Unmanned driving path planning system based on Internet of Things and cloud computing

Abstract

The invention discloses an unmanned driving path planning system based on Internet of Things and cloud computing, and relates to the field of path planning, the unmanned driving path planning system comprises a planning center, the planning center is in communication connection with a path planning module, a data acquisition module, a data analysis module, a path adjustment module and a control execution module; the method comprises the following steps of: preliminarily planning a path from a starting point to a terminal point of the driverless car to obtain a preliminarily planned path, collecting environment data of the obtained preliminarily planned path, and analyzing the collected environment data to obtain the influence degree of the environment data on the time for the driverless car to pass through the preliminary global path; the preliminarily planned path is adjusted according to the obtained influence degree, the driving path of the pilotless automobile is controlled according to the adjustment result, the preliminary path planning is performed firstly, then adjustment is performed according to the environment data, the optimal path is selected for driving, and the time of the pilotless automobile from the starting point to the ending point is greatly shortened.

Description

Technical Field

[0001] The present invention relates to the field of path planning, and specifically to an unmanned driving path planning system based on the Internet of Things and cloud computing. Background Art

[0002] With the development of society and the improvement of people's living standards, unmanned driving technology has gradually become a hot topic in today's society. The core of unmanned driving technology lies in path planning, which determines the safety, efficiency, and adaptability of vehicle driving; In the prior art, after the unmanned driving path planning is completed, the unmanned driving path is no longer changed, and the influence of environmental factors on the unmanned driving path is not considered, resulting in an increase in driving time and energy consumption and a reduction in traffic efficiency. How to adjust the unmanned driving path according to environmental factors so as to reduce driving time and energy consumption and improve traffic efficiency is a problem that we need to solve. For this reason, an unmanned driving path planning system based on the Internet of Things and cloud computing is provided. Summary of the Invention

[0003] In order to solve the above technical problems, the purpose of the present invention is to provide an unmanned driving path planning system based on the Internet of Things and cloud computing.

[0004] The purpose of the present invention can be achieved through the following technical solutions: An unmanned driving path planning system based on the Internet of Things and cloud computing, including a planning center, which is communicatively connected to a path planning module, a data acquisition module, a data analysis module, a path adjustment module, and a control execution module; The path planning module is used to preliminarily plan the path between the starting point and the ending point of the unmanned vehicle to obtain a preliminary global path; The data acquisition module is used to collect the environmental data of the preliminary global path; The data analysis module is used to analyze the collected environmental data to obtain the degree of influence of the environmental data on the time taken by the unmanned vehicle to pass through the preliminary global path; The path adjustment module is used to judge whether path adjustment is needed according to the obtained degree of influence and perform path adjustment according to the judgment result; The control execution module is used to control the driving path of the unmanned vehicle according to the path adjustment result.

[0005] Further, the process of the path planning module preliminarily planning the path between the starting point and the ending point of the unmanned vehicle includes: Establish a global map of the driving area of the unmanned vehicle, mark the starting point of the unmanned vehicle as the initial node, mark the ending point of the unmanned vehicle as the final node, and set a process node every m meters on the passable roads in the driving area; Select several corresponding process nodes according to the positions of the starting node and the ending node, and connect the starting node, the selected process nodes, and the ending node to obtain a preliminary global path.

[0006] Further, the environmental data includes the traffic flow of the preliminary global path, the speed limit, and the time that the driverless vehicle needs to wait for the traffic lights. Divide the preliminary global path into several sub-paths, record the sub-paths as driving sections, and collect the traffic flow, speed limit, and the time needed to wait for the traffic lights for each driving section.

[0007] Further, the process of the data analysis module analyzing the collected environmental data includes: Obtain the length of each driving section, and obtain the influence factor of the time taken for the driverless vehicle to pass through each driving section according to the traffic flow, speed limit, and the time needed to wait for the traffic lights of the collected driving section and the obtained length of the driving section, which is denoted as the passing time influence factor. Set the threshold range of the passing time influence factor, and obtain the influence degree of the environmental data of the driving section on the time taken for the driverless vehicle to pass through the driving section according to the comparison result between the obtained passing time influence factor and the set threshold range of the passing time influence factor. The influence degree includes normal influence, moderate influence, and severe influence.

[0008] Further, the process of the path adjustment module judging whether path adjustment is needed according to the obtained influence degree includes: If the influence degree of the environmental data of the driving section on the time taken for the driverless vehicle to pass through the driving section is a normal influence, then no path adjustment is needed. If the influence degree of the environmental data of the driving section on the time taken for the driverless vehicle to pass through the driving section is a moderate influence or a severe influence, then path adjustment is needed.

