Unmanned sweeper path dynamic adjustment cloud algorithm system and method
By using a cloud-based algorithm system that dynamically adjusts the path of unmanned sweepers, real-time data and map data are used to optimize the path, solving the problem of path adjustment for unmanned sweepers in complex environments and achieving efficient sweeping and low-energy operation.
Patent Information
- Application Number
- CN202510849245.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-24
- Publication Date
- 2025-10-31
AI Technical Summary
Existing driverless sweepers are unable to adjust their driving paths in a timely manner when faced with complex and ever-changing dynamic environments, resulting in low work efficiency, inability to effectively avoid obstacles and congestion, and impact on normal operations.
The system employs a cloud-based algorithm for dynamic path adjustment of unmanned sweepers. Through a real-time data acquisition module, a path optimization algorithm module, and a path push module, it utilizes map data and vehicle data to perform real-time path optimization, calculate the optimal driving path, and push it to the sweeper, thereby achieving dynamic path adjustment.
It enables unmanned sweepers to efficiently clean in complex environments, avoid obstacles and congestion, reduce accident risks, improve work efficiency, reduce energy consumption and operating costs, and enhance user experience.
Smart Images
Figure CN120871843A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of autonomous driving, and in particular to a cloud-based algorithm system and method for dynamically adjusting the path of an autonomous sweeper. Background Technology
[0002] In the field of autonomous sweepers, path planning is one of the key technologies for achieving efficient sweeping operations. Existing autonomous sweepers typically employ pre-set path planning methods or rely on the vehicle's own sensors for local path planning and obstacle avoidance. While these methods can meet sweeping needs to a certain extent, they cannot react in time to complex and ever-changing dynamic environments, resulting in an inability to adjust the autonomous sweeper's driving path in a timely manner, thus affecting its normal operation.
[0003] In actual cleaning operations, various unexpected situations may occur, such as:
[0004] (1) Real-time road conditions change: For example, traffic congestion, temporary traffic control, etc., affect the speed of the unmanned sweeper, thus affecting the efficiency of the pre-planned route;
[0005] (2) Sudden obstacles: There may be temporarily parked vehicles, pedestrians or other obstacles on the road, and the sweeper needs to adjust its route in time to avoid them;
[0006] (3) Changes in the vehicle's own status: For example, changes in the status such as the remaining battery power of the sweeper being close to or lower than the preset value, or the amount of garbage stored being greater than the preset value, can affect its ability to continue executing the current path.
[0007] Currently, existing dynamic path planning methods typically rely on the vehicle's own sensing devices and sensor data (external environmental information, such as obstacles, and internal vehicle equipment data, such as battery level and water level) and its own computing power to make local adjustments to ensure the normal operation of the autonomous sweeper. However, this approach is limited by the autonomous sweeper's computing resources and sensing range, making global optimization and prediction difficult. Therefore, it cannot dynamically adjust the vehicle's driving path and sweeping tasks in real time based on road conditions, obstacles, and the sweeper's own status, thus affecting its operational efficiency.
[0008] Therefore, existing technologies still need to be improved. Summary of the Invention
[0009] In view of the shortcomings of the prior art, the purpose of this invention is to provide a cloud-based algorithm system and method for dynamic path adjustment of unmanned sweeping vehicles, which aims to solve the problem that the prior art cannot adjust the vehicle's driving path and sweeping tasks in real time according to real-time road conditions, obstacle road conditions, etc., thus affecting its operating efficiency.
[0010] The technical solution of the present invention is as follows: A cloud-based algorithm system for dynamic path adjustment of an unmanned sweeper, comprising:
[0011] This is a path optimization algorithm module used to calculate the optimal driving path for the autonomous vehicle based on map data after receiving vehicle data. The optimization goal of the path optimization algorithm module is for the autonomous sweeper to complete the task in the shortest possible time and / or with the lowest energy consumption.
[0012] A path-pushing module is used to push the optimal driving path calculated by the path optimization algorithm module to the unmanned sweeper. The calculated optimal driving path is pushed to the unmanned sweeper via wireless communication. After receiving the information, the control module inside the unmanned sweeper controls the unmanned sweeper to travel along the new route.
[0013] Therefore, the present invention can adjust the driving route of the unmanned sweeper according to the real-time situation in the driving route and its own actual situation, so as to ensure that the unmanned sweeper is always driving on the optimal sweeping route and ensuring the high-efficiency and low-energy operation of the unmanned sweeper.
