Robot obstacle avoidance method and device, electronic equipment and computer program product

By obtaining real-time updated operating space hazardous area probability map and virtual domain inverse kinematics method, the robot can flexibly adjust obstacle avoidance strategies in complex environments, solving the problems of insufficient obstacle avoidance efficiency and safety in the existing technology, and achieving high efficiency Safe obstacle avoidance action.

CN119065378APending Publication Date: 2024-12-03SHENGHUI CLEANNESS GRP HLDG LTD +1
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411193723.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-28
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

Existing robots are difficult to flexibly adjust obstacle avoidance strategies in complex and uncertain environments, resulting in insufficient obstacle avoidance efficiency and safety.

Method used

By obtaining the probability map of the dangerous area of ​​the operating space, preset obstacle avoidance cost function and control input constraints, the virtual domain inverse kinematics method is used to solve the target obstacle avoidance control strategy to ensure that the robot has the minimum generation under the constraints. Value obstacle avoidance action.

Benefits of technology

It realizes that robots can avoid obstacles efficiently and safely in a changing environment, improves autonomy and task execution efficiency, and enhances the robustness and adaptability of the system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119065378A_ABST
    Figure CN119065378A_ABST
Patent Text Reader

Abstract

The invention discloses a robot obstacle avoidance method and device, electronic equipment and a computer program product, and relates to the technical field of robot control, and the robot obstacle avoidance method comprises the steps: obtaining a real-time updated operation space dangerous area existence probability map, a preset obstacle avoidance cost function and a preset control input constraint condition, determining a dangerous area avoidance constraint condition according to the dangerous area existence probability map of the operation space; through a virtual domain inverse kinematics method, solving to obtain a target obstacle avoidance control strategy which enables the cost value of an obstacle avoidance cost function to be minimum under the condition that a control input constraint condition and a dangerous area avoidance constraint condition are met; and controlling the robot to avoid the obstacle according to the target obstacle avoidance control strategy. According to the invention, it can be ensured that the robot can efficiently and safely avoid obstacles in an uncertain environment.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of robot control technology, and in particular to a robot obstacle avoidance method, device, electronic equipment and computer program product. Background Art

[0002] With the rapid development of robotics technology, robots are increasingly being used to perform tasks in various complex and uncertain environments. In these environments, robots need to be able to autonomously detect obstacles and take obstacle avoidance measures when necessary to ensure their own safety and the successful completion of the task.

[0003] In the related art, robots usually adopt a fixed obstacle avoidance strategy, which is often not well adapted to the ever-changing environment full of uncertain factors. Therefore, it is urgent to develop a method that can flexibly adjust the obstacle avoidance strategy according to environmental changes. Summary of the invention

[0004] The main purpose of this application is to provide a robot obstacle avoidance method, device, electronic equipment and computer program product, aiming to solve the technical problem of efficient and safe obstacle avoidance of robots in uncertain environments.

[0005] To achieve the above objectives, the present application provides a robot obstacle avoidance method, comprising:

[0006] Obtaining a real-time updated probability map of the existence of a dangerous area in the operating space, a preset obstacle avoidance cost function, and a preset control input constraint condition, and determining a dangerous area avoidance constraint condition based on the probability map of the existence of a dangerous area in the operating space;

[0007] By using a virtual domain inverse kinematics method, a target obstacle avoidance control strategy is solved to minimize the cost value of the obstacle avoidance cost function while satisfying the control input constraint condition and the dangerous area avoidance constraint condition;

[0008] According to the target obstacle avoidance control strategy, the robot is controlled to avoid obstacles.

[0009] In one embodiment, the control input includes longitudinal thrust and steering torque, and the obstacle avoidance cost function is:

[0010]

[0011] Among them, J is the cost value of the obstacle avoidance cost function, τ u is the longitudinal thrust, τ r is the steering torque, t is the time, t f is the preset end time, is the upper limit of the longitudinal thrust.

[0012] In one embodiment, the step of determining the dangerous area avoidance constraint conditions according to the dangerous area existence probability map of the operation space includes:

[0013] Determine the dangerous area coordinates and the safety distance threshold of the dangerous area in the operating space based on the probability map of the dangerous area in the operating space;

[0014] The dangerous area avoidance constraint condition is determined according to the dangerous area coordinates and the safety distance threshold.

[0015] In one embodiment, the step of determining the dangerous area coordinates and the safety distance threshold of the dangerous area in the operation space based on the dangerous area existence probability map in the operation space includes:

[0016] Obtaining the dangerous area coordinates and the dangerous coefficient of the dangerous area in the operation space from the dangerous area existence probability map of the operation space;

[0017] Substituting the risk factor and the preset safety distance reference value into a preset safety distance threshold calculation formula to obtain the safety distance threshold of the danger zone;

[0018] The calculation formula of the safety distance threshold is:

[0019]

[0020] Among them, e w is the safety distance threshold, L o is the safety distance reference value, D r Is the risk factor.

[0021] In one embodiment, the method further comprises:

[0022] Obtaining obstacle parameters of the operation space in real time through a preset sensor, and inputting the obstacle parameters into a pre-trained dangerous area discrimination model to obtain dangerous area coordinates and a dangerous coefficient of the dangerous area in the operation space;

[0023] The existence probability map of the dangerous area in the operation space is updated in real time according to the dangerous area coordinates and the dangerous coefficient.

[0024] In one embodiment, the method further comprises:

[0025] Substituting the target obstacle avoidance control strategy into a preset robot dynamics model to obtain a target obstacle avoidance trajectory;

[0026] Monitor the motion trajectory of the robot in real time to obtain an actual obstacle avoidance trajectory;

[0027] When it is detected that the trajectory deviation between the actual obstacle avoidance trajectory and the target obstacle avoidance trajectory is greater than the preset trajectory deviation, return to execute: the step of obtaining the real-time updated operation space dangerous area existence probability map, the preset obstacle avoidance cost function, and the preset control input constraint condition.