[0009] Further, the process of adjusting the path for the driving section with a moderate influence degree includes: Denote the starting point of the driving section as the starting node, the ending point of the driving section as the final node, and the process nodes adjacent to the starting node as adjacent process nodes. Obtain the adjacent process nodes of the starting node except the final node. Select the corresponding adjacent process node according to the positions of the starting node and the final node. Connect the starting node, the selected adjacent process node, and the final node to obtain an alternative driving section. If the impact degree of the alternative driving section is a normal impact, replace the driving section with the alternative driving section. If the impact degree of the alternative driving section is not a normal impact, obtain the adjacent process nodes of the starting node except the final node and the selected adjacent process node, and so on, until the impact degree of the alternative driving section is a normal impact. Replace the driving section with the alternative driving section. If there is no alternative driving section with a normal impact degree, drive according to the original driving section.

[0010] Further, the process of path adjustment for a driving section with a severe impact degree includes: Denote the starting point of the driving section as the starting node, the ending point of the driving section as the final node. Obtain the adjacent process nodes of the starting node except the final node. Select the corresponding adjacent process node according to the positions of the starting node and the final node. Connect the starting node, the selected adjacent process node, and the final node to obtain an alternative driving section. If the impact degree of the alternative driving section is a normal impact, replace the driving section with the alternative driving section; If the impact degree of the alternative driving section is not a normal impact, obtain the adjacent process nodes of the starting node except the final node and the selected adjacent process node, and so on, until the impact degree of the alternative driving section is a normal impact. Replace the driving section with the alternative driving section. If there is no alternative driving section with a normal impact degree, obtain the impact degrees of all alternative driving sections. If there is a moderate impact, replace the driving section with the first alternative driving section with a moderate impact degree. If there is no moderate impact, drive according to the original driving section.

[0011] Further, the process in which the control execution module controls the driving path of the driverless vehicle according to the path adjustment result includes: If the driving path is not adjusted, control the driverless vehicle to drive according to the original driving section; If the driving path is adjusted, control the driverless vehicle to drive according to the alternative driving section.

[0012] Compared with the prior art, the beneficial effects of the present invention are as follows: The path of the driverless vehicle from the starting point to the ending point is preliminarily planned to obtain a preliminary planned path. The environmental data of the obtained preliminary planned path is collected. The collected environmental data is analyzed to obtain the influence degree of the environmental data on the time taken by the driverless vehicle to pass through the preliminary global path. The preliminary planned path is adjusted according to the obtained influence degree. The driving path of the driverless vehicle is controlled according to the adjustment result. First, the preliminary path planning is carried out and then adjusted according to the environmental data, and the optimal path is selected for driving, reducing the driving time and energy consumption and improving the traffic efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 It is a schematic diagram of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0014] As Figure 1 shown, a driverless path planning system based on the Internet of Things and cloud computing includes a planning center, and the planning center is communicatively connected to a path planning module, a data collection module, a data analysis module, a path adjustment module, and a control execution module; The path planning module is used to preliminarily plan the path between the starting point and the ending point of the driverless vehicle to obtain a preliminary global path; It should be further noted that in the specific implementation process, the process of the path planning module preliminarily planning the path between the starting point and the ending point of the driverless vehicle includes: Establish a global map of the driving area of the driverless vehicle, mark the starting point of the driverless vehicle as the initial node, mark the ending point of the driverless vehicle as the final node, and set a process node every m meters on the passable roads within the driving area; Mark the process nodes adjacent to the starting node as adjacent process nodes, obtain the distance between the starting node and the adjacent process nodes, obtain the distance between the adjacent process nodes and the final node, add the obtained distance between the starting node and the adjacent process nodes to the corresponding distance between the adjacent process nodes and the final node to obtain the reachable distance of each adjacent process node, compare the reachable distances of each adjacent process node, and mark the adjacent process node with the smallest reachable distance as the reachable node; Obtain the adjacent process nodes of the reachable nodes, obtain the distances between the reachable nodes and their adjacent process nodes, obtain the distances between the adjacent process nodes of the reachable nodes and the final node, add the obtained distances between the reachable nodes and their adjacent process nodes to the distances between the adjacent process nodes of the reachable nodes and the final node to obtain the reachable distances of the adjacent process nodes of each reachable node, compare the reachable distances of the adjacent process nodes of each reachable node, and record the adjacent process node with the smallest reachable distance as the reachable node, and so on until the reachable node is the final node; Connect the starting node, all reachable nodes, and the final node, and the path formed by the connection is the preliminary global path.

