CN108646752B

CN108646752B - Control method and device of automatic driving system

Info

Publication number: CN108646752B
Application number: CN201810650806.3A
Authority: CN
Inventors: 周倪青; 范贤根; 徐达学
Original assignee: Chery Automobile Co Ltd
Current assignee: Chery Automobile Co Ltd
Priority date: 2018-06-22
Filing date: 2018-06-22
Publication date: 2021-12-28
Anticipated expiration: 2038-06-22
Also published as: CN108646752A

Abstract

The invention discloses a control method of an automatic driving system, which comprises the following steps: acquiring map information in real time from a cloud platform, wherein the map information comprises geographical position information and road characteristic information corresponding to the geographical position information, and the road characteristic information is acquired by a plurality of vehicle terminals in the driving process and is sent to the cloud platform; importing map information into a locally stored road characteristic map; dividing the road characteristic map into a plurality of grid units with binary information by adopting a grid method to obtain a grid map; determining a first grid unit corresponding to the position of the vehicle and a second grid unit corresponding to a set terminal point in a grid map; planning a path between a first grid cell and a second grid cell within a grid map; and controlling the vehicle to automatically run according to the path. The invention can plan the driving path of the vehicle by adopting the map which is updated in real time and has high timeliness, thereby improving the accuracy of the planned path.

Description

Control method and device of automatic driving system

Technical Field

The invention relates to the field of automatic driving, in particular to a control method and a control device of an automatic driving system.

Background

An automatic automobile driving system, also called an automatic automobile and also called an unmanned automobile, is an intelligent automobile system which realizes unmanned driving through a vehicle-mounted computer system. At present, an automatic driving system of an automobile usually plans a driving path for the automobile by using a map, navigates the automobile and controls the automobile to drive. In the driving process, sensor assemblies such as a video camera, a radar sensor and a laser range finder are used for detecting the information of obstacles around the vehicle, and the vehicle is controlled to avoid the obstacles around the vehicle.

In the process of implementing the invention, the inventor finds that the prior art has at least the following problems:

in the prior art, the map used for planning the driving path for the vehicle is updated regularly by collecting data through a special mapping vehicle and then updating based on the collected data, the updating period is long, and the timeliness is poor, so that the accuracy of the driving path of the vehicle planned by using the map is not high, and the map is not beneficial to the automatic driving of the vehicle.

Disclosure of Invention

The embodiment of the invention provides a control method and a control device of an automatic driving system, which can plan a driving path of a vehicle by adopting a map which is updated in real time and has high timeliness, and improve the accuracy of the planned path. The technical scheme is as follows:

in one aspect, an embodiment of the present invention provides a control method for an automatic driving system, where the method includes: map information is acquired from a cloud platform in real time, the map information comprises geographical position information and road characteristic information corresponding to the geographical position information, and the road characteristic information comprises: the system comprises a cloud platform, a lane width, a road curvature, a road gradient, a tunnel length, a lane line, a road surface arrow and traffic marks, wherein the road characteristic information is acquired by a plurality of vehicle terminals in the driving process and is sent to the cloud platform; importing the map information into a locally stored road characteristic map; dividing the road characteristic map into a plurality of grid units with binary information by adopting a grid method to obtain a grid map; determining a first grid unit corresponding to the position of the vehicle and a second grid unit corresponding to a set terminal point in the grid map; planning a path between the first grid cell and the second grid cell within the grid map; and controlling the vehicle to automatically run according to the path.

Further, the method further comprises: collecting the road characteristic information in real time in the driving process of the vehicle; comparing the acquired road characteristic information with road characteristic information in the map information to acquire incremental characteristics, wherein the incremental characteristics are the road characteristic information which is different from the road characteristic information in the map information in the acquired road characteristic information; uploading the incremental features to the cloud platform.

Further, after the planning the path between the first grid cell and the second grid cell within the grid map, the method further comprises: obtain road conditions information through car and infrastructure communication, road conditions information includes: at least one of indicator light information, road speed limit information and road congestion information; and controlling the running speed of the vehicle in the path according to the road condition information.

Further, the method further comprises: in the running process of a vehicle, acquiring the state information of the vehicles around the vehicle through vehicle-to-vehicle communication, wherein the state information is used for indicating whether the corresponding vehicle has a fault or not; if the state information indicates that a fault vehicle exists in the vehicles around the vehicle, acquiring the position and size information of the fault vehicle; and controlling the vehicle to avoid the fault vehicle according to the position and size information of the fault vehicle.

Further, the method further comprises: acquiring a path of a vehicle ahead of the vehicle through vehicle-to-vehicle communication, wherein the vehicle ahead is a vehicle within a set distance from the vehicle in a driving direction of the vehicle; and if the paths of the vehicle and the front vehicle are at least partially the same, controlling the vehicle to track the front vehicle to run.

In another aspect, an embodiment of the present invention provides a control apparatus for an automatic driving system, where the apparatus includes: the acquisition module is used for acquiring map information from a cloud platform in real time, wherein the map information comprises geographic position information and road characteristic information corresponding to the geographic position information, and the road characteristic information comprises: the system comprises a cloud platform, a lane width, a road curvature, a road gradient, a tunnel length, a lane line, a road surface arrow and traffic marks, wherein the road characteristic information is acquired by a plurality of vehicle terminals in the driving process and is sent to the cloud platform; the importing module is used for importing the map information into a locally stored road characteristic map; the dividing module is used for dividing the road characteristic map into a plurality of grid units with binary information by adopting a grid method to obtain a grid map; the determining module is used for determining a first grid unit corresponding to the position of the vehicle and a second grid unit corresponding to the set terminal point in the grid map; a planning module to plan a path between the first grid cell and the second grid cell within the grid map; and the control module is used for controlling the vehicle to automatically run according to the path.

In one implementation manner of the present invention, the apparatus further includes: the acquisition module is used for acquiring the road characteristic information in real time in the driving process of the vehicle; the comparison module is used for performing feature comparison on the acquired road feature information and the road feature information in the map information to obtain an incremental feature, wherein the incremental feature is the road feature information which is different from the road feature information in the map information in the acquired road feature information; a sending module, configured to upload the incremental features to the cloud platform.

In an implementation manner of the present invention, the obtaining module is further configured to obtain road condition information through vehicle-infrastructure communication, where the road condition information includes: at least one of indicator light information, road speed limit information and road congestion information; the control module is further used for controlling the running speed of the vehicle in the path according to the road condition information.

