Desktop mobile robot obstacle avoidance control method and system based on infrared debugging

Abstract

The invention discloses a desktop mobile robot obstacle avoidance control method and system based on infrared debugging, and relates to the technical field of robot obstacle avoidance control. A desktop camera obtains desktop image data and identifies static obstacles and dynamic obstacles on a desktop; the optimal cruise path is automatically selected by combining the identification information of the obstacle and the historical information of the cruise path, the dynamic obstacle information in the moving direction is obtained through an infrared sensor arranged on the mobile robot, and the dynamic obstacle information obtained by the infrared sensor is combined with the dynamic obstacle information obtained by a desktop camera. According to the method, the moving trend of a dynamic obstacle is analyzed, the moving speed of the mobile robot is analyzed and dynamically adjusted based on an analysis result, a control system is dynamically optimized on the basis of static planning, path selection is enabled to be global and real-time, and the moving speed of the robot is adjusted in real time based on motion trend prediction of the dynamic obstacle. And the operation efficiency and the safety are considered while obstacle avoidance is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of robot obstacle avoidance control, and in particular to an infrared debugging-based desktop mobile robot obstacle avoidance control method and system. Background Art

[0002] In a desktop environment, due to limited space and the presence of multiple static and dynamic obstacles, how to achieve efficient obstacle avoidance has become an important research direction. Desktop mobile robots are usually small in size and flexible in movement, and are suitable for performing tasks in a small space, such as teaching experiments, material transportation or smart entertainment.

[0003] There are many types of obstacles in the desktop environment, which may include static obstacles (such as cups, books) and dynamic obstacles (such as hand interference, other mobile devices). The robot must be able to quickly and accurately identify obstacles and plan paths to avoid collisions, ensure the safety of the system and the effective completion of the task.

[0004] The prior art has the following defects:

[0005] 1. Most path planning algorithms rely on a single preset path or local environment information based on the robot's sensors for planning, and cannot fully grasp the global environment. When the environment changes (such as the appearance of dynamic obstacles or the adjustment of the target position), the robot's path is difficult to adjust in time, which may lead to invalid paths or reduced efficiency;

[0006] 2. For the obstacle avoidance process of dynamic obstacles, the existing technology mainly responds by simply slowing down or stopping, lacks a more intelligent speed adjustment mechanism, and does not fully consider the movement trend of the obstacles, which can easily cause the robot to slow down excessively or start and stop frequently, making it difficult to achieve the optimal balance in moving speed. Overly conservative strategies will significantly reduce the efficiency of the robot, while overly aggressive strategies may increase the risk of collision.

[0007] Based on this, the present invention proposes a desktop mobile robot obstacle avoidance control method and system based on infrared debugging, which performs dynamic optimization on the basis of static planning, so that the path selection is both global and real-time, and adjusts the robot's movement speed in real time based on the motion trend prediction of dynamic obstacles to ensure both operational efficiency and safety while avoiding obstacles. Summary of the invention

[0008] The purpose of the present invention is to provide an obstacle avoidance control method and system for a desktop mobile robot based on infrared debugging, so as to solve the shortcomings in the background technology.

[0009] In order to achieve the above object, the present invention provides the following technical solution: a desktop mobile robot obstacle avoidance control method based on infrared debugging, the control method comprising the following steps:

[0010] The control system obtains the current task information of the mobile robot, and obtains multiple cruise paths matching the current task information based on the database, obtains desktop image data through the desktop camera, and after processing the desktop image data, identifies static obstacles and dynamic obstacles on the desktop;

[0011] The optimal cruising path is automatically selected by combining the recognition information of obstacles and the historical information of the cruising path, and the mobile robot is controlled to move along the optimal cruising path;

[0012] During the movement process, the control system obtains dynamic obstacle information in the moving direction through the infrared sensor configured by the mobile robot, and combines the dynamic obstacle information obtained by the infrared sensor with the dynamic obstacle information obtained by the desktop camera to analyze the movement trend of the dynamic obstacles, and dynamically adjusts the moving speed of the mobile robot based on the analysis results.

[0013] In a preferred embodiment, the optimal cruise path is automatically selected by combining the identification information of the obstacle and the historical information of the cruise path, including the following steps:

[0014] The optimal coefficient of the cruise path is obtained by comprehensively calculating the path performance index, the number of static obstacles in the occupied path, the static obstacles in the occupied path, the number of dynamic obstacles in the occupied path, and the moving speed of dynamic obstacles. The expression is:

[0015] , where is the optimization coefficient, Static obstacles in the occupied path can be assigned values, is the moving speed of the dynamic obstacle, is the path performance index, is the number of static obstacles in the occupied path, is the number of dynamic obstacles in the occupied path, , , is the adjustment coefficient, and , , All are greater than 0;

[0016] The cruising path with the largest optimization coefficient is selected as the optimal cruising path for the mobile robot to perform the current task, and the mobile robot is controlled to move along the optimal cruising path.

[0017] In a preferred embodiment, the dynamic obstacle information obtained by the infrared sensor is combined with the dynamic obstacle information obtained by the desktop camera to analyze the movement trend of the dynamic obstacle, including the following steps:

[0018] The amplitude error is calculated based on the first dynamic obstacle impact amplitude and the second dynamic obstacle impact amplitude. The expression is: , where is the amplitude error, is the impact amplitude of the first dynamic obstacle, is the second dynamic obstacle impact amplitude. If the amplitude error is less than or equal to the error threshold, it is determined that the dynamic obstacle data obtained by the infrared sensor can be used. If the amplitude error is greater than the error threshold, it is determined that the dynamic obstacle data obtained by the infrared sensor cannot be used.

