KR101454824B1 - System and Method for estimating positions of an autonomous mobile vehicle - Google Patents

Abstract

The present invention relates to a vehicle position estimation system, and more particularly, to a vehicle position estimation system that estimates the position of an autonomous vehicle using a plurality of sensors, estimates the reliability of each sensor in real time, And more particularly to an autonomous moving vehicle position estimation system that further improves estimation accuracy.
According to the present invention, even if the position of the autonomous mobile vehicle is estimated using a plurality of sensors, the reliability of each sensor can be determined in real time, and optimal sensor fusion can be performed, thereby reducing the calculation amount of the algorithm and improving the accuracy of the position estimation.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a system and method for estimating an autonomous moving vehicle,

The present invention relates to a vehicle position estimation system, and more particularly, to a vehicle position estimation system that estimates the position of an autonomous vehicle using a plurality of sensors, estimates the reliability of each sensor in real time, And more particularly to an autonomous moving vehicle position estimation system that further improves estimation accuracy.

In addition, even if the position of the autonomous moving vehicle is estimated using a plurality of sensors, it is possible to estimate the position of the autonomous moving vehicle, which realizes the reliability of each sensor in real time and performs optimal sensor fusion, Estimation method.

 In general, GPS (Global Positioning System) / INS (Inertial Navigation System) is used for location estimation of autonomous vehicles in ground environment.

However, in the ground environment, GPS is studying the use of various sensors (Compass, speedometer, image sensor, etc.) to compensate the INS error because the signal is easily disconnected by the surrounding environment (trees, buildings, etc.) Multi-sensor fusion is mainly based on centralized / distributed / federated methods.

Techniques for demonstrating this include QT Gu and J. Fang, "Global optimality for generalized federated filter", ACTA AUTOMATICA SINICA , vol. 35, no. 10, pp. 1310-1316, 2009., XB Gao, JG Chen, DC Tao, and XL Li, "Multi-Sensor Centralized Fusion without Measurement Noise Covariance by Variational Bayesian Approximation," IEEE Transactions on Aerospace and Electronic Systems , vol. 1, pp. 718-272, 2011. L. Cong, HL Qin, and ZH Tan, "Intelligent fault-tolerant algorithm with two-stage and feedback for integrated navigation federated filtering," Journal of Systems Engineering and Electronics , vol. 22, no. 2, pp. 274-282, 2011. < / RTI >

However, in the multi-sensor fusion method, as the number of used sensors increases, the computational complexity to process the sensors increases. In addition, when the performance of sensors that change according to changes in the surrounding environment is not considered, Accuracy can be rather reduced.

Also, in general, the autonomous moving vehicle position estimation system sets the initial position of the vehicle using the GPS when the INS is aligned. However, if the GPS signal is disconnected, it is impossible to set the initial position of the autonomous moving vehicle, and the autonomous driving is not smooth. In order to solve this problem, a method of hierarchically setting an initial position using multiple sensor information should be considered.

In addition, the general navigation operation of the autonomous mobile vehicle including the position estimation has many limitations in the navigation design and the sensor fusion because the parameters necessary for the navigation are included in the library and the access is impossible from the outside.

Therefore, in order to solve this problem, an open navigation system which makes all parameters related to the navigation including the position estimation of the autonomous mobile vehicle easily accessible through an external I / F is required.

1. Korean Patent No. 10-1061066 2. Korean Patent No. 10-1116033 3. Korean Patent No. 10-0912927

1. Q. T. Gu and J. Fang, "Global optimality for generalized federated filter ", ACTA AUTOMATICA SINICA, vol. 35, no. 10, pp. 1310-1316, 2009 2. X. B. Gao, J. G. Chen, D. C. Tao, and X. L. Li, "Multi-Sensor Centralized Fusion without Measurement Noise Covariance by Variational Bayesian Approximation," IEEE Transactions on Aerospace and Electronic Systems, vol. 1, pp. 718-272, 2011 3. L. Cong, H. L. Qin, and Z. H. Tan, "Intelligent fault-tolerant algorithm with two-stage and feedback for integrated navigation federated filtering," Journal of Systems Engineering and Electronics, vol. 22, no. 2, pp. 274-282, 2011.

