A laser radar-based object delivery robot

By identifying and optimizing paths to bypass obstacles, the problem of item transport robot avoiding obstacles on the transport path is solved, and transportation efficiency and safety are improved.

CN118759534BActive Publication Date: 2024-11-22GANSU DONGYUN TECHNOLOGY DEVELOPMENT CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411253877.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-09
Publication Date
2024-11-22
Estimated Expiration
2044-09-09

AI Technical Summary

Technical Problem

It is difficult for existing item transport robots to achieve reasonable obstacle avoidance when there are obstacles on the transport path, which affects transportation efficiency.

Method used

The path obstacle avoidance analysis module based on lidar is adopted to divide the paths and identify obstacles through multiple segments, generate avoidance signals and select signals, optimize path selection to bypass or cross obstacles, and improve the efficiency of the transportation path.

Benefits of technology

Identify obstacles through lidar scanning and three-dimensional modeling, generate optimized paths, improve the overall transportation efficiency of item delivery robots and ensure safe passage.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118759534B_ABST
    Figure CN118759534B_ABST
Patent Text Reader

Abstract

The present invention discloses a laser radar-based article transport robot, comprising a transport information collection module, a path obstacle avoidance analysis module and a path generation output module. The present invention relates to the technical field of transport robots, and solves the technical problem that some robots fail to achieve reasonable obstacle avoidance when transporting articles, which further affects the overall transport efficiency. The present invention generates a path according to a transport starting point and a transport end point, analyzes the generated transport path, divides the transport path into multiple sections, and separately analyzes the segmented transport paths. All transport paths are comprehensively sorted out according to whether there are obstacles and whether the obstacles can be directly traversed, and finally a path suitable for robot transport is obtained. Subsequent transport is carried out according to the generated path, thereby improving the overall transport efficiency.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of transport robots, and in particular to an article transport robot based on laser radar. Background Art

[0002] The object delivery robot is an intelligent automatic guided vehicle, mainly used for automated handling and transportation of goods. As an important part of modern intelligent manufacturing and automated logistics, the object delivery robot is gradually changing the traditional material handling mode with its high efficiency, flexibility and safety. Object delivery robots are also used in modern funeral homes.

[0003] According to Chinese patent application number CN202310730352.1, an item delivery robot, an item delivery method and an apparatus are disclosed, the method comprising: in response to item delivery demand information, collecting user information of users who need item delivery services; scanning and identifying text information on a pickup call display screen of a pickup window, and / or collecting voice reminder information of the pickup call; when the text information and / or voice reminder information indicates that the user's pickup call information has been queued, the item delivery robot moves to the pickup window and docks with the distribution personnel to pick up items of the user who needs item delivery services; and delivers the picked-up items to the user according to the user's name, facial image, and item delivery destination.

[0004] When the robot is transporting items, it will generate and analyze the path. However, when the robot is transporting items, if there are obstacles on the transportation path, it will affect the robot's transportation. Therefore, it is necessary to plan and analyze the transportation path in advance to select a suitable transportation path. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention provides a laser radar-based article delivery robot, which solves the problem that some robots fail to reasonably avoid obstacles when transporting articles, which further affects the overall transportation efficiency.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: A laser radar-based object transport robot, comprising:

[0007] The path obstacle avoidance analysis module is used to obtain the transport information transmitted by the transport information acquisition module, generate a transport path according to the transport information, and divide the transport path into segments with equal distances, and then classify the segments into normal segments and abnormal segments according to whether there are obstacles, and transmit the abnormal segment information to the avoidance information analysis module;

[0008] The avoidance information analysis module is used to obtain the abnormal segment information, identify and classify the obstacles in the abnormal segment through three-dimensional modeling to obtain regular obstacles and irregular obstacles, and calculate the travel widths of regular obstacles and irregular obstacles respectively, and compare the travel widths to generate avoidance signals and selection signals. For the selection signal, the three-dimensional coordinate information is generated by analyzing the travel position, and the three-dimensional coordinate information is transmitted to the path generation output module, and the avoidance signal is transmitted to the path selection analysis module;

[0009] The path selection analysis module is used to analyze the obtained avoidance signal, divide the remaining transportation path into segments to be analyzed, and make obstacle avoidance judgments on the segments to be analyzed to generate secondary analysis signals and rejection signals. For the secondary analysis signal, the analysis signal and rejection signal are generated by analyzing the adjacent numbered segments to be analyzed. At the same time, for the analysis signal, the one with the shortest transportation time is selected as the standard to generate standard information, and the path information is integrated and generated, and then the path information is transmitted to the path generation output module.

