Path planning method of express delivery unmanned aerial vehicle in community

Abstract

The invention discloses a path planning method of an express delivery unmanned aerial vehicle in a community. A two-dimensional plane graph in the community is acquired; important information in the plane graph and intersection points of different plane areas are extracted, and boundaries and angular points of obstacles are recognized; the unmanned aerial vehicle determines the starting point and the ending point of the path according to the express cabinet and the required delivery position; according to actual requirements, different path planning algorithms are adopted to plan an optimal flight path; detecting flight time windows of other unmanned aerial vehicles according to the planned flight path; according to the flight time window, detecting whether other unmanned aerial vehicles pass through the same section of flight path at the same time; and if a plurality of unmanned aerial vehicles pass through the same flight path at the same time, generating an evasion route according to an algorithm, and regenerating a flight path. The method has the advantages that the flight path of the unmanned aerial vehicle is planned through the method for planning the path of the express delivery unmanned aerial vehicle in the community, and on the premise that the flight safety of the unmanned aerial vehicle is guaranteed, the delivery efficiency can be improved, and meanwhile the flight cost is reduced to the minimum.

Description

Technical Field

[0001] The present application relates to the field of drone express delivery, and in particular to a path planning method for a delivery drone within a community. Background Art

[0002] Nowadays, express delivery and takeout have become an increasingly important part of people's daily lives. With the increasing number of takeout and express delivery in cities, more and more problems have been exposed.

[0003] The first is how to solve the problem of the final distance of delivery. Due to the widespread high-rise buildings in cities and increasingly strict personnel management in communities, delivery personnel are increasingly unwilling to deliver express and take-out food to users. Users pay but cannot get the corresponding services, which deepens the conflict between users and delivery personnel.

[0004] In this situation, takeaway and express drones came into being, but with it came new problems with drone delivery. With the increasing number of express delivery and takeaways, if drones are used for delivery, a large number of drones will be needed to fly continuously.

[0005] How to plan the flight route of drones, which can not only improve the efficiency of delivery while reducing the flight cost to a minimum and carry out photovoltaic power generation under the premise of ensuring the flight safety of drones, has become the biggest problem hindering the development of drone delivery business. Summary of the invention

[0006] In order to solve the above problems, the present invention provides a method for path planning of a delivery drone in a community, which is characterized by comprising the following steps: Obtain a two-dimensional plan view of the cell, and divide the plan view into multiple plan areas; Extract important information from the plan view, the intersection of different planar areas, and identify the boundaries and corners of obstacles; The drone determines the starting and ending points of the route based on the express cabinet and the location to be delivered; And according to actual needs, different path planning algorithms are used to plan the optimal flight path; Detect the flight time windows of other drones based on the planned flight path; According to the flight time window, detect whether there are other drones passing through the same track at the same time; If multiple drones pass through the same track at the same time, an avoidance route is generated based on the algorithm and the flight path is regenerated; After the drone takes off, it monitors the flight path status in real time. If a moving obstacle is found, the background algorithm will replan the flight path to avoid the obstacle.

[0007] Preferably, the plane area of ​​the two-dimensional plane graph is divided by a Voronoi diagram.

[0008] Preferably, the important information and boundaries and corner points of obstacles in the plan view are analyzed and automatically extracted through image processing technology and computer vision algorithms.

[0009] Furthermore, the path planning algorithms include A* algorithm, Dijkstra algorithm, Bellman-Ford algorithm and Floyd-Varshall algorithm.

[0010] The A* algorithm is a heuristic search algorithm used to find the optimal path on a two-dimensional plane. By evaluating the estimated cost from the current location to the end point, the route with the shortest path and the lowest cost is selected; The Dijkstra algorithm is applicable to path planning of weighted graphs, evaluating different weights of each path, including path length, power consumption, finding the shortest path, and making dynamic adjustments; The Bellman-Ford is used to calculate the shortest path from the starting point through all nodes, and is used to generate the optimal flight path when flying to multiple nodes; The Floyd-Varshall algorithm is used to calculate the shortest path between all nodes and generate a global optimal path by updating the distance matrix between nodes.