[0028] In one embodiment, the method further comprises:

[0029] Acquire the robot coordinates of the robot in real time, and acquire the dangerous area coordinates of the dangerous area in the operation space from the dangerous area existence probability map in real time;

[0030] When it is detected that the coordinate difference between the robot coordinates and the dangerous area coordinates is less than a preset coordinate difference threshold, the execution is triggered: the steps of obtaining a real-time updated probability map of the dangerous area in the operating space, a preset obstacle avoidance cost function, and a preset control input constraint condition.

[0031] In addition, to achieve the above-mentioned purpose, the present application also provides a robot obstacle avoidance device, the device comprising:

[0032] The first obstacle avoidance module is used to obtain a real-time updated operation space dangerous area existence probability map, a preset obstacle avoidance cost function, and a preset control input constraint condition, and determine the dangerous area avoidance constraint condition according to the operation space dangerous area existence probability map;

[0033] A second obstacle avoidance module is used to solve, by a virtual domain inverse kinematics method, a target obstacle avoidance control strategy that minimizes the cost value of the obstacle avoidance cost function while satisfying the control input constraint condition and the dangerous area avoidance constraint condition;

[0034] The third obstacle avoidance module is used to control the robot to avoid obstacles according to the target obstacle avoidance control strategy.

[0035] In addition, to achieve the above-mentioned purpose, the present application also provides an electronic device, which includes: a memory, a processor, and a robot obstacle avoidance program stored in the memory and executable on the processor, and when the robot obstacle avoidance program is executed by the processor, the robot obstacle avoidance method as described above is implemented.

[0036] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, including a computer program, which implements the steps of the robot obstacle avoidance method as described above when executed by a processor.

[0037] The present application provides a robot obstacle avoidance method, device, electronic device and computer program product. The technical solution of the present application is to first obtain a real-time updated probability map of the existence of dangerous areas in the operating space, a preset obstacle avoidance cost function, and a preset control input constraint condition, and determine the dangerous area avoidance constraint condition based on the probability map of the existence of dangerous areas in the operating space. Secondly, through the virtual domain inverse kinematics method, a target obstacle avoidance control strategy is solved to minimize the cost value of the obstacle avoidance cost function while satisfying the control input constraint condition and the dangerous area avoidance constraint condition. Finally, according to the target obstacle avoidance control strategy, the robot is controlled to avoid obstacles, so that the present application can flexibly adjust the obstacle avoidance strategy according to environmental changes in real time, thereby ensuring that the robot can efficiently and safely avoid obstacles in a constantly changing environment full of uncertain factors. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0039] 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 or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying any creative work.

[0040] Figure 1 A schematic diagram of a flow chart of the first embodiment of the robot obstacle avoidance method of the present application;

[0041] Figure 2 A schematic diagram of a flow chart of a second embodiment of the robot obstacle avoidance method of the present application;

[0042] Figure 3 A schematic diagram of a flow chart of a third embodiment of the robot obstacle avoidance method of the present application;

[0043] Figure 4 A schematic diagram of a flow chart provided for the fourth embodiment of the robot obstacle avoidance method of the present application;

[0044] Figure 5 This is a schematic diagram of the module structure of the robot obstacle avoidance device according to an embodiment of the present application;

[0045] Figure 6 Schematic diagram of the device structure of the hardware operating environment involved in the robot obstacle avoidance method in the embodiment of the present application.

[0046] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0047] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0048] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0049] At present, robots in related technologies usually adopt fixed obstacle avoidance strategies, which often cannot adapt well to the ever-changing environment full of uncertain factors. Therefore, it is urgent to develop a method that can flexibly adjust the obstacle avoidance strategy according to environmental changes.

[0050] The main solution of the embodiment of the present application is: obtaining a real-time updated probability map of the existence of dangerous areas in the operating space, a preset obstacle avoidance cost function, and a preset control input constraint, and determining the dangerous area avoidance constraint based on the probability map of the existence of dangerous areas in the operating space; solving the target obstacle avoidance control strategy that minimizes the cost value of the obstacle avoidance cost function while satisfying the control input constraint and the dangerous area avoidance constraint through the virtual domain inverse kinematics method; and controlling the robot to avoid obstacles according to the target obstacle avoidance control strategy.

[0051] The embodiments of the present application can flexibly adjust the obstacle avoidance strategy in real time according to environmental changes, thereby ensuring that the robot can avoid obstacles efficiently and safely in an environment that is constantly changing and full of uncertain factors.

[0052] It should be noted that the execution subject of the embodiment of the present application is an electronic device, which is a control device of the robot, which can be built into the robot or connected to the robot as a peripheral. The electronic device may include but is not limited to mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs (Televisions), desktop computers, etc., or any electronic device that can achieve the above functions, and the embodiment of the present application does not specifically limit this. The following uses the electronic device as an example of the execution subject to illustrate the following embodiments of the present application.

[0053] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0054] Please refer to Figure 1 , Figure 1 A flowchart diagram of the first embodiment of the robot obstacle avoidance method of the present application.

[0055] The present application proposes a robot obstacle avoidance method according to a first embodiment, comprising steps S100 to S300:

[0056] Step S100, obtaining a real-time updated operation space dangerous area existence probability map, a preset obstacle avoidance cost function, and a preset control input constraint condition, and determining a dangerous area avoidance constraint condition according to the operation space dangerous area existence probability map;

[0057] Those skilled in the art will know that the operating space refers to the set of all possible positions and postures that a robot can reach when performing a task. It includes not only the position and posture of the robot itself, but also the interaction space between the robot and the environment, such as the range of space that the robot's arm or mobile platform can reach. The danger zone refers to the position in the robot's operating space where there are dangers (such as potential risks or obstacles) that may pose a threat to the robot, causing damage to the robot or mission failure.

[0058] Generally speaking, danger zones are divided into static danger zones and dynamic danger zones. Static danger zones refer to the locations of fixed obstacles (such as walls, furniture, etc.) in the operating space, and dynamic danger zones refer to the locations of moving obstacles or changing environmental factors (such as pedestrians, moving objects, etc.).

