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

Abstract

The invention relates to a high-efficiency robot obstacle avoidance control method and system in a dynamic environment, and the method comprises the following steps: segmenting an object in the environment, obtaining a static object and a dynamic object, and extracting the center position information of the dynamic object; calculating a motion velocity vector of the dynamic object according to the center position information of the dynamic object; calculating a possible meeting position of the robot and the dynamic object based on the motion velocity vector of the dynamic object; counting the number of dynamic objects in the environment, and determining a hazard prediction constraint based on the number; calculating a first motion vector of the robot and a second motion vector of the dynamic object, and determining an efficient control constraint based thereon; solving steering optimal control based on the danger prediction constraint and the efficient control constraint; and obstacle avoidance control is carried out on the robot through steering optimal control. According to the invention, the robot realizes obstacle avoidance control in a dynamic environment by combining with the visual sensor, so that the robot can work in a complex dynamic environment more effectively and safely.

Description

Technical Field

[0001] The present invention relates to the technical field related to intelligent robots, and in particular to a highly efficient robot obstacle avoidance control method and system in a dynamic environment. Background Art

[0002] In the autonomous application of robots, the intelligent application of robots faces many challenges and key issues, such as autonomous obstacle avoidance of robots, especially in complex dynamic environments, there are still many problems to be solved in terms of obstacle avoidance efficiency, safety and reliability. With the development of robot technology, efficient robot obstacle avoidance control has a broad development prospect in robot applications.

[0003] At present, there are many methods for robot obstacle avoidance control, and the commonly used ones mainly include artificial potential method, speed barrier method and dynamic window method, etc. The artificial potential method is simple and effective, but its disadvantages are also obvious. The robot is prone to jitter during obstacle avoidance movement and the direction of movement is difficult to control. In addition, the randomness of the robot's obstacle avoidance direction makes it inefficient to avoid moving obstacles in a dynamic environment. The speed barrier method is a geometric analysis method that maps the environmental space to the speed space. Its advantages are better obstacle avoidance maneuverability and lower computational cost, but there is also jitter during obstacle avoidance. The dynamic window method's control of obstacle avoidance mainly depends on the weighted setting in the cost function, but the changes in the dynamic environment make it difficult to adjust its weighting, so it is difficult to apply to complex working environments. Summary of the invention

[0004] The purpose of the present invention is to solve at least one of the deficiencies of the prior art and to provide a highly efficient robot obstacle avoidance control method and system in a dynamic environment.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions: Specifically, a highly efficient robot obstacle avoidance control method in a dynamic environment is proposed, including the following: Segment the dynamic and static objects in the environment, obtain static objects and dynamic objects, and extract the center position information of dynamic objects; Calculate the motion velocity vector of the dynamic object according to the center position information of the dynamic object; Based on the motion velocity vector of the dynamic object, the possible encounter position between the robot and the dynamic object is calculated; Count the number of dynamic objects in the environment and determine hazard prediction constraints based on this; calculating a first motion vector of the robot and a second motion vector of the dynamic object, and determining an efficient control constraint based thereon; Solve the steering optimal control based on the danger prediction constraint and the efficient control constraint; The robot is controlled to avoid obstacles through optimal steering control.

[0006] Further, specifically, segmenting the dynamic and static objects in the environment includes: Two channels of visual information in the environment are obtained through the left and right cameras preset on the robot, and the two channels of visual information are input into the DRAM of the robot host. At the same time, feature extraction is performed on the two channels of visual information to obtain feature information, and the two channels of visual information are stereo matched to obtain the position information of the feature points; then, K-means clustering is used to segment the feature points into static objects and dynamic objects based on their feature information, and the center position information of the dynamic objects is extracted.

[0007] Further, specifically, according to the center position information of the dynamic object, the motion velocity vector of the dynamic object is calculated, including: Assume that the center position of the dynamic object at time t is , then the velocity vector of the dynamic object at time t is , T is the time interval between time t and time t-1.

[0008] Further, specifically, based on the motion velocity vector of the dynamic object, the possible encounter position of the robot and the dynamic object is calculated, including: Assume the center position of the robot at the current moment , the center position at time t is , the robot's motion velocity vector is calculated according to the calculation method of the motion velocity vector of the dynamic object , then the robot's motion trajectory can be estimated by the motor encoder information carried by the robot and the Kalman filter equation, then the possible encounter position between the robot and the dynamic object It can be obtained by the intersection of two straight lines determined by the dynamic object and the robot's motion velocity vector.