[0011] In order to better realize the path planning of the drone, a dynamic planning algorithm is also included. During the path planning, the planning algorithm is adjusted dynamically according to the actual situation to ensure that the optimal flight path can be generated under different circumstances.

[0012] Furthermore, the algorithm for generating avoidance routes by multiple UAVs includes a time window scheduling algorithm, a priority scheduling algorithm, a conflict detection and avoidance algorithm, an auction-based conflict resolution algorithm, and a trajectory prediction-based conflict resolution algorithm.

[0013] Furthermore, the path planning method of the express delivery drone in the community is The time window scheduling algorithm allocates different time windows to each drone, ensuring that each drone passes through the same trajectory in different time periods to avoid conflicts; The priority scheduling algorithm assigns different priorities to each UAV and sorts the flights according to the different priorities; The conflict detection and avoidance algorithm monitors the flight path of the drone in real time and detects potential conflicts and generates an avoidance path; The auction-based conflict resolution algorithm is that when the computing power of the main system is insufficient or busy, the drones determine the priority flight order through bidding, and other drones adjust their paths or wait; The trajectory prediction-based conflict resolution algorithm identifies potential conflicts in advance by predicting the flight trajectory of the UAV and generates an avoidance path.

[0014] Furthermore, the priority of the priority scheduling algorithm includes the urgency of the task and the battery level of the drone; and the auction content in the auction-based conflict resolution algorithm is the importance and urgency of the task.

[0015] In order to solve the path conflict problem of multiple UAVs, a multi-agent system is also included. The UAVs are independent intelligent agents that collaborate and communicate with the algorithm to jointly decide on conflict resolution strategies.

[0016] The advantages of the path planning method for express delivery drones in a community are: By using the path planning method for express delivery drones in a community of the present application and planning the flight path of the drone, it is possible to not only improve the efficiency of delivery while reducing the flight cost to a minimum while ensuring the flight safety of the drone. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0018] The purpose of this application is to provide a path planning method for a delivery drone in a community, which is characterized by comprising the following steps: Obtain a two-dimensional plan view of the cell, and divide the plan view into multiple plan areas; Extract important information from the plan view, the intersection of different planar areas, and identify the boundaries and corners of obstacles; The drone determines the starting and ending points of the route based on the express cabinet and the location to be delivered; And according to actual needs, different path planning algorithms are used to plan the optimal flight path; Detect the flight time windows of other drones based on the planned flight path; According to the flight time window, detect whether there are other drones passing through the same track at the same time; If multiple drones pass through the same track at the same time, an avoidance route is generated based on the algorithm and the flight path is regenerated; After the drone takes off, it monitors the flight path status in real time. If a moving obstacle is found, the background algorithm will replan the flight path to avoid the obstacle.

[0019] Preferably, the plane area of ​​the two-dimensional plane graph is divided by a Voronoi diagram.

[0020] Preferably, the important information and boundaries and corner points of obstacles in the plan view are analyzed and automatically extracted through image processing technology and computer vision algorithms.

[0021] Furthermore, the path planning algorithms include A* algorithm, Dijkstra algorithm, Bellman-Ford algorithm and Floyd-Varshall algorithm.

[0022] The A* algorithm is a heuristic search algorithm used to find the optimal path on a two-dimensional plane. By evaluating the estimated cost from the current location to the end point, the route with the shortest path and the lowest cost is selected; The Dijkstra algorithm is applicable to path planning of weighted graphs, evaluating different weights of each path, including path length, power consumption, finding the shortest path, and making dynamic adjustments; The Bellman-Ford is used to calculate the shortest path from the starting point through all nodes, and is used to generate the optimal flight path when flying to multiple nodes; The Floyd-Varshall algorithm is used to calculate the shortest path between all nodes and generate a global optimal path by updating the distance matrix between nodes.

[0023] In order to better realize the path planning of the drone, a dynamic planning algorithm is also included. During the path planning, the planning algorithm is adjusted dynamically according to the actual situation to ensure that the optimal flight path can be generated under different circumstances.

