GIS-based automatic driving system and method

Abstract

The invention discloses a GIS-based automatic driving system and method, and the system comprises an automatic driving center which is in communication connection with a data collection module, a data processing module, a data analysis module, and a data execution module. Acquiring the position of the vehicle in real time, setting a judgment instruction, judging whether the vehicle runs on the mountain road or not, and acquiring image data in front of the vehicle in real time; setting a mountain position coefficient, and determining the value of the mountain coefficient according to the position of the mountain in the image data; according to the image data, obtaining a height vector, a width vector and a side vector of an obstacle in front of the vehicle, establishing a three-dimensional rectangular space, and mapping the obstacle in front of the vehicle into the three-dimensional rectangular space to obtain a geographic model; and obtaining an initial driving route according to the initial position and the final position of the vehicle, obtaining the obstacle offset of each obstacle, obtaining an offset index according to the mountain position coefficient, and further obtaining a final driving route.

Description

Technical Field

[0001] The present invention relates to the technical field of autonomous driving, and specifically provides an autonomous driving system and method based on GIS. Background Art

[0002] The autonomous driving technology based on GIS is a method that uses geographic information system technology to assist in realizing autonomous driving; on an autonomous driving vehicle, GIS combines high-precision maps and sensor data, and can provide detailed information on roads and traffic conditions. This helps the autonomous driving vehicle obtain the relative position relationship with the external environment, and at the same time obtain the current state of the vehicle and the absolute position relationship based on the map level; by comparing the perceived position relationship with the real-time data recognized by the sensor, the autonomous driving of the vehicle can be realized.

[0003] In the prior art, the autonomous driving technology mainly aims at obstacle avoidance and automatic driving route planning on conventional roads. For vehicles driving on mountain roads, the closer the vehicle is to the mountain, the lower the risk factor. However, the existing autonomous driving technology cannot make a safer driving route plan according to the position of the mountain. Therefore, an autonomous driving system and method based on GIS are provided. Summary of the Invention

[0004] In order to solve the above technical problems, the purpose of the present invention is to provide an autonomous driving system and method based on GIS.

[0005] In order to achieve the above purpose, the present invention provides the following technical solutions:

[0006] An autonomous driving system and method based on GIS, including an autonomous driving center, and the autonomous driving center is communicatively connected to a data acquisition module, a data processing module, a data analysis module, and a data execution module;

[0007] The data acquisition module is used to collect vehicle information, image data, and propagation time sets;

[0008] The data processing module is used to process the collected vehicle information, image data, and propagation time sets, and establish a geographic model when the vehicle is driving on a mountain road;

[0009] The data analysis module is used to plan a driving route according to the established geographic model;

[0010] The data execution module completes the driving process of the vehicle on the mountain road according to the driving route.

[0011] Further, the data acquisition module is provided with a positioning terminal, a collection terminal, and a detection terminal;

[0012] The positioning terminal is used to obtain the speed of the vehicle driving on a winding mountain road and to obtain the vehicle position of the vehicle driving on the winding mountain road in real time;

[0013] The acquisition terminal is arranged at the front of the vehicle and is used to obtain image data in the acquisition area at each acquisition time node;

[0014] The detection terminal is arranged at the front of the vehicle and is used to emit a parallel infrared light beam into each rectangular area in the acquisition area at each acquisition time node.

[0015] Further, the process of the positioning terminal obtaining the vehicle position further includes:

[0016] Set a judgment instruction. When the vehicle is driving on a winding mountain road, the judgment instruction is recorded as 1. When the vehicle is not driving on a winding mountain road, the judgment instruction is recorded as 0;

[0017] Record the vehicle position, the speed of the vehicle driving, and the judgment instruction as vehicle information.

[0018] Further, the process of the acquisition terminal acquiring the image data in front of the vehicle further includes:

[0019] Associate each acquired image data with the corresponding acquisition time node, and number each image data from front to back in the order of the acquisition time nodes to obtain image data;

[0020] Record the acquisition range of the acquisition terminal as the acquisition area, divide the acquisition area into several equal rectangular areas, and number each rectangular area.

[0021] Further, the process of the detection terminal emitting infrared light further includes:

[0022] Record the moment when the infrared light is emitted as the initial moment, record the moment when the infrared light contacts the obstacle and stops propagating as the cut-off moment, and record the time period between the initial moment and the cut-off time as the propagation time;

[0023] At each acquisition time node, obtain the propagation time of the infrared light in each rectangular area, associate the obtained propagation times with the numbers of the corresponding rectangular areas to obtain a propagation time set, and associate the propagation time set with the corresponding acquisition time node.