In one implementation manner of the present invention, the obtaining module is further configured to obtain status information of vehicles around the vehicle through vehicle-to-vehicle communication during a vehicle driving process, where the status information is used to indicate whether a corresponding vehicle is faulty; the vehicle monitoring system is also used for acquiring the position and size information of the fault vehicle if the state information indicates that the fault vehicle exists in the vehicles around the vehicle; the control module is further used for controlling the vehicle to avoid the fault vehicle according to the position and size information of the fault vehicle.

In one implementation manner of the invention, the obtaining module is further configured to obtain, through vehicle-to-vehicle communication, a path of a vehicle ahead of the vehicle, where the vehicle ahead is a vehicle within a set distance from the vehicle in a traveling direction of the vehicle; the control module is further used for controlling the vehicle to track the front vehicle to run if the paths of the vehicle and the front vehicle are at least partially the same.

The technical scheme provided by the embodiment of the invention has the following beneficial effects:

according to the embodiment of the invention, the map information is acquired from the cloud platform in real time, the working space of the vehicle is divided into a plurality of grid units with binary information by adopting a grid method according to the map information, and the driving path of the vehicle is planned on the grid map, so that the driving path of the vehicle is planned by adopting the map which is updated in real time and has high timeliness, and the accuracy of the planned path is improved.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

FIG. 1 is a schematic diagram of an application scenario of an autopilot system according to an embodiment of the invention;

FIG. 2 is a flow chart of a control method for an autopilot system according to an embodiment of the present invention;

FIG. 3 is a flow chart of another control method for an autopilot system according to an embodiment of the present invention;

FIG. 4 is a schematic diagram of a sensor arrangement for an autopilot system according to an embodiment of the present invention;

FIG. 5 is a schematic diagram of information communication of an autopilot system according to an embodiment of the invention;

FIG. 6 is a schematic structural diagram of a control device of an automatic driving system according to an embodiment of the present invention;

fig. 7 is a block diagram of a control device of an automatic driving system according to an embodiment of the present invention.

The symbols in the drawings represent the following meanings:

1-laser radar, 21-first radar sensor, 22-second radar sensor, 3-ultrasonic radar, 41-stereo camera, 42-panoramic camera and 5-positioning module.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

Fig. 1 is a schematic diagram of an application scenario of an automatic driving system according to an embodiment of the present invention. As shown in fig. 1, a plurality of vehicle terminals 100 perform data interaction with a cloud platform 200, and the vehicle terminals 100 implement data interaction with the cloud platform 200 through a network. Each vehicle terminal 100 may download map information from the cloud platform 200, the map information including geographical location information and road characteristic information corresponding to the geographical location information, the road characteristic information including: lane width, road curvature, road slope, tunnel length, lane line, road surface arrow, and traffic sign. And each vehicle terminal 100 may also upload map information collected during driving to the cloud platform 200.

Fig. 2 is a flowchart of a control method of an automatic driving system according to an embodiment of the present invention. The method may be performed by a control unit of a vehicle. As shown in fig. 2, the method includes:

step 101: and acquiring map information from the cloud platform in real time.

The map information comprises geographical position information and road characteristic information corresponding to the geographical position information, and the road characteristic information comprises: lane width, road curvature, road slope, tunnel length, lane line, road surface arrow and traffic sign to road characteristic information is that each vehicle terminal gathers and sends to cloud platform in the driving process.

In step 101, the road characteristic information corresponding to the geographic position information indicates that the road characteristic information carries geographic position information, so that the control unit of the vehicle can distinguish which road the acquired road characteristic information indicates. For example, the lane width corresponding to the geographic location information indicates that the lane width carries the geographic location information, and the lane width of the road section to which the lane width specifically refers can be obtained according to the geographic location information.

Step 102: and importing the map information into a locally stored road characteristic map.

The locally stored road feature map is a map stored in a storage unit of the vehicle, and the road feature map includes the road on which the vehicle is traveling, the distribution of the road, and various types of road feature information as described in step 101.

In step 102, the process of importing the map information into the road feature map is a process of updating the road feature information in the road feature map, so as to obtain an updated road feature map.

Step 103: and dividing the road characteristic map into a plurality of grid units with binary information by adopting a grid method to obtain the grid map.

The binary information refers to two kinds of information, namely that each part in the road characteristic map has an obstacle and does not have the obstacle, for example, if a certain grid unit does not contain any obstacle, the grid unit is called as a free grid; otherwise, it is called barrier grid. In the embodiment of the invention, the free space and the obstacles for the vehicle to run are integrated into the grid unit. For example, the parts of the road feature map other than the road are divided into obstacle grids, and the parts of the road where vehicles can travel are free grids.

In the embodiment of the invention, when the road characteristic map is divided by adopting a grid method, the road characteristic map is firstly divided into a plurality of grid units with the same size, namely the whole road characteristic map is in a grid shape, and then whether each grid unit in the road characteristic map is a free grid or an obstacle grid is judged. In some embodiments of the present invention, the method for determining whether each grid cell in the road feature map is a free grid or an obstacle grid may be implemented by determining a grid cell representing a lane and a grid cell representing a non-lane in the road feature map, defining the grid cell representing the non-lane as an obstacle grid, temporarily positioning the grid cell representing the lane as a free grid, then obtaining map information from the locally stored road feature map, obtaining lane lines from the map information, screening lane lines (such as solid lines) indicating that the lane lines cannot cross, and replacing grid cells at the same position as the screened lane lines in the grid cells of the representative lane map with the screened lane lines as the obstacle grids, i.e., completing the grid division.

After the grid map is divided, the specific positions of the grid cells in the grid map can be represented by a rectangular coordinate method, a serial number method or a quadtree method.

In some embodiments of the present invention, when the vehicle is to upload the collected road characteristic information, in addition to adding the longitude and latitude to each road characteristic information in step 101, the vehicle may also upload the marked location information of the grid map and the road characteristic information to the cloud platform after being located in the above-mentioned marking manner of the grid map. The cloud platform and the vehicle can conveniently and quickly acquire the position information of the road characteristic information.

Step 104: and determining a first grid cell corresponding to the position of the vehicle and a second grid cell corresponding to the set terminal point in the grid map.

Prior to step 104, comprising obtaining a set endpoint.

In some implementations of embodiments of the invention, the set endpoint may be obtained from a vehicle-mounted human-computer interaction module, such as an endpoint input screen provided in the vehicle, and input by the user.

In some implementations of embodiments of the invention, the set destination may also be obtained from a destination command sent remotely to the vehicle via a mobile terminal (e.g., a smartphone).