The present invention has been proposed in order to solve the problem according to the above background art, and it is an object of the present invention to provide an open navigation method for easily accessing all parameters related to the navigation including the position estimation of an autonomous moving vehicle through an external I / The present invention provides a position estimation system for an autonomous mobile vehicle capable of realizing an autonomous mobile vehicle.

In addition, the present invention provides a position estimation method of an autonomous mobile vehicle capable of an open navigation structure that makes all variables related to the navigation including the position estimation of the autonomous mobile vehicle easily accessible through an external I / F , There are other purposes.

In order to accomplish the above-mentioned object, the present invention provides an autonomous moving vehicle capable of providing an open navigation structure allowing easy access to all the parameters related to the navigation including the position estimation of the autonomous moving vehicle through an external I / Of the position estimation system.

The position estimation system comprises:

A unit sensor layer for generating sensor data using sensors installed in the autonomous moving vehicle;

A unit navigation layer for generating navigation information corresponding to one of sensor-based navigation, image-based navigation, terrain-based navigation, and SLAM (Simultaneous Localization And Mapping) navigation using the sensor data;

An integrated navigation layer for determining and fusing the navigation mode using the navigation information; And

A navigation service layer for providing navigation service information on a user interface of the autonomous moving vehicle according to a fused navigation result; And a control unit.

The data communication between the unit sensor layer, the unit navigation layer, the integrated navigation layer, and the navigation service layer may be based on a distributed object-oriented middleware.

The unit sensor layer may include at least one of (D) a differential global positioning system (GPS), an inertial measurement unit (IMU), a compass, a traveling system, a stereo camera, a panoramic camera, a 2D radar, a 3D radar, Continuous Wave) radar.

The integrated navigation layer may further include a navigation manager for determining the navigation mode; And an integrated filter for fusing the determined navigation mode.

In addition, the navigation manager may receive the QoS information in real time from the sensors configured in the unit navigation layer, and divide the navigation mode into the localization mode and the SLAM mode based on the estimated navigation reliability.

The navigation manager may switch the localization mode to the SLAM mode if the current position of the autonomous vehicle can not be estimated.

The convergence mode includes a GPS / INS, a video / INS, a radar / INS, a traveling system / INS, a compass / INS. ≪ / RTI >

In addition, the user interface may include a configuration screen for setting navigation of the autonomous mobile vehicle, a data list showing navigation information of the unit navigation layer, and a map showing a real-time map of the navigation information of the unit navigation layer . ≪ / RTI >

In addition, the user interface may further include a post-processing navigation mode for performing performance analysis.

Another embodiment of the present invention, on the other hand,

A sensor data generation step of generating sensor data for the autonomous moving vehicle in the unit sensor layer;

A reliability determination step of determining reliability of an initial position of the autonomous mobile vehicle estimated using the sensor data;

A navigation mode determination step in which the navigation manager determines a navigation mode based on reliability judgment;

A sensor fusion step in which the integrated filter performs sensor fusion based on the navigation mode; And

And providing navigation service information on the user interface of the autonomous mobile vehicle according to the sensor fusion result.

The reliability determination step may include sequentially requesting the initial position to the unit navigation layer; Setting a previous end position of the autonomous moving vehicle as a current initial position and performing a navigation if the initial position is not set in the unit navigation layer; And if the initial position is set in the unit navigation layer, estimating the current position based on the previous last position and examining the entire area thereafter.

In addition, the sensor fusion step may further include a step of comparing the error between the current position and the GPS when the GPS is available, and correcting the navigation position error when the position error becomes larger than the threshold value.

According to the present invention, even if the position of the autonomous mobile vehicle is estimated using a plurality of sensors, the reliability of each sensor can be determined in real time, and optimal sensor fusion can be performed, thereby reducing the calculation amount of the algorithm and improving the accuracy of the position estimation.

As another effect of the present invention, the navigation manager can automatically set the initial position of the autonomous moving vehicle in a hierarchical manner using the multiple sensor information even when the GPS is disconnected, and the navigation variable can be accessed through the external I / F, Design / analysis and sensor fusion can be performed very efficiently.

