Automatic feed feeding method and device, robot and computer storage medium

Abstract

The invention relates to an automatic feed feeding method and device, a robot and a computer storage medium, and belongs to the technical field of intelligent breeding, the automatic feed feeding method comprises the following steps: collecting environment information of a feed feeding environment where the automatic feeding robot is located, and constructing an environment map of the feed feeding environment; acquiring a real-time positioning position of the automatic feeding robot and a feed feeding target position, and planning a global navigation path from the real-time positioning position to the feed feeding target position based on an environment map; a local navigation path from the real-time positioning position to the feed feeding target position is planned based on the global navigation path and the environment information, and the automatic feeding robot is navigated to the feed feeding target position for feed feeding. Automatic navigation of the feed feeding robot is achieved, the robot can adapt to complex and changeable feed feeding environments, feeding accuracy and efficiency are improved, manual intervention and operation and maintenance cost are reduced, and powerful support is provided for intelligent management of the modern aquaculture industry.

Description

Technical Field

[0001] The present invention relates to the field of intelligent breeding technology, and in particular to an automatic feeding method, device, robot and computer storage medium. Background Art

[0002] With the rapid development of modern aquaculture, higher requirements are placed on the intelligent and automated level of aquaculture management. The traditional manual feeding method is not only inefficient, but also difficult to accurately control the feeding amount, resulting in resource waste and environmental pollution.

[0003] Although automatic feeding robots are available on the market, most of the existing automatic feeding robots perform timed and quantitative feeding at fixed locations. It is necessary to set up an automatic feeding robot at each feeding point, which has high deployment costs. Some mobile automatic feeding robots can only move on fixed tracks, cannot adapt to site changes, and cannot avoid obstacles, and cannot be used in actual production.

[0004] It can be seen that the existing automatic feeding robots have the problem of high deployment cost and cannot be used in complex environments. Summary of the invention

[0005] In view of this, it is necessary to provide an automatic feeding method, device, robot and computer storage medium to solve the problems of high deployment cost and inability to be used in complex environments of existing automatic feeding robots.

[0006] In order to solve the above problems, the present invention provides an automatic feeding method for feed, comprising: Collecting environmental information of the feed feeding environment in which the automatic feeding robot is located, and constructing an environmental map of the feed feeding environment based on the environmental information; Acquire the real-time positioning position and the target position of feed feeding of the automatic feeding robot, and plan a global navigation path from the real-time positioning position to the target position of feed feeding based on the environmental map; A local navigation path from the real-time positioning position to the feed feeding target position is planned based on the global navigation path and the environmental information, and the automatic feeding robot is navigated to the feed feeding target position for feed feeding based on the local navigation path.

[0007] In a possible implementation, the collecting of environmental information of the feed feeding environment in which the automatic feeding robot is located, and constructing an environmental map of the feed feeding environment based on the environmental information, includes: A single-line laser radar provided on the automatic feeding robot is used to collect spatial distance data between the automatic feeding robot and the feed feeding environment; Determining the position information of the automatic feeding robot based on the spatial distance data of continuous frames; An environmental map of the feed feeding environment is constructed by combining the spatial distance data of the continuous frames and the posture information.

[0008] In a possible implementation manner, the obtaining of the real-time positioning position of the automatic feeding robot and the target position of feed feeding includes: Acquire a plurality of continuous frame scanning data collected by the single-line laser radar, and use a preset positioning algorithm to combine the environmental map and the plurality of continuous frame scanning data to determine the real-time positioning position of the automatic feeding robot; A preset feed feeding target location is determined based on the environmental map.

[0009] In a possible implementation, planning a global navigation path from the real-time positioning position to the feed feeding target position based on the environmental map includes: Based on the real-time positioning position and the feed feeding target position, a preset path planning algorithm is used to plan the shortest path from the real-time positioning position to the feed feeding target position in the environmental map; A plurality of intermediate navigation points are added to the shortest path to obtain a global navigation path.