[0014] In one embodiment, the cloud-based algorithm system for dynamic path adjustment of an unmanned sweeper further includes a real-time data acquisition module, which collects the vehicle data information. The real-time data acquisition module is located on the unmanned sweeper and collects environmental data surrounding the sweeper and the vehicle's own parameters, transmitting these data to the path optimization algorithm module via wireless communication.
[0015] In one embodiment, the path optimization algorithm module calculates the current optimal driving path of the autonomous vehicle based on vehicle data information and map data information as follows:
[0016] Based on the received vehicle and map data, the system determines whether the road ahead of the autonomous sweeper's current path is clear and whether the vehicle status parameters within the vehicle data meet the set thresholds. It should be noted that thresholds can be set for all relevant parameters in the vehicle status data according to specific needs, and the system simultaneously checks whether each vehicle status parameter is within a normal range.
[0017] Based on the judgment results, it is determined whether the current driving path of the unmanned sweeper needs to be adjusted. If adjustment is required, the optimal driving path is calculated based on real-time vehicle data and map data.
[0018] In one embodiment, the vehicle data information includes: real-time vehicle location information, surrounding environment image information, and vehicle status parameters. The real-time vehicle location information reveals the real-time position of the autonomous sweeper, while the surrounding environment image information indicates whether there are obstacles or other obstructions affecting the sweeper's normal operation. The vehicle status parameters provide information on the sweeper's battery level, water tank level, and other conditions. Therefore, the path optimization algorithm module considers the sweeper's own status to adjust its operating path. For example, when the battery is low, it charges it promptly to avoid interrupting the sweeping task due to battery depletion.
[0019] In one embodiment, the vehicle status parameters include: vehicle speed, battery charge level, water tank level, and waste storage level.
[0020] In one embodiment, the cloud-based algorithm system for dynamically adjusting the path of an unmanned sweeper utilizes map data provided by map software and / or an urban traffic management system. This map data includes real-time and historical traffic information. The map data is sourced from a wide range of sources, providing a comprehensive understanding of the real-time traffic conditions (whether there is traffic congestion, the current traffic flow rate on the road where the unmanned sweeper is located, etc.) and historical traffic information (traffic congestion on the current road segment at the same time each day in the past, etc.). If poor road conditions are encountered, the system can promptly adjust the driving path to avoid congested sections, shorten sweeping time, and improve overall operational efficiency.
[0021] This invention also provides a method for dynamically adjusting the path of an unmanned sweeper, comprising the aforementioned cloud-based algorithm system for dynamically adjusting the path of an unmanned sweeper, the method comprising:
[0022] S1: Receives real-time vehicle data and map data from unmanned sweeping vehicles.
[0023] S2: Determine whether the battery charge, water tank volume, and garbage storage volume of the unmanned sweeper meet the set threshold values.
[0024] S3: If the judgment result meets the corresponding threshold, then determine whether the road ahead of the current driving path of the unmanned sweeper is clear based on the received vehicle data information and map data information.
[0025] The road ahead may be congested due to traffic jams or obstacles.
[0026] S4: If the judgment result of S3 is negative, calculate the optimal driving route based on vehicle data and map data, and send it to the unmanned sweeper.
[0027] Obviously, this invention can calculate the optimal driving path in a timely manner when the unmanned sweeper encounters obstacles and / or traffic congestion, so as to realize the effective obstacle avoidance of the unmanned sweeper and reduce the risk of accidents; at the same time, it avoids the sweeper being in a congested environment, which affects its normal operating efficiency, effectively shortens the sweeping time, and improves the overall operating efficiency.
[0028] In one embodiment, if the judgment result of step S2 is negative, the optimal driving route passing through charging stations and / or water stations and / or garbage stations is calculated based on the judgment result, vehicle data information, and map data information. This enables timely charging, water refilling, and garbage dumping operations for the unmanned sweeper, avoiding disruption to its normal operation.
[0029] In one embodiment, if the determination result of step S3 is yes, then an instruction is sent to the vehicle to continue driving according to the current driving path.
[0030] In summary, this paper proposes a cloud-based algorithm system and method for dynamic path adjustment of unmanned sweeping vehicles.
[0031] 1. By optimizing the driving path of the unmanned sweeper through real-time vehicle data and map data, congested road sections can be avoided, sweeping time can be shortened, and vehicle operating efficiency and work efficiency can be improved.