1 is an example of a layered open navigation structure for more effectively performing multi-sensor fusion in an autonomous mobile vehicle position estimation system according to an embodiment of the present invention.
FIG. 2 is an example in which the navigation manager 121 shown in FIG. 1 performs data fusion using QoS information of unit navigation methods.
FIG. 3 is a flowchart illustrating a process of automatically setting an initial position of an autonomous moving vehicle when the navigation system is aligned, according to an embodiment of the present invention.
FIG. 4 is an example of a GUI (Graphic User Interface) for making variables necessary for operating a position estimation system of an autonomous mobile vehicle accessible from the outside according to an embodiment of the present invention.
FIG. 5 is an example of a screen for setting environment in the navigation operation GUI shown in FIG.
6 is an example of a screen of a data list displayed to the user in real time in the navigation operation GUI shown in FIG.
FIG. 7 is an example of a map showing a real-time image of unit navigation information in the navigation operation GUI shown in FIG.
FIG. 8 is an example of a selection screen for post-processing to further facilitate performance analysis of the position estimation system in the navigation operation GUI shown in FIG.
9 is a block diagram illustrating an adaptive federated sensor fusion architecture in the layered open navigation architecture shown in FIG.

While the invention is susceptible to various modifications and alternative forms, specific embodiments thereof are shown by way of example in the drawings and will herein be described in detail. It is to be understood, however, that the invention is not to be limited to the specific embodiments, but includes all modifications, equivalents, and alternatives falling within the spirit and scope of the invention.

Like reference numerals are used for similar elements in describing each drawing.

The terms first, second, etc. may be used to describe various components, but the components should not be limited by the terms. The terms are used only for the purpose of distinguishing one component from another.

For example, without departing from the scope of the present invention, the first component may be referred to as a second component, and similarly, the second component may also be referred to as a first component. The term "and / or" includes any combination of a plurality of related listed items or any of a plurality of related listed items.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

Terms such as those defined in commonly used dictionaries are to be interpreted as having a meaning consistent with the contextual meaning of the related art and are to be interpreted as either ideal or overly formal in the sense of the present application Should not.

Hereinafter, a system and method for estimating an autonomous moving vehicle according to an embodiment of the present invention will be described in detail with reference to the accompanying drawings.

1 is an example of a layered open navigation structure for more effectively performing multi-sensor fusion of an autonomous mobile vehicle position estimation system 100 according to an embodiment of the present invention.

Referring to FIG. 1, the position estimation system 100 is a multi-sensor fusion hierarchical structure, and has four layers (unit sensor layer, unit navigation layer, integrated navigation layer, and navigation service layer) And the hierarchical structure can be expanded / reduced according to the nature of the system.

The dual unit sensor layer 140 is composed of sensors used in an autonomous moving vehicle and the other layer is composed of software and / or hardware components for processing a navigation algorithm have. The data processing in each layer is roughly as follows.

1) Unit Sensor Layer 140: The sensor data is time-stamped for data fusion and passed to the unit navigation layer 130. To this end, the unit sensor layer 140 is provided with (D) a GPS (Differential Global Positioning System), an IMU (Inertial Measurement Unit), a compass, a traveling system and the like for generating sensor data for sensor- A stereo camera for generating image data for image-based navigation, a panoramic camera and the like, a 2D radar and a 3D radar for generating measurement data for terrain-based navigation, a SLAM (Simultaneous Localization and Mapping) And a frequency modulated continuous wave (FMCW) radar that generates measurement data for navigation.

2) Unit Navigation Layer 130: A sensor-based navigation component 131, an image-based navigation component 133, a terrain-based navigation module 130, Component 135, a simultaneous localization and mapping (SLAM) navigation component 137, and the like.

Based navigation component 133 is a GPS-based location, the image-based navigation component 133 is an image DB and a matching-based location, and the terrain-based navigation component 135 is an image- Dimensional matching-based position.

Each component processes the corresponding algorithm using the environment database (DB) and navigation information of the upper component, if necessary. Each position and navigation information and various information estimated in the unit navigation layer 130 are transmitted to the navigation manager of the upper component. Here, the navigation information and / or various types of information may include quality of service (QoS), for example.

3) Integrated Navigation Layer 120: It is composed of a navigation manager 121 and an integration filter 123, receives information generated in the unit navigation layer 130, and filters information. Based on the filtered information, .

The navigation mode is determined based on the QoS information of the sensor navigation unit 131, the image-based navigation unit 133, the terrain-based navigation 135, and the SLAM navigation 137 of the unit navigation layer 130. Here, the integration filter 123 performs navigation mode-based data fusion.

