A method, system, electronic device and cleaning machine vehicle for the edge sticking of a cleaning machine vehicle
By obtaining the location and environment information of the cleaning machine truck, using the hybrid A* algorithm to generate the welt and detour path, and through the cost function decision, the existing technology cleaning machine truck is solved to accurately welt and get rid of difficulties in complex environments. Improves cleaning efficiency and reliability of the robot system.
Patent Information
- Application Number
- CN202411011202.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-26
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2044-07-26
AI Technical Summary
Existing cleaning machines are difficult to achieve accurate welding and effective escape in complex environments, resulting in low cleaning efficiency and increased wear of the robot drive system.
By obtaining the location information and environmental information of the cleaning machine truck, the hybrid A* algorithm is used to generate the edge cleaning path and the bypass point path, and the cost function is calculated through the path decision, and the path is adjusted in real time to avoid the stuck state and achieve automatic escape.
It improves the precise welding capability and escape efficiency of cleaning machines in complex environments, reduces the frequency of robot stoppage and the wear of the drive system.
Smart Images

Figure CN118584961B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of automatic operation of robot vehicles, and in particular to a method for accurate edge-adherence and escape of a cleaning robot vehicle. Background Art
[0002] With the continuous advancement of robot technology, sweeping robots are increasingly used in various environments, especially in large-scale park environments where manual cleaning is difficult to fully cover. In these environments, a large amount of road garbage usually accumulates on the roadside, which puts higher requirements on the precise edge-adhering and effective escape capabilities of sweeping robots. Existing sweeping robots use the method of offline processing of edge-adhering trajectory data after manual control or the method of artificial potential field to achieve precise edge-adhering, which performs well in simple or regular environments, but requires a large amount of manually collected data. In addition, in complex environments such as parks, due to the presence of a large number of irregular edges and unexpected obstacles, traditional navigation and cleaning technologies often cannot meet the cleaning efficiency, and may also cause the robot to frequently freeze or be damaged. In addition, when the sweeping robot encounters difficult terrain or is trapped by obstacles, the existing escape technology often cannot avoid or effectively respond in advance. In such cases, the robot needs multiple attempts to escape, which greatly reduces the operating efficiency and increases the wear on the robot drive system. Summary of the invention
[0003] The purpose of the present invention is to provide a method for a cleaning robot vehicle to accurately follow the edge and escape from trouble, so as to solve the problems raised in the above-mentioned background technology.
[0004] In a first aspect, the present invention provides a method for cleaning a vehicle edge, characterized by comprising:
[0005] Get the location information of the cleaning machine;
[0006] Obtain environmental information around the cleaning machine, and obtain curb information and obstacle information from the environmental information;
[0007] Based on the acquired location information and environmental information, the cleaning robot vehicle's edge cleaning path and detour point path are planned. The cleaning robot vehicle's driving speed is used to determine whether it is stuck, and the path decision is made by calculating the cost function of each path.
[0008] Based on the real-time tracking result of the path decision, the cleaning robot vehicle is controlled to enter an escape mode or a normal working mode.
[0009] Preferably, the step of planning a cleaning path for the cleaning machine based on the acquired position information and environmental information includes:
[0010] A first path along the edge reference line is generated by a hybrid A* algorithm;
[0011] The first path is used as an initial trajectory input and passed into a trajectory smoother based on a differential flattening technique to generate a second path;
[0012] A third path that can safely reach the detour target point is generated in real time through a hybrid A* algorithm.
[0013] Preferably, the path length of the first path is 3-5 meters, and the distance between the end point of the first path and the edge reference line is within 10 cm, and the angle deviation is within plus or minus 5 degrees.
[0014] Preferably, the planning process of the detour path includes:
[0015] Obtain obstacle information and mark it as a target point;
[0016] Taking the target point as the goal, the path to the target point is generated by the hybrid A* algorithm.
[0017] Preferably, the step of judging whether the cleaning machine is in a stuck state by the driving speed of the cleaning machine includes:
[0018] Determine whether the first path, the second path, and the third path collide;
[0019] If the traveling speed of the cleaning robot vehicle is 0 within 2 seconds after the collision, the cleaning robot vehicle is in a stuck state.