[0024] Furthermore, the algorithm for generating avoidance routes by multiple UAVs includes a time window scheduling algorithm, a priority scheduling algorithm, a conflict detection and avoidance algorithm, an auction-based conflict resolution algorithm, and a trajectory prediction-based conflict resolution algorithm.

[0025] Furthermore, the path planning method of the express delivery drone in the community is The time window scheduling algorithm allocates different time windows to each drone, ensuring that each drone passes through the same trajectory in different time periods to avoid conflicts; The priority scheduling algorithm assigns different priorities to each UAV and sorts the flights according to the different priorities; The conflict detection and avoidance algorithm monitors the flight path of the drone in real time and detects potential conflicts and generates an avoidance path; The auction-based conflict resolution algorithm is that when the computing power of the main system is insufficient or busy, the drones determine the priority flight order through bidding, and other drones adjust their paths or wait; The trajectory prediction-based conflict resolution algorithm identifies potential conflicts in advance by predicting the flight trajectory of the UAV and generates an avoidance path.

[0026] Furthermore, the priority of the priority scheduling algorithm includes the urgency of the task and the battery level of the drone; and the auction content in the auction-based conflict resolution algorithm is the importance and urgency of the task.

[0027] In order to solve the path conflict problem of multiple UAVs, a multi-agent system is also included. The UAVs are independent intelligent agents that collaborate and communicate with the algorithm to jointly decide on conflict resolution strategies. Example

[0028] In actual use, the drone control background imports the two-dimensional plan of the community in advance, divides the plan into multiple plane areas, and records important information in the plan as nodes. Important information in the plan includes the intersection of different plane areas, the boundaries of obstacles, corner points, etc.

[0029] After the control background receives the instruction to use drones for express or takeout delivery, it first determines the starting and ending points of the route based on the address where the drone takes off and the location to be delivered.

[0030] After determining the starting point and the end point, the path planning algorithm is used for path planning. Different algorithms plan paths according to different weights, and the optimal solution is selected as the final path planning solution.

[0031] After completing the path planning, the background continues to detect the flight time windows of other drones and compares them. After comparison, if there are no multiple drones passing through the same track at the same time, the background sends a command and the drone takes off and performs flight dispatch according to the planned flight path.

[0032] If there are multiple drones passing through the same track at the same time, the drone flight path will continue to be adjusted. At this time, the algorithm for avoiding multiple drones is used to calculate and plan the flight path. At this time, multiple algorithms are used to independently calculate and generate flight paths to form multiple drone flight paths, and the optimal flight path is selected based on different weights such as flight time, path length, and battery consumption.

[0033] After completing the above path planning, the background issues a command and the drone takes off for flight delivery.

[0034] During the flight, the drone will also provide real-time feedback on path and road conditions. After receiving the information from the drone, the background uses a dynamic planning algorithm combined with the drone path planning algorithm to dynamically adjust the flight path according to actual conditions. At the same time, the multi-agent system enables the drone to act independently as an intelligent agent, collaborate and communicate with the algorithm, and jointly decide on conflict resolution strategies to ensure that the drone can fly on the optimal flight path.

[0035] During the flight of the drone, the background will also monitor the status of the flight route in real time through the sensors on the drone. If a moving obstacle is found in front of the drone, affecting the flight of the drone, the flight route will be replanned immediately to avoid the obstacle, and then return to the original route until the drone completes the delivery and returns.

[0036] The advantages of the path planning method for express delivery drones in a community are: By using the path planning method for express delivery drones in a community of the present application and planning the flight path of the drone, it is possible to not only improve the efficiency of delivery while reducing the flight cost to a minimum while ensuring the flight safety of the drone.

[0037] The present application is described in detail above in conjunction with specific implementation methods and exemplary examples, but these descriptions cannot be understood as limiting the present application. Those skilled in the art understand that, without departing from the spirit and scope of the present application, a variety of equivalent replacements, modifications or improvements can be made to the technical solution of the present application and its implementation methods, all of which fall within the scope of the present application. The scope of protection of the present application shall be subject to the attached claims.