[0059] In this embodiment, the probability map of dangerous areas in the operation space is an updated map that records the probability of each position in the robot's operation space becoming a dangerous area, or the probability of each position being dangerous. The probability map of dangerous areas in the operation space can be updated in real time by integrating sensor data fusion and prior knowledge, that is, integrating the surrounding environment data collected in real time by various sensors (such as lidar, visual camera, ultrasonic sensor, etc.) from the robot or other equipment, and combining historical surrounding environment data and prior knowledge to determine whether each position in the operation space is dangerous and the probability of danger, thereby constructing a real-time updated probability map of dangerous areas in the operation space.

[0060] It should be noted that, in this embodiment, a danger probability threshold may be preset, and the location is marked as a danger zone only when the probability of danger existing is greater than the danger probability threshold.

[0061] It should be noted that, in this embodiment, control input refers to the command sent by the robot control system to the robot actuator to drive the robot to move or perform specific actions. The control input determines how the robot moves, and generally includes linear control input, angular control input and mixed control input. Among them, linear control input such as longitudinal thrust, lateral thrust, etc. are used to control the linear motion of the robot, angular control input such as steering torque, rotation speed, etc. are used to control the rotation or rotation of the robot, and mixed control input combines linear control input and angular control input to achieve more complex motion.

[0062] It is not difficult to understand that control inputs usually have a certain range limit to prevent the robot from exceeding its physical limits or causing danger, and can be adjusted based on real-time environmental information to adapt to changing environmental conditions.

[0063] In this embodiment, the control input constraint condition is a range limit of the robot's control input determined comprehensively based on information such as the robot's physical characteristics, the task currently being executed, and the environment in which it is located.

[0064] In addition, it should be noted that the danger zone avoidance constraint is a constraint determined based on the probability map of the danger zone in the operation space, which is used to prevent the robot from entering the danger zone and ensure the robot's safe obstacle avoidance.

[0065] For example, in a feasible implementation manner, the step of determining the dangerous area avoidance constraint condition according to the dangerous area existence probability map of the operation space may include steps S110 to S120:

[0066] Step S110, determining the dangerous area coordinates and the safety distance threshold of the dangerous area in the operation space based on the probability map of the dangerous area in the operation space;

[0067] It should be noted that, in this embodiment, the coordinates of the dangerous area may refer to the coordinates of the center point of the dangerous area, the coordinates of the boundary points of the dangerous area, or the coordinates of each point in the dangerous area. The safety distance threshold refers to the minimum safety distance that the robot must maintain from the coordinates of the dangerous area in order to avoid collision or threat with the dangerous area, that is, the coordinate difference (that is, the distance) between the robot's own coordinates and the coordinates of the dangerous area should be greater than or equal to the safety distance threshold. Once it is less than the safety distance threshold, the robot may encounter danger, resulting in damage to the robot or mission failure.

[0068] It is not difficult to understand that the probability of danger existing at positions corresponding to different coordinates in the danger zone is different, and the threat posed by the possible danger to the robot is also different. Therefore, the greater the probability of danger, the greater the danger posed to the robot by the possible danger, and the greater the safety distance threshold corresponding to the coordinate should be. That is, in this embodiment, when the danger zone coordinates refer to the coordinates of the center point of the danger zone, a safety distance threshold can be set for each center point of the danger zone, and when the danger zone coordinates refer to the coordinates of the boundary points of the danger zone, a safety distance threshold can be set for each boundary point of the danger zone, and when the danger zone coordinates refer to the coordinates of each point in the danger zone, a safety distance threshold can be set for each point in the danger zone.

[0069] It is worth mentioning that in this embodiment, the safety distance threshold can be based on the real-time update of the probability map of dangerous areas in the operating space, and the corresponding algorithm or model is used to evaluate the probability of danger and the type of danger at each position in the operating space. Then, based on the probability of danger and the type of danger at each position, the threat that each dangerous area coordinate may cause to the robot, that is, the degree of danger, is evaluated, and the corresponding safety distance threshold is estimated based on factors such as the robot size and the needs.

[0070] In this embodiment, the safety distance threshold can be synchronously estimated and marked on the probability map of dangerous areas in the operating space when the probability map of dangerous areas in the operating space is updated in real time, so as to facilitate the robot to directly obtain the safety distance threshold of the coordinates of each dangerous area when avoiding obstacles. Alternatively, only information such as the probability of danger and the type of danger at each position in the operating space can be marked, and estimated in real time when avoiding obstacles.

[0071] For example, in a feasible implementation, step S110 may include steps S111 to S112:

[0072] Step S111, obtaining the dangerous area coordinates and the dangerous coefficient of the dangerous area in the operation space from the dangerous area existence probability map of the operation space;

[0073] It should be noted that the risk factor is a parameter used to quantify the degree of risk, and the higher the value, the greater the risk.

[0074] In this embodiment, when the coordinates of the danger zone are the coordinates of the center point of the danger zone, that is, each danger zone has only one danger zone coordinate, the danger coefficient quantifies the danger level of the entire danger zone, that is, there is a danger coefficient corresponding to each danger zone, and when the coordinates of the danger zone are the coordinates of the boundary point of the danger zone, or the coordinates of each point in the danger zone, the danger coefficient quantifies the danger level of the position corresponding to the danger zone coordinate.

[0075] It is not difficult to understand that in this embodiment, when the probability map of dangerous areas in the operating space is updated in real time, the risk factor can be synchronously evaluated and marked on the probability map of dangerous areas in the operating space, so as to directly obtain the risk factor when avoiding obstacles. Alternatively, only information such as the probability of danger and the type of danger at each position in the operating space can be marked, and the risk factor can be evaluated in real time when avoiding obstacles.

[0076] Step S112, substituting the risk factor and the preset safety distance reference value into a preset safety distance threshold calculation formula to obtain the safety distance threshold of the dangerous area.

[0077] The calculation formula of the safety distance threshold is:

[0078]

[0079] Among them, e w is the safety distance threshold, L o is the safety distance reference value, D r Is the risk factor.

[0080] It should be noted that the safety distance reference value refers to the minimum distance that the robot should maintain from any obstacle without any additional risk factors. The safety distance reference value is a fixed value pre-set based on factors such as the robot's size, speed, and even the type of hazard.

[0081] In this embodiment, the safety distance threshold calculation formula is used to calculate the safety distance threshold.