[0010] In a possible implementation, the determining and planning a local navigation path from the real-time positioning position to the feed feeding target position based on the global navigation path and the environmental information includes: Obtaining the current speed, current acceleration and obstacle information on the navigation path of the automatic feeding robot; Determine a plurality of candidate local navigation paths between the plurality of intermediate navigation points based on the current speed, the current acceleration, and obstacle information on the navigation path; The plurality of candidate local navigation paths are scored using a preset local path planning algorithm, and the candidate local navigation path with the highest score is determined as the target local navigation path.

[0011] In a possible implementation, the feeding of feed includes: Get the current remaining weight of feed and the real-time remaining weight of feed when feeding; When the difference between the current feed remaining weight and the real-time feed remaining weight reaches the target feed feeding weight of the feed feeding target position, the feeding is stopped.

[0012] In a possible implementation, the method further includes: After the automatic feeding of feed is completed at the feed feeding target position, the next feed feeding target position is obtained, and the feed feeding target position is used as a new real-time positioning position to construct a new navigation path for a new round of feeding navigation.

[0013] The present invention also provides an automatic feeding device for feed, comprising: A map construction module, used to collect environmental information of the feed feeding environment in which the automatic feeding robot is located, and to construct an environmental map of the feed feeding environment based on the environmental information; A path planning module, used to obtain the real-time positioning position of the automatic feeding robot and the feed feeding target position, and plan a global navigation path from the real-time positioning position to the feed feeding target position based on the environmental map; A navigation and feeding module is used to plan a local navigation path from the real-time positioning position to the feed feeding target position based on the global navigation path and the environmental information, and navigate the automatic feeding robot to the feed feeding target position for feed feeding based on the local navigation path.

[0014] The present invention also provides an automatic feeding robot, comprising a memory and a processor, wherein: The memory is used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps in the automatic feeding method described in any of the above embodiments.

[0015] The present invention also provides a computer-readable storage medium for storing a computer-readable program or instruction, which, when executed by a processor, can implement the steps in the automatic feeding method described in any of the above embodiments.

[0016] The beneficial effects of the present invention are as follows: the automatic feeding method provided by the present invention obtains environmental information of the feed feeding environment in which the automatic feeding robot is located, and constructs an environmental map, then obtains the real-time position of the automatic feeding robot and the feed feeding target position, and plans a global navigation path based on the environmental map, and plans a local navigation path in combination with the global navigation path and the environmental information of the feed feeding environment, navigates according to the local navigation path, and automatically feeds the feed after the automatic feeding robot reaches the feed feeding target position. One feed feeding robot can complete large-scale automatic feed feeding, and realizes automatic navigation of the feed feeding robot, can adapt to complex and changeable feed feeding environments, effectively improves the accuracy and efficiency of feeding, reduces manual intervention and operation and maintenance costs, and provides strong support for the intelligent management of modern aquaculture. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 A schematic diagram of a flow chart of an automatic feeding method for feed provided in an embodiment of the present invention; Figure 2 A schematic diagram of a flow chart of an environment map construction method provided by an embodiment of the present invention; Figure 3 A schematic diagram of a flow chart of a location determination method provided by an embodiment of the present invention; Figure 4 A schematic diagram of a flow chart of a method for determining a global navigation path provided by an embodiment of the present invention; Figure 5 A schematic diagram of a flow chart of a local navigation method provided by an embodiment of the present invention; Figure 6 A schematic diagram of a feed feeding method provided by an embodiment of the present invention; Figure 7 A schematic structural diagram of an automatic feed feeding device provided by an embodiment of the present invention; Figure 8 A schematic structural diagram of an automatic feeding robot provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0019] The preferred embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a part of the present invention and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not used to limit the scope of the present invention.

[0020] Reference to an "embodiment" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiment may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0021] A specific embodiment of the present invention, as Figure 1 As shown, a method for automatically feeding feed is disclosed, comprising: S101, collecting environmental information of the feeding environment in which the automatic feeding robot is located, and constructing an environmental map of the feeding environment based on the environmental information; S102, obtaining the real-time positioning position and the target position of the feed feeding of the automatic feeding robot, and planning a global navigation path from the real-time positioning position to the target position of the feed feeding based on the environmental map; S103, planning a local navigation path from the real-time positioning position to the feed feeding target position based on the global navigation path and environmental information, and navigating the automatic feeding robot to the feed feeding target position for feeding based on the local navigation path.