[0010] As a further solution of the present invention: it also includes a transportation information collection module and a path generation output module;

[0011] The transportation information acquisition module is used to obtain the transportation information of the robot, and the transportation information includes the transportation starting point and the transportation end point, and transmit the transportation information to the path obstacle avoidance analysis module;

[0012] The path generation output module is used to transmit the acquired path information to the robot.

[0013] As a further solution of the present invention: the specific manner in which the path obstacle avoidance analysis module analyzes the generated transport path is:

[0014] All transport paths are obtained and labeled as i, where i=1, 2, ..., j, and j represents the number of transport paths, and j is a positive integer. Then any transport path is obtained as a target object for analysis, and the target object is segmented into multiple segments, which are labeled as a, where a=1, 2, ..., b, and b represents the number of segments, and b is a positive integer, and the lengths of the segments are the same;

[0015] Perform a laser radar scan on segment a in the order of the labels, and determine whether there is an obstacle in segment a. If there is an obstacle in segment a, the corresponding segment is classified as an abnormal segment a1. Otherwise, if there is no obstacle in the segment, the corresponding segment is classified as a normal segment a2. Both a1 and a2 represent the number of corresponding classified segments, and the normal segment a2 obtained by classification is not processed.

[0016] As a further solution of the present invention: the avoidance information analysis module classifies obstacles in the abnormal segment information in a specific manner as follows:

[0017] All abnormal segmentation segments a1 are obtained, and then the obstacles are scanned by laser radar and three-dimensional modeling is performed to obtain a three-dimensional model. At the same time, the three-dimensional model is judged, and a three-dimensional coordinate system is established based on the plane where the obstacle is located, and the origin of the three-dimensional coordinate system is the center point of the abnormal segmentation segment. Then all vertices of the three-dimensional model are represented by three-dimensional coordinates, and the shape of the obstacle is judged by the three-dimensional coordinates, and the obstacles are classified into regular obstacles and irregular obstacles.

[0018] As a further solution of the present invention: the specific method of analyzing regular obstacles is:

[0019] The object width of the regular obstacle is obtained, and at the same time, the path width corresponding to the abnormal segment a1 is obtained, and the robot width is obtained. Then, the difference between the path width and the robot width is calculated and recorded as the driving width, and the object width is compared with the driving width. When the object width is greater than the driving width, it means that the regular obstacle affects the robot transportation, and an avoidance signal is generated. Conversely, when the object width is less than the driving width, it means that the regular obstacle does not affect the robot transportation, and a selection signal is generated.

[0020] As a further solution of the present invention: the specific method of analyzing irregular obstacles is:

[0021] All vertex coordinates of the irregular obstacle are obtained, and then the horizontal coordinates of the vertex coordinates are compared, and the vertex with the largest horizontal coordinate is selected as the standard point. At the same time, the standard point is analyzed to obtain the object width of the irregular obstacle, and then the object width is compared with the driving width. When the object width is greater than the driving width, an avoidance signal is generated. Conversely, when the object width is less than the driving width, a selection signal is generated.

[0022] As a further solution of the present invention: the specific manner in which the avoidance information analysis module analyzes the selected signal is:

[0023] The driving width is obtained, and the driving width is evenly divided to obtain two groups of evenly divided widths, and the evenly divided points of the driving width are obtained, and the three-dimensional coordinates corresponding to the evenly divided points are obtained, and the three-dimensional coordinate information is generated at the same time.

