Traffic accident auxiliary processing method and system based on unmanned aerial vehicle

Abstract

The invention provides an unmanned aerial vehicle-based traffic accident auxiliary processing method and system, and the method comprises the steps: determining a first coordinate of an accident site on an electronic map according to alarm information, and obtaining second coordinates and electric quantity of a plurality of unmanned aerial vehicles in a standby state at the periphery; respectively calculating the distance between the unmanned aerial vehicle and the accident site, and calculating the distance score and the electric quantity score of each unmanned aerial vehicle; performing comprehensive scoring according to a preset distance weight and an electric quantity weight, and selecting the unmanned aerial vehicle with the highest comprehensive score to execute a task; the node with the minimum f (n) value is selected as the current node, and circulation is carried out in sequence until the first coordinate is reached, and a flight path is obtained; and the unmanned aerial vehicle goes to the accident site according to the flight path, shoots a field picture according to the control instruction, performs voice communication with the field, obtains picture data and voice data, and returns the picture data and the voice data to the command center. According to the invention, the most suitable unmanned aerial vehicle can be quickly and accurately selected to go to the accident scene, and the path and unmanned aerial vehicle unified scheduling are planned.

Description

Technical Field

[0001] The present invention relates to the field of traffic management systems, and in particular, to a method and system for assisting in handling traffic accidents based on unmanned aerial vehicles (UAVs). Background Art

[0002] In existing emergency handling scenarios, the information collection and preliminary processing of accident scenes are often inefficient. The traditional method relies on manual personnel to rush to the scene. In cases such as traffic congestion, it is impossible to quickly reach the accident site for situation collection and preliminary disposal.

[0003] Patent document CN109598938A discloses a UAV-based urban traffic guidance system and an urban comprehensive intelligent traffic system, which use UAVs to go to the scene for data collection and to command traffic on-site through a loudspeaker. Although UAVs have the advantage of quickly reaching the scene. However, the current endurance of UAVs is limited, generally about 30 - 40 minutes. The round-trip control of UAVs is manually controlled by independent personnel, and there are often situations where the battery power cannot support the completion of the entire task, and seamless unified scheduling cannot be achieved. Summary of the Invention

[0004] Aiming at the defects in the prior art, the purpose of the present invention is to provide a method and system for assisting in handling traffic accidents based on UAVs.

[0005] According to a method for assisting in handling traffic accidents based on UAVs provided by the present invention, it includes:

[0006] Data acquisition step: Determine the first coordinate of the accident location on the electronic map according to the alarm information, and according to the first coordinate, obtain the second coordinates and battery powers of multiple standby UAVs in the vicinity;

[0007] Distance calculation step: Calculate the distances between the UAVs and the accident location respectively according to the first coordinate and the second coordinates of multiple UAVs, and calculate the distance score and battery power score of each UAV;

[0008] Comprehensive evaluation step: Perform a comprehensive score on each UAV according to the preset distance weight and battery power weight, and select the UAV with the highest comprehensive score to execute the task;

[0009] Path planning step: The command center adds the second coordinate and the first coordinate to an open list storing nodes to be evaluated, takes the second coordinate as the starting point, selects the node with the smallest f(n) value as the current node and loops accordingly until reaching the first coordinate to obtain the flight path;

[0010] UAV flight control step: The UAV goes to the accident location according to the flight path, takes on-site pictures and conducts voice communication with the site according to the control instructions, obtains picture data and voice data, and transmits them back to the command center;

[0011] Dispatch steps: The command center establishes communication with the traffic police department, the fire department, or the emergency department based on the picture data and voice data.

[0012] Furthermore, the calculation method of the distance score includes:

[0013] The distance d between the second coordinate and the first coordinate i :

[0014]

[0015] (x i , y i ) is the second coordinate of the i-th drone, and (x0, y0) is the first coordinate;

[0016] Distance score D i :

[0017]

[0018] The calculation method of the power score includes:

[0019] Power score E si :

[0020]

[0021] Among them, E i is the current power, and E max is the full power.

[0022] Furthermore, the calculation method of the comprehensive score includes:

[0023] Comprehensive score S i :

[0024] S i = D i × ω d + E si × ω e

[0025] Among them, ω d is the distance weight, ω e is the power weight, ω d + ω e = 1.