In step 104, when the position of the vehicle is determined, the geographic position information (such as longitude and latitude) of the current position of the vehicle can be acquired through a positioning system of the vehicle, and the geographic position information is matched with a first grid unit corresponding to the current position of the vehicle in a grid map. And meanwhile, determining a corresponding second grid unit in the grid map according to the end point (set end point) input by the user.

Step 105: a path between the first grid cell and the second grid cell is planned within the grid map.

Step 105 comprises: and acquiring a path between the first grid unit and the second grid unit in the grid map by adopting a path searching algorithm.

In some embodiments of the invention, the path search algorithm may be an a-Star algorithm by which the shortest path between a first grid cell and a second grid cell in the grid map may be solved. The algorithm a is prior art and will not be described in detail here. In addition to the a-algorithm, various algorithms such as Dijkstra algorithm (Dijkstra algorithm) and Floyd algorithm (Floyd-Warshall, freouard algorithm) may be used in some embodiments of the present invention.

Step 106: and controlling the vehicle to automatically run according to the planned path.

Fig. 3 is a flowchart of another control method of an automatic driving system according to an embodiment of the present invention. The method may be performed by a control unit of a vehicle. As shown in fig. 3, the method includes:

step 201: and acquiring map information from the cloud platform in real time.

Wherein, the map information includes road characteristic information, and road characteristic information includes: lane width with location indicator, road curvature with location indicator, road gradient with location indicator, tunnel length with location indicator, lane line with location indicator, road surface arrow with location indicator, and traffic indicator with location indicator.

The map information may be acquired from the cloud platform periodically during the driving of the vehicle, and the period is short in the step 201. The map information can be acquired and downloaded from the cloud platform through a Vehicle to Network (V2N for short) unit.

Step 202: and importing the map information into a road characteristic map, wherein the road characteristic map is a map with initial map information.

After the map information is imported into the road characteristic map, the lane width, the road curvature, the road gradient, the tunnel length, the lane line, the road surface arrow and the traffic sign in the road characteristic map are updated.

In the embodiment of the invention, the lane width is used for defining the lateral movement range of the vehicle when the vehicle runs on the lane, and the situation that the vehicle runs across the lane can be avoided after updating, so that the running safety of the vehicle is improved. The lane curvature is used for defining the degree of bending of the lane (the lane is a curve), and the lane curvature is updated to avoid that the vehicle deviates from the curve due to the fact that the vehicle does not conform to the degree of bending of the curve when driving on the curve to turn. The road gradient is used for defining the degree of steepness of the lane, and after updating, the vehicle can be shifted and adjusted in speed in advance when entering the ramp, and the vehicle can smoothly pass through the ramp. The tunnel length is used for defining the length of the tunnel, and after the tunnel length is updated, the vehicle can be prevented from executing wrong driving instructions according to wrong tunnel length (for example, when the vehicle does not enter the tunnel, the vehicle lamp is turned on in advance to influence a driver driving the vehicle or misjudges that the vehicle leaves the tunnel to change the lane in the tunnel or turn off the vehicle lamp), so that the driving safety of the vehicle is improved. The lane line is a line for dividing the lane, and the condition that the vehicle is pressed to cross the lane when running can be avoided after updating. The road surface arrow is an arrow on the road surface for guiding the vehicle to run, and the situation that the vehicle runs along the reverse road and the like and does not run according to the instruction can be avoided after updating. The traffic sign is road facilities which transmit guidance, restriction, warning or indication information by characters or symbols, and is convenient for guiding vehicles to run after being updated.

In the embodiment of the invention, when the imported map information is the lane width, the control unit of the vehicle firstly acquires the geographical position information corresponding to the lane width from the map information, determines the lane width as the specific width of which lane according to the geographical position information, and further changes the lane width in the road characteristic map. It should be noted that the lane width is one sub-lane where the vehicle travels in the lane, for example, when the lane is a multi-lane, in order to accurately determine which sub-lane of the multi-lane the vehicle travels, each sub-lane in the lane may be labeled. In some embodiments of the present invention, the lane marking principle may be that, based on the driving direction of the lane, the respective sub-lanes in the lane are marked in a left-to-right sequence, for example, when the lane is a six-lane, the sequence of the marks from left to right may be 1, 2, 3, 4, 5, and 6. Therefore, the map information of the lane width uploaded to the cloud platform by the vehicle should include the serial number of the specific sub-lane in addition to the lane width and the geographic position information. After the control unit of the vehicle acquires the map information of the lane width from the cloud platform, when the characteristic road map is imported, the control unit of the vehicle can confirm the geographical position of the lane and also determine the serial number of the sub lane with the lane width to be updated, so that the sub lane with the changed width in the lane can be accurately found and the width of the sub lane can be updated.

In the embodiment of the present invention, when the imported map information is a road curvature, since the road curvatures of different sub-lanes are different, that is, the curvature degree of each sub-lane is different, the angle at which the vehicle needs to change direction through different sub-lanes is also different, and similarly to the above, the map information of the road curvature includes the road curvature and the geographic location information, and also includes the serial number of the sub-lane whose road curvature needs to be updated, wherein the specific serial number principle is consistent with the above.

In the embodiment of the invention, when the imported map information is the road gradient, the control unit of the vehicle firstly acquires the geographical position information corresponding to the road gradient from the map information, determines the road gradient as the specific gradient of which lane according to the geographical position information, and further changes the road gradient in the road characteristic map. Since the gradient of each sub lane in the lane for facilitating the vehicle to pass should be kept consistent when the lane has a gradient, the map information of the road gradient may not include the sequence number information of the sub lane.

In the embodiment of the invention, when the imported map information is the length of the tunnel, the control unit of the vehicle firstly acquires the geographical position information corresponding to the length of the tunnel from the map information, determines the length of the tunnel as the specific length of which tunnel according to the geographical position information, and further changes the length of the tunnel in the road characteristic map.

In the embodiment of the invention, when the imported map information is a lane line, a road surface arrow and a traffic sign, the control unit of the vehicle firstly acquires the geographical position information corresponding to the lane line, the road surface arrow and the traffic sign from the map information, and determines the road characteristic information of which specific lane line, road surface arrow and traffic sign are according to the geographical position information.

Step 203: and dividing the road characteristic map into a plurality of grid units with binary information by adopting a grid method to obtain the grid map.