[0022] In an embodiment of the present invention, the feed feeding environment refers to a breeding site where automatic feed feeding is required. Taking a water plant breeding base as an example, a plurality of breeding pools are generally built in a water plant breeding base. When feeding feed, feed can be fed into the pool at a regular time and in a fixed quantity at the side of the pool. The automatic feed feeding method provided in an embodiment of the present invention can control the automatic feeding robot to move to each pool side in the water plant breeding base for automatic feed feeding. The environmental information of the feed feeding environment refers to information that can be used to construct an environmental map, which can be collected in a variety of ways, such as laser radar, image acquisition device, etc., to collect data on various obstacles and spaces in the feed feeding environment, and construct an environmental map based on the data.

[0023] In an embodiment of the present invention, after completing the environmental map of the feeding environment, it is necessary to obtain the real-time positioning position of the automatic feeding robot. The real-time positioning position refers to the position of the automatic feeding robot at the current moment in the environmental map. The feed feeding target position refers to the position of the preset feed feeding point by the pool in the environmental map. Based on the environmental map, a global navigation path from the real-time positioning position to the feed feeding target position can be planned. The specific path planning method will be described later in the present invention.

[0024] In an embodiment of the present invention, after planning the global navigation path from the real-time positioning position of the automatic feeding robot to the target feeding position of the feed, it is also necessary to plan a local navigation path based on the global navigation path and in combination with the environmental information of the feed feeding environment. The local navigation path is used to guide the automatic feeding robot to travel to the target feeding position of the feed while avoiding obstacles in a complex feed feeding environment. In order to ensure the optimality of the path, the real-time positioning position of the automatic feeding robot is updated while the automatic feeding robot moves, and the navigation path is updated in real time until the automatic feeding robot reaches the target feeding position of the feed, thereby completing the fully automatic feeding of the feed.

[0025] The automatic feeding method provided by the present invention obtains environmental information of the feed feeding environment in which the automatic feeding robot is located, and constructs an environmental map, then obtains the real-time position of the automatic feeding robot and the feed feeding target position, and plans a global navigation path based on the environmental map, and plans a local navigation path in combination with the global navigation path and the environmental information of the feed feeding environment, navigates according to the local navigation path, and automatically feeds the feed after the automatic feeding robot reaches the feed feeding target position. One feed feeding robot can complete large-scale automatic feed feeding, and automatic navigation of the feed feeding robot is realized, which can adapt to complex and changeable feed feeding environments, effectively improves the accuracy and efficiency of feeding, reduces manual intervention and operation and maintenance costs, and provides strong support for the intelligent management of modern aquaculture.

[0026] As a possible implementation mode of the present invention, in this implementation mode, Figure 2 As shown, the environmental information of the feeding environment where the automatic feeding robot is located is collected, and an environmental map of the feeding environment is constructed based on the environmental information, including: S201, using a single-line laser radar provided on the automatic feeding robot to collect spatial distance data between the automatic feeding robot and the feed feeding environment; S202, determining the position and posture information of the automatic feeding robot based on the spatial distance data of the continuous frames; S203, constructing an environmental map of the feeding environment by combining the spatial distance data and posture information of the continuous frames.

[0027] In an embodiment of the present invention, when constructing an environmental map of a feed feeding environment, a single-line laser radar provided on the automatic feeding robot can be used to collect spatial distance data between the automatic feeding robot and the feed feeding environment. Specifically, the automatic feeding robot can first circle around the feed feeding environment, and use a single-line laser radar to collect distance information of the surrounding environment. When the laser radar scans the environment, it will return distance data of objects in space. After collecting multiple frames of continuous distance data, a robot mobile mapping algorithm can be used to process these distance data, such as the Hector algorithm. When processing the distance data, the posture information of the automatic feeding robot is first determined based on multiple frames of continuous distance data. Based on the posture information, the environmental map is constructed in combination with multiple frames of continuous distance data. Optionally, the environmental map is a 2D occupancy grid map, which can effectively reflect the spatial layout around the automatic feeding robot.