[0026] Furthermore, the calculation method of the f(n) value includes:

[0027] f(n) = g(n) + h(n)

[0028]

[0029] Among them, g(n) is the actual cost from the current node to the starting point, l i is the path length from the current node to the starting point, k is the number of path segments from the current node to the starting point, h(n) is the estimated cost from the current node to the first coordinate, and (x n , y n ) is the coordinate of the current node.

[0030] Furthermore, in the UAV flight control step, when the power of the UAV is lower than the first preset value, a replacement request message is sent to the command center, and the command center orders the UAV with the second-highest comprehensive score to take over the task. When the power of the UAV is lower than the second preset value or the UAV taking over the task reaches the accident site, it returns to the base for charging.

[0031] A traffic accident assistance processing system based on a UAV according to the present invention includes:

[0032] Data acquisition module: determining the first coordinate of the accident site on the electronic map according to the alarm information, and acquiring the second coordinates and power of multiple standby UAVs around according to the first coordinate;

[0033] Distance calculation module: calculating the distances between the UAVs and the accident site respectively according to the first coordinate and the second coordinates of multiple UAVs, and calculating the distance scores and power scores of each UAV;

[0034] Comprehensive evaluation module: comprehensively evaluating each UAV according to the preset distance weight and power weight, and selecting the UAV with the highest comprehensive score to execute the task;

[0035] Path planning module: The command center adds the second coordinate and the first coordinate to an open list storing nodes to be evaluated, takes the second coordinate as the starting point, and selects the node with the smallest f(n) value as the current node and loops accordingly until the first coordinate is reached to obtain the flight path;

[0036] UAV flight control module: The UAV goes to the accident site according to the flight path, takes pictures of the scene and communicates with the scene by voice according to the control instructions, obtains picture data and voice data, and transmits them back to the command center;

[0037] Scheduling module: The command center establishes communication with the traffic police department, the fire department or the emergency department according to the picture data and the voice data.

[0038] Furthermore, the calculation method of the distance score includes:

[0039] The distance d between the second coordinate and the first coordinate i :

[0040]

[0041] (x i , y i ) is the second coordinate of the i-th drone, and (x0, y0) is the first coordinate;

[0042] Distance score D i :

[0043]

[0044] The calculation method of the power score includes:

[0045] Power score E si :

[0046]

[0047] where E i is the current power, and E max is the full power.

[0048] Furthermore, the calculation method of the comprehensive score includes:

[0049] Comprehensive score S i :

[0050] S i = D i × ω d + E si × ω e

[0051] where ω d is the distance weight, ω e is the power weight, ω d + ω e = 1.

[0052] Furthermore, the calculation method of the f(n) value includes:

[0053] f(n) = g(n) + h(n)

[0054]

[0055] where g(n) is the actual cost from the current node to the starting point, l i is the path length from the current node to the starting point, k is the number of path segments from the current node to the starting point, h(n) is the estimated cost from the current node to the first coordinate, and (x n , y n ) is the coordinate of the current node.

[0056] Further, in the UAV flight control module, when the power of the UAV is lower than the first preset value, a replacement request message is sent to the command center, and the command center orders the UAV with the second-highest comprehensive score to replace and execute the task. When the power of the UAV is lower than the second preset value or the UAV replacing the task arrives at the accident site, it returns to the base for charging.

[0057] Compared with the prior art, the present invention has the following beneficial effects:

[0058] The present invention can quickly and accurately select the most suitable UAV to go to the accident scene, avoiding task delays or failures caused by insufficient UAV power or excessive distance, and greatly improving the efficiency and accuracy of traffic accident scene investigation and command. Through the present invention, a unified dispatching management of all UAVs can be constructed, reducing the vacuum period of accident scene management. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] By reading the following detailed description of non-limiting embodiments with reference to the accompanying drawings, other features, objects, and advantages of the present invention will become more apparent:

[0060] Figure 1 It is a flowchart of the operation of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0061] The present invention will be described in detail below with reference to specific embodiments. The following embodiments will help those skilled in the art to further understand the present invention, but do not limit the present invention in any form. It should be noted that those of ordinary skill in the art can make several changes and improvements without departing from the concept of the present invention. These all belong to the protection scope of the present invention.