Illustratively, the size of the grid cell may be 0.2m × 0.2m, and the smaller the size of the grid cell, the higher the accuracy of the grid map is indicated. The grid cell size can be reduced if the accuracy requirement for the grid map is higher, and the grid cell size can be increased if the accuracy requirement for the grid map is lower, and the work strength of the control unit of the vehicle can be reduced.

In the embodiment of the present invention, after the road feature map is divided into the grid maps by the grid method, each grid in the grid maps is labeled, and a rectangular coordinate method, a serial number method, or a quadtree method is generally adopted. When each grid in the grid map is labeled, the geographic position information or the positioning information corresponding to the grid is paired with the label of the grid, namely the geographic position information given to the grid can be determined through the grid label, or the grid label can be determined through the geographic position information of the grid.

Step 204: and determining a first grid cell corresponding to the position of the vehicle and a second grid cell corresponding to the set terminal point in the grid map.

In step 204, the vehicle positioning system obtains the position of the vehicle and determines the first grid cell, and determines the second grid cell according to the set end point input by the user.

In the embodiment of the invention, when the first grid unit is determined, the geographical position information of the position of the vehicle is determined through the positioning system, and how to pair the grid serial number corresponding to the geographical position information through the geographical position information is determined, so that the serial number of the first grid unit is determined.

In addition, when the user inputs a set terminal and then determines the second grid unit, the terminal characteristic building or the terminal characteristic building facility may be determined according to the set terminal, and then the grid serial number corresponding to the geographical location information may be obtained according to the geographical location information of the terminal characteristic building or the terminal characteristic building facility obtained and the pairing according to the geographical location information, so as to determine the second grid unit.

Illustratively, the set destination input by the user is usually a certain road or a certain building (such as a shopping square or an office building), when the set destination input by the user is a certain road, the control unit of the vehicle may acquire a characteristic building (such as an office building) or a characteristic facility (such as an intersection signal lamp) existing on the road through V2N as a destination characteristic building or a destination characteristic facility, and simultaneously acquire geographic characteristic information corresponding to the destination characteristic building or the destination characteristic facility through V2N, and then perform pairing to determine a corresponding second grid unit. When the set terminal input by the user is a certain building, the building can be directly used as a terminal characteristic building, the geographic characteristic information corresponding to the terminal characteristic building is obtained through V2N, and then pairing is carried out to determine the corresponding second grid unit.

Step 205: a path between the first grid cell and the second grid cell is planned within the grid map.

In step 205, a path search algorithm is used to obtain a path between a first grid cell and a second grid cell in the grid map. The path search algorithm may use a variety of algorithms such as an a-algorithm, Dijkstra algorithm (Dijkstra algorithm), Floyd algorithm (Floyd-Warshall, freuder algorithm), and the like.

In some embodiments of the present invention, when planning a path between a first grid cell and a second grid cell, road restriction information in a road feature map may be obtained first through Vehicle to Infrastructure communication (V2I), and a grid cell included in the restricted road is determined, and when planning a path, it is avoided that the planned path includes a grid cell representing the restricted road, and it is avoided that the Vehicle re-plans a path after traveling to the restricted path, thereby improving the operating efficiency of a control unit of the Vehicle.

Step 206: and controlling the vehicle to automatically run according to the path.

After the path is acquired through the step 204 and the step 206, the vehicle speed is controlled during the vehicle running, and the running speed is set for the vehicle, which can be acquired through executing the steps 206a to 206b, that is, the steps 206a to 206b can be executed while executing the step 206, or the steps 206a to 206b can be executed after executing the step 205.

Step 206 a: obtain road conditions information through car and infrastructure communication, road conditions information includes: at least one of indicator light information, road speed limit information and road congestion information.

In step 206a, the vehicle obtains the road condition information through the built-in V2I. When acquiring the information of the indicator light, the state of the indicator light and the time information of the state are acquired, and V2I can acquire the current state of the indicator light and the time information of the state from the traffic signal facility by establishing communication with the traffic signal facility (e.g., signal light) on the road. When acquiring the speed limit information of the road, the information to be acquired should include the speed limit and information on the road, and V2I may acquire the speed limit information of the road through networking. When the road congestion information is acquired, communication can be established with monitoring facilities arranged beside the road through V2I, and the vehicle congestion information or people flow density information on the road is acquired.

Step 206 b: and controlling the running speed of the vehicle in the path according to the road condition information.

In step 206b, when the indicator light information is acquired, the running speed of the vehicle may be determined according to the state of the indicator light and the time of the state. For example, the distance between the vehicle and the indicator light and the current vehicle speed can be obtained, the time for the vehicle to reach the indicator light is calculated, the state of the indicator light when the vehicle reaches the intersection where the indicator light is located is judged, if the indicator light is a red light, the running speed of the vehicle is adjusted to be low, and the state of the indicator light when the vehicle reaches the intersection where the indicator light is located is a green light; or when the vehicle reaches the intersection where the indicator light is located, the indicator light is changed from the green light to the red light, the running speed of the vehicle is increased, and the state of the indicator light is changed to the green light when the vehicle reaches the intersection where the indicator light is located.

For example, when the vehicle is acquired through the V2I that the distance from the vehicle to the next indicator lamp is 400m, the status of the indicator lamp is red, the duration of the red state is 30s, the vehicle running speed is 20m/s, it can be determined that the vehicle will arrive at the indicator lamp after 20s, and the indicator lamp is still red, in order to avoid waiting for parking, the vehicle speed needs to be adjusted to be lower than 13.3m/s, so as to ensure that the vehicle may not wait for directly passing through the indicator lamp.

When the road speed limit information is acquired, the driving speed of the vehicle on the road section can be directly adjusted according to the speed limit information.

When the acquired road congestion information is the vehicle congestion information, controlling the vehicle to run by changing lanes, and similarly, after the lane change, executing step 204 and step 205 again to obtain a new path; when the acquired road congestion information is the people flow dense information, the vehicle running speed is reduced, for example, the vehicle speed is reduced to a safe running speed of 5m/s, so that the vehicle is ensured to safely run through the people flow dense area.

After the path is determined in

step

201 and 206 and the vehicle travels along the planned path, steps 207a to 207c may be further executed, the road characteristic information is collected in steps 207a to 207c, and the map information is updated for the cloud platform, that is, in step 206, steps 207a to 207c should be synchronously executed, and steps 207a to 207c and steps 206a to 206b are independent from each other and have no sequence.

Step 207 a: and in the driving process of the vehicle, acquiring road characteristic information in real time.

Step 207a comprises: when the vehicle runs along the planned path, the road characteristic information is collected in real time through a sensor of the vehicle.