[0009] Further, specifically, the number of dynamic objects in the environment is counted, and based on this, the hazard prediction constraints are determined, including, Assuming there are N dynamic objects in the environment, the hazard prediction constraint ,in; , , for and the speed of the i-th dynamic object The product of It means to obtain the minimum value of a product, i=1,…,N.

[0010] Further, specifically, a first motion vector of the robot and a second motion vector of the dynamic object are calculated, and based on this, an efficient control constraint is determined, including: Calculate the robot's first motion vector , calculate the second motion vector of the dynamic object ; Assume that the robot is a wheeled robot with left and right wheels. , is the rotation speed of the left and right wheels, then the efficient control constraint is, ; in Expressed as and Inner product operation of vectors; is the threshold value and satisfies ; k is a coefficient and satisfies , and k can be determined experimentally.

[0011] Further, specifically, solving the steering optimal control based on the danger prediction constraint and the efficient control constraint includes: The optimal steering control calculation formula is as follows: ; In the formula ; ; is the weighted penalty matrix; is the reference trajectory of the robot, which is the straight line connecting the given motion initial point and target point; For reference speed control, it is determined according to actual needs; is the maximum value of the control quantity U, that is, the maximum speed of the drive motor. U refers to the speed of the drive motor. , the robot's position Satisfies the following wheeled robot motion model, namely ; In the above formula, R and D are the wheel radius and the distance between the two wheels of the robot respectively, and θ is the turning angle of the robot.

[0012] The present invention also proposes a highly efficient robot obstacle avoidance control system in a dynamic environment, comprising the following: The object state segmentation module is used to segment the dynamic and static objects in the environment, obtain static objects and dynamic objects, and extract the center position information of dynamic objects; A motion velocity vector calculation module, used to calculate the motion velocity vector of the dynamic object according to the center position information of the dynamic object; A possible encounter position calculation module, used for calculating the possible encounter position between the robot and the dynamic object based on the motion velocity vector of the dynamic object; A hazard prediction constraint determination module, used to count the number of dynamic objects in the environment and determine the hazard prediction constraints based on the count; An efficient control constraint determination module, used for calculating a first motion vector of the robot and a second motion vector of the dynamic object, and determining an efficient control constraint based thereon; Steering optimal control calculation module, used to solve the steering optimal control based on the danger prediction constraint and the efficient control constraint; The obstacle avoidance control module is used to control the robot to avoid obstacles through optimal steering control.

[0013] The beneficial effects of the present invention are: The present invention proposes a highly efficient robot obstacle avoidance control method and system in a dynamic environment. By calculating the possible encounter positions between the robot and the dynamic object, the danger prediction constraint and the efficient control constraint are determined, and finally the optimal steering control is solved. The robot is controlled to avoid obstacles through the optimal steering control. The present invention enables the robot to more efficiently achieve obstacle avoidance control in a dynamic environment by combining a visual sensor, thereby enabling the robot to work more effectively and safely in a complex dynamic environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The above and other features of the present disclosure will become more apparent by describing in detail the embodiments shown in the accompanying drawings. The same reference numerals in the accompanying drawings of the present disclosure represent the same or similar elements. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure. For those skilled in the art, other accompanying drawings can be obtained based on these accompanying drawings without creative work. In the accompanying drawings: Figure 1 Shown is a flow chart of a highly efficient robot obstacle avoidance control method in a dynamic environment according to the present invention. DETAILED DESCRIPTION

[0015] The following will be combined with the embodiments and drawings to clearly and completely describe the concept, specific structure and technical effects of the present invention, so as to fully understand the purpose, scheme and effect of the present invention. It should be noted that the embodiments in this application and the features in the embodiments can be combined with each other without conflict. The same reference numerals used throughout the drawings indicate the same or similar parts.

[0016] Example 1, reference Figure 1 The present invention proposes a highly efficient robot obstacle avoidance control method in a dynamic environment, comprising the following steps: Step 110, segment the dynamic and static objects in the environment to obtain static objects and dynamic objects and extract the center position information of the dynamic objects; Step 120, calculating the motion velocity vector of the dynamic object according to the center position information of the dynamic object; Step 130: Calculate the possible encounter position between the robot and the dynamic object based on the motion velocity vector of the dynamic object; Step 140: Count the number of dynamic objects in the environment, and determine the hazard prediction constraints based on the count; Step 150, calculating a first motion vector of the robot and a second motion vector of the dynamic object, and determining an efficient control constraint based thereon; Step 160, solving the steering optimal control based on the danger prediction constraint and the efficient control constraint; Step 170: Perform obstacle avoidance control on the robot through optimal steering control.

