Intelligent robot obstacle avoidance control method

Abstract

The invention discloses an intelligent robot obstacle avoidance control system and method, and particularly relates to the technical field of obstacle avoidance control. The path is segmented by obtaining the historical motion track of the robot and combining the obstacle distribution condition. And aiming at the historical dangerous path segment set and the historical alternative obstacle avoidance path segment set, carrying out collision risk assessment, and generating an obstacle threat degree prediction result. Under the same-direction movement condition, obtaining a historical obstacle avoidance efficiency factor set through trajectory similarity analysis; and under the condition of different-direction movement, outputting an obstacle avoidance safety margin data set in combination with the minimum distance overlapping interval of the path section and the obstacle. Based on a historical obstacle avoidance efficiency factor set and an obstacle avoidance safety margin data set, a real-time obstacle avoidance decision model is established, a path section where collision may occur is predicted in combination with an obstacle threat degree prediction result, a real-time obstacle avoidance control instruction is generated and output, deep combination of historical data and real-time dynamic analysis is achieved, and the real-time obstacle avoidance control method is suitable for a real-time obstacle avoidance system. And the obstacle avoidance accuracy and decision-making efficiency of the robot are improved.

Description

Technical Field

[0001] The present invention relates to the field of obstacle avoidance control technology, and more specifically, to an intelligent robot obstacle avoidance control system and method. Background Art

[0002] With the rapid development of robotics technology, robots are increasingly used in industrial manufacturing, logistics and transportation, home services and other fields. However, there are usually dynamic or static obstacles in complex operating environments, and robots must have accurate and efficient obstacle avoidance capabilities to ensure safe operation. Existing obstacle avoidance technologies are mostly based on real-time obstacle detection and path planning by sensors, but these methods rely on the accuracy of real-time perception and are easily disturbed by factors such as ambient light and dynamic changes in obstacles, resulting in unstable obstacle avoidance strategies. At the same time, the lack of full use of historical data makes it impossible for robots to learn from past movement experience to optimize obstacle avoidance paths or improve decision-making efficiency.

[0003] In order to solve the above problems, a technical solution is now provided. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present invention provide an intelligent robot obstacle avoidance control system and method to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] An intelligent robot obstacle avoidance control method comprises the following steps:

[0007] Obtain the robot's historical motion trajectory, segment the path according to the obstacle distribution, and obtain a set of historical safe path segments, a set of historical dangerous path segments, a set of historical main obstacle avoidance path segments, and a set of historical alternative obstacle avoidance path segments;

[0008] Perform collision risk assessment on the historical dangerous path segment set and the historical alternative obstacle avoidance path segment set, and output the obstacle threat degree prediction result;

[0009] When the historical safety path segment set and the historical main obstacle avoidance path segment set are in the same direction of movement, the historical safety path segment set and the historical main obstacle avoidance path segment set are subjected to trajectory similarity analysis to obtain a historical obstacle avoidance efficiency factor set;

[0010] When the historical safe path segment set and the historical main obstacle avoidance path segment set are in different-direction moving conditions, the minimum distance overlap interval between the path segments and obstacles in the historical safe path segment set and the historical main obstacle avoidance path segment set is analyzed, and the obstacle avoidance safety margin data set is output;

[0011] According to the historical obstacle avoidance efficiency factor set and obstacle avoidance safety margin data set, a real-time obstacle avoidance decision model is established. Combined with the obstacle threat degree prediction results, the path segments where collisions may occur are predicted and obstacle avoidance control instructions are output.

[0012] In a preferred embodiment, the robot's historical motion trajectory is obtained, and the path is segmented according to the obstacle distribution to obtain a historical safe path segment set, a historical dangerous path segment set, a historical main obstacle avoidance path segment set, and a historical alternative obstacle avoidance path segment set, specifically:

[0013] Obtain the motion trajectory information of the robot within a given time period and discretize the motion trajectory into several path points;

[0014] The obstacle information around the path points is calibrated and aggregated, and the path segments are divided according to the obstacle density distribution and path hazard level;

[0015] By calculating the average minimum safe distance between the path segment and the obstacle, the path segment is divided into a historical safe path segment and a historical dangerous path segment;

[0016] According to whether the robot has taken effective obstacle avoidance actions in the historical dangerous path segments, the historical dangerous path segments are divided into historical main obstacle avoidance path segments and historical alternative obstacle avoidance path segments.