Fig. 4 is a schematic layout diagram of sensors of an automatic driving system according to an embodiment of the present invention, and as shown in fig. 4, in this embodiment, the sensors provided on the vehicle include: the device comprises a laser radar 1 arranged on the roof of the vehicle, a radar sensor arranged on the vehicle body in a surrounding mode, an ultrasonic radar 3 arranged on the vehicle body in a surrounding mode and a camera. The horizontal radiation angle of the laser radar 1 is 360 degrees, so that the obstacle information of the intelligent vehicle can be acquired within the range of 360 degrees; the radar sensor can be arranged on the two sides of a trunk and a front engine cover of the intelligent vehicle and in the front or the rear of the vehicle body, so that the distance information of the obstacles in the front, rear, left and right directions can be obtained; generally, the ultrasonic radar 3 has a short detection distance, so that the ultrasonic radar 3 can be used for detecting obstacles in a short distance, can be arranged around a vehicle body at equal intervals when the ultrasonic radar 3 is arranged, also can be intensively arranged at a certain position (the position where the vehicle is easy to rub and collide when running, such as the positions of four corners of the vehicle body), and is used for detecting the distance information of the obstacles in the circumferential direction of the intelligent vehicle when the ultrasonic radar 3 is arranged; the camera is used for observing barrier information and road condition information around the intelligent vehicle.

In the embodiment of the invention, the vehicle further comprises a positioning module 5, and the positioning precision of the positioning module 5 is 1-2 cm. The positioning module 5 is used for acquiring the position information of the intelligent vehicle, so that the control unit can conveniently acquire the map information of the place where the intelligent vehicle is located and the position relation between the map information and the road infrastructure, and the reliability of the intelligent vehicle is improved.

As shown in fig. 4, the radar sensors include four first radar sensors 21 disposed at four corners of the vehicle body and one second radar sensor 22 disposed in front of the vehicle body. Wherein the detection angle of the first radar sensor 21 is 150 °, the detection distance is 0-80m, the detection angle of the second radar sensor 22 is 20 °, and the detection distance is 0-175 m. The second radar sensor 22 disposed at the front of the vehicle body may be disposed near a middle position of a hood of the vehicle body, and in the embodiment of the present invention, the second radar sensor 22 may be a horizontal rotation radar sensor capable of performing a range of 20 ° or 90 ° and has a detection distance of 0 to 175m, which is not large, and is mainly used for detecting a front position obstacle of the smart car. The first radar sensors 21 are arranged at four corners of the vehicle body, have detection angles of 150 degrees and detection distances of 0-80m, and are mainly used for detecting obstacle information of the vehicle body position and the vehicle rear position.

Alternatively, the ultrasonic radar 3 includes ten ultrasonic radars 3 disposed around the vehicle body, and the detection range of the ultrasonic radar 3 is 0 to 60 m. The detection distance of the ultrasonic radar 3 is smaller than that of the radar sensor, the ultrasonic radar is mainly used for acquiring the obstacle information of the intelligent vehicle at the close-distance position in the embodiment of the invention, and the radar sensor is used for acquiring the remote obstacle information and is in division cooperation with the radar sensor, so that the reliability of the intelligent vehicle is improved.

As shown in fig. 4, the cameras include a stereo camera 41 and four all-round cameras 42, one stereo camera 41 is disposed on a front windshield of a vehicle window, two all-round cameras 42 are disposed on both sides of the smart car, and the other two all-round cameras 42 are disposed in front and rear of the smart car. The stereo camera 41 is a front-view camera arranged on the front windshield of the vehicle window and is responsible for observing objects or signal lights in front of the vehicle, and the all-round cameras 42 arranged on the two sides are used for observing objects around the intelligent vehicle.

Fig. 5 is a schematic diagram of information communication of an automatic driving system according to an embodiment of the present invention, and as shown in fig. 5, a radar sensor and an ultrasonic radar 3 are connected to a control unit by using a Controller Area Network (CAN) bus, and are connected to the control unit by using the CAN bus. The CAN bus has strong real-time performance, long transmission distance, strong anti-electromagnetic interference capability and strong error detection capability, CAN work in a high-noise interference environment, and improves the stability of signal transmission of an intelligent vehicle system. As shown in fig. 5, the laser radar 1 is connected to the Control unit through a User Datagram Protocol (UDP), and the camera is connected to the Control unit through a Transmission Control Protocol (TCP). Because the information acquired by the camera is more important to the information acquired by the laser radar 1, a TCP (transmission control protocol) connection mode with better stability is adopted when the camera is connected with the control unit, and because the radar sensor and the ultrasonic radar 3 exist, a UDP (user datagram protocol) connection mode with general stability is adopted when the laser radar 1 is connected with the control unit, so that the reasonability of line connection and distribution of the invention is embodied.

The lane width, road curvature, road slope, tunnel length, lane lines, road surface arrows and traffic signs are detected by the sensors. The lane width, road curvature, road slope and tunnel length may be detected by laser radar, radar sensors, for example, the lane width may be taken by a camera taking a picture of the lane, and the distance of the lane lines may be determined using image processing techniques to obtain the lane width. For another example, the road gradient may be determined by detecting the longitude and latitude and the height of two points on the road via a positioning module of the vehicle, thereby determining the distance and the height difference between the two points. The lane line, the road surface arrow and the traffic mark can be shot by the camera, feature recognition is carried out, and the lane line, the road surface arrow or the traffic mark is judged, the process of the feature recognition can be that the shot picture is compared with a template in a template database of the lane line, the road surface arrow and the traffic mark, and when the similarity of the comparison is greater than a set value, the lane line, the road surface arrow or the traffic mark is determined.

In addition, in the process of collecting the road characteristic information, the vehicle needs to be positioned in real time, and the positioned position information is matched with the corresponding road characteristic information, namely, each piece of road characteristic information has the position information corresponding to the road characteristic information.

Step 207 b: and comparing the acquired road characteristic information with the road characteristic information in the map information to acquire the incremental characteristic, wherein the incremental characteristic is the road characteristic information which is different from the road characteristic information in the map information in the acquired road characteristic information.

In step 207b, the lane width, the road curvature, the road gradient and the tunnel length of the road characteristic information can all be represented by numerical values, so that when the characteristics are compared, whether the corresponding numerical values are the same or not is determined by comparing, and if the numerical values are different after the characteristics are compared, the acquired numerical values of the lane width, the road curvature, the road gradient or the tunnel length are indicated as incremental characteristics.

