed sensor data from the sensor unit 110 and perform map matching based on the pre-processed sensor data, pre-stored map data, and second trajectory data.

At this time, a local time tag corresponding to the second processor 130 may be attached to the pre-processed sensor data, pre-stored map data, and second trajectory data, respectively.

The second processor 130 may perform time synchronization by changing the coordinate system of the map data to the coordinate system of the preprocessed sensor data based on an interpolation method, as shown in (a) of FIG. 5.

Additionally, the second processor 130 can synchronize map data based on the local time tag of sensor data as shown in FIG. 6, and in this case, the amount of movement of the vehicle over time utilizes the second trajectory data.

The second processor 130 may perform map matching for each sensor corresponding to the preprocessed sensor data. In other words, map matching can be performed for each sensor such as AVM, LIDAR, and front camera.

Each sensor corresponding to this preprocessed sensor data may have different time information as a local time tag is attached and synchronized. As time passes while map matching is performed, this all becomes past data, so the second processor ( 130) can perform time synchronization by compensating the delay time for each different time information, as shown in (b) of FIG. 5.

The first processor 130 may perform time synchronization by compensating for a delay time while the fusion positioning result is generated and transmitted from the second processor 130 to the first processor 120. That is, since the fusion positioning result generated by the second processor 130 becomes past data depending on the time of generating it and the communication time of transmitting it to the first processor 120, the first processor 130 is the data of FIG. 5. Time synchronization to compensate for this is performed as shown in (c).

At this time, the first processor 130 may perform time synchronization based on the real-time timer and the first trajectory data.

Figure 7 is a diagram to explain the time synchronized result.

Referring to FIG. 7, with respect to the map matching result (A1) at the previous viewpoint, the second processor 130 may estimate the location (A2) corresponding to the current viewpoint using the second trajectory data. Then, the second processor 130 compensates for the delay time within the location distribution range A3 and generates a map matching result A4 corresponding to the current time.

Next, the first processor 120 may perform time synchronization based on the real-time timer and the first trajectory data to generate the final fusion positioning result (A5).

Meanwhile, the second processor 130 can perform map matching using data sorting algorithms such as ICP, Hungarian action, and linear fitting algorithm, and fusion positioning using algorithms such as EKF (Extended Kalman Filter) and weighted sum. can produce results.

As such, the location information positioning system 100 according to an embodiment of the present invention provides real-time current information through logic separation and time synchronization between the first processor 120, which has real-time performance, and the second processor 130, which has high computational efficiency. The location can be transmitted to the recognition/planning/control module 140.

For reference, the components shown in FIG. 3 according to an embodiment of the present invention may be implemented in the form of software or hardware such as FPGA (Field Programmable Gate Array) or ASIC (Application Specific Integrated Circuit), and perform certain roles. can do.

However, 'components' are not limited to software or hardware, and each component may be configured to reside on an addressable storage medium or may be configured to run on one or more processors.

Thus, as an example, a component may include components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, procedures, and sub-processes. Includes routines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables.

Components and the functionality provided within them may be combined into a smaller number of components or further separated into additional components.

According to one of the embodiments of the present invention, it is possible to provide location information positioning results that can guarantee real-time and stability in autonomous vehicles.

Meanwhile, an embodiment of the present invention may also be implemented in the form of a computer program stored on a medium executed by a computer or a recording medium containing instructions executable by a computer. Computer-readable media can be any available media that can be accessed by a computer and includes both volatile and non-volatile media, removable and non-removable media. Additionally, computer-readable media may include both computer storage media and communication media. Computer storage media includes both volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules or other data. Communication media typically includes computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave, or other transmission mechanism, and includes any information delivery medium.

Although the methods and systems of the present invention have been described with respect to specific embodiments, some or all of their components or operations may be implemented using a computer system having a general-purpose hardware architecture.

The description of the present invention described above is for illustrative purposes, and those skilled in the art will understand that the present invention can be easily modified into other specific forms without changing the technical idea or essential features of the present invention. will be. Therefore, the embodiments described above should be understood in all respects as illustrative and not restrictive. For example, each component described as single may be implemented in a distributed manner, and similarly, components described as distributed may also be implemented in a combined form.

The scope of the present invention is indicated by the claims described below rather than the detailed description above, and all changes or modified forms derived from the meaning and scope of the claims and their equivalent concepts should be construed as being included in the scope of the present invention. do.

100: Location information positioning system
110: sensor unit
120: first processor
130: second processor

Claims (11)

In the vehicle location information positioning system,
A sensor unit including one or more sensors mounted on the vehicle,
Dead reckoning is performed based on the sensing data of the sensor unit to generate dead reckoning data, GNSS (Global Navigation Satellite System) data is acquired, and pps (pulse per second) of the GPS included in the sensor unit is generated. second) a first processor that generates a real time timer using a signal, and
After acquiring the dead reckoning data, GNSS data, and real-time timer, time synchronization is performed by attaching a local time tag, and a fusion positioning result in which the current location of the vehicle is estimated is generated based on the time synchronization result. and a second processor that transmits the information to the first processor,
The first processor outputs the final location of the vehicle based on the fusion positioning result,
The location information positioning system for a vehicle, wherein the first processor operates at preset intervals, and the second processor operates asynchronously.
delete According to claim 1,
The first processor outputs the dead recording data and the real-time timer to the second processor at the preset period, and outputs the GNSS data to the second processor at less than the preset period. .
According to claim 1,
The location information positioning system wherein the second processor performs the time synchronization based on second trajectory data that independently accumulates dead reckoning data obtained from the first processor.
According to claim 4,
The location information positioning system wherein the first processor compensates for the time delay of the fusion positioning result using first trajectory data independently accumulated from the generated dead recording data.
According to claim 5,
The location information positioning system wherein the first trajectory data is accumulated over a preset period of time and stored in a ring buffer.
According to claim 5,
The second processor receives pre-processed sensor data from the sensor unit and performs map matching based on the pre-processed sensor data, pre-stored map data, and the second trajectory data,
The location information positioning system wherein the local time tag is attached to the pre-processed sensor data, the pre-stored map data, and the second trajectory data, respectively.
According to claim 7,
The location information positioning system wherein the second processor performs the time synchronization by changing the coordinate system of the map data to the coordinate system of the preprocessed sensor data based on an interpolation method.
According to claim 7,
The location information positioning system wherein the second processor synchronizes the map data based on a local time tag of the preprocessed sensor data.
According to claim 7,
The map matching is performed for each sensor corresponding to the preprocessed sensor data,
Each sensor corresponding to the preprocessed sensor data has different time information as the local time tag is attached and synchronized, and the second processor performs the time synchronization by compensating for the delay time for each different time information. A location information positioning system that does this.
According to claim 5,
The first processor performs the time synchronization by compensating for the delay time while the fusion positioning result is generated and delivered,
The first processor performs the time synchronization based on the real-time timer and the first trajectory data.

Images