[0019] When it is determined that the dynamic obstacle data acquired by the infrared sensor is usable, the first dynamic obstacle impact amplitude is used; when it is determined that the dynamic obstacle data acquired by the infrared sensor is not usable, the second dynamic obstacle impact amplitude is used;

[0020] The first dynamic obstacle influence amplitude or the second dynamic obstacle influence amplitude adopted is compared with the influence threshold. If the first dynamic obstacle influence amplitude is greater than or equal to the influence threshold or the second dynamic obstacle influence amplitude is greater than or equal to the influence threshold, it is analyzed that the dynamic obstacle moves in the direction of the cruise path and the moving speed is fast. If the first dynamic obstacle influence amplitude is less than the influence threshold or the second dynamic obstacle influence amplitude is less than the influence threshold, it is analyzed that the dynamic obstacle moves in the opposite direction of the cruise path.

[0021] In a preferred embodiment, dynamically adjusting the moving speed of the mobile robot based on the analysis result comprises the following steps:

[0022] When analyzing that the dynamic obstacle moves toward the cruising path and moves at a fast speed, the moving speed of the mobile robot needs to be dynamically adjusted. The expression is:

[0023] , where is the moving speed after dynamic adjustment. is the moving speed before dynamic adjustment, To account for the impact amplitude of dynamic obstacles, the control system controls the movement of the mobile robot according to the dynamically adjusted moving speed.

[0024] In a preferred embodiment, the logic for obtaining the first dynamic obstacle influence amplitude is as follows: obtaining dynamic obstacle data obtained by the infrared sensor, including a first dynamic obstacle moving direction value, a first dynamic obstacle moving speed, and a first dynamic obstacle volume, normalizing the first dynamic obstacle moving speed and the first dynamic obstacle volume, and summing them to obtain a first dynamic obstacle influence factor, and obtaining the first dynamic obstacle influence amplitude by multiplying the first dynamic obstacle moving direction value by the first dynamic obstacle influence factor;

[0025] The logic for obtaining the second dynamic obstacle influence amplitude is as follows: obtaining the dynamic obstacle data obtained by the desktop camera, including the second dynamic obstacle moving direction assignment, the second dynamic obstacle moving speed and the second dynamic obstacle volume, normalizing the second dynamic obstacle moving speed and the second dynamic obstacle volume, and then summing them to obtain the second dynamic obstacle influence factor, and multiplying the second dynamic obstacle influence factor by the second dynamic obstacle moving direction assignment to obtain the second dynamic obstacle influence amplitude.

[0026] In a preferred embodiment, the logic for obtaining the value of the first dynamic obstacle moving direction is: after detecting the position of the dynamic object at multiple times by an infrared sensor, the moving direction of the first dynamic obstacle is analyzed; if the dynamic obstacle moves in the direction of the cruising path, it indicates that the dynamic obstacle will enter the cruising path and will affect the movement of the mobile robot, and the first dynamic obstacle moving direction is assigned a value of 1; if the dynamic obstacle moves in the opposite direction of the cruising path, it indicates that the dynamic obstacle is away from the cruising path and will not affect the movement of the mobile robot, and the first dynamic obstacle moving direction is assigned a value of 0.

[0027] In a preferred embodiment, the static obstacle on the occupied path can be obtained by assigning a value as follows: obtain the maximum diameter of the mobile robot, obtain the travel distance of the static obstacle on the occupied path, if the maximum diameter of the mobile robot is less than or equal to the travel distance, it indicates that the mobile robot can bypass the static obstacle on the occupied path, and the static obstacle on the occupied path can be assigned a value equal to 1; if the maximum diameter of the mobile robot is greater than the travel distance, it indicates that the mobile robot cannot bypass the static obstacle on the occupied path, and the static obstacle on the occupied path can be assigned a value equal to 0.

[0028] In a preferred embodiment, the calculation logic of the path performance index is: obtain historical data of the cruise path, the historical data including the passing time and the passing success rate, normalize the passing success rate and the passing time, map the value range of the passing success rate and the passing time to between [0,1], obtain the normalized value of the passing success rate and the normalized value of the passing time, and subtract the normalized value of the passing time from the normalized value of the passing success rate to obtain the path performance index.

[0029] In a preferred embodiment, desktop image data is obtained through a desktop camera, and after the desktop image data is processed, static obstacles and dynamic obstacles on the desktop are identified, including the following steps:

[0030] The control system calls the desktop camera to obtain continuous image data, uses a filtering algorithm to remove noise in the image, and highlights the edge features of obstacles by adjusting the contrast and brightness or performing edge enhancement, converting the image from the RGB color space to the HSV color space;

[0031] Use object detection algorithms to identify static objects, use image segmentation technology to extract static obstacle areas, and use shape features to match with a known static obstacle library to confirm the type and location of the obstacle;

[0032] Use the inter-frame difference method or optical flow method to detect moving objects on the desktop, analyze continuous video frames, extract dynamically changing areas, which correspond to dynamic obstacles, and use the target tracking algorithm to continuously track the position, speed and trajectory of dynamic objects;

[0033] All identified obstacle information is stored in the obstacle map, including the location, type, size, and motion trajectory of the obstacle. The status and location of the obstacle are updated in real time, and the obstacle identification results are fed back to the mobile robot.