After the lane lines, the road surface arrows, and the traffic signs in the road characteristic information are identified in step 207a, when the characteristics are compared, it may be directly compared whether the road characteristic information represents the same characteristics, for example, when the characteristics of the lane lines are compared, it is determined whether both the two lane lines are solid lines or dotted lines, and if the two lane lines are different, it indicates that the acquired lane lines are incremental characteristics. The process of comparing the characteristics of the road arrow and the traffic sign is consistent with the lane line, and the embodiment of the invention is not described herein.

Step 207 c: uploading the incremental features to the cloud platform.

In step 207c, the incremental features are uploaded to the cloud platform via the network via V2N.

In some embodiments of the present invention, the acquired road characteristic information may be uploaded to the cloud platform without feature comparison in step 207b, and the map information on the cloud platform may be directly covered after the uploading.

Step 207c only uploads the incremental feature value cloud platform, so that network traffic can be saved, and the updating process of the map information is quicker and quicker.

After the path is determined through the step 201 and the step 206 and the vehicle is driven along the planned path, the steps 208a to 208c are executed, the state information of the vehicle around the vehicle is obtained through the steps 208a to 208c, and the automatic driving of the vehicle is controlled, namely, the steps 208a to 208c can be synchronously executed when the step 206 is executed, and the steps 208a to 208c are independent from the steps 206a to 206b and the steps 207a to 207c without any sequence.

Step 208 a: in the vehicle running process, the state information of the vehicles around the vehicle is obtained through vehicle-to-vehicle communication.

Step 208a includes acquiring state information of surrounding vehicles through a Vehicle-to-Vehicle (V2V) unit during the Vehicle driving along the planned path, wherein the state information is used for indicating whether the corresponding Vehicle is faulty or not.

And step 208b, if the state information indicates that the fault vehicle exists in the vehicles around the vehicle, acquiring the position and size information of the fault vehicle.

In step 208b, if it is detected by the vehicle-to-vehicle communication unit that there is a vehicle in a failure state in the surrounding vehicles, the location and size information of the failed vehicle may be obtained in two ways. Firstly, communication is established with a fault vehicle through V2V, and geographical position information determined by a positioning system of the fault vehicle and size information stored in a storage unit of the vehicle are acquired from the fault vehicle; and secondly, the position information of the fault vehicle is determined by detecting the position and the distance of the fault vehicle through a sensor of the vehicle, and the size information of the fault vehicle is directly detected through the sensor. In the real-time example of the present invention, the position and size information of the faulty vehicle are acquired by the two methods, V2V and the information acquired by the sensor of the vehicle itself can be compared, if the position and size information of the faulty vehicle acquired by the two methods are consistent, the position and size information of the faulty vehicle is stored, and if the position and size information of the faulty vehicle acquired by the two methods are inconsistent, the position and size information detected by the sensor of the vehicle itself is used as the standard.

Step 208 c: and controlling the vehicle to avoid the fault vehicle according to the position and size information of the fault vehicle.

In step 208c, when the vehicle is controlled to avoid the faulty vehicle, whether the faulty vehicle is on the driving path of the vehicle can be judged according to the position information and the size information of the faulty vehicle, and if the faulty vehicle is not on the driving path of the vehicle, the driving path of the vehicle is not changed; and if the fault vehicle is judged to be in the running path of the vehicle, controlling the vehicle to shift the original running path leftwards or rightwards so as to avoid the fault vehicle. In addition, if a driver is carried in the vehicle, the driver can also perform emergency braking on the vehicle.

And 209a, acquiring the path of the vehicle in front of the vehicle through vehicle-to-vehicle communication.

In step 209a, a communication is established with the vehicle ahead through V2V to obtain a traveling path of the vehicle ahead, where the vehicle ahead is within a set distance from the vehicle in the traveling direction of the vehicle, and the set distance may be a distance of 1-2 vehicles.

Step 209 b: and if the paths of the vehicle and the front vehicle are at least partially the same, controlling the vehicle to track the front vehicle to run.

In step 209b, the fact that the vehicle and the preceding vehicle have at least partially the same route means that a partial route exists in the following route of the preceding vehicle from the current position as the starting point and a partial route exists in the following route of the vehicle from the current position as the starting point. And in the same partial path, adjusting the speed of the vehicle to enable the vehicle and the front vehicle to reach a safe distance, such as a distance of one vehicle length, then acquiring the speed of the front vehicle in real time through V2V, and controlling the vehicle to follow the front vehicle at the speed until the front vehicle finishes running the same partial path. At which point steps 209a-209b may be performed again. If the vehicle and the preceding vehicle do not have the same part of the path, step 206 is executed.

After the path is determined through step 201 and step 206, and when the vehicle travels along the planned path, steps 209a to 209b may be further executed, the obstacle information is uploaded through steps 209a to 209b, the remote control instruction of the cloud platform is obtained, and the vehicle is controlled, that is, when step 206 is executed, steps 209a to 209b may be synchronously executed, and steps 209a to 209b are independent from steps 206a to 206b, steps 207a to 207c, and steps 208a to 208c, and have no sequence.

In some embodiments of the invention, obstacle information obtained by a sensor of the vehicle may also be uploaded to the cloud platform. The obstacle information may include: and after the obstacle information is uploaded to the cloud platform, the cloud platform judges whether the obstacle is in the vehicle driving path according to the obstacle size and the position information similarly to the step 208c, generates a vehicle control command and sends the vehicle control command to the vehicle, and the mode is suitable for abnormal states with slow processing speed of a control unit of the vehicle, such as equipment aging and the like.

In some embodiments of the invention, the control unit of the vehicle may also gather a log of the progress of the vehicle. And the log information is stored and transmitted back to the cloud platform, so that a developer can conveniently diagnose on the cloud platform.

Fig. 6 is a schematic structural diagram of a control device of an automatic driving system according to an embodiment of the present invention, and as shown in fig. 6, the device includes:

the obtaining module 301 is configured to obtain map information in real time from a cloud platform, where the map information includes geographic position information and road characteristic information corresponding to the geographic position information, and the road characteristic information includes: the system comprises a lane width, a road curvature, a road gradient, a tunnel length, a lane line, a road surface arrow and a traffic sign, wherein road characteristic information is acquired by a plurality of vehicle terminals in the driving process and is sent to a cloud platform;

an importing module 302, configured to import map information into a locally stored road feature map;

the dividing module 303 is configured to divide the road feature map into a plurality of grid units with binary information by using a grid method to obtain a grid map;

the determining module 304 is used for determining a first grid unit corresponding to the position of the vehicle and a second grid unit corresponding to the set terminal point in the grid map;

a planning module 305 for planning a path between a first grid cell and a second grid cell within a grid map;

and the control module 306 is used for controlling the vehicle to automatically run according to the path.