[0082] In addition to the above formula, the following formula can also be used as the safety distance threshold calculation formula:

[0083] e w =Lo +K·D r ;

[0084] Among them, K is a preset adjustment coefficient, which is used to control the influence of the risk factor on the safety distance threshold.

[0085] This implementation calculates the safety distance threshold by combining the hazard factor and the safety distance baseline value, thereby reducing false alarms or overly conservative behavior caused by a single threshold. The safety distance threshold can be flexibly adjusted according to changes in the hazard factor to adapt to different environmental conditions and task requirements, effectively avoiding the occurrence of collision accidents, and thereby improving the efficiency of robot task execution while ensuring safety.

[0086] Step S120: determining a constraint condition for avoiding a dangerous area according to the dangerous area coordinates and the safety distance threshold.

[0087] In this implementation, for each dangerous area coordinate, an avoidance constraint equation is constructed according to its corresponding safety distance threshold, for example:

[0088] ||(xx w )||2+||(yy w )||2≥e w ;

[0089] Among them, x and y are the coordinates of the robot itself, x w and w is the coordinate of the dangerous area, e w is the safety distance threshold.

[0090] After constructing the avoidance constraint equations for each dangerous area coordinate, this embodiment can directly summarize the avoidance constraint equations for each dangerous area coordinate as the dangerous area avoidance constraint conditions for this robot's obstacle avoidance, to guide the robot on how to plan the path to avoid entering the dangerous area, which may cause damage to the robot or mission failure.

[0091] By dynamically monitoring and identifying dangerous areas and setting a reasonable safety distance threshold, this implementation can effectively avoid contact with dangerous areas and significantly improve the safety of task execution. Since the dangerous area avoidance constraints are dynamically adjusted according to real-time information, this implementation can enable the robot to better cope with unpredictable environmental changes, thereby enhancing the robustness of the system and ensuring the safety of the robot's obstacle avoidance. By accurately determining dangerous areas and safety distances, this implementation can reduce unnecessary obstacle avoidance behaviors and help the robot find the optimal path in a complex environment, thereby reducing mutual interference with other objects or robots, allowing the robot to complete obstacle avoidance tasks more efficiently and safely.

[0092] In addition to the above implementation, this embodiment can also directly set the danger zone avoidance constraint condition as: prohibiting the robot's coordinates from coinciding with a position where the probability of danger is greater than a preset probability threshold, based on the probability of danger at each position in the real-time updated operation space danger zone existence probability map. Alternatively, the danger level of each position in the operation space is quantified by the danger coefficient, and then the danger zone avoidance constraint condition is set as: prohibiting the robot's coordinates from coinciding with a position where the danger coefficient is greater than a preset coefficient threshold.

[0093] In addition, it should be noted that the obstacle avoidance cost function is a predefined function used to quantify the costs of different obstacle avoidance control strategies. The obstacle avoidance cost function can be set according to the actual needs of the user. For example, when the user focuses on green energy consumption and control smoothness, a function that can quantify the energy consumption cost and control smoothness cost can be set as the obstacle avoidance cost function, thereby minimizing the energy consumption and control change rate of obstacle avoidance.

[0094] Exemplarily, in a feasible implementation manner, the control input includes longitudinal thrust and steering torque, and the obstacle avoidance cost function is:

[0095]

[0096] Among them, J is the cost value of the obstacle avoidance cost function, τ u is the longitudinal thrust, τ r is the steering torque, t is the time, t f is the preset end time, is the upper limit of the longitudinal thrust.

[0097] In this embodiment, the end time t represents a time point at a preset time interval from the current moment, which is used to guide the robot to plan from the current moment when avoiding obstacles. t=0 represents the current moment, τ u (t) represents the longitudinal thrust at time t, τ r (t) represents the steering torque at time t, and from t = 0 to t = t f The control inputs of the longitudinal torque and steering torque at each moment in the preset time interval are a set of control inputs in chronological order, which is the obstacle avoidance control strategy. The cost value of the obstacle avoidance cost function is used to quantify the cost of the obstacle avoidance control strategy.

[0098] This implementation method aims at green energy consumption and control smoothness. The control input includes longitudinal thrust and steering torque, that is, the robot avoids obstacles through longitudinal thrust and steering torque. Accordingly, when designing the obstacle avoidance cost function, a function that can quantify the energy consumption and control smoothness of the longitudinal thrust and steering torque is set as the obstacle avoidance cost function, that is, the cost value of the obstacle avoidance cost function, which should be able to reflect the energy consumption cost and control smoothness cost of an obstacle avoidance control strategy composed of a set of longitudinal thrust and steering torque within a preset time interval from the current moment.

[0099] Step S200, using a virtual domain inverse kinematics method, solving a target obstacle avoidance control strategy that minimizes the cost value of the obstacle avoidance cost function while satisfying the control input constraint condition and the dangerous area avoidance constraint condition;

[0100] As known to those skilled in the art, Virtual Domain Inverse Kinematics (VDIK) is a technique for solving optimal control problems, especially when a fast solution is required. The main idea of ​​this method is to simplify the optimization process by converting the form of the problem, thereby increasing the speed of solution. Virtual Domain Inverse Kinematics converts the original nonlinear programming problem into a more manageable form, that is, maps the original nonlinear programming problem to a new problem in the virtual domain, so that the nonlinear constraints of the original problem become simpler or easier to handle, thereby solving the problem more quickly and efficiently in the virtual domain, obtaining the optimal solution, and mapping it back to the original space, thereby obtaining the solution to the original problem.

[0101] This embodiment adopts a virtual domain inverse kinematics method to map the nonlinear optimal control problem of solving the optimal obstacle avoidance control strategy into the virtual domain, so that the control input upper limit constraint and the dangerous area avoidance constraint become simpler or easier to handle in the virtual domain, thereby selecting a suitable optimization algorithm (such as gradient descent method, Newton method, etc.) to quickly and efficiently solve the optimal control problem, and map the solution back to the original domain, thereby obtaining a target obstacle avoidance control strategy that minimizes the cost value of the obstacle avoidance cost function while satisfying the control input constraint and the dangerous area avoidance constraint.