[0017] In a preferred embodiment, the collision risk assessment is performed on the historical dangerous path segment set and the historical candidate obstacle avoidance path segment set, and the obstacle threat degree prediction result is output, specifically:

[0018] Calculate the probability of collision between the robot and obstacles in the historical dangerous path segment;

[0019] Evaluate the obstacle interference intensity of the historical candidate obstacle avoidance path segments to determine the feasibility of the path obstacle avoidance;

[0020] The collision probability and path obstacle avoidance feasibility are combined to output the obstacle threat degree prediction result.

[0021] In a preferred embodiment, when the historical safety path segment set and the historical main obstacle avoidance path segment set are in the same direction of movement, the historical safety path segment set and the historical main obstacle avoidance path segment set are subjected to trajectory similarity analysis to obtain a historical obstacle avoidance efficiency factor set, specifically:

[0022] Extract trajectory features of historical safe path segments and historical main obstacle avoidance path segments;

[0023] Dynamic time warping method is used to determine trajectory similarity;

[0024] The obstacle avoidance efficiency is evaluated based on trajectory similarity, and a historical obstacle avoidance efficiency factor set is generated.

[0025] In a preferred embodiment, when the historical safety path segment set and the historical main obstacle avoidance path segment set are in a condition of moving in different directions, the minimum distance overlap interval between the path segments and obstacles in the historical safety path segment set and the historical main obstacle avoidance path segment set is analyzed, and an obstacle avoidance safety margin data set is output, specifically:

[0026] Calculate the minimum distance between the robot and the obstacle in the path segment;

[0027] Identify the overlapping areas between the historical safe path segments and the historical main obstacle avoidance path segments;

[0028] Evaluate the obstacle avoidance safety margin in the overlapping area and output the obstacle avoidance safety margin dataset.

[0029] In a preferred embodiment, a real-time obstacle avoidance decision model is established based on the historical obstacle avoidance efficiency factor set and the obstacle avoidance safety margin data set. Combined with the obstacle threat prediction results, the path segment where collision may occur is predicted and the obstacle avoidance control instruction is output, specifically:

[0030] Construct a real-time obstacle avoidance decision model based on the historical obstacle avoidance efficiency factor set and obstacle avoidance safety margin data set;

[0031] The obstacle threat degree prediction result is input into the model to determine whether there is a risk of collision with the obstacle in the current robot's travel path;

[0032] If the collision risk exceeds the preset threshold, an obstacle avoidance control command is output.

[0033] On the other hand, the present invention provides an intelligent robot obstacle avoidance control system, including a path segmentation module, a collision risk assessment module, a trajectory similarity analysis module, an overlapping interval analysis module, and an obstacle avoidance instruction output module;

[0034] Path segmentation module: obtains the robot's historical motion trajectory, segments the path according to the obstacle distribution, and obtains a set of historical safe path segments, a set of historical dangerous path segments, a set of historical main obstacle avoidance path segments, and a set of historical alternative obstacle avoidance path segments;

[0035] Collision risk assessment module: performs collision risk assessment on the historical dangerous path segment set and the historical alternative obstacle avoidance path segment set, outputs obstacle threat degree prediction results and obstacle avoidance instruction output module;

[0036] Trajectory similarity analysis module: When the historical safety path segment set and the historical main obstacle avoidance path segment set are in the same direction of movement, trajectory similarity analysis is performed on the historical safety path segment set and the historical main obstacle avoidance path segment set to obtain a historical obstacle avoidance efficiency factor set;

[0037] Overlapping interval analysis module: when the historical safety path segment set and the historical main obstacle avoidance path segment set are in different directions of movement, the minimum overlapping interval between the path segments and obstacles in the historical safety path segment set and the historical main obstacle avoidance path segment set is analyzed, and the obstacle avoidance safety margin data set is output;

[0038] Obstacle avoidance command output module: Based on the historical obstacle avoidance efficiency factor set and obstacle avoidance safety margin data set, a real-time obstacle avoidance decision model is established. Combined with the obstacle threat degree prediction results, the path segments where collisions may occur are predicted and obstacle avoidance control commands are output.