[0032] 2. It can avoid obstacles in time, reduce the risk of accidents, and ensure the normal operation of the unmanned sweeper;
[0033] 3. It can determine whether the status parameters of each vehicle are within the normal range, and perform path planning based on the vehicle's own status to realize timely charging, water replenishment and other operations, ensuring that the unmanned sweeper is in the best sweeping state and on the best sweeping task and driving path, thus ensuring high operating efficiency; it can reduce its mileage and energy consumption, reduce operating costs and improve user experience. Attached Figure Description
[0034] The present invention will be further described below with reference to the accompanying drawings and embodiments. In the accompanying drawings:
[0035] Figure 1 This is a schematic diagram of the system of the present invention;
[0036] Figure 2 This is a flowchart of the method of the present invention.
[0037] The system includes: 1. Unmanned sweeper; 2. Real-time data acquisition module; 3. Path optimization algorithm module; 4. Path push module. Detailed Implementation
[0038] To make the objectives, technical solutions, and effects of this invention clearer and more explicit, the invention is further described in detail below. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. The embodiments of the invention are described below in conjunction with the accompanying drawings.
[0039] Example 1
[0040] Please refer to Figure 1 This invention provides a cloud-based algorithm system for dynamic path adjustment of an unmanned sweeper. This system adjusts the driving path of the unmanned sweeper 1 based on real-time conditions along its route and its own actual situation, ensuring that the unmanned sweeper 1 always travels on the optimal sweeping path and guarantees high-efficiency, low-energy operation. Specifically, it includes: a real-time data acquisition module 2, a path optimization algorithm module 3, and a path push module 4.
[0041] Specifically, in this embodiment, the real-time data acquisition module 2 is used to collect vehicle data information of the unmanned sweeper 1 and send it to the path optimization algorithm module 3 via wireless communication; the wireless communication method includes 4G / 5G / WIFI, etc. The real-time data acquisition module 2 mainly collects environmental data around the unmanned sweeper 1 and the vehicle's own parameters. Specifically, in this embodiment, the collected vehicle data information includes: real-time vehicle location information, surrounding environment image information, and vehicle status parameters; specifically, the real-time vehicle location information is obtained by a GPS module or SLAM positioning module, through which the specific real-time location of the unmanned vehicle can be determined. The surrounding environment image information is collected by the sensing devices (radar, camera, etc.) on the unmanned sweeper 1, through which it can be determined whether there are obstacles or other obstacles in the surrounding environment of the unmanned sweeper 1, the road environment, etc., and whether they affect the normal driving of the unmanned sweeper 1; and the vehicle status parameters specifically include: vehicle speed, battery power, water tank level, and garbage storage capacity; through the vehicle status parameters, the specific values of battery power, water tank level, etc., on the unmanned sweeper 1 can be determined. Of course, other parameters from other autonomous vehicles can be added as vehicle data information as needed to ensure better planning and selection of the autonomous sweeper's driving path.
[0042] Specifically, in this embodiment, the path optimization algorithm module 3 is used to calculate the optimal driving path of the autonomous vehicle based on map data information after receiving vehicle data information. The optimization objective of the path optimization algorithm module 3 is to enable the autonomous sweeper 1 to complete the task in the shortest possible time and / or complete the sweeping task with the lowest energy consumption. The calculation process of the path optimization algorithm module 3 is as follows:
[0043] Based on the received vehicle data and map data, the system determines whether the road ahead of the unmanned sweeper 1 is clear and whether the vehicle status parameters in the vehicle data of the unmanned sweeper 1 meet the set thresholds. Specifically, the set thresholds include battery power threshold, water tank water level threshold, and garbage storage level threshold. The system also determines whether the battery power level, water tank water level, and garbage storage level meet the requirements and are within the normal range.
[0044] Based on the judgment result, it is determined whether the current driving path of the unmanned sweeper 1 needs to be adjusted. If adjustment is required, the optimal driving path is calculated based on real-time vehicle data and map data. Specifically, it should be noted that when calculating the optimal driving path, the path optimization algorithm module 3 in this invention generally needs to consider the following: First, traffic congestion and road closure information to avoid congested sections and choose smoother roads. Therefore, this invention can avoid congested sections, shorten cleaning time, and improve vehicle operating efficiency and work efficiency. Second, temporary obstacles need to be planned and detoured. Therefore, this invention can avoid obstacles in time, reduce accident risks, and ensure the normal operation of the unmanned sweeper 1. Third, the status of the unmanned sweeper 1, namely battery power, water tank level, and garbage storage capacity, to plan for the unmanned sweeper 1 to charge, refill water, and dispose of garbage nearby during the cleaning path, ensuring that the unmanned sweeper 1 is in a normal state, avoiding the problem of interruption of cleaning tasks, while reducing its mileage and energy consumption, lowering operating costs, and improving user experience.