[0024] Further, the process of the data processing module processing the image data and the propagation time set includes:

[0025] Obtain the image data and the propagation time set, associate the image data with the propagation times of each rectangular area in the acquisition area and then integrate them;

[0026] According to the set of propagation times, each rectangular region in the image data is marked. Each rectangular region with an infinite propagation time is marked as 0, and the remaining rectangular regions are marked as 1;

[0027] The region formed by adjacent rectangular regions marked as 1 is denoted as an obstacle, and thus several obstacles are obtained in the image data.

[0028] Furthermore, the process of the data processing module processing the image data and the set of propagation times also includes:

[0029] According to the determination instruction in the vehicle information and according to the image data;

[0030] Denote the four vertices of the rectangular image data as point A, point B, point C, and point D respectively. Then the line segments AC and BD are associated with the two sides of the image data;

[0031] Taking the line segments AC and BD as the bases respectively, two triangles are obtained, and the midpoints of the two sides of the image data are obtained. Connecting the two midpoints, a median line is obtained;

[0032] Set a determination threshold, denoted as At a distance of from the line segment AC on the median line, a point is obtained, denoted as point O. At a distance of from the line segment BD on the median line, a point is obtained, denoted as point P. Thus, two points are obtained on the median line;

[0033] Then, two triangles are obtained from point O and the line segment AC, and from point P and the line segment BD, which are ΔACO and ΔBDP respectively;

[0034] Set the mountain position coefficient, denoted as g;

[0035] For each obstacle in the image data, when there is one obstacle that completely overlaps with ΔACO or ΔBDP, denote this obstacle as a mountain;

[0036] When the obstacle completely overlaps with ΔACO, then the mountain is on the left side of the vehicle, and at this time, denote g = 1;

[0037] When the obstacle completely overlaps with ΔBDP, then the mountain is on the right side of the vehicle, and at this time, denote g = -1;

[0038] When there are two obstacles that respectively completely overlap with ΔACO or ΔBDP, then there are mountains on both sides of the vehicle. When none of the obstacles in the image data completely overlap with ΔACO or ΔBDP, there are no mountains on both sides of the vehicle. In both of the above cases, denote g = 0;

[0039] When the determination instruction obtained in the vehicle information is 0, directly denote g = 0;

[0040] Based on the determination threshold and the image data, determine whether each obstacle in the image data is a mountain

[0041] And set the mountain position coefficient, and determine the value of the mountain position coefficient according to the position of the mountain in the image data

[0042] Further, the process of establishing the geographical model includes:

[0043] Based on the propagation time set, obtain the height vector, width vector and side vector of each obstacle in the image data

[0044] Establish a three-dimensional histogram space, obtain the position of the center point of the obstacle, and map each obstacle to the three-dimensional histogram space according to the position of the center point to obtain the geographical model

[0045] Further, the process of the data analysis module planning the driving route includes:

[0046] According to the vehicle position obtained in real time, record the first obtained vehicle position as the initial position, and the latest obtained vehicle position as the end position. Taking the initial position of the vehicle as the starting point and the end position as the end point, obtain the direction vector

[0047] According to the direction vector, draw the extension line of the direction vector to obtain an initial driving route

[0048] Obtain the distance between the center point of the obstacle in the geographical model and the end position of the vehicle, and obtain the obstacle offset of each obstacle according to the height vector, width vector and side vector of the obstacle

[0049] Obtain the driving route according to the obstacle offset of each obstacle and the mountain position coefficient

[0050] Compared with the prior art, the beneficial effects of the present invention are:

[0051] This method collects the vehicle position in real time, sets the determination instruction, determines whether the vehicle is driving on a winding mountain road according to the vehicle position, and collects the image data in front of the vehicle in real time; sets the mountain position coefficient, and determines the value of the mountain coefficient according to the position of the mountain in the image data; according to the image data collected in real time, obtain the height vector, width vector and side vector of the obstacle in front of the vehicle, and establish a three-dimensional histogram space, map the obstacle in front of the vehicle to the three-dimensional histogram space to obtain the geographical model; obtain the initial driving route according to the initial position and end position of the vehicle, and obtain the obstacle offset of each obstacle according to the position of the center point of the obstacle in the geographical model; finally, obtain the offset index according to the obstacle offset of each obstacle and the mountain position coefficient, and obtain the final driving route according to the offset index and the initial driving route Brief Description of the Drawings

[0052] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings.