In an implementation manner of the embodiment of the present invention, the apparatus further includes: the acquisition module 307 is used for acquiring road characteristic information in real time in the driving process of the vehicle; a comparison module 308, configured to perform feature comparison on the acquired road feature information and road feature information in the map information to obtain an incremental feature, where the incremental feature is road feature information that is different from the road feature information in the map information in the acquired road feature information; a sending module 309, configured to upload the incremental features to the cloud platform.

In an implementation manner of the embodiment of the present invention, the obtaining module 301 is further configured to obtain the traffic information through vehicle-infrastructure communication, where the traffic information includes: at least one of indicator light information, road speed limit information and road congestion information; the control module 306 is further configured to control the driving speed of the vehicle in the path according to the road condition information.

In an implementation manner of the embodiment of the present invention, the obtaining module 301 is further configured to obtain status information of vehicles around the vehicle through vehicle-to-vehicle communication during a vehicle driving process, where the status information is used to indicate whether a corresponding vehicle is faulty; the vehicle monitoring system is also used for acquiring the position and size information of the fault vehicle if the state information indicates that the fault vehicle exists in the vehicles around the vehicle; the control module 306 is further configured to control the vehicle to avoid the faulty vehicle according to the location and size information of the faulty vehicle.

In one implementation manner of the present invention, the obtaining module 301 is further configured to obtain, through vehicle-to-vehicle communication, a path of a vehicle ahead of the vehicle, where the vehicle ahead is a vehicle within a set distance from the vehicle in a driving direction of the vehicle; the control module 306 is further configured to control the vehicle to follow the vehicle ahead if the vehicle and the vehicle ahead have at least partially the same path.

Fig. 7 is a block diagram of a control device of an autopilot system according to an embodiment of the present invention, and as shown in fig. 7, the control device 700 of the autopilot system may be an in-vehicle computer or the like.

Generally, a control device 700 of an automatic driving system includes: a processor 701 and a memory 702.

The processor 701 may include one or more processing cores, such as a 4-core processor, an 8-core processor, and so on. The processor 701 may be implemented in at least one hardware form of a DSP (Digital Signal Processing), an FPGA (Field-Programmable Gate Array), and a PLA (Programmable Logic Array). The processor 701 may also include a main processor and a coprocessor, where the main processor is a processor for Processing data in an awake state, and is also called a Central Processing Unit (CPU); a coprocessor is a low power processor for processing data in a standby state. In some embodiments, the processor 701 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content required to be displayed on the display screen. In some embodiments, the processor 701 may further include an AI (Artificial Intelligence) processor for processing computing operations related to machine learning.

Memory 702 may include one or more computer-readable storage media, which may be non-transitory. Memory 702 may also include high-speed random access memory, as well as non-volatile memory, such as one or more magnetic disk storage devices, flash memory storage devices. In some embodiments, a non-transitory computer readable storage medium in memory 702 is used to store at least one instruction for execution by processor 701 to implement a method of controlling an autopilot system as provided by method embodiments herein.

In some embodiments, the control device 700 of the automatic driving system may further include: a peripheral interface 703 and at least one peripheral. The processor 701, the memory 702, and the peripheral interface 703 may be connected by buses or signal lines. Various peripheral devices may be connected to peripheral interface 703 via a bus, signal line, or circuit board. Specifically, the peripheral device includes: at least one of radio frequency circuitry 704, touch screen display 705, camera 706, audio circuitry 707, positioning components 708, and power source 709.

The peripheral interface 703 may be used to connect at least one peripheral related to I/O (Input/Output) to the processor 701 and the memory 702. In some embodiments, processor 701, memory 702, and peripheral interface 703 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 701, the memory 702, and the peripheral interface 703 may be implemented on a separate chip or circuit board, which is not limited in this embodiment.

The display screen 705 is used to display a UI (User Interface). The UI may include graphics, text, icons, video, and any combination thereof. When the display screen 705 is a touch display screen, the display screen 705 also has the ability to capture touch signals on or over the surface of the display screen 705. The touch signal may be input to the processor 701 as a control signal for processing. At this point, the display 705 may also be used to provide virtual buttons and/or a virtual keyboard, also referred to as soft buttons and/or a soft keyboard. In some embodiments, the display 705 may be one, the front panel of the control device 700 that provides the autopilot system; in other embodiments, the display screen 705 may be at least two, each disposed on a different surface of the control device 700 of the autopilot system or in a folded design; in still other embodiments, the display 705 may be a flexible display disposed on a curved surface or on a folding surface of the control device 700 of the autopilot system. Even more, the display 705 may be arranged in a non-rectangular irregular pattern, i.e. a shaped screen. The Display 705 may be made of LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode), or the like.

Power supply 709 is used to supply power to various components in control device 700 of the autopilot system. The power source 709 may be alternating current, direct current, disposable batteries, or rechargeable batteries. When power source 709 includes a rechargeable battery, the rechargeable battery may support wired or wireless charging. The rechargeable battery may also be used to support fast charge technology.

Those skilled in the art will appreciate that the configuration shown in fig. 7 does not constitute a limitation of the control device 700 of the autopilot system and may include more or fewer components than shown, or some components may be combined, or a different arrangement of components may be employed.

Embodiments of the present invention also provide a non-transitory computer-readable storage medium, where instructions of the storage medium, when executed by a processor of a control device of an autopilot system, enable the control device of the autopilot system to perform the control method of the autopilot system provided in the embodiment shown in fig. 2.

A computer program product containing instructions which, when run on a computer, cause the computer to carry out the control method of an autopilot system as provided in the embodiment shown in figure 2 above.

It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.