[0024] As a further solution of the present invention: the specific manner in which the path selection analysis module analyzes the avoidance signal is:

[0025] The remaining transport path i-1 is obtained, and the remaining transport path here is represented by the remaining transport path after removing the target object, and the transport path is divided in the same way to obtain the segment to be analyzed. At the same time, the segment to be analyzed corresponding to the same label as the avoidance signal is obtained, and the obstacle avoidance judgment is performed on the segment to be analyzed. If the segment to be analyzed satisfies the obstacle avoidance, a secondary analysis signal is generated. Otherwise, if the segment to be analyzed does not meet the obstacle avoidance, a rejection signal is generated.

[0026] As a further solution of the present invention: the specific method of analyzing the secondary analysis signal is:

[0027] For the generated secondary analysis signal, the corresponding segment to be analyzed is selected and recorded as the selected segment. At the same time, the segment to be analyzed adjacent to the selected segment is obtained, and the label of the segment to be analyzed is greater than the selected segment. Then, the adjacent segment to be analyzed is judged for obstacle avoidance. If it meets the conditions, an analysis signal is generated, otherwise a rejection signal is generated.

[0028] As a further solution of the present invention: the specific method of analyzing the generated analysis signal is:

[0029] The length of the selected segment is obtained, and the transportation time of the selected segment is calculated according to the transportation speed of the robot. The transportation time of all the selected segments is calculated in this way, and the selected segment corresponding to the minimum transportation time is selected as the standard. At the same time, standard information is generated, and path information is generated with the standard information, and then the path information is transmitted to the path generation output module.

[0030] The present invention provides an article transport robot based on laser radar, which has the following beneficial effects compared with the prior art:

[0031] The present invention generates a path according to the transportation starting point and the transportation end point, analyzes the generated transportation path, divides the transportation path into multiple sections, and analyzes the divided transportation paths separately. All transportation paths are comprehensively sorted out according to whether there are obstacles and whether the obstacles can be directly crossed. Finally, a path suitable for robot transportation is obtained. Subsequent transportation is carried out according to the generated path to improve the overall transportation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 This is a block diagram of the system principle of the present invention.

[0033] Figure 2 This is a schematic diagram of irregular obstacle analysis according to the present invention.

[0034] Figure 3 This is a schematic diagram of the regular obstacle analysis of the present invention. DETAILED DESCRIPTION

[0035] 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.

[0036] For example, see Figure 1 and Figure 3 The present application provides a laser radar-based object transport robot, including: a transport information acquisition module, a path obstacle avoidance analysis module, a path selection analysis module, an avoidance information analysis module and a path generation output module.

[0037] The transportation information acquisition module is used to obtain the transportation information of the robot and transmit the obtained transportation information to the path obstacle avoidance analysis module, where the transportation information includes the transportation starting point, transportation end point and transportation items.

[0038] The path obstacle avoidance analysis module is used to generate the robot's transportation path according to the acquired transportation information, generate the transportation path according to the transportation starting point and transportation end point, and analyze and judge the transportation path. The specific analysis and judgment methods are as follows:

[0039] First, it is necessary to determine all the transport paths. When determining the transport paths, the transport paths are generated according to the locations of the transport starting point and the transport end point. To this end, each path is numbered and denoted as i, where the value of i is 1, 2, ..., j, where j represents the total number of transport paths, which is a positive integer. Next, any specific transport path is selected as the research object and analyzed in depth. In order to understand the characteristics of this path more carefully, it is divided into multiple segments, each segment is denoted as a, where the value of a is 1, 2, ..., b, where b represents the total number of segments, which is also a positive integer. It is worth noting that the length of each segment obtained here is the same;

[0040] For example, suppose there are three delivery routes, numbered 1, 2, and 3, and route 1 is selected as the research object. Path 1 starts from the receiving area of ​​the warehouse, passes through the inventory area, and finally reaches the shipping area. If this path is divided into five segments, that is, b=5, then each segment may represent a specific area or a specific processing process on the path. For example, the first segment (a=1) represents the movement from the receiving area to the inventory area, the second segment (a=2) represents the processing process in the inventory area, and so on.

[0041] Obstacle analysis of the divided segments is a crucial step. This process involves a detailed inspection of each segment a to ensure that the transportation path is unobstructed. Specifically, we will use lidar technology to scan each segment a in sequence to determine whether there are obstacles in the segment. If an obstacle is detected in a segment a, we will mark it as an abnormal segment, denoted as a1. This classification is based on the possible interference or obstruction of the transportation process by the obstacle. On the contrary, if there is no obstacle in the segment a, we classify it as a normal segment, denoted as a2. Here, a1 and a2 are the corresponding number of segments after classification.