[0034] A desktop mobile robot obstacle avoidance control system based on infrared debugging, including a cruise path acquisition module, an optimal path selection module, and a dynamic control module;

[0035] Cruise path acquisition module: obtains the current task information of the mobile robot, and obtains multiple cruise paths matching the current task information based on the database;

[0036] Optimal path selection module: obtains desktop image data through the desktop camera, processes the desktop image data, identifies static and dynamic obstacles on the desktop, and automatically selects the optimal cruise path based on the obstacle identification information and the historical information of the cruise path;

[0037] Dynamic control module: controls the mobile robot to move along the optimal cruising path. During the movement, the infrared sensor configured on the mobile robot obtains the dynamic obstacle information in the moving direction, and combines the dynamic obstacle information obtained by the infrared sensor with the dynamic obstacle information obtained by the desktop camera to analyze the movement trend of the dynamic obstacles. Based on the analysis results, the moving speed of the mobile robot is dynamically adjusted.

[0038] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0039] The present invention obtains desktop image data through a desktop camera, processes the desktop image data, identifies static obstacles and dynamic obstacles on the desktop, automatically selects the optimal cruise path by combining the identification information of the obstacles and the historical information of the cruise path, obtains dynamic obstacle information in the moving direction through the infrared sensor configured by the mobile robot, combines the dynamic obstacle information obtained by the infrared sensor with the dynamic obstacle information obtained by the desktop camera, analyzes the movement trend of the dynamic obstacles, and dynamically adjusts the movement speed of the mobile robot based on the analysis results. The control system performs dynamic optimization on the basis of static planning, so that the path selection is both global and real-time, and adjusts the movement speed of the robot in real time based on the prediction of the movement trend of the dynamic obstacles, ensuring that both operation efficiency and safety are taken into account while avoiding obstacles. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0041] Figure 1 The present invention is a flow chart of the method. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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] Example 1: Please refer to Figure 1 As shown, the obstacle avoidance control method of a desktop mobile robot based on infrared debugging described in this embodiment includes the following steps:

[0044] The control system obtains the current task information of the mobile robot, and obtains multiple cruise paths matching the current task information based on the database, obtains desktop image data through the desktop camera, identifies static obstacles and dynamic obstacles on the desktop after processing the desktop image data, automatically selects the optimal cruise path based on the obstacle identification information and the historical information of the cruise path, and controls the mobile robot to move along the optimal cruise path. During the movement, the control system obtains dynamic obstacle information in the moving direction through the infrared sensor configured by the mobile robot, and combines the dynamic obstacle information obtained by the infrared sensor with the dynamic obstacle information obtained by the desktop camera, analyzes the movement trend of the dynamic obstacles, and dynamically adjusts the movement speed of the mobile robot based on the analysis results.

[0045] This application obtains desktop image data through a desktop camera, processes the desktop image data, identifies static and dynamic obstacles on the desktop, combines the obstacle identification information and the historical information of the cruise path to automatically select the optimal cruise path, obtains dynamic obstacle information in the moving direction through the infrared sensor configured by the mobile robot, and combines the dynamic obstacle information obtained by the infrared sensor with the dynamic obstacle information obtained by the desktop camera to analyze the movement trend of the dynamic obstacles, and dynamically adjusts the movement speed of the mobile robot based on the analysis results. The control system performs dynamic optimization on the basis of static planning, so that the path selection is both global and real-time. Based on the prediction of the movement trend of dynamic obstacles, the robot's movement speed is adjusted in real time to ensure that both operation efficiency and safety are taken into account while avoiding obstacles.

[0046] Embodiment 2: The control system obtains the current task information of the mobile robot, and obtains multiple cruise paths matching the current task information based on the database, including the following steps:

[0047] The control system receives task request information (such as task type, target location, priority, etc.) from users or other systems.

[0048] The control system parses the task information and extracts key parameters (such as target location, task nature, expected completion time, etc.) Based on the task requirements, it determines whether a specific path planning strategy is needed, such as whether obstacle avoidance is required in a desktop environment, whether the path needs to prioritize the shortest distance or the least obstacles, etc.

[0049] The control system retrieves the historical cruise paths in the database based on the mission information. The control system accesses the database and retrieves the historical cruise paths that match the mission based on the current mission information (such as target location, mission type). Based on the data in the database, multiple possible cruise paths are screened out.

[0050] Example 1: The task type is a desktop cleaning task

[0051] Mission information analysis:

[0052] Target location: The specified area in the upper right corner of the desktop.

[0053] Nature of task: Clean dust or debris on the desktop.

[0054] Expected completion time: Complete the cleanup task within 15 minutes.

[0055] Path planning strategy judgment:

[0056] Obstacle avoidance requirement: The robot needs to avoid static obstacles on the desktop (such as books, pen holders, etc.).

[0057] Path requirements: shortest distance path, avoiding static obstacles.

[0058] Database search and path selection:

[0059] Preset Path 1: Starting from the robot's starting point, it passes the left side of the desktop, avoids known obstacles (such as large books and pen holders), and reaches the upper right corner cleaning area. This path is suitable for situations where there are few obstacles on the desktop. It is direct and efficient.

[0060] Preset Path 2: If there are many obstacles on the desktop, Path 2 will avoid densely populated areas (such as the center of the desktop) and bypass the path to ensure that the robot can reach the cleaning area smoothly.

[0061] Preset Path 3: If the desktop environment is complex and contains multiple dynamic obstacles (such as movement of human hands and other objects), select Path 3, which avoids areas with dense dynamic obstacles and ensures that the robot's cleaning area is not disturbed.

[0062] Select path: The control system selects a suitable path from the preset paths according to the task environment (such as desktop obstacle layout, dynamic obstacles, etc.). If there are few obstacles, path 1 is preferred; if there are many obstacles and more dynamic obstacles, path 2 or path 3 is selected.

[0063] Example 2: The task type is an item transport task

[0064] Mission information analysis:

[0065] Target location: Move the item from the lower left corner of the desktop to the upper right corner.