[0062] As Figure 1 shown, a traffic accident assistance processing method based on UAVs provided by the present invention includes:

[0063] Data acquisition step: The command center determines the first coordinate of the accident location on the electronic map according to the alarm information, and obtains the second coordinates and power of multiple standby UAVs in the vicinity according to the first coordinate. The first coordinate can be obtained by manual marking by the alarm call operator or directly by voice recognition of the alarm call. The second coordinates and power can be obtained through the communication equipment of the patrol vehicle carrying the UAV. The standby UAVs are in standby and charging states on the patrol vehicle, avoiding power consumption due to direct communication with the intelligent center. After the UAV takes off, the patrol vehicle can serve as a communication transfer station between the UAV and the intelligent center, or the data collected by the UAV can be transmitted back to the command center and the patrol vehicle simultaneously.

[0064] Distance calculation steps: The command center calculates the distances between the drones and the accident location based on the first coordinate and the second coordinates of multiple drones, and calculates the distance scores and power scores of each drone.

[0065] Specifically, the distance d between the second coordinate and the first coordinate i :

[0066]

[0067] (x i , y i ) is the second coordinate of the i-th drone, and (x0, y0) is the first coordinate.

[0068] To unify the dimension, the distance is normalized, and the distance score D i :

[0069]

[0070] The distance score is mapped to the interval (0, 1) through this formula, and the closer the distance, the higher the score.

[0071] The power score is also normalized, and the power score E si :

[0072]

[0073] where E i is the current power, and E max is the full power.

[0074] Comprehensive evaluation steps: According to the preset distance weight and power weight, each drone is comprehensively scored, and the drone with the highest comprehensive score is selected to perform the task. According to the preset distance weight ω d and power weight ω e , ω d +ω e = 1. For example, ω d = 0.6, ω e = 0.4. The present invention does not limit this, and those skilled in the art can adjust the weights according to the actual situation.

[0075] S i = D i ×ω d +E si ×ω e

[0076] According to the comprehensive score S i score, the drone with the highest score is selected as the drone to perform the task.

[0077] Path planning steps: The command center adds the second coordinate and the first coordinate to an open list that stores nodes to be evaluated. Taking the second coordinate as the starting point, it selects the node with the smallest f(n) value as the current node and loops in this way until it reaches the first coordinate to obtain the flight path.

[0078] f(n) = g(n) + h(n), where g(n) is the actual cost from the current node to the starting point, and this cost can be calculated by accumulating the lengths of each segment of the path from the starting point to the current node. Let the path length from the current node i to the starting point be l i , and k be the number of path segments from the current node to the starting point. Then:

[0079]

[0080] h(n) is the estimated cost from the current node to the first coordinate. (x n , y n ) is the coordinate of the current node. Then:

[0081]

[0082] When the path planning algorithm starts, the command center adds the second coordinate and the first coordinate to an open list that stores nodes to be evaluated. Taking the second coordinate as the starting point, it adds it to an open list (open list), which is used to store nodes to be evaluated. Then, it continuously takes out the node with the smallest f(n) value from the open list as the current node for processing. For the current node, it checks whether it is the target node (accident site). If so, a path has been found, and the optimal path can be obtained by backtracking the node sequence from the target node to the starting point. If the current node is not the target node, it traverses all its adjacent nodes. For each adjacent node, if it is not in the open list and the visited list (ClosedList), and is not an obstacle node such as terrain or no-fly zone, it is added to the open list, and its predecessor node is recorded as the current node. At the same time, its f(n), g(n), and h(n) values are calculated. If the adjacent node is already in the open list, it checks whether the g(n) value of reaching this adjacent node through the current node is smaller. If so, the predecessor node of this adjacent node is updated to the current node, and its f(n) and g(n) values are recalculated. When the open list is empty, it means that no feasible path has been found, and at this time, it is necessary to handle it according to the actual situation, such as expanding the search range or re-evaluating the task.

[0083] Drone flight control steps: The command center sends the planned path to the drone performing the task. The drone travels to the accident site according to the flight path, takes on-site pictures and conducts voice communication with the site according to the control instructions, obtains picture data and voice data, and transmits them back to the command center. The process of taking on-site pictures can be manually controlled by the operator in the patrol vehicle. The drone can also establish voice communication with the patrol vehicle, play the voices of the operator and the commander in the patrol vehicle through the loudspeaker, direct the normal driving vehicles to detour in an orderly manner, guide the accident victims to evacuate to the side of the site, etc. It can also communicate with the on-site personnel by voice to facilitate understanding the severity of the accident and the casualties.