[0042] For example, consider a real-world scenario where a delivery route is divided into several segments for analysis. Suppose that when one of the segments a passes through a certain area, if it is found that there are boxes that are not properly placed in the area when scanning with LiDAR, this segment will be classified as an abnormal segment a1 because there is an obstacle (box that is not properly placed). On the contrary, if the boxes in the area are placed in an orderly manner and no obstacles are detected, then this segment will be classified as a normal segment a2 and no further processing measures will be taken.

[0043] For the normal segment a2 obtained by classification, the corresponding normal segment information is generated and transmitted to the path selection analysis module. For the abnormal segment a1 obtained by classification, the corresponding abnormal segment information is generated and transmitted to the avoidance information analysis module.

[0044] The avoidance information analysis module is used to analyze the acquired abnormal segment information, and the specific analysis method is as follows:

[0045] For the identified abnormal segment a1, further processing is required to ensure that the robot can pass through these sections smoothly. To this end, the obstacles in these segments are first scanned with high precision using laser radar. The data obtained from the scanning can be used to construct an accurate three-dimensional model of the obstacle. After obtaining the three-dimensional model of the obstacle, it is then determined whether the robot can pass through these obstacles. In order to make this judgment, a three-dimensional coordinate system is first established on the plane where the obstacle is located. In this coordinate system, the origin is set at the center point of the abnormal segment, and then all vertices of the three-dimensional model are represented by three-dimensional coordinates.

[0046] When dealing with regular obstacles in the abnormal segment a1, a detailed analysis is required to ensure that the robot's delivery path is not obstructed. First, the object width of the regular obstacle is obtained through laser radar scanning. At the same time, the path width corresponding to the abnormal segment a1 is also obtained;

[0047] Next, the object width of the obstacle is compared to the travel width. This comparison process is crucial because it directly determines whether the obstacle will affect the robot's delivery task. If the object width is greater than the travel width, it means that the obstacle occupies too much space and may hinder the robot's passage. In this case, an avoidance signal will be generated;

[0048] On the contrary, if the object width is smaller than the driving width, this indicates that the obstacle exists but is not large enough to affect the robot's transportation. In this case, a pick signal is generated, which means that the robot can continue to perform the task along the intended path without making additional path adjustments.

[0049] Then, the generated selection signal is analyzed to obtain the driving width, and the driving width is evenly divided to obtain two sets of average widths. At the same time, the driving position of the robot is calculated based on the average width, and the specific calculation method is as follows:

[0050] The average point of the driving width is obtained, and the three-dimensional coordinates corresponding to the average point are obtained, and the three-dimensional coordinate information is generated at the same time. Then the three-dimensional coordinate information is transmitted to the path generation output module. All abnormal segmentation segments are analyzed and processed in this way, and all transportation paths are analyzed in the same way.

[0051] At the same time, the generated avoidance signal is transmitted to the path selection analysis module.

[0052] For example 2, please refer to Figure 2 As the second embodiment of the present invention, the difference from the first embodiment is that the avoidance information analysis module analyzes the irregular obstacles, and the specific analysis method is as follows:

[0053] All vertex coordinates of the irregular obstacle are obtained through LiDAR scanning. Next, the horizontal coordinates of the vertex coordinates are compared and the vertex with the largest horizontal coordinate is selected as the standard point, because it allows the maximum horizontal extension of the obstacle to be determined. Based on this standard point, we further analyze and obtain the actual object width of the irregular obstacle. Here, the point with the largest width is marked and used as a standard to obtain the corresponding object width. This method ensures that the widest part of the obstacle is taken into account, thereby accurately evaluating the space occupancy.

[0054] For the generated selection signal, the analysis method in the first embodiment is similar, and then the generated avoidance signal is transmitted to the path selection analysis module.

[0055] Embodiment 3, as the embodiment 3 of the present invention, is implemented on the basis of embodiment 1 and embodiment 2, and is different from embodiment 1 and embodiment 2 in that.