[0066] Task nature: Carrying objects, requiring the robot to avoid collisions and keep the objects stable.

[0067] Expected completion time: The transport should be completed within 10 minutes.

[0068] Path planning strategy judgment:

[0069] Obstacle avoidance requirements: Static obstacles on the desktop (such as other objects) must be avoided, and ensure that no collisions occur during transportation.

[0070] Path requirements: Choose a relatively stable path, avoid sharp turns and high obstacle areas, and ensure that items do not fall.

[0071] Database search and path selection:

[0072] Preset Path 1: A straight path directly from the starting point to the target area without obstacles. Suitable for an empty desktop environment with no moving objects.

[0073] Preset Path 2: In order to avoid some large static objects on the desktop (such as coffee cups, folders, etc.), Path 2 takes a slight detour, but the path is longer and avoids passing through dangerous areas.

[0074] Preset Path 3: When there are many dynamic obstacles on the desktop (such as the movement of other objects), Path 3 avoids these areas and has a slower speed to ensure a stable handling process.

[0075] Select path: The control system selects the most appropriate path based on the real-time feedback of the desktop environment. If there are few obstacles on the desktop, select path 1; if there are many obstacles and dynamic objects need to be avoided, select path 3.

[0076] Example 3: Task type is desktop patrol task

[0077] Mission information analysis:

[0078] Target location: Not fixed, the robot needs to check multiple points on the table regularly.

[0079] Task nature: Regular patrols to check if any items on the desk are missing or changed.

[0080] Expected completion time: Complete the patrol mission within 30 minutes.

[0081] Path planning strategy judgment:

[0082] Obstacle avoidance requirements: Static and dynamic obstacles on the desktop need to be avoided.

[0083] Path requirements: A combination of multiple paths is required for patrolling to ensure that the task can be completed efficiently.

[0084] Database search and path selection:

[0085] Preset Path 1: Applicable to situations where there are fewer obstacles on the desktop. The robot quickly patrols along Path 1 and traverses the main areas of the desktop.

[0086] Preset Path 2: When encountering dynamic obstacles (such as human hands or other robots), Path 2 will avoid these areas and go around the tabletop to ensure that the robot is not disturbed during the patrol process.

[0087] Preset Path 3: If the obstacles in the desktop area are more complex, Path 3 will take a longer path to ensure that the robot avoids areas that may block patrols and responds to dynamic obstacles.

[0088] Select path: The control system selects the appropriate path according to the specific requirements of the task (specific order of patrol paths, desktop environment, etc.). For example, if it is a fast patrol, the system selects path 1; if it needs to avoid dynamic obstacles, it selects path 2 or path 3.

[0089] Example 4: Mission type is emergency response mission

[0090] Mission information analysis:

[0091] Target location: An emergency occurs in the upper right corner of the desktop, requiring the robot to respond and arrive immediately.

[0092] Nature of mission: Emergency response mission, ensuring the robot arrives quickly and handles emergencies.

[0093] Expected completion time: Arrive at the target area within 5 minutes.

[0094] Path planning strategy judgment:

[0095] Obstacle avoidance requirements: In emergency situations, path planning needs to ensure that the target location is reached as quickly as possible, avoiding any static or dynamic obstacles.

[0096] Path requirements: reach the target as quickly as possible and avoid any interference from obstacles.

[0097] Database search and path selection:

[0098] Preset Path 1: The shortest path, which is suitable for situations where there are fewer obstacles on the desktop and can reach the target area quickly and directly.

[0099] Preset Path 2: If there are many obstacles on the desktop, Path 2 will take a moderate detour to ensure that these obstacles are avoided, but it will slightly increase the time.

[0100] Preset Path 3: If the desktop environment is more complex and there are multiple dynamic obstacles, Path 3 uses more complex detours to avoid all potential collision risks and ensure that the robot reaches the target area quickly.

[0101] Select path: The control system will give priority to the shortest path (path 1) according to the requirements of the emergency task and the complexity of the desktop environment. If obstacles are found to affect the passage, a detour path (path 2 or path 3) will be selected.

[0102] In these scenarios, all cruise paths are preset manually. This application only gives simple scenario examples. In complex scenario examples, the cruise paths include more (more than ten), which are usually set during the system design phase according to the characteristics of the desktop environment and task requirements. When the control system executes the task, based on real-time environmental feedback (such as the location of obstacles, changes in dynamic obstacles, etc.), it selects the most suitable path for the current task from these preset paths. According to the task type (such as cleaning, handling, patrolling, etc.) and environmental conditions (such as the distribution of obstacles, the presence of dynamic obstacles, etc.), the most suitable path is selected to perform the task.

[0103] The desktop image data is obtained through the desktop camera, and after processing the desktop image data, the static obstacles and dynamic obstacles on the desktop are identified, including the following steps:

[0104] The control system calls the desktop camera to obtain continuous image data (pictures or video frames).

[0105] The image data must have sufficient resolution and clarity for subsequent image processing and obstacle identification. Adjust the camera's angle, focal length, lighting and other parameters as needed to ensure good visualization of the desktop area.

[0106] Use filtering algorithms (such as Gaussian filtering and median filtering) to remove noise from the image, improve image quality, and prevent noise from affecting obstacle recognition. By adjusting contrast and brightness or performing edge enhancement (such as Canny edge detection), the edge features of obstacles can be highlighted to improve the accuracy of subsequent recognition. Convert images from RGB color space to other color spaces suitable for processing (such as grayscale or HSV color space) to reduce computational complexity.