[0039] The technical effects and advantages of the intelligent robot obstacle avoidance control system and method of the present invention are as follows:

[0040] 1. By segmenting the robot's historical motion trajectory, a set of safe path segments, dangerous path segments, main obstacle avoidance path segments, and alternative obstacle avoidance path segments is formed, making full use of historical obstacle avoidance experience and enhancing the pertinence of the obstacle avoidance strategy. Secondly, by evaluating the collision risk of dangerous path segments and alternative obstacle avoidance path segments, the obstacle threat prediction results are generated, providing a key reference for real-time obstacle avoidance decision-making. Under the conditions of moving in the same or different directions, the obstacle avoidance efficiency factor and safety margin data set are obtained through trajectory similarity and minimum distance overlap interval analysis, further improving the accuracy and safety of decision-making.

[0041] 2. Based on the historical obstacle avoidance efficiency factor set and obstacle avoidance safety margin data set, a real-time obstacle avoidance decision model is established. The path segments where collisions may occur are predicted in combination with the obstacle threat degree prediction results, and obstacle avoidance control instructions are output, realizing intelligent and autonomous obstacle avoidance control. It has good adaptability and scalability, and can be applied to a variety of complex environments and dynamically changing scenarios. It effectively solves the problems of obstacle avoidance failure and low efficiency of existing obstacle avoidance methods in the case of multiple obstacle interference or path intersection, and is suitable for a variety of application scenarios such as industry, logistics, and service robots. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 A schematic diagram of an intelligent robot obstacle avoidance control method of the present invention;

[0043] Figure 2 The present invention is a schematic structural diagram of an intelligent robot obstacle avoidance control system. DETAILED DESCRIPTION

[0044] 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.

[0045] Example 1

[0046] Figure 1 The present invention provides an intelligent robot obstacle avoidance control method, which comprises the following steps:

[0047] Obtain the robot's historical motion trajectory, segment the path according to the obstacle distribution, and obtain a set of historical safe path segments, a set of historical dangerous path segments, a set of historical main obstacle avoidance path segments, and a set of historical alternative obstacle avoidance path segments;

[0048] Perform collision risk assessment on the historical dangerous path segment set and the historical alternative obstacle avoidance path segment set, and output the obstacle threat degree prediction result;

[0049] When the historical safety path segment set and the historical main obstacle avoidance path segment set are in the same direction of movement, the historical safety path segment set and the historical main obstacle avoidance path segment set are subjected to trajectory similarity analysis to obtain a historical obstacle avoidance efficiency factor set;

[0050] When the historical safe path segment set and the historical main obstacle avoidance path segment set are in different-direction moving conditions, the minimum distance overlap interval between the path segments and obstacles in the historical safe path segment set and the historical main obstacle avoidance path segment set is analyzed, and the obstacle avoidance safety margin data set is output;

[0051] According to the historical obstacle avoidance efficiency factor set and obstacle avoidance safety margin data set, a real-time obstacle avoidance decision model is established. Combined with the obstacle threat degree prediction results, the path segments where collisions may occur are predicted and obstacle avoidance control instructions are output.

[0052] Specifically, the robot's historical motion trajectory is obtained, and the path is segmented according to the obstacle distribution to obtain a historical safe path segment set, a historical dangerous path segment set, a historical main obstacle avoidance path segment set, and a historical alternative obstacle avoidance path segment set, including:

[0053] Obtain the motion trajectory information of the robot within a given time period and discretize the motion trajectory into several path points;

[0054] Specifically, the robot will generate continuous motion trajectories during actual operation, and these trajectories are usually recorded in the form of time series. For example, the trajectory points may be recorded as: (x1, y1, t1), (x1, y1, t1), ..., (x n ,y n ,t n ), indicating that the robot is at time t1 to t nThe trajectory points are discretized and key path points are extracted (for example, recorded every 0.1 seconds). For example, the robot moves from point A to point B, and the path is recorded as a continuous curve. Through discretization, the curve is converted into a set of discrete points, for example: A(0,0), P(1,2),..., B(10,5).