[0102] This embodiment simplifies the problem-solving process and reduces the computational complexity through the virtual domain inverse kinematics method, thereby finding the optimal obstacle avoidance control strategy under complex constraints, enabling the robot to respond faster and effectively improving the robot's adaptability in uncertain environments.

[0103] Step S300, controlling the robot to avoid obstacles according to the target obstacle avoidance control strategy.

[0104] After solving and obtaining the target obstacle avoidance control strategy, this embodiment controls the robot to perform corresponding obstacle avoidance actions according to the target obstacle avoidance control strategy, thereby completing obstacle avoidance efficiently and safely.

[0105] This embodiment first obtains a real-time updated probability map of dangerous areas in the operating space, a preset obstacle avoidance cost function, and a preset control input constraint condition, and determines the dangerous area avoidance constraint condition based on the probability map of dangerous areas in the operating space. Secondly, through the virtual domain inverse kinematics method, a target obstacle avoidance control strategy is solved to minimize the cost value of the obstacle avoidance cost function while satisfying the control input constraint condition and the dangerous area avoidance constraint condition. Finally, according to the target obstacle avoidance control strategy, the robot is controlled to avoid obstacles, so that the present application can flexibly adjust the obstacle avoidance strategy according to environmental changes in real time, thereby ensuring that the robot can avoid obstacles efficiently and safely in a constantly changing environment full of uncertainties.

[0106] This embodiment can effectively solve the problem of safe obstacle avoidance of the robot in an uncertain environment by introducing a real-time updated probability map of dangerous areas in the operating space and a virtual domain inverse kinematics method, thereby improving the robot's autonomy and task execution efficiency.

[0107] Based on the above-mentioned first embodiment, a robot obstacle avoidance method according to a second embodiment of the present application is proposed.

[0108] In the second embodiment of the present application, the same or similar contents as those in the above embodiments can be referred to the above introduction and will not be described in detail later.

[0109] Please refer to Figure 2 , Figure 2 A flowchart diagram of the second embodiment of the robot obstacle avoidance method of the present application.

[0110] In this embodiment, the method may further include steps S410 to S420:

[0111] Step S410, obtaining obstacle parameters of the operation space in real time through a preset sensor, and inputting the obstacle parameters into a pre-trained dangerous area discrimination model to obtain dangerous area coordinates and dangerous coefficients of dangerous areas in the operation space;

[0112] In this embodiment, the preset sensor may refer to a camera, radar, GPS, indoor positioning equipment, laser, gyroscope or other sensors carried by the robot, or may be a sensor installed on other equipment in the operating space that can inspect the operating space, or may include both types of sensors.

[0113] It should be noted that obstacle parameters refer to information describing the physical properties of obstacles, such as the type, position, shape, size, quantity, and speed of movement of obstacles. Taking a camera as an example, obstacles in the surrounding environment can be photographed by the camera, and then the type, position, shape, size, quantity, and speed of movement of obstacles can be identified through the corresponding image recognition algorithm. Accordingly, when there are multiple sensors, the data collected by each sensor can be fused to obtain the final obstacle parameters.

[0114] In addition, it should be noted that the danger zone discrimination model is pre-built and can predict the probability of danger and the type of danger at each location in the operating space based on the input obstacle parameters, and then evaluate the degree of danger. It quantifies the degree of danger through the danger coefficient, marks the locations where the probability of danger is greater than the preset probability threshold as danger zones, and outputs the corresponding neural network model of the danger zone coordinates.

[0115] In this embodiment, a large number of obstacle parameters can be collected in advance as training data, and annotated by industry experts to obtain corresponding training sets, test sets and validation sets, and then a suitable basic neural network model is selected for training, so as to obtain a danger zone discrimination model that can accurately predict the danger probability, danger type, danger coefficient and other information according to the input obstacle parameters, and output the danger zone coordinates.

[0116] Step S420: updating the existence probability map of the dangerous area in the operation space in real time according to the dangerous area coordinates and the dangerous coefficient.

[0117] This embodiment monitors obstacles in the operating space in real time, obtains real-time obstacle parameters, and inputs them into the danger zone discrimination model, determines the coordinates and danger coefficients of the danger zone in the operating space in real time, and thus updates the probability map of the danger zone in the operating space in real time, ensuring that the robot can better adapt to the changing environmental conditions, accurately identify potential danger zones, and take corresponding obstacle avoidance measures to avoid obstacles safely and efficiently, thereby significantly improving the safety, adaptability and efficiency of the robot in complex environments.

[0118] Based on the above-mentioned first embodiment, a robot obstacle avoidance method according to the third embodiment of the present application is proposed.

[0119] In the third embodiment of the present application, the same or similar contents as those in the above embodiments can be referred to the above introduction and will not be repeated later.

[0120] Please refer to Figure 3 , Figure 3 A flowchart diagram of the third embodiment of the robot obstacle avoidance method of the present application.

[0121] In this embodiment, the method may further include steps S510 to S530:

[0122] Step S510, substituting the target obstacle avoidance control strategy into a preset robot dynamics model to obtain a target obstacle avoidance trajectory;

[0123] Those skilled in the art will appreciate that a robot dynamics model is a mathematical model that describes the motion characteristics of a robot and is used to simulate the motion behavior of the robot under different control inputs.

[0124] In this embodiment, the robot is modeled in advance to obtain its dynamic model, that is, the robot dynamic model, so that the target obstacle avoidance control strategy is input into the robot dynamic model to simulate the robot's action behavior under a series of control inputs of the target obstacle avoidance control strategy, so as to obtain the ideal running trajectory when the robot is controlled to avoid obstacles in strict accordance with the target obstacle avoidance control strategy, that is, the target obstacle avoidance trajectory.

[0125] Step S520, monitoring the motion trajectory of the robot in real time to obtain an actual obstacle avoidance trajectory;

[0126] It should be noted that, in this embodiment, the actual obstacle avoidance trajectory is the actual motion trajectory of the robot when performing the obstacle avoidance action under the guidance of the target obstacle avoidance control strategy. The actual obstacle avoidance trajectory can be monitored by sensors carried by the robot itself or sensors installed on other devices in the surrounding environment.