[0107] Use object detection algorithms (such as contour-based detection and morphological operations) to identify static objects. These algorithms identify stationary objects on the desktop (such as books, coffee cups, pen holders, etc.) based on features such as shape, size, and edges. The algorithms belong to the prior art and will not be described in detail in this application.

[0108] Separate static objects from the background in the image and use image segmentation techniques (such as threshold segmentation, color or texture-based segmentation) to extract static obstacle areas. Use shape features (such as contours and areas) to match with a library of known static obstacles to further confirm the type and location of the obstacle.

[0109] Use the inter-frame difference method (identifying dynamic areas by comparing the differences between consecutive frame images) or the optical flow method (estimating the movement of objects in the image) to detect moving objects on the desktop. Analyze consecutive video frames and extract dynamically changing areas, which correspond to dynamic obstacles.

[0110] Track the identified dynamic obstacles and use target tracking algorithms (such as Kalman filtering, Meanshift, Camshift, or YOLO, SSD, etc. in deep learning) to continuously track the position, speed, and trajectory of dynamic objects. This technology belongs to the prior art and will not be described in detail in this application. Analyze the possible future movement path and speed of dynamic obstacles through their motion trajectory.

[0111] By comparing motion estimation with the background model, false alarms caused by non-obstacles such as lighting changes or camera jitter are eliminated. Determine whether dynamic obstacles affect the robot's path and conduct further analysis (such as speed, direction, etc.). If there are multiple dynamic obstacles on the desktop, use a multi-target tracking algorithm (such as SORT, DeepSORT, etc.) to track multiple moving targets simultaneously to ensure the identification and position update of all dynamic obstacles. Track dynamic obstacles, record their motion characteristics such as speed and direction, and predict their possible future movement paths.

[0112] All identified obstacle information (static and dynamic) is stored in the obstacle map, including the location, type, size, motion trajectory, etc. The status and location of obstacles are updated in real time to ensure that the robot can make dynamic obstacle avoidance decisions in a real-time environment.

[0113] The control system feeds back the obstacle recognition results to the mobile robot for path planning and obstacle avoidance decisions.

[0114] Through the above steps, the control system can use the desktop camera to obtain real-time image data, and accurately identify static and dynamic obstacles in the desktop environment through image processing, object detection, target tracking and other technologies. This information can provide important support for subsequent path planning and obstacle avoidance control, ensuring that the robot can intelligently adapt to changes in the desktop environment, avoid obstacles and complete tasks.

[0115] Combining the obstacle recognition information and the historical information of the cruise path to automatically select the optimal cruise path and control the mobile robot to move along the optimal cruise path, including the following steps:

[0116] Obtain historical data of the cruise path, including the passing time and the passing success rate, normalize the passing success rate and the passing time, map the value range of the passing success rate and the passing time to [0,1], obtain the normalized value of the passing success rate and the normalized value of the passing time, and subtract the normalized value of the passing time from the normalized value of the passing success rate to obtain the path performance index;

[0117] For a desktop mobile robot, static objects on the desktop may not have appeared in the history of the mobile robot (i.e., the static objects appeared recently), and the recently appeared static objects may occupy certain cruise paths. When occupying a cruise path, it is also necessary to analyze whether the mobile robot can bypass the static objects occupying the cruise path (if it cannot bypass, it means that the mobile robot cannot pass through the cruise path). Therefore, we have the following solutions:

[0118] Get the number of static obstacles occupying the path on each cruise path. The more static obstacles occupying the path, the more detours the mobile robot makes when moving on the cruise path. The static obstacles occupying the path can be obtained by assigning values, and the number of dynamic obstacles occupying the path on the cruise path and the moving speed of the dynamic obstacles can be obtained. Since dynamic obstacles are in a mobile state, they may or may not appear on the cruise path. Therefore, as long as the dynamic obstacles appear on the cruise path at least once, we will record them, indicating that the dynamic obstacles have an impact on the passage of the mobile robot. The faster the dynamic obstacle moves, the greater the uncertainty on the cruise path.

[0119] The optimal coefficient of the cruise path is obtained by comprehensively calculating the path performance index, the number of static obstacles in the occupied path, the static obstacles in the occupied path, the number of dynamic obstacles in the occupied path, and the moving speed of dynamic obstacles. The expression is:

[0120] , where is the optimization coefficient, Static obstacles in the occupied path can be assigned values, is the moving speed of the dynamic obstacle, is the path performance index, is the number of static obstacles in the occupied path, is the number of dynamic obstacles in the occupied path, , , is the adjustment coefficient, and , , All are greater than 0;

[0121] The larger the preferred coefficient of the cruise path, the more conducive the cruise path is to traffic as a whole. The cruise path with the largest preferred coefficient is selected as the optimal cruise path for the mobile robot to perform the current task, and the mobile robot is controlled to move along the optimal cruise path.

[0122] The acquisition logic of the static obstacle on the occupied path through assignment is as follows: obtain the maximum diameter of the mobile robot (the mobile robot usually has a mobile chassis and an operating upper body. After obtaining the diameter of the operating upper body and the diameter of the mobile chassis, select the larger value as the maximum diameter), obtain the travel distance of the static obstacle on the occupied path (obtain the distance between the static obstacle on the occupied path and the obstacles on both sides, and select the larger value as the travel distance). If the maximum diameter of the mobile robot is less than or equal to the travel distance, it indicates that the mobile robot can bypass the static obstacle on the occupied path, and the static obstacle on the occupied path can be assigned a value equal to 1. If the maximum diameter of the mobile robot is greater than the travel distance, it indicates that the mobile robot cannot bypass the static obstacle on the occupied path, and the static obstacle on the occupied path can be assigned a value equal to 0.