[0020] Preferably, the escape mode refers to the cleaning robot guiding the cleaning robot to reverse with the goal of bypassing the target point through the backward search function of the hybrid A* algorithm.
[0021] Preferably, the performing path decision by calculating the cost function of each path includes:
[0022] By judging the stuck state, the cleaning robot is guided to start the escape mode first;
[0023] When there are no obstacles on the edge cleaning path, the edge cleaning path is adjusted by calculating the cost function of distance and angle;
[0024] When there is an obstacle on the edge cleaning path, the path of the cleaning vehicle is adjusted according to the distance between the obstacle and the cleaning vehicle.
[0025] In a second aspect, the present invention provides a system for accurately following the edge and getting out of trouble for a cleaning robot, comprising:
[0026] The positioning module obtains the location information of the cleaning robot through the on-board automatic driving system;
[0027] A perception module, which is used to obtain image data from vehicle-mounted sensors and extract obstacle information and curb information;
[0028] The planning module performs path planning for the cleaning task, generates edge cleaning paths and detour paths, and calculates the cost function of each real-time path for real-time decision making;
[0029] The control module controls the state of the cleaning robot vehicle by tracking the decision results of the path planning module.
[0030] In a third aspect, the present invention provides an electronic device, characterized in that it comprises at least one processor, which is communicatively connected to at least one memory, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described in any one of claims 1 to 7.
[0031] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a processor to implement the method for precise edging and escape of a cleaning robot vehicle as described in any embodiment of the present invention when executed.
[0032] The technical solution of the present invention obtains position information through an automatic driving system based on a cleaning robot vehicle; obtains obstacle and curb information based on image information provided by a camera; generates a first path, a second path, and a third path through a hybrid A* algorithm, and plans a smooth route for the cleaning robot vehicle through the first path and the second path, so that the cleaning robot vehicle can perform cleaning operations close to the edge; the third path can predict obstacle information and bypass obstacles; the path of the cleaning vehicle is selected through path decision, effectively predicting and reducing the occurrence of the cleaning robot vehicle being stuck, thereby reducing the triggering frequency of the escape mode and reducing the wear on the robot drive system. When the cleaning robot vehicle completes the planning and decision-making of the edge cleaning trajectory, the resulting trajectory is transmitted to the control module and the execution module to realize trajectory tracking, thereby ultimately achieving accurate edge cleaning and escape in a complex park environment. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] Figure 1 A flow chart of a cleaning machine vehicle edge-adhering method provided by the present invention;
[0034] Figure 2 For the present invention Figure 1 The sub-flow chart of S300;
[0035] Figure 3 The relationship between the cost function and the position of the trajectory collision point in an environment with obstacles according to an embodiment of the present invention;
[0036] Figure 4 is the relationship between the cost function and the position of the trajectory collision point in an obstacle-free environment of an embodiment of the present invention;
[0037] Figure 5 This is a diagram showing the edge-adhesion effect of an embodiment of the present invention in a simulation scene;
[0038] Figure 6 This is a schematic diagram of an edge path in a map with a radius of 5M according to an embodiment of the present invention;
[0039] Figure 7 This is a schematic diagram of the edge path in a map with a radius of 23M according to an embodiment of the present invention;
[0040] Figure 8 A precise edge-adhering and escape system for a cleaning machine vehicle provided in the embodiment of the present invention;
[0041] Fig. 9 A schematic diagram of the structure of an electronic device for the precise edge-adhering and escape method according to an embodiment of the present invention. DETAILED DESCRIPTION
[0042] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0043] The method for precise edge cleaning and escape from difficulties provided by the embodiment of the present invention can be applied to a cleaning robot vehicle. The cleaning robot vehicle can be an unmanned cleaning vehicle, which can automatically clean garbage on the road, automatically bypass obstacles, automatically drive, automatically turn around, automatically pass traffic lights, and automatically park, etc., and mainly can clean the roads in complex park environments.