[0045] Specifically, in this embodiment, the path push module 4 is used to push the optimal driving path calculated by the path optimization algorithm module to the unmanned sweeper 1. The calculated optimal driving path is pushed to the unmanned sweeper 1 via a 4G network, 5G network, or WIFI network, and the unmanned sweeper 1 performs sweeping operations according to the optimal driving path.
[0046] Specifically, in this embodiment, the cloud-based algorithm system for dynamic path adjustment of the unmanned sweeper vehicle utilizes map data provided by map software and urban traffic management systems. This map data includes real-time and historical traffic information. In this embodiment, the map software is Gaode Maps, Baidu Maps, etc., and it also integrates with existing map software and urban traffic management systems (depending on the city where the unmanned sweeper 1 operates, it integrates with the local traffic management bureau's urban traffic management system). This ensures a wide range of map data sources and diverse data, allowing for a comprehensive understanding of the real-time traffic conditions of the unmanned vehicle's current route, as well as historical traffic information (which can determine the traffic flow of the current route at the current time of day, and the duration of congestion, etc.). If the road conditions along the route are poor, the system can promptly adjust the route to avoid congested sections, shorten cleaning time, and improve overall operational efficiency.
[0047] Example 2
[0048] Please refer to Figure 2 The present invention also provides a method for dynamically adjusting the path of an unmanned sweeper, comprising the aforementioned cloud-based algorithm system for dynamically adjusting the path of an unmanned sweeper, wherein the method includes:
[0049] S1: Receives vehicle data and map data from the unmanned sweeper 1 in real time. After the unmanned sweeper 1 starts, the real-time data acquisition module 2 begins to work, collecting vehicle data in real time and sending it to the path optimization algorithm module 3.
[0050] S2: Determine whether the battery charge, water tank volume, and garbage storage volume of the unmanned sweeper 1 meet the corresponding set thresholds.
[0051] S3: If the judgment result meets the corresponding threshold, then determine whether the road ahead of the current driving path of the unmanned sweeper 1 is clear based on the received vehicle data information and map data information. Situations where the road ahead is not clear include: traffic congestion, the presence of obstacles, etc.
[0052] S4: If the judgment result of S3 is negative, the optimal driving path is calculated based on vehicle data and map data, and sent to the unmanned sweeper 1. For example, when the unmanned sweeper 1 is about to reach point C, it is determined through vehicle data and map data that the road segment ahead at point C is congested, and the current driving path will be affected. Therefore, the optimal path from the current location to point B (the next station) needs to be recalculated, and a new path is selected to bypass the congested road segment, such as passing through point D. After the calculation is completed, the unmanned sweeper 1 travels according to the new path. In addition, if there is an obstacle on the road ahead, the judgment result of step S3 is also negative. For example, when the unmanned sweeper 1 travels to a certain road segment, the surrounding environment image information in the received vehicle data shows that there is an obstacle ahead. The present invention will immediately calculate and plan a new optimal driving path to bypass the obstacle. Of course, in order to bypass the obstacle, since the size of the obstacle is limited, it is generally only necessary to adjust the local driving path. Generally, after bypassing the obstacle, it will return to the original driving path.
[0053] In one embodiment, if the judgment result of step S2 is negative, the optimal driving path passing through charging stations and / or water stations and / or garbage stations is calculated based on the judgment result, vehicle data information, and map data information. In this embodiment, the thresholds corresponding to the battery power value, water tank water level value, and garbage storage volume value in the vehicle data information are set to 20%, 10%, and 90%, respectively, meaning the battery power value cannot be lower than 20%, the water tank water level value cannot be lower than 10%, and the garbage storage volume cannot be higher than 90%. For example, if the battery power value is lower than 20% in the vehicle data information collected during the operation of the unmanned sweeper 1, it is determined that the battery power is insufficient and charging is required. A low battery power alarm will be received. At this time, the present invention will combine map data information to calculate the path that passes through the charging station with the shortest distance and fastest time to complete the sweeping task, and push it to the unmanned sweeper 1 as the optimal driving path. Of course, the charging of the unmanned sweeper 1 will be determined based on its actual charging time. Whether to continue the current task depends on several factors. Generally, if fast charging is possible without interrupting the cleaning task, the task will continue. However, if the charging station is far away and the charging time is long, this invention will, when calculating a new driving route, consider the requirements of the existing task scheduling system for the unmanned sweeper 1 (which communicates with the path optimization algorithm module 3 in this invention and is generally used for the release and scheduling of cleaning tasks for the unmanned sweeper 1). After the unmanned sweeper 1 has finished charging, it will be scheduled to perform a new cleaning task. Therefore, the given route is the optimal driving route when charging and performing other cleaning tasks. Obviously, the unmanned sweeper path dynamic adjustment method in this invention can realize timely charging, watering, and garbage dumping operations of the unmanned sweeper 1, avoiding affecting the normal operation of the unmanned sweeper 1.