[0028] The embodiments of the present invention do not rely on prior maps, but directly perform positioning and mapping through real-time scanning data of the lidar. Especially in some complex breeding environments, through continuous scanning and matching, it can adapt to dynamically changing environments and generate accurate environmental maps in real time.

[0029] As a possible implementation mode of the present invention, in this implementation mode, Figure 3 As shown, the real-time positioning position of the automatic feeding robot and the target position of the feed are obtained, including: S301, obtaining a plurality of continuous frame scanning data collected by a single-line laser radar, and using a preset positioning algorithm to combine the environment map and the plurality of continuous frame scanning data to determine the real-time positioning position of the automatic feeding robot; S302, determining a preset feed feeding target location based on the environmental map.

[0030] In an embodiment of the present invention, after the construction of the environmental map is completed, the automatic feeding robot can be accurately positioned. Specifically, the AMCL (Adaptive Monte Carlo Positioning) algorithm can be used. The AMCL algorithm is a positioning method based on particle filtering. A large number of particles are generated to represent the possible positions of the robot, and then the laser radar data is matched with the map to update the weight of each particle. The particle with a larger weight represents the possibility of the current position of the robot. In practical applications, the automatic feeding robot needs to continuously receive the scanning data of the laser radar, and update its posture information in real time in combination with the current environmental map. The AMCL algorithm can quickly and accurately determine the position and orientation of the robot through multiple iterations, thereby ensuring the accuracy of the navigation process. In addition, for the target position of feed feeding, the corresponding position can be determined in the constructed environmental map according to the pre-set feed feeding point, wherein there are generally multiple target positions for feed feeding, such as a feed feeding point can be set at each pool in the water plant breeding environment, or multiple pools share a feed feeding point, or a pool is set with multiple feed feeding points. This is not limited by the present invention.

[0031] The embodiment of the present invention determines the real-time positioning position of the automatic feeding robot through an algorithm, thereby ensuring the accuracy of the positioning of the automatic feeding robot and further ensuring the navigation accuracy.

[0032] As a possible implementation mode of the present invention, in this implementation mode, Figure 4 As shown, a global navigation path from the real-time positioning position to the feed feeding target position is planned based on the environmental map, including: S401, planning the shortest path from the real-time positioning position to the feed feeding target position in the environment map using a preset path planning algorithm based on the real-time positioning position and the feed feeding target position; S402, adding multiple intermediate navigation points to the shortest path to obtain a global navigation path.

[0033] In an embodiment of the present invention, in order for the automatic feeding robot to move from the current positioning position to the feed feeding target position, global path planning is required. Specifically, a path planning algorithm, such as the Dijkstra algorithm, can be used for global path planning, and the shortest path from the starting point to the target point can be found on the global map. Specifically, according to the environmental map constructed in the aforementioned embodiment, the real-time positioning position of the automatic feeding robot in the environmental map is used as the starting point, and the feed feeding target position is used as the end point. The shortest path from the starting point to the end point is drawn, and according to the obstacle information displayed in the environmental map, multiple intermediate navigation points are added to the shortest path to obtain a global navigation path from the real-time positioning position to the feed feeding target position.

[0034] Further, such as Figure 5 As shown, based on the global navigation path and environmental information, a local navigation path from the real-time positioning position to the feed feeding target position is determined and planned, including: S501, obtaining the current speed, current acceleration and obstacle information on the navigation path of the automatic feeding robot; S502, determining a plurality of candidate local navigation paths between a plurality of intermediate navigation points based on the current speed, the current acceleration, and obstacle information on the navigation path; S503: Using a preset local path planning algorithm to score multiple candidate local navigation paths, and determining the candidate local navigation path with the highest score as the target local navigation path.