[0044] See also Figure 1 , Figure 2 The present invention provides a method for cleaning machine vehicle to follow the edge, which can be performed by the cleaning machine vehicle, and includes the following steps:
[0045] S100. Obtaining the location information of the cleaning machine;
[0046] In an embodiment of the present invention, the location information of the sweeping robot vehicle is obtained through the automatic driving system of the sweeping robot vehicle, and the automatic driving GNSS system can provide longitude and latitude, direction, and speed information.
[0047] S200. Obtaining environmental information around the cleaning machine, and obtaining curb information and obstacle information from the environmental information;
[0048] In an embodiment of the present invention, the sweeping robot vehicle is equipped with a front camera, which obtains image information of the road to be cleaned on the right side, detects the road edge line after grayscale processing of the image information, and obtains the road contour after filtering and edge detector processing.
[0049] S300. Based on the acquired location information and environmental information, a cleaning path along the edge and a detour path are planned for the cleaning robot vehicle. Whether the cleaning robot vehicle is stuck is determined by its driving speed, and a path decision is made by calculating the cost function of each path.
[0050] In an embodiment of the present invention, the edge cleaning path of the sweeping robot vehicle includes three candidate paths, namely the first path, the second path and the third path. The goal of this stage is to allow the sweeping robot vehicle to travel along the edge of the road contour so that the cleaning range of the sweeping robot vehicle can be as close to the curb as possible.
[0051] S301. Generate a first path along the edge reference line by using a hybrid A* algorithm.
[0052] In a specific embodiment of the present invention, the first path is used as the target path for the sweeping robot to sweep close to the roadside. The first path is generated by a hybrid A* algorithm, wherein the cost function of the portion close to the reference line in the hybrid A* algorithm is designed as follows:
[0053] Distance cost:
[0054]
[0055] Angle cost:
[0056]
[0057] Among them, cur_dist represents the distance between the current position of the robot and the nearest point of the reference line, cur_theta represents the deviation between the current orientation of the robot and the orientation of the nearest point of the reference line, α and β represent the cost function coefficients of distance and angle respectively, both of which are 5, γ_dist and γ_theta represent the coefficients of distance and angle in the exponential function respectively, with the sizes of 10 and 8. These two parameters are used to adjust the influence of distance and angle on the edge effect under different deviations from the reference line. The search cutoff condition of hybrid A* is set as the distance between the end point of the trajectory and the edge reference line is within 10cm, the angle deviation is controlled within plus or minus 5°, the trajectory length is 3-5 meters, and the end of the trajectory is connected to the edge reference line to generate the first path.
[0058] S302. The first path is used as an initial trajectory input and passed into a trajectory smoother based on differential flattening technology to generate a second path.
[0059] In a specific embodiment of the present invention, the generation process of the second path is as follows: the second path uses the trajectory of the first path as the initial trajectory input, constructs a safe driving corridor, and imports a trajectory smoother based on differential flattening technology, that is, through a few state variables and the derivatives of the state variables, it can characterize the entire state of the sweeping robot vehicle to reduce energy consumption and improve operating efficiency.
[0060] In a specific embodiment of the present invention, the differential flatness principle is as follows: Assuming that the sweeping robot does not skid and the tires can achieve perfect steering, the state space of the sweeping robot is represented by ,in and They represent the positions of the rear wheels of the sweeping vehicle in the x-axis and y-axis directions respectively. is the direction of the robot, For the speed of the robot, , They represent the longitudinal acceleration and lateral acceleration of the robot vehicle respectively, Indicates the direction of the front tire. represents the curvature. , As flat outputs, other state variables can be expressed as:
[0061] ,
[0062] ,
[0063] ,
[0064] ,
[0065] ,
[0066] ,
[0067] Where L represents the wheelbase of the cleaning machine. Indicates the direction of the car's movement.
[0068] S303. Generate a third path that can safely reach the detour target point in real time through the hybrid A* algorithm.
[0069] In a specific embodiment of the present invention, the third path takes the bypass target point as the target, and generates a trajectory that can safely reach the bypass target point through hybrid A*. At this time, the heuristic function of the hybrid A* is restored and set to the maximum value of the distance between the current node and the target point considering collision and ignoring dynamic constraints and the distance considering dynamic constraints and ignoring collision as the heuristic function, and uses the Reeds-Shepp curve to try to connect the current node and the target point, thereby speeding up the search speed.