The present invention is not limited to the above preferred embodiments, and any modifications, equivalent replacements, improvements, etc. within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A control method of an automatic driving system, characterized in that the method comprises:

map information is acquired from a cloud platform in real time, the map information comprises geographical position information and road characteristic information corresponding to the geographical position information, and the road characteristic information in the map information comprises: the map information comprises lane width, road curvature, road gradient, tunnel length, lane lines, road surface arrows and traffic marks, wherein the road characteristic information in the map information further comprises serial numbers of sub lanes corresponding to the lane width, the sub lanes corresponding to the road curvature, the lane lines, the road surface arrows and the sub lanes corresponding to the traffic marks, and the road characteristic information in the map information is acquired by a plurality of vehicle terminals in the driving process and is sent to the cloud platform;

updating road characteristic information in a locally stored road characteristic map by adopting the map information;

dividing the road characteristic map into a plurality of grid units with binary information by adopting a grid method to obtain a grid map;

determining a first grid unit corresponding to the position of the vehicle and a second grid unit corresponding to a set terminal point in the grid map;

planning a path between the first grid cell and the second grid cell within the grid map;

controlling the vehicle to automatically run according to the path;

collecting road characteristic information in real time in the driving process of the vehicle; determining a grid label of the vehicle in the grid map according to the geographical position information of the vehicle;

comparing the acquired road characteristic information with the road characteristic information in the map information to obtain an incremental characteristic, wherein the incremental characteristic is different from the road characteristic information in the map information in the road characteristic information acquired by the vehicle;

uploading the incremental features and the grid labels to the cloud platform;

in the driving process of the vehicle, acquiring the state of an indicator light and the time of the state through vehicle-infrastructure communication; acquiring the distance between the vehicle and the indicator light and the vehicle speed of the vehicle; calculating a time of arrival of the vehicle at the indicator light; if the state of the indicator light is judged to be red when the vehicle reaches the intersection where the indicator light is located, the running speed of the vehicle is reduced, and the state of the indicator light is green when the vehicle reaches the intersection where the indicator light is located; if the state of the indicator light is changed from a green light to a red light when the vehicle reaches the intersection where the indicator light is located, the running speed of the vehicle is increased, and the state of the indicator light is changed into the green light when the vehicle reaches the intersection where the indicator light is located;

in the running process of the vehicle, acquiring the state information of the vehicles around the vehicle through vehicle-to-vehicle communication, wherein the state information is used for indicating whether the corresponding vehicle has a fault or not;

if the state information indicates that a faulty vehicle exists in the vehicles around the vehicle, the position and size information of the faulty vehicle is acquired in two ways:

acquiring geographical position information determined by the fault vehicle through a positioning system and size information stored in a storage unit from the fault vehicle through vehicle-to-vehicle communication; detecting the position and the distance of the fault vehicle through a sensor of the vehicle, so as to determine the position of the fault vehicle, and directly detecting the size information of the fault vehicle through the sensor;

and if the position and size information of the fault vehicle acquired by the two modes are inconsistent, controlling the vehicle to avoid the fault vehicle according to the position and size information of the fault vehicle detected by a sensor of the vehicle.

2. The control method according to claim 1, characterized in that the method further comprises:

acquiring a path of a vehicle ahead of the vehicle through vehicle-to-vehicle communication, wherein the vehicle ahead is a vehicle within a set distance from the vehicle in a driving direction of the vehicle;

and if the paths of the vehicle and the front vehicle are at least partially the same, controlling the vehicle to track the front vehicle to run.

3. A control apparatus of an automatic driving system, characterized in that the apparatus comprises:

the map information comprises geographic position information and road characteristic information corresponding to the geographic position information, and the road characteristic information in the map information comprises: the map information comprises lane width, road curvature, road gradient, tunnel length, lane lines, road surface arrows and traffic marks, wherein the road characteristic information in the map information further comprises serial numbers of sub lanes corresponding to the lane width, the sub lanes corresponding to the road curvature, the lane lines, the road surface arrows and the sub lanes corresponding to the traffic marks, and the road characteristic information in the map information is acquired by a plurality of vehicle terminals in the driving process and is sent to the cloud platform;

the import module is used for updating the road characteristic information in the locally stored road characteristic map by adopting the map information;

the dividing module is used for dividing the road characteristic map into a plurality of grid units with binary information by adopting a grid method to obtain a grid map;

the determining module is used for determining a first grid unit corresponding to the position of the vehicle and a second grid unit corresponding to the set terminal point in the grid map;

a planning module to plan a path between the first grid cell and the second grid cell within the grid map;

the control module is used for controlling the vehicle to automatically run according to the path;

the acquisition module is used for acquiring road characteristic information in real time in the driving process of the vehicle; the determining module is further used for determining a grid label of the vehicle in the grid map according to the geographic position information of the vehicle;

the comparison module is used for carrying out feature comparison on the acquired road feature information and the road feature information in the map information to obtain an incremental feature, wherein the incremental feature is the road feature information which is different from the map information in the acquired road feature information;

a sending module, configured to upload the incremental features and the grid labels to the cloud platform;

the control module is also used for acquiring the state of the indicator light and the time of the state through communication between the vehicle and infrastructure in the driving process of the vehicle; acquiring the distance between the vehicle and the indicator light and the vehicle speed of the vehicle; calculating a time of arrival of the vehicle at the indicator light; if the state of the indicator light is judged to be red when the vehicle reaches the intersection where the indicator light is located, the running speed of the vehicle is reduced, and the state of the indicator light is green when the vehicle reaches the intersection where the indicator light is located; if the state of the indicator light is changed from a green light to a red light when the vehicle reaches the intersection where the indicator light is located, the running speed of the vehicle is increased, and the state of the indicator light is changed into the green light when the vehicle reaches the intersection where the indicator light is located;

the control module is further used for acquiring state information of vehicles around the vehicle through vehicle-to-vehicle communication in the running process of the vehicle, wherein the state information is used for indicating whether the corresponding vehicle has a fault or not; if the state information indicates that a faulty vehicle exists in the vehicles around the vehicle, the position and size information of the faulty vehicle is acquired in two ways: acquiring geographical position information determined by the fault vehicle through a positioning system and size information stored in a storage unit from the fault vehicle through vehicle-to-vehicle communication; detecting the position and the distance of the fault vehicle through a sensor of the vehicle, so as to determine the position of the fault vehicle, and directly detecting the size information of the fault vehicle through the sensor; and if the position and size information of the fault vehicle acquired by the two modes are inconsistent, controlling the vehicle to avoid the fault vehicle according to the position and size information of the fault vehicle detected by a sensor of the vehicle.

4. The control device according to claim 3, wherein the acquisition module is further configured to acquire, through vehicle-to-vehicle communication, a path of a vehicle ahead of the vehicle, the vehicle ahead being a vehicle within a set distance from the vehicle in a traveling direction of the vehicle;

the control module is further used for controlling the vehicle to track the front vehicle to run if the paths of the vehicle and the front vehicle are at least partially the same.