[0127] Step S530, when it is detected that the trajectory deviation between the actual obstacle avoidance trajectory and the target obstacle avoidance trajectory is greater than the preset trajectory deviation, return to execute: the step of obtaining the real-time updated operation space dangerous area existence probability map, the preset obstacle avoidance cost function, and the preset control input constraint condition.

[0128] It should be noted that trajectory deviation refers to the difference between the target obstacle avoidance trajectory and the actual obstacle avoidance trajectory, which is used to evaluate the effectiveness of the robot's obstacle avoidance action. The preset trajectory deviation is a pre-set threshold used to determine whether the deviation between the actual obstacle avoidance trajectory and the target obstacle avoidance trajectory is too large.

[0129] It is worth mentioning that the preset trajectory deviation is related to the type of robot and the task it performs. Different types of robots that perform different tasks have different preset trajectory deviations. For example, the preset trajectory deviation corresponding to a sweeping robot may be greater than that of a medical surgery robot.

[0130] After solving the target obstacle avoidance control strategy, this embodiment substitutes it into the robot dynamics model to calculate the expected state (expected position and expected posture) of the robot at different time points when avoiding obstacles, thereby drawing the ideal motion trajectory of the robot when performing obstacle avoidance actions, that is, the target obstacle avoidance trajectory, and then monitors the actual state of the robot when performing obstacle avoidance actions according to the target obstacle avoidance control strategy in real time to form an actual obstacle avoidance trajectory, and calculates the trajectory deviation between the two. When the trajectory deviation is greater than the preset trajectory deviation and it is determined that the actual obstacle avoidance trajectory deviates from the target obstacle avoidance trajectory, the real-time updated probability map of the existence of dangerous areas in the operating space, the preset obstacle avoidance cost function, and the preset control input constraints are re-acquired to update the target obstacle avoidance control strategy, thereby ensuring that the robot is always on a safe obstacle avoidance path.

[0131] This embodiment can reduce the deviation between the actual obstacle avoidance trajectory and the target obstacle avoidance trajectory by continuously updating the target obstacle avoidance trajectory, thereby improving the accuracy of the obstacle avoidance action, so that the robot can better adapt to the changing environmental conditions and avoid the robot continuing to perform obstacle avoidance actions that may cause a collision when the deviation between the actual obstacle avoidance trajectory and the target obstacle avoidance trajectory is large.

[0132] Through this embodiment, the robot can perform obstacle avoidance actions more accurately and can adjust the obstacle avoidance strategy in time when encountering unexpected situations, thereby improving its safety, adaptability and accuracy in complex environments.

[0133] Based on the above-mentioned first embodiment, a robot obstacle avoidance method according to a fourth embodiment of the present application is proposed.

[0134] In the fourth embodiment of the present application, the same or similar contents as those in the above embodiments can be referred to the above introduction and will not be described in detail later.

[0135] Please refer to Figure 4 , Figure 4 A flowchart diagram of the fourth embodiment of the robot obstacle avoidance method of the present application.

[0136] In this embodiment, the method may further include steps S610 to S620:

[0137] Step S610, obtaining the robot coordinates of the robot in real time, and obtaining the dangerous area coordinates of the dangerous area in the operation space from the dangerous area existence probability map in real time;

[0138] Step S620, when it is detected that the coordinate difference between the robot coordinates and the dangerous area coordinates is less than a preset coordinate difference threshold, triggers the execution of: the step of obtaining a real-time updated probability map of the dangerous area in the operating space, a preset obstacle avoidance cost function, and a preset control input constraint condition.

[0139] In this embodiment, the coordinate difference refers to the distance difference between the robot coordinates and the dangerous area coordinates, and the preset coordinate difference threshold is a pre-set distance threshold used to determine the proximity between the robot and the dangerous area.

[0140] In this embodiment, the preset coordinate difference threshold is divided into a first preset coordinate difference threshold and a second preset coordinate difference threshold, wherein the first preset coordinate difference threshold is greater than the second preset coordinate difference threshold.

[0141] In this embodiment, when the coordinate difference is less than the first preset coordinate difference threshold, it indicates that there may be danger in the original route of the robot and it needs to be avoided in advance. If the robot is performing an obstacle avoidance task at this time, no processing is performed. If the robot is not performing an obstacle avoidance task at this time, or the coordinate difference is still less than the first preset coordinate difference threshold after completing an obstacle avoidance task, a real-time updated probability map of the existence of dangerous areas in the operating space, a preset obstacle avoidance cost function, and preset control input constraints are obtained to generate a target obstacle avoidance control strategy to control the robot to perform obstacle avoidance tasks and avoid possible dangers in the original route.

[0142] In addition, when the coordinate difference is less than the second preset coordinate difference threshold, it means that the robot has a deviation when performing the obstacle avoidance task and fails to accurately complete the obstacle avoidance goal. Instead, it is getting closer to the dangerous area. It is necessary to immediately obtain the real-time updated probability map of the dangerous area in the operating space, the preset obstacle avoidance cost function, and the preset control input constraints, and regenerate the target obstacle avoidance control strategy to stay away from the dangerous area.

[0143] It is not difficult to understand that a first preset coordinate difference threshold and a second preset coordinate difference threshold can be set for each dangerous area coordinate in real time, and marked in the real-time updated operation space dangerous area existence probability map, or a unified and fixed first preset coordinate difference threshold and second preset coordinate difference threshold can be used. When setting the first preset coordinate difference threshold and the second preset coordinate difference threshold, the robot size, the type of task it is engaged in, and even the type of danger and the danger coefficient corresponding to the dangerous area coordinate can be combined for flexible setting.

[0144] This implementation method monitors the distance between the robot and the dangerous area in real time, thereby triggering the obstacle avoidance task when approaching the dangerous area, generating a target obstacle avoidance control strategy, and controlling the robot to avoid obstacles. At the same time, when the original target obstacle avoidance control strategy fails to execute, or a new dangerous area suddenly appears, or the original dangerous area suddenly approaches, causing the robot to get closer and closer to the dangerous area, the target obstacle avoidance control strategy is regenerated, and the robot is controlled to avoid obstacles urgently according to the new target obstacle avoidance control strategy, thereby enabling the robot to quickly respond to changes in the surrounding environment and make immediate obstacle avoidance reactions to prevent the robot from being in danger and ensure the robot's safety.