[0070] S304: Determine whether the first path, the second path and the third path collide. If the speed of the cleaning robot vehicle is 0 within 2 seconds after the collision, the cleaning robot vehicle is in a stuck state.
[0071] In an embodiment of the present invention, at this stage, it is determined whether the cleaning robot has entered a stuck state according to preset conditions, and the robot enters an escape mode when in a stuck state. Specifically, if the speed of the cleaning robot remains at 0 m / s for 2 seconds or remains at 0 m / s for 3 seconds, it is determined that the robot is stuck. In this case, the escape mode will be automatically triggered. In the present invention, it is preferred that the speed of the cleaning robot remains at 0 m / s for 2 seconds and is determined to be in a stuck mode, so as to shorten the time for judging the stuck state and allow the cleaning robot to enter the escape mode in time.
[0072] In the escape mode, the goal is to bypass the target point. The planning method is the same as the third path generation method in S303. On this basis, the backward search function of the hybrid A* algorithm is enabled to allow the cleaning robot to perform reverse operations, thereby effectively planning an escape trajectory. This escape mode not only improves the robot's adaptive ability to cope with complex environments, but also ensures the continuity and efficiency of the cleaning task.
[0073] S305. Path decision is made by calculating the cost function of each path, including:
[0074] By judging the stuck state, the cleaning robot is guided to start the escape mode first;
[0075] When there are no obstacles on the edge cleaning path, the edge cleaning path is adjusted by calculating the cost function of distance and angle;
[0076] When there is an obstacle on the edge cleaning path, the path of the cleaning vehicle is adjusted according to the distance between the obstacle and the cleaning vehicle.
[0077] See also Figure 3 , Figure 4 In the embodiment of the present invention, the real-time path is decided by the cost function, and the following processing methods are respectively used for the first path, the second path, and the third path:
[0078] 1. If the robot is judged to be in a stuck state, the trajectory planned in the stuck state judgment and escape mode phase will be used first to quickly restore the robot to its normal working state and guide the cleaning robot to travel along the first path;
[0079] 2. In the case of no obstacles in the current environment, the cost function of the left and right distances and angle deviations between each candidate trajectory and the edge reference line is calculated. The function is as follows: Figure 3 As shown, a path with the best edge-adhering effect is selected to improve the cleaning efficiency and accuracy, and the design of the cost function is the same as the cost function shown in step S301;
[0080] 3. When there are obstacles in the current environment, in addition to considering the left and right distance and angle deviation between the trajectory and the edge reference line, the trajectory length from the nearest collision point to the current position of the robot will also be evaluated. If this distance is less than 5 meters (the distance is calculated by adding twice the maximum turning radius to the length of the cleaning robot body), it is considered that the trajectory may cause the cleaning robot to get stuck or get stuck in a dead end, so a higher cost is assigned to avoid selecting this trajectory, such as Figure 4 As shown, the specific cost function is set as follows:
[0081]
[0082] in , , They are 0.3m, 5.0m, and 15.0m respectively, indicating the arc length of the collision point of the planned trajectory.
[0083] S400. Based on the real-time tracking result of the path decision, control the cleaning robot vehicle to enter an escape mode or a normal working mode.
[0084] The method provided by the present invention effectively predicts and reduces the occurrence of the cleaning machine getting stuck, thereby reducing the triggering frequency of the escape mode and reducing the wear on the robot drive system. After the cleaning robot completes the planning and decision-making of the edge cleaning trajectory, the resulting trajectory is transmitted to the control module and the execution module to achieve trajectory tracking, thereby ultimately achieving accurate edge cleaning and escape in a complex park environment.
[0085] See also Figure 5 The figure shows a simulation experiment of the method provided by the present invention through a cleaning robot in a simulation environment. The simulation scene includes multiple complex park scenes such as straight lines and large curvature curbs. In the figure, A is a cleaning robot, the orange box B represents the location information of the cleaning robot, the red path is the reference line along the curb, the blue is the cleaning path of the cleaning robot, that is, the path planning result, the yellow area D is the real-time search range of the cleaning robot, and the C area is the obstacle range.