[0123] During the movement, the control system obtains dynamic obstacle information in the moving direction through the infrared sensor configured by the mobile robot, including the following steps:

[0124] Reflective infrared sensors (such as most simple infrared distance sensors) usually use sector scanning. The infrared sensor emits an infrared beam, which is reflected back within a certain angle range (such as 30°, 45°, 60° or more). The sensor calculates the distance and position of the obstacle based on the intensity or time difference of the reflected light.

[0125] Sector scanning is usually used to cover a wider area in front of the robot, providing a larger detection range. The angle range of the sector can be adjusted according to the design of the sensor to meet the needs of different application scenarios. Sector scanning is usually suitable for simple obstacle avoidance tasks, such as the detection of obstacles in front, and can effectively avoid static and dynamic obstacles.

[0126] Before the robot moves, the control system initializes the configured infrared sensors (such as the front infrared sensor, side infrared sensor, etc.) and starts to continuously collect infrared data. The infrared sensor detects the distance and position of the obstacle in front by emitting infrared beams and receiving reflected light. The system performs data calibration to ensure that the output data of the infrared sensor is accurate and avoids environmental interference (such as light reflection, temperature change, etc.).

[0127] Infrared sensors measure the distance to obstacles by calculating the time difference between the emitted light and the reflected light. Typical sensors such as reflective infrared sensors provide a distance value representing the distance from the sensor to the obstacle. If the obstacle is too close to the sensor or exceeds the effective measurement range, the sensor output will give a corresponding warning or error signal.

[0128] The control system processes the distance data fed back by the infrared sensor and converts it into actual obstacle information. For example, a shorter distance value indicates the presence of an obstacle, while a larger value indicates that the path is unobstructed. Based on the installation position and angle of the sensor, combined with the distance information, the relative position of the obstacle is calculated. If the robot is equipped with multiple infrared sensors, the spatial distribution of obstacles can be obtained in multiple dimensions.

[0129] The control system collects infrared data continuously to analyze whether the obstacle is moving. If the distance of the obstacle detected by the sensor changes over time, it means that it is a dynamic obstacle (such as a person, other robots, moving objects, etc.). By comparing the continuous measurement data, the control system can detect the movement trend of the obstacle (such as speed, direction, acceleration, etc.). For example, if the obstacle gradually approaches the robot in several consecutive frames, it means that the obstacle is in an approaching state, and the robot needs to make corresponding obstacle avoidance actions.

[0130] The dynamic obstacle information obtained by the infrared sensor is combined with the dynamic obstacle information obtained by the desktop camera to analyze the movement trend of the dynamic obstacles, including the following steps:

[0131] The dynamic obstacle data acquired by the infrared sensor includes a first dynamic obstacle moving direction value, a first dynamic obstacle moving speed, and a first dynamic obstacle volume, normalizes the first dynamic obstacle moving speed and the first dynamic obstacle volume, and then sums them to obtain a first dynamic obstacle influence factor, and obtains a first dynamic obstacle influence amplitude by multiplying the first dynamic obstacle moving direction value by the first dynamic obstacle influence factor;

[0132] The dynamic obstacle data acquired by the desktop camera is obtained, including the second dynamic obstacle moving direction value, the second dynamic obstacle moving speed and the second dynamic obstacle volume. The second dynamic obstacle moving speed and the second dynamic obstacle volume are normalized and then summed to obtain the second dynamic obstacle influence factor. The second dynamic obstacle influence amplitude is obtained by multiplying the second dynamic obstacle influence factor by the second dynamic obstacle moving direction value.

[0133] The amplitude error is calculated based on the first dynamic obstacle impact amplitude and the second dynamic obstacle impact amplitude. The expression is: , where is the amplitude error, is the impact amplitude of the first dynamic obstacle, is the second dynamic obstacle impact amplitude. If the amplitude error is less than or equal to the error threshold, it is determined that the dynamic obstacle data obtained by the infrared sensor can be used. If the amplitude error is greater than the error threshold, it is determined that the dynamic obstacle data obtained by the infrared sensor cannot be used.

[0134] When it is determined that the dynamic obstacle data acquired by the infrared sensor is usable, the first dynamic obstacle impact amplitude is used; when it is determined that the dynamic obstacle data acquired by the infrared sensor is not usable, the second dynamic obstacle impact amplitude is used;

[0135] The first dynamic obstacle influence amplitude or the second dynamic obstacle influence amplitude adopted is compared with the influence threshold. If the first dynamic obstacle influence amplitude is greater than or equal to the influence threshold or the second dynamic obstacle influence amplitude is greater than or equal to the influence threshold, it is analyzed that the dynamic obstacle moves in the direction of the cruise path and the moving speed is fast (that is, it has a large impact on the cruise path). If the first dynamic obstacle influence amplitude is less than the influence threshold or the second dynamic obstacle influence amplitude is less than the influence threshold, it is analyzed that the dynamic obstacle moves in the opposite direction of the cruise path.

[0136] In actual applications, the infrared sensor data collected by the mobile robot may have large errors due to the influence of the surrounding environment or the health status of the sensor itself. In this application, the dynamic obstacle data collected by the infrared sensor of the mobile robot is compared with the dynamic obstacle data obtained by the desktop camera (there are more than two desktop cameras), so as to avoid infrared sensor data errors that cause the mobile robot to collide with dynamic obstacles;

[0137] In the present application, the logic for obtaining the value of the first dynamic obstacle moving direction is: after detecting the position of the dynamic object at multiple times by an infrared sensor, the first dynamic obstacle moving direction is analyzed. If the dynamic obstacle moves toward the cruising path, it indicates that the dynamic obstacle will enter the cruising path and will affect the movement of the mobile robot. The first dynamic obstacle moving direction is assigned a value of 1. If the dynamic obstacle moves in the opposite direction of the cruising path, it indicates that the dynamic obstacle is away from the cruising path and will not affect the movement of the mobile robot. The first dynamic obstacle moving direction is assigned a value of 0. The logic for obtaining the value of the second dynamic obstacle moving direction is the same as that of the first dynamic obstacle moving direction, and will not be repeated in this application.