[0035] In an embodiment of the present invention, on the basis of global path planning, the automatic feeding robot also needs to perform local path planning to ensure dynamic obstacle avoidance during actual operation. Specifically, a dynamic window algorithm can be used to plan the local path. The dynamic window algorithm generates a series of feasible trajectories within the local range of the robot's movement by considering the robot's current speed, acceleration, and obstacle information, and then scores each trajectory. The scoring criteria include the distance to the target point, the safety of avoiding obstacles, and the smoothness of the movement. Finally, the dynamic window algorithm will select the trajectory with the highest score and generate corresponding linear velocity and angular velocity control instructions to guide the robot to move. In practical applications, the dynamic window algorithm can respond to changes in the environment in real time. For example, when a dynamic obstacle appears, the local path will be quickly replanned to ensure that the robot safely avoids obstacles and continues to move toward the target point.

[0036] In an embodiment of the present invention, when a dynamic window algorithm is used to avoid obstacles in a local range to produce a local navigation path, a possible sample space is generated according to the current speed and acceleration limits of the automatic feeding robot, a forward simulation is performed on each speed sample, the trajectory in a short period of time is predicted, the score of each trajectory is evaluated, and finally the trajectory with the highest score is selected, and the corresponding linear speed and angular velocity control instructions are output. The linear speed and angular velocity control instructions are used to control the automatic feeding robot to move.

[0037] The present invention ensures that the automatic feeding robot can avoid obstacles in a complex environment by performing local navigation on the automatic mobile robot.

[0038] As a possible implementation mode of the present invention, in this implementation mode, Figure 6 As shown, feeding includes: S601, obtaining the current remaining weight of feed, and obtaining the real-time remaining weight of feed when feeding; S602, when the difference between the current remaining weight of feed and the real-time remaining weight of feed reaches the target feeding weight of feed at the target feeding position, stop feeding.

[0039] In an embodiment of the present invention, the automatic feeding robot is equipped with a feed feeding machine, which can be controlled by the operating system of the automatic feeding robot. When the automatic feeding robot moves to the target feeding position, before starting feeding, a communication connection between the robot operating system and the feeder is first established through the RS485 serial port. Specifically, the PyModbus library can be used to implement the communication function of the Modbus RTU protocol. Through the library, the robot can send instructions to the feeder through the 485 serial port and receive feedback information from the feeder in real time. After the feeder is started, the robot reads the weight of the feed in the feeder in real time. The feeding target amount set by the system is assumed to be 100 grams. When the real-time monitoring shows that the feed has decreased by 100 grams, the robot will immediately send a stop feeding instruction to stop feeding the feed. During the entire feeding process, the automatic feeding robot can control the start and stop of the feeder, and can also monitor the feeding status in real time, including reading the real-time weight of the feeder, monitoring the stability of the communication link, and providing feedback on the current feeding execution status. Through these status monitoring, the robot can ensure that the feeding amount at each feeding point is accurate and can respond in time when an abnormality occurs.

[0040] Furthermore, the automatic feeding method also includes: When the automatic feeding of feed is completed at the feeding target position, the next feeding target position is obtained, and the feeding target position is used as the new real-time positioning position to construct a new navigation path for a new round of feeding navigation.

[0041] In an embodiment of the present invention, after feeding is completed at the current feed feeding target position, a new feed feeding target position is obtained, and then a new round of path planning and feed feeding is performed according to the above embodiment until feed feeding is completed at all feed feeding target positions.

[0042] The present invention constructs a map, obtains the real-time position of the automatic feeding robot and the target position of feed feeding, and relies on an algorithm to navigate and avoid obstacles for the automatic feeding robot, thereby effectively solving the feeding problem in the factory-scale recirculating aquaculture system, freeing up labor and improving feeding accuracy.

[0043] In order to better implement the automatic feeding method of feed in the embodiment of the present invention, based on the automatic feeding method of feed, correspondingly, Figure 7 As shown, the embodiment of the present invention further provides an automatic feed feeding device, the automatic feed feeding device 700 comprises: A map construction module 701 is used to collect environmental information of the feed feeding environment in which the automatic feeding robot is located, and to construct an environmental map of the feed feeding environment based on the environmental information; The path planning module 702 is used to obtain the real-time positioning position of the automatic feeding robot and the feed feeding target position, and plan a global navigation path from the real-time positioning position to the feed feeding target position based on the environmental map; The navigation and feeding module 703 is used to plan a local navigation path from the real-time positioning position to the feed feeding target position based on the global navigation path and environmental information, and navigate the automatic feeding robot to the feed feeding target position for feeding based on the local navigation path.