[0086] Figure 6 The method provided by the present invention is shown in which a cleaning robot is used to simulate a test of a route along the edge in an environment with a map radius of 5m. The test results of the scene data set are as follows:
[0087] Table 1: Experimental results of hybrid A* edge-fitting in a map with a radius of 5m
[0088] Number of scenes Average edge distance difference Average edge angle difference Planning success rate 10798 0.0514m 1.375° 99.69%
[0089] See also Figure 7 , showing that the present invention also compares the smoothed edge-adhering trajectory based on differential flatness with the edge-adhering effect of the original trajectory. The trajectory smoother based on differential flatness constructs a safe driving corridor as shown in the rectangle in the figure by taking the trajectory planned by the hybrid A* as the initial trajectory.
[0090] Table 2: Comparison of the effects before and after differential flattening in the data set with a map radius of 5m
[0091] Number of scenes Average edge distance difference Average edge angle difference before smoothing 751 0.0391m 1.031° After smoothing 751 0.0967m 4.675°
[0092] It can be seen from Table 2 that after the differential flat smoother is connected, the edge-adhering effect decreases. However, near some large curvature curbs, the trajectory is smoother after the smoother is connected, which is more conducive to the subsequent control module to track the trajectory and prevent the AEB from stopping due to control overshoot.
[0093] Figure 8 The present invention provides a path planning system 10 for a cleaning machine vehicle, which is used to be installed on a cleaning machine vehicle to clean complex park roads. The system can execute the precise edge-adhering and escape method for the cleaning machine vehicle described in any of the above embodiments, and the system includes:
[0094] The positioning module 100 obtains the position information of the cleaning robot through the vehicle-mounted automatic driving system;
[0095] A perception module 200, which is used to obtain image data from vehicle-mounted sensors and extract obstacle information and curb information;
[0096] The planning module 300 performs path planning for the cleaning task to be performed, generates a cleaning path close to the edge and a detour point path, and calculates the cost function of each real-time path for real-time decision making;
[0097] The control module 400 controls the state of the cleaning robot vehicle by tracking the decision result of the path planning module.
[0098] Fig. 9A schematic diagram of an electronic device 20 that can implement an embodiment of the present invention is shown, and the electronic device is intended to represent various forms of control devices. The components shown herein, their connections and relationships, and their functions are only examples and are not intended to limit the implementation of the present invention described and / or required herein.
[0099] like Fig. 9 As shown, the electronic device 20 includes at least one processor 21, and a memory connected to the at least one processor 21, such as a read-only memory (ROM) 22, a random access memory (RAM) 23, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 22 or the computer program loaded from the storage unit 28 to the random access memory (RAM) 13. In the RAM 23, various programs and data required for the operation of the electronic device 20 can also be stored. The processor 21, ROM 22 and RAM 23 are connected to each other through a bus 24. An input / output (I / O) interface 25 is also connected to the bus 24.
[0100] A number of components in the electronic device 20 are connected to the I / O interface 25, including: an input unit 26, such as a keyboard, a mouse, etc.; an output unit 27, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 29, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 29 allows the electronic device 20 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.
[0101] The processor 21 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 21 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 21 executes the various methods and processes described above, such as the precise edge-adherence and escape method of the sweeping robot vehicle.
[0102] In some embodiments, the method for accurately following the edge and getting out of trouble for a cleaning robot vehicle can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 28. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 20 via the ROM 22 and / or the communication unit 29. When the computer program is loaded into the RAM 23 and executed by the processor 21, one or more steps in the wall line detection method described above can be executed. Alternatively, in other embodiments, the processor 21 can be configured to execute the method for accurately following the edge and getting out of trouble for a cleaning robot vehicle in any other appropriate manner (for example, by means of firmware).
[0103] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
[0104] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.
[0105] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0106] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and
[0107] Input from the user may be received in any form, including acoustic input, voice input, or tactile input.
[0108] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.