[0055] The obstacle information around the path points is calibrated and aggregated, and the path segments are divided according to the obstacle density distribution and path hazard level;

[0056] Specifically, obstacle information can be detected and calibrated by sensors (such as lidar or cameras). If there are dense obstacles around the path point, the path is considered dangerous; otherwise, the path is considered safe. For example, when a robot passes through a path, there may be multiple obstacles around it. For example, the obstacle density of a certain path is 10 / m 2 , then this section of the path is defined as a dangerous section; if the obstacle density is 1 / m 2 , it is defined as a safe path segment.

[0057] By calculating the average minimum safe distance between the path segment and the obstacle, the path segment is divided into a historical safe path segment and a historical dangerous path segment;

[0058] Specifically, the average minimum safe distance measures the overall safety of a path segment. For example, if the robot's minimum distance on path segment A is 2 meters, and the minimum distance on path segment B is 0.5 meters (below the 1-meter threshold), then A is a safe path segment and B is a dangerous path segment. Among them, d avg Represents the average minimum safety distance; d i is the distance from the path point to the nearest obstacle; N is the total number of path points. Exemplarily, if the average minimum safe distance between the robot and the obstacle in path segment C is 1.2 meters and is greater than the safety threshold of 1 meter, then path segment C is a safe path segment.

[0059] According to whether the robot has taken effective obstacle avoidance actions in the historical dangerous path segments, the historical dangerous path segments are divided into historical main obstacle avoidance path segments and historical alternative obstacle avoidance path segments.

[0060] Specifically, the main obstacle avoidance path segment represents the path segment where the robot has successfully bypassed obstacles through effective obstacle avoidance strategies in the past; the alternative obstacle avoidance path segment represents the path segment where no obstacle avoidance action has been taken or where other feasible obstacle avoidance strategies exist; illustratively, if the robot successfully avoids obstacles by decelerating on path segment D, then D is the main obstacle avoidance path segment; and path segment E has not been attempted to avoid obstacles, but it is theoretically feasible to bypass it, then E is the alternative obstacle avoidance path segment.

[0061] Specifically, the collision risk of the historical dangerous path segment set and the historical alternative obstacle avoidance path segment set is evaluated, and the obstacle threat degree prediction result is output, including:

[0062] Calculate the probability of collision between the robot and obstacles in the historical dangerous path segment;

[0063] Specifically, the collision probability is calculated based on the minimum distance between the path point and the obstacle in the historical dangerous path segment, the robot speed, and the obstacle moving speed. The calculation formula is P col =f(d min ,v rob ,v obs ), where P col is the collision probability; d min is the minimum distance between the path point and the obstacle in the historical dangerous path segment; v rob ,v obs are the robot speed and obstacle speed in the historical dangerous path segment, respectively. For example, in path segment F, the obstacle speed is fast and the distance is close (0.3 meters), and the calculated collision probability is 90%.

[0064] Evaluate the obstacle interference intensity of the historical candidate obstacle avoidance path segments to determine the feasibility of the path obstacle avoidance;

[0065] Specifically, the interference intensity evaluates the degree to which obstacles hinder the path segment obstacle avoidance strategy. The interference intensity can be predicted by calculating the obstacle coverage and dynamic behavior. The calculation formula for interference intensity is: I = g(v obs ,R cov ), where I is the interference intensity; R cov is the obstacle influence radius. For example, the obstacle movement range around the path segment G is large, the interference intensity is 70%, and the path obstacle avoidance feasibility is low.

[0066] The collision probability and path obstacle avoidance feasibility are combined to output the obstacle threat degree prediction result.

[0067] Specifically, the collision probability and obstacle avoidance feasibility are combined to generate a comprehensive threat level prediction. A high collision probability and low obstacle avoidance feasibility means a high threat level.

[0068] Specifically, when the historical safety path segment set and the historical main obstacle avoidance path segment set are in the same direction moving condition, the historical safety path segment set and the historical main obstacle avoidance path segment set are subjected to trajectory similarity analysis to obtain a historical obstacle avoidance efficiency factor set, including:

[0069] Extract trajectory features of historical safe path segments and historical main obstacle avoidance path segments;

[0070] Specifically, the historical safe path segment indicates a path segment in which a relatively safe distance from obstacles (meeting the safety threshold) was maintained in the past operation, and the robot did not collide or encounter dangerous situations. The historical main obstacle avoidance path segment is a path segment in which the robot has used effective obstacle avoidance actions and successfully bypassed obstacles when encountering obstacles in the past. Trajectory features include position coordinate sequence, the orientation, speed and acceleration of the robot at different time points, etc. Exemplarily, the robot travels on two different paths over a period of time: Safe path segment (Ptah_S): The average distance from obstacles on the entire path is large, such as maintaining more than 2 meters, and no emergency braking is triggered. Main obstacle avoidance path segment (Ptah_M): In this path segment, the robot has made obvious obstacle avoidance actions (such as deceleration or detour) and successfully avoided obstacles.