[0015] The data acquisition module is used to acquire the environmental data of the preliminary global path; It should be further noted that, in the specific implementation process, the process of the data acquisition module acquiring the environmental data of the preliminary global path includes: The environmental data includes the traffic flow of the preliminary global path, the speed limit, and the time that the driverless vehicle needs to wait for the traffic lights; Record the sections from the starting node to the first reachable node, from the first reachable node to the second reachable node, from the second reachable node to the third reachable node, and so on until the section from the penultimate node to the antepenultimate node and the section from the last reachable node to the final node as the driving sections, label the driving sections, denoted as i, i = 1, 2, 3, ……, n, n≥1 and n is an integer; Acquire the traffic flow, speed limit, and the time needed to wait for the traffic lights of each driving section.

[0016] The data analysis module is used to analyze the acquired environmental data to obtain the influence degree of the environmental data on the time taken by the driverless vehicle to pass through the preliminary global path; It should be further noted that, in the specific implementation process, the process of the data analysis module analyzing the acquired environmental data includes: Denote the traffic flow of each driving section as Ci, denote the speed limit of each driving section as Vi, denote the time that each driving section needs to wait for the traffic lights as Ti, obtain the length of each driving section denoted as Li, and set the length of the driving section as the environmental data of the driving section; Obtain the influence factor of the time taken by the driverless vehicle to pass through each driving section according to the traffic flow, speed limit, the time needed to wait for the traffic lights, and the length of each driving section, denoted as the passing time influence factor; Denote the passing time influence factor as CTi; Where CTi = a×Ci + b / Vi + c×Ti + d×Li, where a is the weight coefficient of the traffic flow of each driving section, b is the weight coefficient of the speed limit of each driving section, c is the weight coefficient of the time required to wait for traffic lights at each driving section, d is the weight coefficient of the length of each driving section, and a, b, c, and d are all greater than zero; Set the threshold range of the passing time impact factor, and denote the set threshold range of the passing time impact factor as (CT0, CT1); Obtain the degree of influence of the environmental data of the driving section on the time taken by the driverless vehicle to pass through the driving section based on the comparison result between the obtained passing time impact factor and the set threshold range of the passing time impact factor; When CTi ≤ CT0, the degree of influence of the environmental data of the driving section on the time taken by the driverless vehicle to pass through the driving section is a normal influence; When CT0 < CTi < CT1, the degree of influence of the environmental data of the driving section on the time taken by the driverless vehicle to pass through the driving section is a moderate influence; When CTi ≥ CT1, the degree of influence of the environmental data of the driving section on the time taken by the driverless vehicle to pass through the driving section is a severe influence.