[0109] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.
[0110] An embodiment of the present invention also provides a cleaning robot vehicle, which includes the electronic device described in the embodiment of the present invention. The cleaning robot vehicle can execute the cleaning robot vehicle precise edge adhesion and escape method provided by any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.
[0111] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.
[0112] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.
Claims
1. A method for cleaning machine vehicle edge-adhering, characterized in that: include: Get the location information of the cleaning machine; Obtain environmental information around the cleaning machine, and obtain curb information and obstacle information from the environmental information; Based on the acquired position information and environmental information, a cleaning path and a detour path of the cleaning robot are planned, including: generating a first path along a reference line of the cleaning robot by a hybrid A* algorithm; The first path is used as the initial trajectory input and passed into the trajectory smoother based on differential flattening technology to generate the second path; the third path that can safely reach the detour target point is generated in real time through the hybrid A* algorithm, the speed of the sweeping robot is used to determine whether it is in a stuck state, and the path decision is made by calculating the cost function of each path; Based on the real-time tracking result of the path decision, the cleaning robot vehicle is controlled to enter an escape mode or a normal working mode.
2. A method for cleaning machine vehicle edge following according to claim 1, characterized in that: The path length of the first path is 3-5 meters, and the distance between the end point of the first path and the edge reference line is within 10 cm, and the angle deviation is within plus or minus 5 degrees.
3. A method for cleaning machine vehicle edge following according to claim 2, characterized in that: The planning process of the detour path includes: Obtain obstacle information and mark it as a target point; Taking the target point as the goal, the path to the target point is generated by the hybrid A* algorithm.
4. A method for cleaning machine vehicle edge following according to claim 3, characterized in that: The method of judging whether the cleaning machine is in a stuck state by the driving speed of the cleaning machine includes: Determine whether the first path, the second path, and the third path collide; If the traveling speed of the cleaning robot vehicle is 0 within 2 seconds after the collision, the cleaning robot vehicle is in a stuck state.
5. A method for cleaning machine vehicle edge following according to claim 4, characterized in that: The escape mode means that the cleaning robot takes the target point as the goal and guides the cleaning robot to reverse through the backward search function of the hybrid A* algorithm.
6. A method for cleaning machine vehicle edge following according to claim 5, characterized in that: The path decision is made by calculating the cost function of each path, including: By judging the stuck state, the cleaning robot is guided to start the escape mode first; When there are no obstacles on the edge cleaning path, the edge cleaning path is adjusted by calculating the cost function of distance and angle; When there is an obstacle on the edge cleaning path, the path of the cleaning vehicle is adjusted according to the distance between the obstacle and the cleaning vehicle.
7. A cleaning machine vehicle edge system, characterized in that: include: The positioning module obtains the location information of the cleaning robot through the on-board automatic driving system; A perception module, which is used to obtain image data from vehicle-mounted sensors and extract obstacle information and curb information; A planning module, the planning module is used to plan the cleaning path of the cleaning machine vehicle along the edge and the detour point path based on the location information and environmental information obtained by the perception module, including: generating a first path along the reference line along the edge through a hybrid A* algorithm; using the first path as an initial trajectory input and passing it into a trajectory smoother based on differential flattening technology to generate a second path; generating a third path that can safely reach the detour target point in real time through a hybrid A* algorithm, judging whether the cleaning machine vehicle is in a stuck state through the driving speed, and making a path decision by calculating the cost function of each path; The control module controls the state of the cleaning robot vehicle by tracking the decision results of the planning module.
8. An electronic device, characterized in that: The invention comprises at least one processor, wherein the processor is communicatively connected to at least one memory, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method according to any one of claims 1 to 6.
9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement a cleaning machine vehicle edge following method according to any one of claims 1 to 7 when executed.
10. A cleaning machine vehicle, characterized in that: The cleaning machine vehicle comprises the electronic device described in claim 8.
Citation Information
Cited By
Full-automatic obstacle-avoiding paying-off mobile equipment and using method thereof
CN121853449A
A full-automatic obstacle-avoiding wire laying mobile device and a method for using the same
CN121853449B