[0145] In addition, please refer to Figure 5 , Figure 5 This is a schematic diagram of the module structure of the robot obstacle avoidance device according to an embodiment of the present application;

[0146] The present application also provides a robot obstacle avoidance device, the robot obstacle avoidance device comprising:

[0147] The first obstacle avoidance module 10 is used to obtain a real-time updated operation space dangerous area existence probability map, a preset obstacle avoidance cost function, and a preset control input constraint condition, and determine a dangerous area avoidance constraint condition according to the operation space dangerous area existence probability map;

[0148] The second obstacle avoidance module 20 is used to solve the target obstacle avoidance control strategy that minimizes the cost value of the obstacle avoidance cost function while satisfying the control input constraint condition and the dangerous area avoidance constraint condition through a virtual domain inverse kinematics method;

[0149] The third obstacle avoidance module 30 is used to control the robot to avoid obstacles according to the target obstacle avoidance control strategy.

[0150] In one embodiment, the control input includes longitudinal thrust and steering torque, and the obstacle avoidance cost function is:

[0151]

[0152] Among them, J is the cost value of the obstacle avoidance cost function, τ u is the longitudinal thrust, τ r is the steering torque, t is the time, t f is the preset end time, is the upper limit of the longitudinal thrust.

[0153] In one embodiment, the first obstacle avoidance module 10 is further used for:

[0154] Determine the dangerous area coordinates and the safety distance threshold of the dangerous area in the operating space based on the probability map of the dangerous area in the operating space;

[0155] The dangerous area avoidance constraint condition is determined according to the dangerous area coordinates and the safety distance threshold.

[0156] In one embodiment, the first obstacle avoidance module 10 is further used for:

[0157] Obtaining the dangerous area coordinates and the dangerous coefficient of the dangerous area in the operation space from the dangerous area existence probability map of the operation space;

[0158] Substituting the risk factor and the preset safety distance reference value into a preset safety distance threshold calculation formula to obtain the safety distance threshold of the danger zone;

[0159] The calculation formula of the safety distance threshold is:

[0160]

[0161] Among them, e w is the safety distance threshold, L o is the safety distance reference value, D r Is the risk factor.

[0162] In one embodiment, the robot obstacle avoidance device further includes a fourth obstacle avoidance module (not shown) for:

[0163] Obtaining obstacle parameters of the operation space in real time through a preset sensor, and inputting the obstacle parameters into a pre-trained dangerous area discrimination model to obtain dangerous area coordinates and a dangerous coefficient of the dangerous area in the operation space;

[0164] The existence probability map of the dangerous area in the operation space is updated in real time according to the dangerous area coordinates and the dangerous coefficient.

[0165] In one embodiment, the robot obstacle avoidance device further includes a fifth obstacle avoidance module (not shown) for:

[0166] Substituting the target obstacle avoidance control strategy into a preset robot dynamics model to obtain a target obstacle avoidance trajectory;

[0167] Monitor the motion trajectory of the robot in real time to obtain an actual obstacle avoidance trajectory;

[0168] When it is detected that the trajectory deviation between the actual obstacle avoidance trajectory and the target obstacle avoidance trajectory is greater than the preset trajectory deviation, return to execute: the step of obtaining the real-time updated operation space dangerous area existence probability map, the preset obstacle avoidance cost function, and the preset control input constraint condition.

[0169] In one embodiment, the robot obstacle avoidance device further includes a sixth obstacle avoidance module (not shown) for:

[0170] Acquire the robot coordinates of the robot in real time, and acquire the dangerous area coordinates of the dangerous area in the operation space from the dangerous area existence probability map in real time;

[0171] When it is detected that the coordinate difference between the robot coordinates and the dangerous area coordinates is less than a preset coordinate difference threshold, the execution is triggered: the steps of obtaining a real-time updated probability map of the dangerous area in the operating space, a preset obstacle avoidance cost function, and a preset control input constraint condition.

[0172] The robot obstacle avoidance device provided by the present application adopts the robot obstacle avoidance method in the above embodiment, which can solve the technical problem of efficient and safe obstacle avoidance of the robot in an uncertain environment. Compared with the prior art, the beneficial effects of the robot obstacle avoidance device provided by the present application are the same as the beneficial effects of the robot obstacle avoidance method provided by the above embodiment, and the other technical features of the robot obstacle avoidance device are the same as the features disclosed in the robot obstacle avoidance method in the above embodiment, which will not be repeated here.

[0173] In addition, please refer to Figure 6 , Figure 6 Schematic diagram of the device structure of the hardware operating environment involved in the robot obstacle avoidance method in the embodiment of the present application.

[0174] The present application also provides an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the robot obstacle avoidance method in the above-mentioned embodiment.

[0175] Reference below Figure 6 , which shows a schematic diagram of the structure of an electronic device suitable for implementing an embodiment of the present application. The electronic device in the embodiment of the present application is a control device of the robot, which can be built into the robot or connected to the robot as a peripheral. The electronic device includes but is not limited to mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs (Televisions), desktop computers, etc., or any electronic device that can implement the above functions. Figure 6 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0176] like Figure 6As shown, the electronic device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the electronic device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows an electronic device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0177] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0178] The electronic device provided by the present application adopts the robot obstacle avoidance method in the above embodiment, which can solve the technical problem of efficient and safe obstacle avoidance of the robot in an uncertain environment. Compared with the prior art, the beneficial effects of the electronic device provided by the present application are the same as the beneficial effects of the robot obstacle avoidance method provided by the above embodiment, and other technical features in the electronic device are the same as the features disclosed in the robot obstacle avoidance method in the above embodiment, which will not be repeated here.

[0179] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0180] In addition, the present application also provides a computer-readable storage medium having computer-readable program instructions (ie, computer program) stored thereon, and the computer-readable program instructions are used to execute the robot obstacle avoidance method in the above-mentioned embodiment.