[0017] The path adjustment module is used to determine whether path adjustment is required based on the obtained degree of influence and perform path adjustment according to the determination result; It should be further noted that in the specific implementation process, the process by which the path adjustment module determines whether path adjustment is required based on the obtained degree of influence and performs path adjustment according to the determination result includes: If the degree of influence of the environmental data of the driving section on the time taken by the driverless vehicle to pass through the driving section is a normal influence, no path adjustment is required; If the degree of influence of the environmental data of the driving section on the time taken by the driverless vehicle to pass through the driving section is a moderate influence, path adjustment is required; Denote the starting point of the driving section as the starting node, and the end point of the driving section as the final node. Obtain the adjacent process nodes of the starting node except the final node, obtain the distance between the starting node and the adjacent process nodes, obtain the distance between the adjacent process nodes and the final node, add the obtained distance between the starting node and the adjacent process nodes to the distance between the adjacent process nodes and the final node to obtain the reachable distance of the adjacent process nodes, compare the reachable distances of each adjacent process node, denote the adjacent process node with the minimum reachable distance as the standby node, connect the starting node, the standby node and the final node to obtain a standby driving section, obtain the influence degree of the environmental data of the standby driving section on the time taken for the driverless vehicle to pass through the standby driving section. If the influence degree of the environmental data of the standby driving section on the time taken for the driverless vehicle to pass through the standby driving section is a normal influence, then replace the driving section with the standby driving section; If the influence degree of the environmental data of the standby driving section on the time taken for the driverless vehicle to pass through the standby driving section is not a normal influence, then obtain the adjacent process nodes of the starting node except the final node and the standby node, obtain the distance between the starting node and the adjacent process nodes, obtain the distance between the adjacent process nodes and the final node, add the obtained distance between the starting node and the adjacent process nodes to the distance between the adjacent process nodes and the final node to obtain the reachable distance of the adjacent process nodes, compare the reachable distances of each adjacent process node, denote the adjacent process node with the minimum reachable distance as the standby node, connect the starting node, the standby node and the final node to obtain a standby driving section, obtain the influence degree of the environmental data of the standby driving section on the time taken for the driverless vehicle to pass through the standby driving section. If the influence degree of the environmental data of the standby driving section on the time taken for the driverless vehicle to pass through the standby driving section is a normal influence, then replace the driving section with the standby driving section. If the influence degree of the environmental data of the standby driving section on the time taken for the driverless vehicle to pass through the standby driving section is not a normal influence, then continue to obtain other standby driving sections, and so on until the influence degree of the environmental data of the standby driving section on the time taken for the driverless vehicle to pass through the standby driving section is a normal influence, and replace the driving section with the standby driving section. If there is no standby driving section with a normal influence degree, then do not adjust the driving section; If the influence degree of the environmental data of the driving section on the time taken for the driverless vehicle to pass through the driving section is a severe influence, then path adjustment is required; Denote the starting point of the driving section as the starting node, and the end point of the driving section as the final node. Obtain the adjacent process nodes of the starting node except the final node, obtain the distance between the starting node and the adjacent process nodes, obtain the distance between the adjacent process nodes and the final node, add the obtained distance between the starting node and the adjacent process nodes to the distance between the adjacent process nodes and the final node to obtain the reachable distance of the adjacent process nodes. Compare the reachable distances of each adjacent process node, denote the adjacent process node with the smallest reachable distance as the standby node, connect the starting node, the standby node and the final node to obtain a standby driving section, and obtain the influence degree of the environmental data of the standby driving section on the time taken for the driverless vehicle to pass through the standby driving section. If the influence degree of the environmental data of the standby driving section on the time taken for the driverless vehicle to pass through the standby driving section is a normal influence, then replace the driving section with the standby driving section; If the influence degree of the environmental data of the standby driving section on the time taken for the driverless vehicle to pass through the standby driving section is not a normal influence, then obtain the adjacent process nodes of the starting node except the final node and the standby node, obtain the distance between the starting node and the adjacent process nodes, obtain the distance between the adjacent process nodes and the final node, add the obtained distance between the starting node and the adjacent process nodes to the distance between the adjacent process nodes and the final node to obtain the reachable distance of the adjacent process nodes. Compare the reachable distances of each adjacent process node, denote the adjacent process node with the smallest reachable distance as the standby node, connect the starting node, the standby node and the final node to obtain a standby driving section, and obtain the influence degree of the environmental data of the standby driving section on the time taken for the driverless vehicle to pass through the standby driving section. If the influence degree of the environmental data of the standby driving section on the time taken for the driverless vehicle to pass through the standby driving section is a normal influence, then replace the driving section with the standby driving section. If the influence degree of the environmental data of the standby driving section on the time taken for the driverless vehicle to pass through the standby driving section is not a normal influence, then continue to obtain other standby driving sections, and so on until the influence degree of the environmental data of the standby driving section on the time taken for the driverless vehicle to pass through the standby driving section is a normal influence, and replace the driving section with the standby driving section. If there is no standby driving section with a normal influence degree, then check the influence degrees of all standby driving sections. If there is a moderate influence, then replace the driving section with the first standby driving section with a moderate influence degree. If there is no moderate influence, then do not adjust the driving section.

[0018] The control execution module is used to control the driving path of the driverless vehicle according to the path adjustment result; It should be further noted that in the specific implementation process, the process of the control execution module controlling the driving path of the driverless vehicle according to the path adjustment result includes: If the driving path is not adjusted, the driverless vehicle is controlled to drive along the original driving section; If the driving path is adjusted, the driverless vehicle is controlled to drive along the alternate driving section.

[0019] 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 unmanned driving path planning system based on the Internet of Things and cloud computing, including a planning center, characterized in that: The planning center is communicatively connected with a path planning module, a data acquisition module, a data analysis module, a path adjustment module and a control execution module; The path planning module is used to preliminarily plan the path of the driverless car from the starting point to the end point to obtain a preliminary global path; The data collection module is used to collect environmental data of the preliminary global path; The data analysis module is used to analyze the collected environmental data to obtain the degree of influence of the environmental data on the time taken by the driverless car to pass the preliminary global path; The path adjustment module is used to determine whether path adjustment is required according to the obtained impact degree and to perform path adjustment according to the determination result; The control execution module is used to control the driving path of the driverless car according to the path adjustment result.