[0053] Figure 1 It is the schematic diagram of the present invention. Detailed Embodiments

[0054] To make the objectives, technical solutions, and advantages of the present invention clearer, the following will describe the technical solutions of the present invention in detail. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope protected by the present invention.

[0055] As Figure 1 shown, a GIS-based autonomous driving system and method includes an autonomous driving center, and the autonomous driving center is communicatively connected to a data acquisition module, a data processing module, a data analysis module, and a data execution module;

[0056] The data acquisition module is used to acquire vehicle information, image data, and a set of propagation times;

[0057] The data acquisition module is provided with a positioning terminal, a collection terminal, and a detection terminal;

[0058] The positioning terminal is used to obtain the speed of the vehicle traveling on a mountain road and to obtain the vehicle position of the vehicle traveling on the mountain road in real time;

[0059] Based on the obtained vehicle position, it is determined whether the vehicle is traveling on a mountain road;

[0060] A determination instruction is set. When the vehicle is traveling on a mountain road, the determination instruction is recorded as 1. When the vehicle is not traveling on a mountain road, the determination instruction is recorded as 0;

[0061] The vehicle position, the speed of the vehicle traveling, and the determination instruction are recorded as vehicle information;

[0062] A collection time node threshold is set, and every other collection time node threshold is a collection time node;

[0063] The collection terminal is arranged at the front of the vehicle and is used to obtain image data in the collection area at each collection time node;

[0064] Associate each collected image data with the corresponding acquisition time node, and number each image data from front to back in the order of the acquisition time nodes to obtain the image data;

[0065] Record the acquisition range of the acquisition terminal as the acquisition area, divide the acquisition area into several equal rectangular areas, and number each rectangular area;

[0066] The detection terminal is set at the front of the vehicle and is used to emit a parallel infrared light to each rectangular area in the acquisition area at each acquisition time node;

[0067] Record the moment when the infrared light is emitted as the initial moment, record the moment when the infrared light touches the obstacle and stops propagating as the cut-off moment, and record the time period between the initial moment and the cut-off time as the propagation time;

[0068] At each acquisition time node, obtain the propagation time of the infrared light in each rectangular area, associate the obtained propagation times with the numbers of the corresponding rectangular areas to obtain a propagation time set, and associate the propagation time set with the corresponding acquisition time node;

[0069] The data acquisition module communicates and transmits the obtained vehicle information, image data and propagation time set to the data processing module;

[0070] The data processing module is used to process the collected vehicle information, image data and propagation time set, and establish a geographical model of the vehicle when driving on the mountain road;

[0071] The data processing module analyzes the image data and propagation time set at each acquisition time node in sequence according to the numbering order;

[0072] Obtain the image data and propagation time set at the same acquisition time node, associate the image data with the propagation times of each rectangular area in the acquisition area and then integrate them;

[0073] According to the propagation time set, mark each rectangular area in the image data, mark each rectangular area with an infinite propagation time as 0, and mark the remaining rectangular areas as 1;

[0074] Record the area composed of adjacent rectangular areas marked as 1 as the obstacle, and thus obtain several obstacles in the image data;

[0075] Obtain the determination instruction in the vehicle information. When the determination instruction is 1, judge the position of the mountain body in the image data. The process includes:

[0076] Denote the four vertices of the image data of the rectangle as point A, point B, point C, and point D respectively. Then, line segments AC and BD are associated with the two side edges of the image data.

[0077] Using line segments AC and BD as the bases respectively, obtain two triangles, and acquire the midpoints of the two side edges of the image data. Connect the two midpoints to get a median line.

[0078] Set a determination threshold, denoted as At a distance from line segment AC on the median line obtain a point, denoted as point O. At a distance from line segment BD on the median line obtain a point, denoted as point P. Thus, two points are obtained on the median line.

[0079] Then, from point O and line segment AC, and from point P and line segment BD, obtain two triangles, namely ΔACO and ΔBDP respectively.

[0080] Set a mountain position coefficient, denoted as g.

[0081] For each obstacle in the image data, when there is one obstacle that completely overlaps with ΔACO or ΔBDP, denote this obstacle as a mountain.

[0082] When the obstacle completely overlaps with ΔACO, the mountain is on the left side of the vehicle. At this time, denote g = 1.