4) Navigation service layer 110: The navigation result fused by the integrated navigation layer 120 is transmitted to the navigation service 111. The navigation service 111 transmits the navigation result to the autonomous moving vehicle (not shown) The navigation result is transmitted to the autonomous running component 113 in the format requested by each component. Examples of the autonomous travel component 113 include a world model, a route plan, and an integrated control.

Data communication between layers and components is based on distributed object oriented middleware, which is a software layer between the operating system and applications in a distributed computer environment on the network.

FIG. 2 is an example in which the navigation manager 121 shown in FIG. 1 performs data fusion using QoS information of unit navigation methods. Referring to FIG. 2, in general, the QoS of the unit navigation in the field environment greatly changes according to the surrounding conditions and the accuracy of the DB, so that the QoS threshold of the sensors used in the autonomous mobile system can be corrected through the external I / Design.

In order to determine the actual QoS of the unit navigation, we use the value of the sensor itself, such as the DOP (dilution of precision) of the GPS, as well as the Kaiser quadrature (χ ² ) test.

[Equation 1]

here ,

The navigation manager 121 receives the QoS information 210 in real time from the sensor 200 configured in the unit navigation layer 140 in FIG. 1 and generates the navigation mode 230 based on the estimated QoS conditions 220 ) Are classified into two modes 231 and 233, and the navigation is performed by fusing the sensors 200 to estimate the position of the autonomous moving vehicle (not shown).

In addition, the sensor 200 includes (D) a GPS, a compass, an odometer, a stereo camera, a panoramic camera, a 2D radar, a 3D radar, a Frequency Modulated Continuous Wave (FMCW) Radar, and so on.

Thus, the QoS information 210 is generated from these components of the sensor 200. The QoS information 210 includes RTCM, HDOP, QoS _GPS , QoS _SC , and the like. Here, RTCM is a message format for determining whether the GPS is a DGPS mode or a GPS mode, HDOP is (D) DOP (dilution of precision) of _GPS , QoS _GPS is a QoS value of GPS, and the like.

In the navigation reliability 220, the value generated from the QoS information 210 is compared with a reference value (for example, ε _HDOP , ε _GPS , ε _SC, and the like to convert the navigation mode 230 into a localization mode 231 or a SLAM Mode 233 is selected.

In the situation where GPS is disconnected, components such as image navigation and terrain navigation can estimate the current position of the autonomous moving vehicle by matching with the environment DB. However, when there is no environment DB or inaccurate, the position error greatly increases, The current position can not be accurately estimated.

In this situation, the navigation manager 121 changes the localization mode 231 to the SLAM mode 233 to estimate the position of the autonomous moving vehicle based on the relative position. Below is an example of how the navigation manager 121 determines the navigation mode.

Here, the RTCM is a message format for determining whether the GPS is in the DGPS mode or the GPS mode.

In addition, the localization mode 231 is differentiated into a DGPS / INS (Inertial Navigation System), a GPS / INS, and a fusion mode 231-1. Here, the fusion mode 231-1 is fused with GPS / INS, video / INS, LADAR / INS, traveling system / INS, compass / INS,

In addition, the operation environment for the navigation manager 121 can be set by RDF (Resource Description Framework) 201 and / or user input 203. [

FIG. 3 is a flowchart illustrating a process of automatically setting an initial position of an autonomous moving vehicle when the navigation system is aligned, according to an embodiment of the present invention. That is, FIG. 3 is an example in which the initial position of the autonomous moving vehicle is automatically set upon navigation sorting. In the embodiment of the present invention, the autonomous moving vehicle can set initial positions as follows.

Referring to FIG. 3, the navigation manager (121 in FIG. 1) requests the initial position of the autonomous moving vehicle sequentially in the unit navigation layer (130 in FIG. 1) during the INS alignment time (steps S300 and S310).

For example, a sensor navigation method, a video navigation method, a terrain navigation method, and the like can be used (steps S320, S330, S340).

If one of these sensor navigation, image navigation, and terrain navigation is used, the image navigation method and the terrain navigation method first estimate the current position based on the vicinity of the previous position of the autonomous moving vehicle, and then search the entire area.

If the initial position can not be set in the unit navigation layer (130 in FIG. 1), the previous final position of the autonomous moving vehicle is automatically set as the current initial position and the navigation is performed (steps S350, S360, and S370).