[0044] The automatic feeding device 700 provided by the present invention obtains environmental information of the feed feeding environment in which the automatic feeding robot is located, and constructs an environmental map, then obtains the real-time position of the automatic feeding robot and the feed feeding target position, and plans a global navigation path based on the environmental map, and plans a local navigation path in combination with the global navigation path and the environmental information of the feed feeding environment, navigates according to the local navigation path, and automatically feeds the feed after the automatic feeding robot reaches the feed feeding target position. One feed feeding robot can complete large-scale automatic feed feeding, and realizes automatic navigation of the feed feeding robot, can adapt to complex and changeable feed feeding environments, effectively improves the accuracy and efficiency of feeding, reduces manual intervention and operation and maintenance costs, and provides strong support for the intelligent management of modern aquaculture.

[0045] The automatic feed feeding device 700 provided in the above embodiment can implement the technical solution described in the above automatic feed feeding method embodiment. The specific implementation principles of the above modules or units can refer to the corresponding contents in the above automatic feed feeding method embodiment, which will not be repeated here.

[0046] like Figure 8 As shown, the present invention also provides an automatic feeding robot 800 . The automatic feeding robot 800 includes a processor 801 , a memory 802 and a display 803 . Figure 8 Only some components of the automatic feed feeding robot 800 are shown, but it should be understood that it is not required to implement all the shown components, and more or fewer components may be implemented instead.

[0047] In some embodiments, the processor 801 may be a central processing unit (CPU), a microprocessor or other data processing chip, and is used to run program codes or process data stored in the memory 802, such as the automatic feeding method of the present invention.

[0048] In some embodiments, the processor 801 may be a single server or a server group. The server group may be centralized or distributed. In some embodiments, the processor 801 may be local or remote. In some embodiments, the processor 801 may be implemented in a cloud platform. In some embodiments, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-cloud, etc., or any combination thereof.

[0049] In some embodiments, the memory 802 may be an internal storage unit of the automatic feeding robot 800, such as a hard disk or memory of the automatic feeding robot 800. In other embodiments, the memory 802 may also be an external storage device of the automatic feeding robot 800, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc., equipped on the automatic feeding robot 800.

[0050] Furthermore, the memory 802 may include both an internal storage unit and an external storage device of the automatic feed feeding robot 800. The memory 802 is used to store application software installed by the automatic feed feeding robot 800 and various data.

[0051] In some embodiments, the display 803 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 803 is used to display information of the automatic feeding robot 800 and to display a visual user interface. The components 801-803 of the automatic feeding robot 800 communicate with each other through a system bus.

[0052] In some embodiments, when the processor 801 executes the automatic feeding program in the memory 802, the following steps may be implemented: Collect environmental information of the feeding environment where the automatic feeding robot is located, and construct an environmental map of the feeding environment based on the environmental information; Obtain the real-time positioning position of the automatic feeding robot and the target position of the feed, and plan the global navigation path from the real-time positioning position to the target position of the feed based on the environmental map; Based on the global navigation path and environmental information, a local navigation path from the real-time positioning position to the feed feeding target position is planned, and based on the local navigation path, the automatic feeding robot is navigated to the feed feeding target position for feeding.

[0053] It should be understood that: when the processor 801 executes the automatic feeding program in the memory 802, in addition to the above functions, other functions can also be realized. For details, please refer to the description of the corresponding method embodiment above.

[0054] Accordingly, an embodiment of the present invention also provides a computer-readable storage medium, which is used to store computer-readable programs or instructions. When the program or instructions are executed by a processor, the steps or functions of the automatic feeding method provided in the above-mentioned method embodiments can be implemented.