[0138] Dynamically adjusting the moving speed of the mobile robot based on the analysis results includes the following steps:

[0139] When analyzing that the dynamic obstacle moves toward the cruising path and moves at a fast speed, the moving speed of the mobile robot needs to be dynamically adjusted. The expression is:

[0140] , where is the moving speed after dynamic adjustment. is the moving speed before dynamic adjustment, is the dynamic obstacle impact amplitude (either the first dynamic obstacle impact amplitude or the second dynamic obstacle impact amplitude, depending on the adopted option);

[0141] The control system controls the movement of the mobile robot according to the dynamically adjusted moving speed.

[0142] Embodiment 3: The desktop mobile robot obstacle avoidance control system based on infrared debugging described in this embodiment includes a cruise path acquisition module, an optimal path selection module, and a dynamic control module;

[0143] Cruise path acquisition module: obtains the current task information of the mobile robot, and obtains multiple cruise paths matching the current task information based on the database, and sends the matching cruise path information to the optimal path selection module;

[0144] Optimal path selection module: obtains desktop image data through the desktop camera, processes the desktop image data, identifies static obstacles and dynamic obstacles on the desktop, and automatically selects the optimal cruise path based on the obstacle identification information and the historical information of the cruise path. The optimal path is sent to the dynamic control module;

[0145] Dynamic control module: controls the mobile robot to move along the optimal cruising path. During the movement, the infrared sensor configured on the mobile robot obtains the dynamic obstacle information in the moving direction, and combines the dynamic obstacle information obtained by the infrared sensor with the dynamic obstacle information obtained by the desktop camera to analyze the movement trend of the dynamic obstacles. Based on the analysis results, the moving speed of the mobile robot is dynamically adjusted.

[0146] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0147] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0148] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A desktop mobile robot obstacle avoidance control method based on infrared debugging, characterized in that: The control method comprises the following steps: The control system obtains the current task information of the mobile robot, and obtains multiple cruise paths matching the current task information based on the database, obtains desktop image data through the desktop camera, and after processing the desktop image data, identifies static obstacles and dynamic obstacles on the desktop; The optimal cruising path is automatically selected by combining the recognition information of obstacles and the historical information of the cruising path, and the mobile robot is controlled to move along the optimal cruising path; During the movement, the control system obtains dynamic obstacle information in the moving direction through the infrared sensor configured by the mobile robot, and combines the dynamic obstacle information obtained by the infrared sensor with the dynamic obstacle information obtained by the desktop camera to analyze the movement trend of the dynamic obstacles, and dynamically adjusts the moving speed of the mobile robot based on the analysis results; Dynamically adjusting the moving speed of the mobile robot based on the analysis results includes the following steps: When analyzing that the dynamic obstacle moves toward the cruising path and moves at a fast speed, the moving speed of the mobile robot needs to be dynamically adjusted. The expression is: , where is the moving speed after dynamic adjustment. is the moving speed before dynamic adjustment, To account for the impact amplitude of dynamic obstacles, the control system controls the movement of the mobile robot according to the dynamically adjusted moving speed.

2. The obstacle avoidance control method for a desktop mobile robot based on infrared debugging according to claim 1 is characterized in that: Combining the obstacle identification information and the historical information of the cruise path to automatically select the optimal cruise path includes the following steps: The optimal coefficient of the cruise path is obtained by comprehensively calculating the path performance index, the number of static obstacles in the occupied path, the static obstacles in the occupied path, the number of dynamic obstacles in the occupied path, and the moving speed of dynamic obstacles. The expression is: , where is the optimization coefficient, Static obstacles in the occupied path can be assigned values, is the moving speed of the dynamic obstacle, is the path performance index, is the number of static obstacles in the occupied path, is the number of dynamic obstacles in the occupied path, , , is the adjustment coefficient, and , , All are greater than 0; The cruising path with the largest optimization coefficient is selected as the optimal cruising path for the mobile robot to perform the current task, and the mobile robot is controlled to move along the optimal cruising path.

3. The obstacle avoidance control method for a desktop mobile robot based on infrared debugging according to claim 2 is characterized in that: The dynamic obstacle information obtained by the infrared sensor is combined with the dynamic obstacle information obtained by the desktop camera to analyze the movement trend of the dynamic obstacles, including the following steps: The amplitude error is calculated based on the first dynamic obstacle impact amplitude and the second dynamic obstacle impact amplitude. The expression is: , where is the amplitude error, is the impact amplitude of the first dynamic obstacle, is the second dynamic obstacle impact amplitude. If the amplitude error is less than or equal to the error threshold, it is determined that the dynamic obstacle data obtained by the infrared sensor can be used. If the amplitude error is greater than the error threshold, it is determined that the dynamic obstacle data obtained by the infrared sensor cannot be used. When it is determined that the dynamic obstacle data acquired by the infrared sensor is usable, the first dynamic obstacle impact amplitude is used; when it is determined that the dynamic obstacle data acquired by the infrared sensor is not usable, the second dynamic obstacle impact amplitude is used; The first dynamic obstacle influence amplitude or the second dynamic obstacle influence amplitude adopted is compared with the influence threshold. If the first dynamic obstacle influence amplitude is greater than or equal to the influence threshold or the second dynamic obstacle influence amplitude is greater than or equal to the influence threshold, it is analyzed that the dynamic obstacle moves in the direction of the cruise path and the moving speed is fast. If the first dynamic obstacle influence amplitude is less than the influence threshold or the second dynamic obstacle influence amplitude is less than the influence threshold, it is analyzed that the dynamic obstacle moves in the opposite direction of the cruise path.