2. The unmanned driving path planning system based on the Internet of Things and cloud computing according to claim 1 is characterized in that: The process of the path planning module preliminarily planning the path of the driverless car from the starting point to the end point includes: Establish a global map of the driving area of ​​the driverless car, record the starting point of the driverless car as the initial node, record the end point of the driverless car as the final node, and set a process node every m meters on the passable roads in the driving area; According to the positions of the starting node and the final node, several corresponding process nodes are selected, and the starting node, the selected process nodes and the final node are connected to obtain a preliminary global path.

3. The unmanned driving path planning system based on the Internet of Things and cloud computing according to claim 2 is characterized in that: The environmental data includes the traffic flow of the preliminary global path, the speed limit, and the time the driverless car needs to wait for the traffic light; The preliminary global path is divided into several sub-paths, which are recorded as driving sections. The traffic volume, speed limit and waiting time for traffic lights of each driving section are collected.

4. The unmanned driving path planning system based on the Internet of Things and cloud computing according to claim 3 is characterized in that: The process of the data analysis module analyzing the collected environmental data includes: The length of each driving section is obtained, and the influence factor of the time taken by the driverless car to pass through each driving section is obtained according to the collected traffic volume, the limited speed, the time required to wait for the traffic light and the length of the driving section, which is recorded as the passing time influence factor; Setting a threshold range of a passing time influencing factor, and obtaining the degree of influence of the environmental data of the driving section on the time taken by the driverless vehicle to pass through the driving section according to a comparison result of the obtained passing time influencing factor and the set threshold range of the passing time influencing factor; The impact levels include normal impact, moderate impact, and severe impact.

5. The unmanned driving path planning system based on the Internet of Things and cloud computing according to claim 4 is characterized in that: The process of the path adjustment module judging whether path adjustment is required according to the obtained impact degree includes: If the environmental data of the driving section has a normal impact on the time taken by the driverless car to pass the driving section, no path adjustment is required; If the environmental data of the driving section has a moderate or severe impact on the time taken by the driverless car to pass the driving section, path adjustment is required.

6. The unmanned driving path planning system based on the Internet of Things and cloud computing according to claim 5 is characterized in that: The process of adjusting the route for a driving section with a moderate impact includes: The starting point of the driving section with moderate impact is recorded as the starting node, the end point of the driving section is recorded as the final node, and the process node adjacent to the starting node is recorded as the adjacent process node. The adjacent process nodes of the starting node except the final node are obtained, and the corresponding adjacent process nodes are selected according to the positions of the starting node and the final node. The starting node, the selected adjacent process node and the final node are connected to obtain a spare driving section. If the impact degree of the spare driving section is normal, the driving section is replaced with the spare driving section. If the impact degree of the spare driving section is not normal, the adjacent process nodes of the starting node except the final node and the selected adjacent process node are obtained, and so on, until the impact degree of the spare driving section is normal, the driving section is replaced with the spare driving section. If there is no spare driving section with normal impact, travel according to the original driving section.

7. The unmanned driving path planning system based on the Internet of Things and cloud computing according to claim 6 is characterized in that: The process of adjusting the route for the driving section with a severe impact includes: The starting point of the driving section with a severe impact is recorded as the starting node, and the end point of the driving section is recorded as the final node, and the adjacent process nodes of the starting node except the final node are obtained, and the corresponding adjacent process nodes are selected according to the positions of the starting node and the final node, and the starting node, the selected adjacent process nodes and the final node are connected to obtain a spare driving section, and if the impact degree of the spare driving section is normal, the driving section is replaced with the spare driving section; If the impact degree of the backup driving section is not a normal impact, then the adjacent process nodes of the starting node except the final node and the selected adjacent process nodes are obtained, and so on, until the impact degree of the backup driving section is a normal impact, and the driving section is replaced with the backup driving section. If there is no backup driving section with a normal impact degree, then the impact degree of all backup driving sections is obtained. If there is a moderate impact, then the driving section is replaced with the first backup driving section with a moderate impact degree. If there is no moderate impact, then travel according to the original driving section.

8. The unmanned driving path planning system based on the Internet of Things and cloud computing according to claim 7 is characterized in that: The process of the control execution module controlling the driving path of the driverless car according to the path adjustment result includes: If the driving path is not adjusted, the driverless car is controlled to drive along the original driving route; If the driving route is adjusted, the driverless car is controlled to drive along the alternative driving section.

Images