[0055] Those skilled in the art can understand that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0056] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with the technical field within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention.

Claims

1. A method for automatically feeding feed, characterized in that: include: Collecting environmental information of the feed feeding environment in which the automatic feeding robot is located, and constructing an environmental map of the feed feeding environment based on the environmental information; Acquire the real-time positioning position and the target position of feed feeding of the automatic feeding robot, and plan a global navigation path from the real-time positioning position to the target position of feed feeding based on the environmental map; A local navigation path from the real-time positioning position to the feed feeding target position is planned based on the global navigation path and the environmental information, and the automatic feeding robot is navigated to the feed feeding target position for feed feeding based on the local navigation path.

2. The automatic feeding method according to claim 1, characterized in that: The collecting of environmental information of the feed feeding environment in which the automatic feeding robot is located, and constructing an environmental map of the feed feeding environment based on the environmental information, includes: A single-line laser radar provided on the automatic feeding robot is used to collect spatial distance data between the automatic feeding robot and the feed feeding environment; Determining the position information of the automatic feeding robot based on the spatial distance data of continuous frames; An environmental map of the feed feeding environment is constructed by combining the spatial distance data of the continuous frames and the posture information.

3. The automatic feeding method according to claim 2, characterized in that: The step of obtaining the real-time positioning position of the automatic feeding robot and the target position of feed feeding includes: Acquire a plurality of continuous frame scanning data collected by the single-line laser radar, and use a preset positioning algorithm to combine the environmental map and the plurality of continuous frame scanning data to determine the real-time positioning position of the automatic feeding robot; A preset feed feeding target location is determined based on the environmental map.

4. The automatic feeding method according to claim 3, characterized in that: The planning of the global navigation path from the real-time positioning position to the feed feeding target position based on the environmental map includes: Based on the real-time positioning position and the feed feeding target position, a preset path planning algorithm is used to plan the shortest path from the real-time positioning position to the feed feeding target position in the environmental map; A plurality of intermediate navigation points are added to the shortest path to obtain a global navigation path.

5. The automatic feeding method according to claim 4, characterized in that: The determining and planning of a local navigation path from the real-time positioning position to the feed feeding target position based on the global navigation path and the environmental information includes: Obtaining the current speed, current acceleration and obstacle information on the navigation path of the automatic feeding robot; Determine a plurality of candidate local navigation paths between the plurality of intermediate navigation points based on the current speed, the current acceleration, and obstacle information on the navigation path; The plurality of candidate local navigation paths are scored using a preset local path planning algorithm, and the candidate local navigation path with the highest score is determined as the target local navigation path.

6. The automatic feeding method according to claim 1, characterized in that: The feeding of feed comprises: Get the current remaining weight of feed and the real-time remaining weight of feed when feeding; When the difference between the current feed remaining weight and the real-time feed remaining weight reaches the target feed feeding weight of the feed feeding target position, the feeding is stopped.

7. The automatic feeding method according to claim 1, characterized in that: The method further comprises: After the automatic feeding of feed is completed at the feed feeding target position, the next feed feeding target position is obtained, and the feed feeding target position is used as a new real-time positioning position to construct a new navigation path for a new round of feeding navigation.

8. An automatic feeding device, characterized in that: include: A map construction module, used to collect environmental information of the feed feeding environment in which the automatic feeding robot is located, and to construct an environmental map of the feed feeding environment based on the environmental information; A path planning module, used to obtain the real-time positioning position of the automatic feeding robot and the feed feeding target position, and plan a global navigation path from the real-time positioning position to the feed feeding target position based on the environmental map; A navigation and feeding module is used to plan a local navigation path from the real-time positioning position to the feed feeding target position based on the global navigation path and the environmental information, and navigate the automatic feeding robot to the feed feeding target position for feed feeding based on the local navigation path.

9. An automatic feeding robot, characterized in that: comprising a memory and a processor, wherein: The memory is used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps in the automatic feeding method of any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Used to store computer-readable programs or instructions, which, when executed by a processor, can implement the steps of the automatic feed feeding method described in any one of claims 1 to 7.

Images