[0056] The path selection analysis module is used to analyze the obtained avoidance signal, and the specific analysis method is as follows:

[0057] For the remaining transport path i-1, detailed analysis needs to be continued to ensure the smoothness of the overall process. First, the remaining paths are segmented in the same way as before to obtain a series of segments to be analyzed. Next, special attention is paid to those segments to be analyzed with the same label as the avoidance signal. If the segment to be analyzed meets the obstacle avoidance conditions, it means that the robot can pass safely by adjusting the robot's route, temporarily removing obstacles, etc. In this case, a secondary analysis signal is generated, indicating that this section needs further analysis and adjustment. On the contrary, if the segment to be analyzed does not meet the obstacle avoidance conditions, it means that even if reasonable measures are taken, the robot cannot pass through this area smoothly.

[0058] For the generated secondary analysis signal, the corresponding segment to be analyzed needs to be further processed to determine the best transport path. First, the segment to be analyzed is selected and recorded as the selected segment. Next, the segments to be analyzed adjacent to the selected segment are obtained. Here, "adjacent" means adjacent in number, and the numbers of these segments to be analyzed are greater than the number of the selected segment.

[0059] Then, an obstacle avoidance judgment is performed on this adjacent segment to be analyzed. If this segment meets the obstacle avoidance conditions, it means that the robot can pass safely by adjusting the robot's route, temporarily removing obstacles, etc., and an analysis signal is generated. On the contrary, if the adjacent segment to be analyzed does not meet the obstacle avoidance conditions, it means that even if reasonable measures are taken, the robot cannot pass through this area smoothly. In this case, a rejection signal will be generated.

[0060] Then the generated analysis signal is processed to obtain the length of the selected segment, and the transportation time of the selected segment is calculated according to the transportation speed of the robot. Similarly, the transportation time of all selected segments is calculated, and the selected segment corresponding to the minimum transportation time is selected as the standard. At the same time, standard information is generated, and the robot transportation path is generated in this way, and the path information is generated, and then the path information is transmitted to the path generation output module.

[0061] The path generation output module is used to transmit the acquired path information to the robot, and the robot acquires the path information and executes it.

[0062] Embodiment 4, as the fourth embodiment of the present invention, focuses on combining the implementation processes of Embodiment 1, Embodiment 2 and Embodiment 3 for implementation.

[0063] Some of the data in the above formulas are dimensionless and numerically calculated. Meanwhile, the contents not described in detail in this specification belong to the prior art known to those skilled in the art.

[0064] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A laser radar-based object delivery robot, characterized in that: include: The path obstacle avoidance analysis module is used to obtain the transport information transmitted by the transport information acquisition module, generate a transport path according to the transport information, and divide the transport path into segments with equal distances, and then classify the segments into normal segments and abnormal segments according to whether there are obstacles, and transmit the abnormal segment information to the avoidance information analysis module; The avoidance information analysis module is used to obtain the abnormal segment information, identify and classify the obstacles in the abnormal segment through three-dimensional modeling to obtain regular obstacles and irregular obstacles, and calculate the travel widths of regular obstacles and irregular obstacles respectively, and compare the travel widths to generate avoidance signals and selection signals. For the selection signal, the three-dimensional coordinate information is generated by analyzing the travel position, and the three-dimensional coordinate information is transmitted to the path generation output module, and the avoidance signal is transmitted to the path selection analysis module; The path selection analysis module is used to analyze the obtained avoidance signal, divide the remaining transport path to obtain the segment to be analyzed, and the specific processing method is: obtain the remaining transport path i-1, and divide the transport path in the same way to obtain the segment to be analyzed, and at the same time obtain the segment to be analyzed corresponding to the same number as the avoidance signal, and make an obstacle avoidance judgment on the segment to be analyzed. If the segment to be analyzed meets the obstacle avoidance requirement, a secondary analysis signal is generated. On the contrary, if the segment to be analyzed does not meet the obstacle avoidance requirement, a rejection signal is generated, and an obstacle avoidance judgment is made on the segment to be analyzed to generate a secondary analysis signal and a rejection signal. For the secondary analysis signal, the analysis signal and the rejection signal are generated by analyzing the adjacent numbered segments to be analyzed. For the analysis signal, the one with the shortest transport time is selected as the standard to generate standard information, and the path information is integrated and generated, and then the path information is transmitted to the path generation output module. The specific method of analyzing the secondary analysis signal is: The corresponding segment to be analyzed is selected and recorded as the selected segment. At the same time, the adjacent segment to be analyzed is obtained, and the number of the segment to be analyzed is greater than that of the selected segment. Then, the adjacent segment to be analyzed is judged for obstacle avoidance. If it is satisfied, an analysis signal is generated, otherwise a rejection signal is generated. At the same time, the length of the selected segment is obtained, and the transportation time of the selected segment is calculated according to the transportation speed of the robot. Similarly, the transportation time of all selected segments is calculated, and the selected segment corresponding to the minimum transportation time is selected as the standard. At the same time, standard information is generated, and path information is generated with the standard information, and then the path information is transmitted to the path generation output module.