4. The obstacle avoidance control method for a desktop mobile robot based on infrared debugging according to claim 3 is characterized in that: The logic for obtaining the first dynamic obstacle influence amplitude is as follows: obtaining dynamic obstacle data obtained by the infrared sensor, including a first dynamic obstacle moving direction value, a first dynamic obstacle moving speed, and a first dynamic obstacle volume, normalizing the first dynamic obstacle moving speed and the first dynamic obstacle volume, and summing them to obtain a first dynamic obstacle influence factor, and multiplying the first dynamic obstacle influence factor by the first dynamic obstacle moving direction value to obtain the first dynamic obstacle influence amplitude; The logic for obtaining the second dynamic obstacle influence amplitude is as follows: obtaining the dynamic obstacle data obtained by the desktop camera, including the second dynamic obstacle moving direction assignment, the second dynamic obstacle moving speed and the second dynamic obstacle volume, normalizing the second dynamic obstacle moving speed and the second dynamic obstacle volume, and then summing them to obtain the second dynamic obstacle influence factor, and multiplying the second dynamic obstacle influence factor by the second dynamic obstacle moving direction assignment to obtain the second dynamic obstacle influence amplitude.

5. The obstacle avoidance control method for a desktop mobile robot based on infrared debugging according to claim 4 is characterized in that: The logic for obtaining the value of the first dynamic obstacle moving direction is: after detecting the position of the dynamic object at multiple times through the infrared sensor, the moving direction of the first dynamic obstacle is analyzed. If the dynamic obstacle moves in the direction of the cruising path, it indicates that the dynamic obstacle will enter the cruising path and will affect the movement of the mobile robot. The first dynamic obstacle moving direction is assigned a value of 1. If the dynamic obstacle moves in the opposite direction of the cruising path, it indicates that the dynamic obstacle is away from the cruising path and will not affect the movement of the mobile robot. The first dynamic obstacle moving direction is assigned a value of 0.

6. The obstacle avoidance control method for a desktop mobile robot based on infrared debugging according to claim 5 is characterized in that: The acquisition logic of the static obstacle on the occupied path can be as follows: obtain the maximum diameter of the mobile robot, obtain the travel distance of the static obstacle on the occupied path, if the maximum diameter of the mobile robot is less than or equal to the travel distance, it indicates that the mobile robot can bypass the static obstacle on the occupied path, and the static obstacle on the occupied path can be assigned a value equal to 1; if the maximum diameter of the mobile robot is greater than the travel distance, it indicates that the mobile robot cannot bypass the static obstacle on the occupied path, and the static obstacle on the occupied path can be assigned a value equal to 0.

7. The obstacle avoidance control method for a desktop mobile robot based on infrared debugging according to claim 6, characterized in that: The calculation logic of the path performance index is as follows: obtaining historical data of the cruise path, the historical data including the passing time and the passing success rate, normalizing the passing success rate and the passing time so that the value range of the passing success rate and the passing time is mapped to between [0,1], obtaining the normalized value of the passing success rate and the normalized value of the passing time, and subtracting the normalized value of the passing time from the normalized value of the passing success rate to obtain the path performance index.

8. The obstacle avoidance control method for a desktop mobile robot based on infrared debugging according to claim 7 is characterized in that: The desktop image data is obtained through the desktop camera, and after processing the desktop image data, the static obstacles and dynamic obstacles on the desktop are identified, including the following steps: The control system calls the desktop camera to obtain continuous image data, uses a filtering algorithm to remove noise in the image, and highlights the edge features of obstacles by adjusting the contrast and brightness or performing edge enhancement, converting the image from the RGB color space to the HSV color space; Use object detection algorithms to identify static objects, use image segmentation technology to extract static obstacle areas, and use shape features to match with a known static obstacle library to confirm the type and location of the obstacle; Use the inter-frame difference method or optical flow method to detect moving objects on the desktop, analyze continuous video frames, extract dynamically changing areas, which correspond to dynamic obstacles, and use the target tracking algorithm to continuously track the position, speed and trajectory of dynamic objects; All identified obstacle information is stored in the obstacle map, including the location, type, size, and motion trajectory of the obstacle. The status and location of the obstacle are updated in real time, and the obstacle identification results are fed back to the mobile robot.

9. A desktop mobile robot obstacle avoidance control system based on infrared debugging, used to implement the control method according to any one of claims 1 to 8, characterized in that: It includes cruise path acquisition module, optimal path selection module and dynamic control module; Cruise path acquisition module: obtains the current task information of the mobile robot, and obtains multiple cruise paths matching the current task information based on the database; Optimal path selection module: obtains desktop image data through the desktop camera, processes the desktop image data, identifies static and dynamic obstacles on the desktop, and automatically selects the optimal cruise path based on the obstacle identification information and the historical information of the cruise path; Dynamic control module: controls the mobile robot to move along the optimal cruising path. During the movement, the infrared sensor configured on the mobile robot obtains the dynamic obstacle information in the moving direction, and combines the dynamic obstacle information obtained by the infrared sensor with the dynamic obstacle information obtained by the desktop camera to analyze the movement trend of the dynamic obstacles. Based on the analysis results, the moving speed of the mobile robot is dynamically adjusted.

Images