[0084] Among them, when the battery power of the drone is lower than the first preset value, a replacement request message is sent to the command center. The command center orders the drone with the second-highest comprehensive score to replace and perform the task. The path planning method is the same as the previous one, so as to achieve seamless handover between drones. When the battery power of the drone is lower than the second preset value or the drone taking over the task reaches the accident site, it returns to the base for charging.

[0085] Dispatch steps: The command center establishes communication with the traffic police department, the fire department or the emergency department according to the picture data and voice data. For example, it can inform the traffic police department to further dispatch more police forces, inform the fire department to go to the scene for rescue and fire extinguishing, and inform the emergency department to go to the scene for first aid.

[0086] The present invention also provides a traffic accident auxiliary processing system based on drones. The traffic accident auxiliary processing system based on drones can be realized by executing the process steps of the traffic accident auxiliary processing method based on drones. That is, those skilled in the art can understand the traffic accident auxiliary processing method based on drones as the preferred implementation manner of the traffic accident auxiliary processing system based on drones. The system includes:

[0087] Data acquisition module: Determine the first coordinate of the accident site on the electronic map according to the alarm information. According to the first coordinate, obtain the second coordinates and battery powers of multiple drones in the standby state around.

[0088] Distance calculation module: Calculate the distances between the drones and the accident site respectively according to the first coordinate and the second coordinates of multiple drones, and calculate the distance scores and battery power scores of each drone.

[0089] Comprehensive evaluation module: Conduct a comprehensive evaluation of each drone according to the preset distance weight and battery power weight, and select the drone with the highest comprehensive score to perform the task.

[0090] Path planning module: The command center adds the second coordinate and the first coordinate to an open list that stores nodes to be evaluated. Taking the second coordinate as the starting point, it selects the node with the smallest f(n) value as the current node and loops in this way until it reaches the first coordinate to obtain the flight path.

[0091] UAV flight control module: The UAV travels to the accident site according to the flight path, takes on-site pictures and conducts voice communication with the site according to the control instructions, obtains picture data and voice data, and transmits them back to the command center.

[0092] Dispatch module: The command center establishes communication with the traffic police department, fire department or emergency department according to the picture data and voice data.

[0093] Those skilled in the art know that in addition to implementing the system and its various devices, modules, and units provided by the present invention in the form of pure computer-readable program code, the method steps can be logically programmed to enable the system and its various devices, modules, and units provided by the present invention to be implemented in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers, etc. to achieve the same functions. Therefore, the system and its various devices, modules, and units provided by the present invention can be regarded as a hardware component, and the devices, modules, and units included therein for implementing various functions can also be regarded as the structure within the hardware component; the devices, modules, and units for implementing various functions can also be regarded as either software modules for implementing the method or the structure within the hardware component.

[0094] The specific embodiments of the present invention have been described above. It should be understood that the present invention is not limited to the above specific implementation manners, and those skilled in the art can make various changes or modifications within the scope of the claims, which does not affect the essence of the present invention. Without conflict, the embodiments of the present application and the features in the embodiments can be combined arbitrarily with each other.

Claims

1. A method for assisting in the handling of traffic accidents based on drones, characterized in that, Including: Data acquisition step: Determine the first coordinate of the accident location on the electronic map according to the alarm information, and obtain the second coordinates and battery levels of multiple standby drones in the vicinity according to the first coordinate; Distance calculation step: Calculate the distances between the drones and the accident location respectively according to the first coordinate and the second coordinates of the multiple drones, and calculate the distance scores and battery scores of each drone; Comprehensive evaluation step: Conduct a comprehensive evaluation of each drone according to the preset distance weight and battery weight, and select the drone with the highest comprehensive score to execute the task; Path planning step: The command center adds the second coordinate and the first coordinate to an open list storing nodes to be evaluated, takes the second coordinate as the starting point, and selects the node with the smallest f(n) value as the current node and loops in this way until reaching the first coordinate to obtain the flight path; Drone flight control step: The drone travels to the accident location according to the flight path, takes pictures of the scene and conducts voice communication with the scene according to the control instructions, obtains picture data and voice data, and transmits them back to the command center; Dispatch step: The command center establishes communication with the traffic police department, fire department or emergency department according to the picture data and voice data.