[0071] Both paths have a large amount of time series data, which are extracted into feature sequences, such as:

[0072]

[0073]

[0074] Dynamic time warping method is used to determine trajectory similarity;

[0075] Specifically, dynamic time warping is an algorithm used to measure the similarity of two time series (or trajectories), which allows nonlinear matching on the time scale. Dynamic time warping can calculate the degree of difference between two trajectories in spatial and temporal dimensions. The smaller the difference, the higher the similarity.

[0076] The obstacle avoidance efficiency is evaluated based on trajectory similarity, and a historical obstacle avoidance efficiency factor set is generated.

[0077] Specifically, trajectory similarity: if the historical safe path segment is highly similar to the historical main obstacle avoidance path segment (dynamic time warping distance is small), then the main obstacle avoidance path segment is considered to have a similar passing method as the safe path segment in this scenario; obstacle avoidance efficiency: the efficiency is quantified by combining the success rate of the main obstacle avoidance path segment (such as low collision rate, low energy consumption, short time, etc.). Factor set: the above indicators (trajectory similarity obstacle avoidance efficiency) are comprehensively recorded to form a historical obstacle avoidance efficiency factor set.

[0078] Specifically, when the historical safety path segment set and the historical main obstacle avoidance path segment set are in different moving directions, the minimum distance overlap interval between the path segments and obstacles in the historical safety path segment set and the historical main obstacle avoidance path segment set is analyzed, and an obstacle avoidance safety margin data set is output, including:

[0079] Calculate the minimum distance between the robot and the obstacle in the path segment;

[0080] Specifically, define the path segment P in the historical safety path segment set and the historical main obstacle avoidance path segment set to contain A path points, and the coordinates of the path points are P a =(x a ,y a ), where a=1,2,...A. Define the obstacle set as O, where the coordinates of each obstacle are O b =(x b ,y b ), b=1,2,...B. The minimum distance between the robot and the obstacle in the path segment is Among them, D min is the minimum distance between the robot and the obstacle in the path segment.

[0081] Identify the overlapping areas between the historical safe path segments and the historical main obstacle avoidance path segments;

[0082] Specifically, the overlapping area refers to the interval where two path segments may overlap or be adjacent in space or time. The condition of different directions of movement means that the moving directions of the two paths are inconsistent, but they may approach or cross the same obstacle within a certain spatial range. For example, in the map coordinate system, the robot's safe path segment moves between (2,2) and (5,5), and the main obstacle avoidance path segment moves between (3,3) and (6,6). The two have temporal and spatial overlap in the area from (3,3) to (5,5).

[0083] Evaluate the obstacle avoidance safety margin in the overlapping area and output the obstacle avoidance safety margin dataset.

[0084] Specifically, the safety margin usually refers to the minimum safe distance or minimum spatial redundancy that the robot maintains relative to the obstacle when avoiding obstacles. For example, if the minimum distance reaches 1 meter and meets the task safety threshold, the safety margin is relatively high. In the overlapping area, if the minimum distance of the historical safe path segment is generally greater than the historical main obstacle avoidance path segment, it means that the main obstacle avoidance path segment may have a greater risk and further optimization of obstacle avoidance is required. Finally, these minimum distance or safety margin parameters are summarized and counted and output as an obstacle avoidance safety margin dataset.

[0085] Specifically, based on the historical obstacle avoidance efficiency factor set and obstacle avoidance safety margin data set, a real-time obstacle avoidance decision model is established. Combined with the obstacle threat prediction results, the path segments where collisions may occur are predicted and obstacle avoidance control instructions are output, including:

[0086] Construct a real-time obstacle avoidance decision model based on the historical obstacle avoidance efficiency factor set and obstacle avoidance safety margin data set;

[0087] The obstacle threat degree prediction result is input into the model to determine whether there is a risk of collision with the obstacle in the current robot's travel path;

[0088] If the collision risk exceeds the preset threshold, an obstacle avoidance control command is output.