[0054] Specifically, in this embodiment, if the judgment result of step S3 is yes, then an instruction is sent to the vehicle to continue driving according to the current driving path. That is, the road ahead of the unmanned sweeper 1 is clear and free of obstacles, and the battery power, water tank water level, and garbage storage capacity of the unmanned sweeper 1 are all within the normal range. Therefore, the current driving path of the unmanned sweeper 1 is the optimal driving path, and there is no need to adjust its driving path.
[0055] As can be seen from the above, the present invention can calculate the optimal driving path in a timely manner when the unmanned sweeper 1 encounters obstacles and / or traffic congestion, so as to realize the effective obstacle avoidance of the unmanned sweeper 1 and reduce the risk of accidents; at the same time, it avoids being in a congested environment, which affects its normal operating efficiency, shortens the sweeping time, and improves the overall operating efficiency.
[0056] It should be understood that the application of the present invention is not limited to the examples above. Those skilled in the art can make improvements or modifications based on the above description, and all such improvements and modifications should fall within the protection scope of the appended claims.
Claims
1. A cloud-based algorithm system for dynamically adjusting the path of an unmanned sweeper, characterized in that, include: A path optimization algorithm module is used to calculate the optimal driving path of the autonomous vehicle based on map data after receiving vehicle data information. A path push module is used to push the optimal driving path calculated by the path optimization algorithm module to the unmanned sweeper.
2. The cloud-based algorithm system for dynamic path adjustment of an unmanned sweeper according to claim 1, characterized in that, Also includes: The vehicle data information is collected by the real-time data acquisition module.
3. The cloud-based algorithm system for dynamic path adjustment of an unmanned sweeper according to claim 1, characterized in that, The path optimization algorithm module calculates the optimal driving path for the autonomous vehicle based on vehicle data and map data as follows: Based on the received vehicle data and map data, it is determined whether the road ahead of the current driving path of the unmanned sweeper is clear, and whether the vehicle status parameters in the vehicle data of the unmanned sweeper meet the set corresponding thresholds. Based on the judgment results, it is determined whether the current driving path of the unmanned sweeper needs to be adjusted. If adjustment is required, the optimal driving path is calculated based on real-time vehicle data and map data.
4. The cloud-based algorithm system for dynamic path adjustment of an unmanned sweeper according to claim 3, characterized in that, The vehicle data information includes: real-time vehicle location information, surrounding environment image information, and vehicle status parameters.
5. The cloud-based algorithm system for dynamic path adjustment of an unmanned sweeper according to claim 4, characterized in that, The vehicle status parameters include: vehicle speed, battery charge level, water tank level, and waste storage capacity.
6. The cloud-based algorithm system for dynamic path adjustment of an unmanned sweeper according to claim 1, characterized in that, The map data information is provided by map software and / or urban traffic management systems, and includes real-time traffic information and historical traffic information.
7. A method for dynamically adjusting the path of an unmanned sweeper, characterized in that, Includes a cloud-based algorithm system for dynamic path adjustment of an unmanned sweeper as described in any one of claims 1-6, wherein the method includes: S1: Receive vehicle data and map data from unmanned sweeping vehicles in real time; S2: Determine whether the battery charge, water tank level, and garbage storage capacity of the unmanned sweeper meet the set thresholds. S3: If the judgment result meets the corresponding threshold, then determine whether the road ahead of the current driving path of the unmanned sweeper is clear based on the received vehicle data information and map data information. S4: If the judgment result of S3 is negative, calculate the optimal driving route based on vehicle data and map data, and send it to the unmanned sweeper.
8. The method for dynamically adjusting the path of an unmanned sweeper according to claim 7, characterized in that, If the judgment result of step S2 is negative, then the optimal driving route passing through charging stations and / or water stations and / or garbage stations is calculated based on the judgment result, vehicle data information, and map data information.
9. The method for dynamically adjusting the path of an unmanned sweeper according to claim 7, characterized in that, If the determination result of step S3 is yes, then a command is sent to the vehicle to continue driving according to the current driving path.