Claims

1. A method for path planning of a delivery drone in a community, characterized in that: The following steps are included: Obtain a two-dimensional plan view of the cell, and divide the plan view into multiple plan areas; Extract important information from the plan view, the intersection of different planar areas, and identify the boundaries and corners of obstacles; The drone determines the starting and ending points of the route based on the express cabinet and the location to be delivered; And according to actual needs, different path planning algorithms are used to plan the optimal flight path; Detect the flight time windows of other drones based on the planned flight path; According to the flight time window, detect whether there are other drones passing through the same track at the same time; If multiple drones pass through the same track at the same time, an avoidance route is generated based on the algorithm and the flight path is regenerated; After the drone takes off, it monitors the flight path status in real time. If a moving obstacle is found, the background algorithm will replan the flight path to avoid the obstacle.

2. The path planning method for a delivery drone in a community according to claim 1, characterized in that: The plane area of ​​the two-dimensional plane graph is divided by a Voronoi diagram.

3. The path planning method for a delivery drone in a community according to claim 1, characterized in that: The important information and boundaries and corner points of obstacles in the plan view are analyzed and automatically extracted through image processing technology and computer vision algorithms.

4. The path planning method for a delivery drone in a community according to claim 1, characterized in that: The path planning algorithms include A* algorithm, Dijkstra algorithm, Bellman-Ford algorithm and Floyd-Varshall algorithm.

5. The path planning method for a delivery drone in a residential area according to claim 4, characterized in that: The A* algorithm is a heuristic search algorithm used to find the optimal path on a two-dimensional plane. By evaluating the estimated cost from the current location to the end point, the route with the shortest path and the lowest cost is selected; The Dijkstra algorithm is applicable to path planning of weighted graphs, evaluating different weights of each path, including path length, power consumption, finding the shortest path, and making dynamic adjustments; The Bellman-Ford is used to calculate the shortest path from the starting point through all nodes, and is used to generate the optimal flight path when flying to multiple nodes; The Floyd-Varshall algorithm is used to calculate the shortest path between all nodes and generate a global optimal path by updating the distance matrix between nodes.

6. The path planning method for a delivery drone in a community according to claim 4, characterized in that: It also includes a dynamic planning algorithm. In path planning, the planning algorithm is adjusted dynamically according to actual conditions to ensure that the optimal flight path can be generated under different circumstances.

7. The path planning method for a delivery drone in a residential area according to claim 1, characterized in that: The algorithms for generating avoidance routes by multiple UAVs include a time window scheduling algorithm, a priority scheduling algorithm, a conflict detection and avoidance algorithm, an auction-based conflict resolution algorithm, and a trajectory prediction-based conflict resolution algorithm.

8. The path planning method for a delivery drone in a residential area according to claim 7, characterized in that: The time window scheduling algorithm allocates different time windows to each drone, ensuring that each drone passes through the same trajectory in different time periods to avoid conflicts; The priority scheduling algorithm assigns different priorities to each UAV and sorts the flights according to the different priorities; The conflict detection and avoidance algorithm monitors the flight path of the drone in real time and detects potential conflicts and generates an avoidance path; The auction-based conflict resolution algorithm is that when the computing power of the main system is insufficient or busy, the drones determine the priority flight order through bidding, and other drones adjust their paths or wait; The trajectory prediction-based conflict resolution algorithm identifies potential conflicts in advance by predicting the flight trajectory of the UAV and generates an avoidance path.

9. The path planning method for a delivery drone in a residential area according to claim 8, characterized in that: The priorities of the priority scheduling algorithm include the urgency of the task and the battery level of the drone; the auction contents in the auction-based conflict resolution algorithm are the importance and urgency of the task.

10. The path planning method for a delivery drone in a community according to claim 1, characterized in that: It also includes a multi-agent system, which can realize independent intelligent agents of drones, cooperate and communicate with algorithms, and jointly decide on conflict resolution strategies.