[0089] Example 2

[0090] The difference between Example 2 of the present invention and Example 1 is that this example introduces an intelligent robot obstacle avoidance control system.

[0091] Figure 2 A structural schematic diagram of an intelligent robot obstacle avoidance control system of the present invention is given, which includes a path segmentation module, a collision risk assessment module, a trajectory similarity analysis module, an overlapping interval analysis module and an obstacle avoidance instruction output module;

[0092] Path segmentation module: obtains the robot's historical motion trajectory, segments the path according to the obstacle distribution, and obtains a set of historical safe path segments, a set of historical dangerous path segments, a set of historical main obstacle avoidance path segments, and a set of historical alternative obstacle avoidance path segments;

[0093] Collision risk assessment module: performs collision risk assessment on the historical dangerous path segment set and the historical alternative obstacle avoidance path segment set, outputs obstacle threat degree prediction results and obstacle avoidance instruction output module;

[0094] Trajectory similarity analysis module: When the historical safety path segment set and the historical main obstacle avoidance path segment set are in the same direction of movement, trajectory similarity analysis is performed on the historical safety path segment set and the historical main obstacle avoidance path segment set to obtain a historical obstacle avoidance efficiency factor set;

[0095] Overlapping interval analysis module: when the historical safety path segment set and the historical main obstacle avoidance path segment set are in different directions of movement, the minimum overlapping interval between the path segments and obstacles in the historical safety path segment set and the historical main obstacle avoidance path segment set is analyzed, and the obstacle avoidance safety margin data set is output;

[0096] Obstacle avoidance command output module: Based on the historical obstacle avoidance efficiency factor set and obstacle avoidance safety margin data set, a real-time obstacle avoidance decision model is established. Combined with the obstacle threat degree prediction results, the path segments where collisions may occur are predicted and obstacle avoidance control commands are output.

[0097] 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 and thresholds in the formula are set by technicians in this field according to actual conditions.

[0098] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0099] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0100] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0101] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0102] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, and may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0103] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0104] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0105] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0106] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent robot obstacle avoidance control method, characterized in that: The steps include: Obtain the robot's historical motion trajectory, segment the path according to the obstacle distribution, and obtain a set of historical safe path segments, a set of historical dangerous path segments, a set of historical main obstacle avoidance path segments, and a set of historical alternative obstacle avoidance path segments; Perform collision risk assessment on the historical dangerous path segment set and the historical alternative obstacle avoidance path segment set, and output the obstacle threat degree prediction result; When the historical safety path segment set and the historical main obstacle avoidance path segment set are in the same direction of movement, the historical safety path segment set and the historical main obstacle avoidance path segment set are subjected to trajectory similarity analysis to obtain a historical obstacle avoidance efficiency factor set; When the historical safe path segment set and the historical main obstacle avoidance path segment set are in different-direction moving conditions, the minimum distance overlap interval between the path segments and obstacles in the historical safe path segment set and the historical main obstacle avoidance path segment set is analyzed, and the obstacle avoidance safety margin data set is output; According to the historical obstacle avoidance efficiency factor set and obstacle avoidance safety margin data set, a real-time obstacle avoidance decision model is established. Combined with the obstacle threat degree prediction results, the path segments where collisions may occur are predicted and obstacle avoidance control instructions are output.

2. The intelligent robot obstacle avoidance control method according to claim 1, characterized in that: Get the robot's historical motion trajectory, segment the path according to the obstacle distribution, and get the historical safe path segment set, historical dangerous path segment set, historical main obstacle avoidance path segment set, and historical alternative obstacle avoidance path segment set, specifically: Obtain the motion trajectory information of the robot within a given time period and discretize the motion trajectory into several path points; The obstacle information around the path points is calibrated and aggregated, and the path segments are divided according to the obstacle density distribution and path hazard level; By calculating the average minimum safe distance between the path segment and the obstacle, the path segment is divided into a historical safe path segment and a historical dangerous path segment; According to whether the robot has taken effective obstacle avoidance actions in the historical dangerous path segments, the historical dangerous path segments are divided into historical main obstacle avoidance path segments and historical alternative obstacle avoidance path segments.