At this time, if the GPS is available, the error between the current position and GPS is compared. If the position error is larger than the threshold value, the navigation position error is corrected as in the following equation.

&Quot; (2) "

,

If

,

는 항법에서 추정한 위치이고

는 GPS가 수신되었을 때 위치이다. here

Is the estimated position in navigation

Is the position when GPS is received.

Next, FIGS. 4 to 8 show an example of the operation of the open navigation system that makes the variables necessary for operating the autonomous moving vehicle position estimation system accessible from the outside. That is, FIG. 4 shows an example of a GUI (Graphic User Interface) for making variables necessary for operating a position estimation system of an autonomous mobile vehicle accessible from the outside according to an embodiment of the present invention.

FIG. 5 is an example of a screen for setting environment in the navigation operation GUI shown in FIG.

6 is an example of a screen of a data list displayed to the user in real time in the navigation operation GUI shown in FIG.

FIG. 7 is an example of a map showing a real-time image of unit navigation information in the navigation operation GUI shown in FIG.

FIG. 8 is an example of a selection screen for post-processing to further facilitate performance analysis of the position estimation system in the navigation operation GUI shown in FIG.

Accordingly, the operator can operate real-time navigation based on a UI (user interface) as shown in FIG. Such a user interface (UI) is largely composed of FIG. 5 showing an example of an environment setting screen, FIG. 6 showing a data list, and FIG. 7 showing a map.

FIG. 5 is a diagram showing an example of the environment setting screen in which all the parameters necessary for operating the position estimation system are accessible through the external I / F. All the input parameters in the environment setting are interlocked with the navigation operation parameters such as the integration filter / RTI >

An example of the screen of the data list shown in FIG. 6 is a part showing the navigation data of the unit navigation methods (for example, location, speed, QoS, etc.) to the user in real time.

The screen example of the map shown in FIG. 7 is a part showing in real time the position, speed, and direction of the unit navigation methods.

Also, in order to facilitate the performance analysis of the position estimation system, the post-processing navigation can be divided into four modes (1x, 5x, fast, step) as shown in FIG. Here, step is a part for processing the navigation data in the time unit inputted by the user.

As shown in FIGS. 4 to 8, the position estimation system can be designed / implemented based on the UI, thereby greatly improving the user's navigational operational convenience.

9 is a block diagram illustrating an adaptive federated sensor fusion architecture in the layered open navigation architecture shown in FIG. 9, the sensor data and the like are transmitted from the unit sensor layer 140 to the unit navigation layer 130 and the summation unit 920 compares the navigation information generated in the unit navigation layer 130 with the INS The information generated by the summation unit 920 is filtered by the local filter 930 and the verification unit 940 verifies the filtered information and transmits the information to the navigation manager 121 The navigation manager 212 determines the navigation mode based on the verified information and the like, and the integration filter 123 performs the navigation mode based data fusion.

In particular, the method of estimating an autonomous mobile vehicle according to an embodiment of the present invention may be implemented in the form of a program command code that can be executed through various computer means and recorded in a computer-readable storage medium.

The computer-readable storage medium may include program instructions, data files, data structures, and the like, alone or in combination.

The program instructions recorded on the medium may be those specially designed and constructed for the present invention or may be available to those skilled in the art of computer software.

Examples of computer-readable storage media include magnetic media such as hard disks, floppy disks and magnetic tape; optical media such as CD-ROMs and DVDs; magneto-optical media such as floppy disks; Magneto-optical media, and hardware devices specifically configured to store and execute program instructions such as ROM, RAM, flash memory, and the like.

The medium may be a transmission medium such as an optical or metal line, a wave guide, or the like, including a carrier wave for transmitting a signal designating a program command, a data structure, or the like.

Examples of program instructions include machine language code such as those produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter or the like. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the present invention, and vice versa.

In addition, one embodiment of the present invention may be implemented in hardware, software, or a combination thereof. (DSP), a programmable logic device (PLD), a field programmable gate array (FPGA), a processor, a controller, a microprocessor, and the like, which are designed to perform the above- , Other electronic units, or a combination thereof.

In a software implementation, it may be implemented as a module that performs the functions described above. The software may be stored in a memory unit and executed by a processor. The memory unit or processor may employ various means well known to those skilled in the art.