[0083] When the obstacle completely overlaps with ΔBDP, the mountain is on the right side of the vehicle. At this time, denote g = -1.

[0084] When there are two obstacles that respectively completely overlap with ΔACO or ΔBDP, there are mountains on both sides of the vehicle. When none of the obstacles in the image data completely overlap with ΔACO or ΔBDP, there are no mountains on both sides of the vehicle. In both of these two cases, denote g = 0.

[0085] When the determination instruction in the vehicle information obtained is 0, directly denote g = 0.

[0086] Furthermore, remove the mountains from the image data and analyze the remaining obstacles. The process includes:

[0087] For any one of the remaining obstacles, denote the vertical direction of this obstacle in the image data as the height vector, and obtain the maximum value of the number of rectangular regions occupied by this obstacle in the vertical direction of the image data, denoted as H. Then, H is the magnitude of the height vector.

[0088] Denote the horizontal direction of this obstacle in the image data as the width vector, and obtain the maximum value of the number of rectangular regions occupied by this obstacle in the horizontal direction of the image data, denoted as W. Then, W is the magnitude of the width vector.

[0089] Obtain each rectangular area representing the width vector of the obstacle in the image data, and the propagation time corresponding to each rectangular area;

[0090] According to the speed of light and the propagation time of the infrared light, obtain the distance that the corresponding infrared light travels from the detection terminal to the rectangular area on each rectangular area, denoted as the propagation distance;

[0091] Obtain the numbers of each rectangular area occupied by the obstacle in the image data, and obtain the image data of the next acquisition time node. Find the corresponding rectangular areas according to the numbers in the image data of the next acquisition time node;

[0092] Obtain the change magnitude of the width vector of the obstacle in the image data of the next acquisition time node;

[0093] Obtain each rectangular area corresponding to the change in the magnitude of the width vector in the image data of the next acquisition time node, obtain the propagation time of the corresponding infrared light for each rectangular area, and then obtain the change amount of the propagation distance of the infrared light corresponding to each changed rectangular area;

[0094] Taking the change amount of the propagation distance as the magnitude and the forward direction as the direction, obtain the side vector of the obstacle, denoted as R;

[0095] Furthermore, obtain the center points of each obstacle, and obtain the numbers of the rectangular areas where the center points of the obstacles are located;

[0096] Establish a three-dimensional histogram space with the bottom surface consistent with the image data. Divide the bottom surface of the three-dimensional space into several rectangular areas, and number each rectangular area. The number of rectangular areas is the same as that of the image data;

[0097] According to the numbers of the rectangular areas where the obstacle center points are located, and then according to the height vectors, width vectors and side vectors of each obstacle, map the models of each obstacle in the three-dimensional histogram space to obtain the geographical model of the vehicle during driving on the mountain road;

[0098] The data processing module communicates and transmits the established geographical model to the data analysis module;

[0099] The data analysis module is used to plan the driving route according to the established geographical model;

[0100] Denote the first obtained vehicle position as the initial position, and the latest obtained vehicle position as the end position. Taking the initial position of the vehicle as the starting point and the end position as the end point, obtain the direction vector;

[0101] According to the direction vector, extend the direction vector to obtain an initial driving route;

[0102] The data analysis module sets an offset index, denoted as I, based on the vehicle position, the number of the obstacle center point, and the initial driving route. The process includes:

[0103] Map the vehicle position to the geographical model, obtain the number of the rectangular area where the vehicle position is located in the geographical model, and obtain the distances between the vehicle position and the centers of each obstacle according to the numbers of the rectangular areas where the center points of each obstacle are located in the geographical model;

[0104] And obtain an obstacle offset, denoted as S, according to the position of the rectangular area where the center point of the obstacle is located relative to the vehicle in the geographical model, as well as the height vector, width vector, and side vector of the obstacle, where

[0105] S = α(R + W) H k;

[0106] where α is a preset constant, k is an obstacle position coefficient. When the obstacle is on the left side of the vehicle, k = -1; when the obstacle is on the right side of the vehicle, k = 1;

[0107] Number each obstacle, denoted as s, where s > 0 and s is an integer. Then the obstacle offset of the obstacle numbered s is denoted as S s ;

[0108] Obtain the offset index I according to the obstacle offsets of each obstacle and the mountain position coefficient, where

[0109]

[0110] where β is a preset constant;

[0111] When the vehicle is driving along the initial driving route, when I < 0, the vehicle deviates to the left by an amount equal to the absolute value of I; when I > 0, the vehicle deviates to the right by an amount equal to the absolute value of I; when I = 0, the vehicle does not deviate, and the final driving route is obtained;

[0112] The data analysis module transmits the obtained driving route to the data execution module through communication;

[0113] The data execution module completes the driving process of the vehicle on the winding mountain road according to the driving route.