3. The intelligent robot obstacle avoidance control method according to claim 1, characterized in that: The collision risk of the historical dangerous path segment set and the historical alternative obstacle avoidance path segment set is evaluated, and the obstacle threat degree prediction result is output, which is as follows: Calculate the probability of collision between the robot and obstacles in the historical dangerous path segment; Evaluate the obstacle interference intensity of the historical candidate obstacle avoidance path segments to determine the feasibility of the path obstacle avoidance; The collision probability and path obstacle avoidance feasibility are combined to output the obstacle threat degree prediction result.

4. The intelligent robot obstacle avoidance control method according to claim 1, characterized in that: When the historical safety path segment set and the historical main obstacle avoidance path segment set are in the same direction of movement, the historical safety path segment set and the historical main obstacle avoidance path segment set are subjected to trajectory similarity analysis to obtain the historical obstacle avoidance efficiency factor set, which is: Extract trajectory features of historical safe path segments and historical main obstacle avoidance path segments; Dynamic time warping method is used to determine trajectory similarity; The obstacle avoidance efficiency is evaluated based on trajectory similarity, and a historical obstacle avoidance efficiency factor set is generated.

5. The intelligent robot obstacle avoidance control method according to claim 1, characterized in that: When the historical safe path segment set and the historical main obstacle avoidance path segment set are in different directions of movement, the minimum distance overlap interval between the path segments and obstacles in the historical safe path segment set and the historical main obstacle avoidance path segment set is analyzed, and the obstacle avoidance safety margin data set is output, which is as follows: Calculate the minimum distance between the robot and the obstacle in the path segment; Identify the overlapping areas between the historical safe path segments and the historical main obstacle avoidance path segments; Evaluate the obstacle avoidance safety margin in the overlapping area and output the obstacle avoidance safety margin dataset.

6. The intelligent robot obstacle avoidance control method according to claim 1, characterized in that: According to the historical obstacle avoidance efficiency factor set and obstacle avoidance safety margin data set, a real-time obstacle avoidance decision model is established. Combined with the obstacle threat prediction results, the path segments where collisions may occur are predicted and obstacle avoidance control instructions are output, specifically: Construct a real-time obstacle avoidance decision model based on the historical obstacle avoidance efficiency factor set and obstacle avoidance safety margin data set; The obstacle threat degree prediction result is input into the model to determine whether there is a risk of collision with the obstacle in the current robot's travel path; If the collision risk exceeds the preset threshold, an obstacle avoidance control command is output.

7. An intelligent robot obstacle avoidance control system, used to implement an intelligent robot obstacle avoidance control method according to any one of claims 1 to 6, characterized in that: It includes path segmentation module, collision risk assessment module, trajectory similarity analysis module, overlapping interval analysis module and obstacle avoidance command output module; Path segmentation module: obtains the robot's historical motion trajectory, segments the path according to the obstacle distribution, and obtains a set of historical safe path segments, a set of historical dangerous path segments, a set of historical main obstacle avoidance path segments, and a set of historical alternative obstacle avoidance path segments; Collision risk assessment module: performs collision risk assessment on the historical dangerous path segment set and the historical alternative obstacle avoidance path segment set, outputs obstacle threat degree prediction results and obstacle avoidance instruction output module; Trajectory similarity analysis module: When the historical safety path segment set and the historical main obstacle avoidance path segment set are in the same direction of movement, trajectory similarity analysis is performed on the historical safety path segment set and the historical main obstacle avoidance path segment set to obtain a historical obstacle avoidance efficiency factor set; Overlapping interval analysis module: when the historical safety path segment set and the historical main obstacle avoidance path segment set are in different directions of movement, the minimum overlapping interval between the path segments and obstacles in the historical safety path segment set and the historical main obstacle avoidance path segment set is analyzed, and the obstacle avoidance safety margin data set is output; Obstacle avoidance command output module: Based on the historical obstacle avoidance efficiency factor set and obstacle avoidance safety margin data set, a real-time obstacle avoidance decision model is established. Combined with the obstacle threat degree prediction results, the path segments where collisions may occur are predicted and obstacle avoidance control commands are output.

Images