[0181] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0182] The computer-readable storage medium may be included in the electronic device, or may exist independently without being installed in the electronic device.

[0183] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by an electronic device, the electronic device: obtains a real-time updated probability map of the existence of dangerous areas in the operating space, a preset obstacle avoidance cost function, and a preset control input constraint condition, and determines the dangerous area avoidance constraint condition based on the probability map of the existence of dangerous areas in the operating space; solves the target obstacle avoidance control strategy that minimizes the cost value of the obstacle avoidance cost function while satisfying the control input constraint condition and the dangerous area avoidance constraint condition through a virtual domain inverse kinematics method; and controls the robot to avoid obstacles according to the target obstacle avoidance control strategy.

[0184] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0185] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0186] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0187] The computer-readable storage medium provided by the present application stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned robot obstacle avoidance method, which can solve the technical problem of efficient and safe obstacle avoidance of robots in uncertain environments. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the robot obstacle avoidance method provided by the above-mentioned embodiment, and will not be elaborated here.

[0188] In addition, an embodiment of the present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the robot obstacle avoidance method in the above embodiment.

[0189] The computer program product provided by this application can solve the technical problem of efficient and safe obstacle avoidance of robots in uncertain environments. Compared with the prior art, the beneficial effects of the computer program product provided by the embodiment of this application are the same as the beneficial effects of the robot obstacle avoidance method provided by the above embodiment, which will not be repeated here.

[0190] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A robot obstacle avoidance method, characterized in that: The method comprises: Obtaining a real-time updated probability map of the existence of a dangerous area in the operating space, a preset obstacle avoidance cost function, and a preset control input constraint condition, and determining a dangerous area avoidance constraint condition based on the probability map of the existence of a dangerous area in the operating space; By using a virtual domain inverse kinematics method, a target obstacle avoidance control strategy is solved to minimize the cost value of the obstacle avoidance cost function while satisfying the control input constraint condition and the dangerous area avoidance constraint condition; According to the target obstacle avoidance control strategy, the robot is controlled to avoid obstacles.

2. The robot obstacle avoidance method according to claim 1, characterized in that: The control input includes longitudinal thrust and steering torque, and the obstacle avoidance cost function is: Among them, J is the cost value of the obstacle avoidance cost function, τ u is the longitudinal thrust, τ r is the steering torque, t is the time, t f is the preset end time, is the upper limit of the longitudinal thrust.

3. The robot obstacle avoidance method according to claim 1, characterized in that: The step of determining the constraint conditions for avoiding the dangerous area according to the probability map of the dangerous area in the operation space comprises: Determine the dangerous area coordinates and the safety distance threshold of the dangerous area in the operating space based on the probability map of the dangerous area in the operating space; The dangerous area avoidance constraint condition is determined according to the dangerous area coordinates and the safety distance threshold.

4. The robot obstacle avoidance method according to claim 3, characterized in that: The step of determining the dangerous area coordinates and the safety distance threshold of the dangerous area in the operation space based on the dangerous area existence probability map in the operation space includes: Obtaining the dangerous area coordinates and the dangerous coefficient of the dangerous area in the operation space from the dangerous area existence probability map of the operation space; Substituting the risk factor and the preset safety distance reference value into a preset safety distance threshold calculation formula to obtain the safety distance threshold of the danger zone; The calculation formula of the safety distance threshold is: Among them, e w is the safety distance threshold, L o is the safety distance reference value, D r Is the risk factor.

5. The robot obstacle avoidance method according to claim 3, characterized in that: The method further comprises: Obtaining obstacle parameters of the operation space in real time through a preset sensor, and inputting the obstacle parameters into a pre-trained dangerous area discrimination model to obtain dangerous area coordinates and a dangerous coefficient of the dangerous area in the operation space; The existence probability map of the dangerous area in the operation space is updated in real time according to the dangerous area coordinates and the dangerous coefficient.

6. The robot obstacle avoidance method according to claim 1, characterized in that: The method further comprises: Substituting the target obstacle avoidance control strategy into a preset robot dynamics model to obtain a target obstacle avoidance trajectory; Monitor the motion trajectory of the robot in real time to obtain an actual obstacle avoidance trajectory; When it is detected that the trajectory deviation between the actual obstacle avoidance trajectory and the target obstacle avoidance trajectory is greater than the preset trajectory deviation, return to execute: the step of obtaining the real-time updated operation space dangerous area existence probability map, the preset obstacle avoidance cost function, and the preset control input constraint condition.

7. The robot obstacle avoidance method according to claim 1, characterized in that: The method further comprises: Acquire the robot coordinates of the robot in real time, and acquire the dangerous area coordinates of the dangerous area in the operation space from the dangerous area existence probability map in real time; When it is detected that the coordinate difference between the robot coordinates and the dangerous area coordinates is less than a preset coordinate difference threshold, the execution is triggered: the steps of obtaining a real-time updated probability map of the dangerous area in the operating space, a preset obstacle avoidance cost function, and a preset control input constraint condition.

8. A robot obstacle avoidance device, characterized in that: The device comprises: The first obstacle avoidance module is used to obtain a real-time updated operation space dangerous area existence probability map, a preset obstacle avoidance cost function, and a preset control input constraint condition, and determine the dangerous area avoidance constraint condition according to the operation space dangerous area existence probability map; A second obstacle avoidance module is used to solve, by a virtual domain inverse kinematics method, a target obstacle avoidance control strategy that minimizes the cost value of the obstacle avoidance cost function while satisfying the control input constraint condition and the dangerous area avoidance constraint condition; The third obstacle avoidance module is used to control the robot to avoid obstacles according to the target obstacle avoidance control strategy.

9. An electronic device, characterized in that: include: A memory, a processor, and a robot obstacle avoidance program stored in the memory and executable on the processor, wherein the robot obstacle avoidance program, when executed by the processor, implements the robot obstacle avoidance method according to any one of claims 1 to 7.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the robot obstacle avoidance method according to any one of claims 1 to 7 are implemented.

Citation Information

Cited By

  • High-efficiency robot obstacle avoidance control method and system in dynamic environment

    CN119668268A