2. The laser radar-based object transport robot according to claim 1, characterized in that: It also includes a transportation information collection module and a path generation output module; The transportation information acquisition module is used to obtain the transportation information of the robot, and the transportation information includes the transportation starting point and the transportation end point, and transmit the transportation information to the path obstacle avoidance analysis module; The path generation output module is used to transmit the acquired path information to the robot.

3. The laser radar-based object transport robot according to claim 1, characterized in that: The path obstacle avoidance analysis module obtains all the transport paths and labels them as i, where i=1, 2, ..., j, and j represents the number of transport paths, and j is a positive integer. Then, any transport path is obtained as a target object for analysis, and the target object is segmented into multiple segments, which are labeled as a, where a=1, 2, ..., b, and b represents the number of segments, and b is a positive integer, and the lengths of the segments are the same. Perform a laser radar scan on segment a in the order of the labels, and determine whether there is an obstacle in segment a. If there is an obstacle in segment a, the corresponding segment is classified as an abnormal segment a1. Otherwise, if there is no obstacle in the segment, the corresponding segment is classified as a normal segment a2. Both a1 and a2 represent the number of corresponding classified segments, and the normal segment a2 obtained by classification is not processed.

4. The laser radar-based object transport robot according to claim 1, characterized in that: The avoidance information analysis module obtains all abnormal segmentation segments a1, then scans the obstacle through the laser radar and performs three-dimensional modeling processing to obtain a three-dimensional model, and at the same time judges the three-dimensional model, establishes a three-dimensional coordinate system based on the plane where the obstacle is located, and the origin of the three-dimensional coordinate system is the center point of the abnormal segmentation segment, then represents all vertices of the three-dimensional model with three-dimensional coordinates, judges the shape of the obstacle through the three-dimensional coordinates, and classifies the obstacles into regular obstacles and irregular obstacles.

5. The laser radar-based object transport robot according to claim 4, characterized in that: The avoidance information analysis module obtains the object width of the regular obstacle, the path width corresponding to the abnormal segment a1, and the robot width, then calculates the difference between the path width and the robot width as the driving width, and compares the object width with the driving width. When the object width is greater than the driving width, it means that the regular obstacle affects the robot transportation and an avoidance signal is generated. Conversely, when the object width is less than the driving width, it means that the regular obstacle does not affect the robot transportation and a selection signal is generated.

6. The laser radar-based object transport robot according to claim 4, characterized in that: The avoidance information analysis module obtains all vertex coordinates of the irregular obstacle, then compares the horizontal coordinates of the vertex coordinates, and selects the vertex with the largest horizontal coordinate as the standard point. At the same time, the standard point is analyzed to obtain the object width of the irregular obstacle, and then the object width is compared with the driving width. When the object width is greater than the driving width, an avoidance signal is generated. Conversely, when the object width is less than the driving width, a selection signal is generated.

7. The laser radar-based object transport robot according to claim 1, characterized in that: The avoidance information analysis module obtains the driving width, and divides the driving width to obtain two groups of average widths, obtains the average points of the driving width, obtains the three-dimensional coordinates corresponding to the average points, and generates three-dimensional coordinate information.