[0114] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical method of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical method of the present invention.

Claims

1. An autonomous driving system based on GIS, including an autonomous driving center, characterized in that, The autonomous driving center is communicatively connected to a data acquisition module, a data processing module, a data analysis module, and a data execution module; The data acquisition module is used to acquire vehicle information, image data, and a set of propagation times; The data processing module is used to process the acquired vehicle information, image data, and set of propagation times, and establish a geographical model of the vehicle when driving on a mountain road; The data analysis module is used to plan a driving route according to the established geographical model; The data execution module completes the driving process of the vehicle on the mountain road according to the driving route.

2. The automatic driving system based on GIS according to claim 1, characterized in that, The data acquisition module is provided with a positioning terminal, a collection terminal, and a detection terminal; The positioning terminal is used to obtain the speed of the vehicle when driving on the mountain road and to obtain the vehicle position of the vehicle when driving on the mountain road in real time; The collection terminal is arranged at the front of the vehicle, obtains the shooting range of the collection terminal, marks it as the collection area, divides the collection area into several rectangular areas, and obtains image data within the collection area through the collection terminal; The detection terminal is arranged at the front of the vehicle and is used to emit infrared light to each rectangular area within the collection area.

3. The automatic driving system based on GIS according to claim 2, characterized in that, The process of the positioning terminal obtaining the vehicle position further includes: Setting a determination instruction. When the vehicle is driving on the mountain road, the determination instruction is recorded as 1. When the vehicle is not driving on the mountain road, the determination instruction is recorded as 0; Recording the vehicle position, the speed of the vehicle, and the determination instruction as vehicle information.

4. The automatic driving system based on GIS according to claim 3, wherein, The process of the detection terminal emitting infrared light further includes: Recording the moment when the infrared light is emitted as the initial moment, recording the moment when the infrared light contacts an obstacle and stops propagating as the cut-off moment, and recording the time period between the initial moment and the cut-off time as the propagation time; Obtaining the propagation times of the infrared light in each rectangular area, associating the obtained propagation times with the numbers of the corresponding rectangular areas to obtain a set of propagation times, and associating the obtained set of propagation times with the image data of the corresponding rectangular areas.

5. The automatic driving system based on GIS according to claim 4, wherein, The process of the data processing module processing the image data and the set of propagation times includes: Obtaining the image data and the set of propagation times, integrating the image data after associating it with the propagation times of each rectangular area within the collection area; According to the set of propagation times, marking each rectangular area in the image data, marking each rectangular area with an infinite propagation time as 0, and marking the remaining rectangular areas as 1; Recording the area composed of adjacent rectangular areas marked as 1 as an obstacle, and thus obtaining several obstacles in the image data.

6. The automatic driving system based on GIS according to claim 5, characterized in that, The process of the data processing module processing the image data and the set of propagation times further includes: Setting a determination threshold according to the determination instruction in the vehicle information and the obtained image data; Judging whether each obstacle in the image data is a mountain body according to the determination threshold and the image data; And setting a mountain body position coefficient, and determining the value of the mountain body position coefficient according to the position of the mountain body in the image data.

7. An automatic driving system based on GIS according to claim 6, characterized in that, The process of establishing the geographical model includes: Obtaining the height vector, width vector, and side vector of each obstacle in the image data according to the set of propagation times; Establish a three-dimensional histogram space, obtain the positions of the obstacle center points, and map each obstacle to the three-dimensional histogram space according to the positions of the center points to obtain a geographical model.

8. The automatic driving system based on GIS according to claim 7, characterized in that, The process of planning the driving route by the data analysis module includes: Based on the vehicle position obtained in real time, obtain the initial position and the final position of the vehicle; And based on the initial position and the final position of the vehicle, obtain the initial driving route; Obtain the distance between the obstacle center point in the geographical model and the final position of the vehicle, and obtain the obstacle offset of each obstacle according to the height vector, width vector and side vector of the obstacle; Obtain the driving route according to the obstacle offset of each obstacle and the mountain position coefficient.

Images