2. The method for assisting in traffic accident handling based on an unmanned aerial vehicle according to claim 1, wherein The calculation method of the distance score includes: The distance d between the second coordinate and the first coordinate i : (x i , y i ) is the second coordinate of the i-th drone, and (x0, y0) is the first coordinate; Distance score D i : The calculation method of the battery score includes: Power score E si : Among them, E i is the current battery level, and E max is the full battery level.

3. The method for assisting in handling traffic accidents based on an unmanned aerial vehicle according to claim 2, wherein, The calculation method of the comprehensive score includes: Comprehensive score S i : S i = D i × ω d + E si × ω e Among them, ω a is the distance weight, ω e is the power weight, ω d + ω e = 1.

4. The method for assisting in handling traffic accidents based on an unmanned aerial vehicle according to claim 1, wherein, The calculation method of the f(n) value includes: f(n)=g(n)+h(n) Among them, g(n) is the actual cost from the current node to the starting point, l i is the path length from the current node to the starting point, k is the number of path segments from the current node to the starting point, h(n) is the estimated cost from the current node to the first coordinate, (x n , y n ) is the coordinate of the current node.

5. The method for assisting in handling traffic accidents based on an unmanned aerial vehicle according to claim 1, wherein In the drone flight control step, when the battery level of the drone is lower than the first preset value, a replacement request message is sent to the command center, and the command center orders the drone with the second highest comprehensive score to replace and execute the task. When the battery level of the drone is lower than the second preset value or the drone taking over the task reaches the accident location, it returns to the base for charging.

6. An accident assistance processing system based on a drone, characterized in that, Including: Data acquisition module: Determine the first coordinate of the accident location on the electronic map according to the alarm information, and obtain the second coordinates and battery levels of multiple standby drones in the vicinity according to the first coordinate; Distance calculation module: Calculate the distances between the drones and the accident location respectively according to the first coordinate and the second coordinates of the multiple drones, and calculate the distance scores and battery scores of each drone; Comprehensive evaluation module: Conduct a comprehensive evaluation of each drone according to the preset distance weight and battery weight, and select the drone with the highest comprehensive score to execute the task; Path planning module: The command center adds the second coordinate and the first coordinate to an open list storing nodes to be evaluated, takes the second coordinate as the starting point, and selects the node with the smallest f(n) value as the current node and loops in this way until reaching the first coordinate to obtain the flight path; Drone flight control module: The drone travels to the accident location according to the flight path, takes pictures of the scene and conducts voice communication with the scene according to the control instructions, obtains picture data and voice data, and transmits them back to the command center; Dispatch module: The command center establishes communication with the traffic police department, fire department or emergency department according to the picture data and voice data.

7. The drone-based traffic accident assistance processing system according to claim 6, wherein, The calculation method of the distance score includes: The distance d between the second coordinate and the first coordinate i : (x i ,y i ) is the second coordinate of the i-th drone, and (x0, y0) is the first coordinate; Distance score D i : The calculation method of the battery score includes: Electricity score E si : Among them, E i is the current battery level, and E max is the full battery level.

8. The UAV-based traffic accident assistance processing system according to claim 7, wherein, The calculation method of the comprehensive score includes: Comprehensive score S i : S i = D i × ω d + E si × ω e Among them, ω d is the distance weight, ω e is the power weight, ω d + ω e = 1.

9. The traffic accident assistance processing system based on an unmanned aerial vehicle according to claim 6, wherein The calculation method of the f(n) value includes: f(n)=g(n)+h(n) Among them, g(n) is the actual cost from the current node to the starting point, l i is the path length from the current node to the starting point, k is the number of path segments from the current node to the starting point, h(n) is the estimated cost from the current node to the first coordinate, (x n , y n ) is the coordinate of the current node.

10. The traffic accident assistance processing system based on an unmanned aerial vehicle according to claim 6, wherein, In the UAV flight control module, when the battery power of the UAV is lower than the first preset value, a replacement request message is sent to the command center. The command center orders the UAV with the second-highest comprehensive score to take over the task and return to charge when the battery power of the UAV is lower than the second preset value or the UAV taking over the task reaches the accident site.

Images