100: Position estimation system
110: Navigation service layer
111: Navigation services
113: Self-running component
120: Integrated Navigation Layer
121: Navigation Manager
123: Integrated Filter
130: Unit Navigation Layer
131: Sensor based navigation component
133: Image-based navigation component
135: Terrain based navigation component
137: SLAM (Simultaneous Localization And Mapping) navigation component
140: Unit sensor layer
141: sensor 143: camera 145: radar
201: RDF (Resource Description Framework) 203: user input
210: QoS information
220: Navigation reliability
230: Navigation mode
231: Localization mode
231-1: Fusion mode
233: SLAM mode
920:
930: Local filter
940:

Claims (14)

A unit sensor layer for generating sensor data using sensors installed in the autonomous moving vehicle;
A unit navigation layer for generating navigation information corresponding to one of sensor-based navigation, image-based navigation, terrain-based navigation, and SLAM (Simultaneous Localization And Mapping) navigation using the sensor data;
An integrated navigation layer for determining and fusing the navigation mode using the navigation information; And
And a navigation service layer for providing navigation service information on the user interface of the autonomous moving vehicle according to the fused navigation result,
Wherein the integrated navigation layer comprises: a navigation manager for determining the navigation mode; And an integrated filter that fuses the determined navigation mode,
Wherein the navigation manager receives QoS information in real time from sensors configured in the unit navigation layer and divides the navigation mode into a localization mode and a SLAM mode based on the estimated navigation reliability,
Wherein the navigation manager switches the localization mode to the SLAM mode if the current position of the autonomous mobile vehicle can not be estimated.
The method according to claim 1,
Wherein the data communication between the unit sensor layer, the unit navigation layer, the integrated navigation layer, and the navigation service layer is based on a distributed object-oriented middleware.
The method according to claim 1,
The unit sensor layer includes at least one of (D) a differential global positioning system (GPS), an inertial measurement unit (IMU), a compass, a traveling system, a stereo camera, a panoramic camera, a 2D radar, a 3D radar, and a Frequency Modulated Continuous Wave ) Radar. ≪ / RTI >
delete delete delete The method according to claim 1,
The localization mode is composed of a DGPS / INS (Inertial Navigation System), a GPS / INS, and a fusion mode. The fusion mode includes a GPS / INS, a video / INS, a radar / INS, a traveling system / INS, a compass / INS Wherein the autonomous moving vehicle is located at a center of the vehicle.
The method according to claim 1,
The user interface may display a configuration screen for setting the navigation of the autonomous mobile vehicle, a data list showing navigation information of the unit navigation layer, and a map showing the navigation information of the unit navigation layer in a real- Of the vehicle.
9. The method of claim 8,
Wherein the user interface further comprises a post-processing navigation mode for performing performance analysis.
A sensor data generation step of generating sensor data for the autonomous moving vehicle in the unit sensor layer;
A reliability determination step of determining reliability of an initial position of the autonomous mobile vehicle estimated using the sensor data;
A navigation mode determination step in which the navigation manager determines a navigation mode based on reliability judgment;
A sensor fusion step in which the integrated filter performs sensor fusion based on the navigation mode; And
And providing navigation service information on a user interface of the autonomous moving vehicle according to a sensor fusion result,
The reliability determination step may include:
Requesting the initial position sequentially to the unit navigation layer;
Setting a previous end position of the autonomous moving vehicle as a current initial position and performing a navigation if the initial position is not set in the unit navigation layer; And
And estimating a current position based on a vicinity of a previous last position and then examining an entire region if the initial position is set in the unit navigation layer.
delete 11. The method of claim 10,
Wherein the sensor fusion step further comprises the step of comparing the error between the current position and the GPS when the GPS is available and correcting the navigation position error when the position error is greater than the threshold value .
11. The method of claim 10,
Wherein the navigation manager receives the QoS information in real time from the sensors configured in the unit navigation layer and divides the navigation mode into the localization mode and the SLAM mode based on the estimated navigation reliability. .
14. The method of claim 13,
The localization mode is composed of a DGPS / INS (Inertial Navigation System), a GPS / INS, and a fusion mode. The fusion mode includes a GPS / INS, a video / INS, a radar / INS, a traveling system / INS, a compass / INS Wherein the autonomous moving vehicle is located at a center of the vehicle.

Images