[0017] In this embodiment 1, by calculating the possible encounter position between the robot and the dynamic object, the danger prediction constraint and the efficient control constraint are determined, and finally the optimal steering control is solved, and the robot is controlled to avoid obstacles through the optimal steering control. The present invention enables the robot to more efficiently achieve obstacle avoidance control in a dynamic environment by combining a visual sensor, so that the robot can work more effectively and safely in a complex dynamic environment.

[0018] As a preferred embodiment of the present invention, specifically, segmenting the dynamic and static objects in the environment includes: Two channels of visual information in the environment are obtained through the left and right cameras preset on the robot, and the two channels of visual information are input into the DRAM of the robot host. At the same time, feature extraction is performed on the two channels of visual information to obtain feature information, and the two channels of visual information are stereo matched to obtain the position information of the feature points; then, K-means clustering is used to segment the feature points into static objects and dynamic objects based on their feature information, and the center position information of the dynamic objects is extracted.

[0019] As a preferred embodiment of the present invention, specifically, calculating the motion velocity vector of the dynamic object according to the center position information of the dynamic object includes: Assume that the center position of the dynamic object at time t is , then the velocity vector of the dynamic object at time t is , T is the time interval between time t and time t-1. The subscript with m represents X, V and α of the dynamic object, which is used to distinguish the corresponding parameters of the robot.

[0020] As a preferred embodiment of the present invention, specifically, based on the motion velocity vector of the dynamic object, the possible encounter position between the robot and the dynamic object is calculated, including: Assume the center position of the robot at the current moment , the center position at time t is , the robot's motion velocity vector is calculated according to the calculation method of the motion velocity vector of the dynamic object , then the robot's motion trajectory can be estimated by the motor encoder information carried by the robot and the Kalman filter equation, then the possible encounter position between the robot and the dynamic object It can be obtained by the intersection of two straight lines determined by the dynamic object and the robot's motion velocity vector.

[0021] As a preferred embodiment of the present invention, specifically, the number of dynamic objects in the environment is counted, and based on this, the hazard prediction constraints are determined, including: Assuming there are N dynamic objects in the environment, the hazard prediction constraint ,in; , , for and the speed of the i-th dynamic object The product of It means to obtain the minimum value of a product, i=1,…,N.

[0022] As a preferred embodiment of the present invention, specifically, calculating the first motion vector of the robot and the second motion vector of the dynamic object, and determining the efficient control constraint based on the first motion vector of the robot and the second motion vector of the dynamic object, including: Calculate the robot's first motion vector , calculate the second motion vector of the dynamic object ; Assume that the robot is a wheeled robot with left and right wheels. , is the rotation speed of the left and right wheels, then the efficient control constraint is, ; in Expressed as and Inner product operation of vectors; is the threshold value and satisfies ; k is a coefficient and satisfies , and k can be determined experimentally.

[0023] As a preferred embodiment of the present invention, specifically, solving the steering optimal control based on the danger prediction constraint and the efficient control constraint includes: The optimal steering control calculation formula is as follows: ; Here we solve under constraints ( + ) is the optimal control U when it is at its minimum value, namely U*, is a function of (X, U), that is: = (X, U), because X implies control U; is a function of U, = (U).

[0024] In the formula ; ; is the weighted penalty matrix; is the reference trajectory of the robot, which is the straight line connecting the given motion initial point and target point; For reference speed control, it is determined according to actual needs; is the maximum value of the control quantity U, that is, the maximum speed of the drive motor. U refers to the speed of the drive motor. , the robot's position Satisfies the following wheeled robot motion model, namely ; In the above formula, R and D are the wheel radius and the distance between the two wheels of the robot respectively, and θ is the turning angle of the robot.

[0025] The present invention also proposes a highly efficient robot obstacle avoidance control system in a dynamic environment, comprising the following: The object state segmentation module is used to segment the dynamic and static objects in the environment, obtain static objects and dynamic objects, and extract the center position information of dynamic objects; A motion velocity vector calculation module, used to calculate the motion velocity vector of the dynamic object according to the center position information of the dynamic object; A possible encounter position calculation module, used for calculating the possible encounter position between the robot and the dynamic object based on the motion velocity vector of the dynamic object; A hazard prediction constraint determination module, used to count the number of dynamic objects in the environment and determine the hazard prediction constraints based on the count; An efficient control constraint determination module, used for calculating a first motion vector of the robot and a second motion vector of the dynamic object, and determining an efficient control constraint based thereon; Steering optimal control calculation module, used to solve the steering optimal control based on the danger prediction constraint and the efficient control constraint; The obstacle avoidance control module is used to control the robot to avoid obstacles through optimal steering control.

[0026] In addition, each functional module in each embodiment of the present invention 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. The above-mentioned integrated module may be implemented in the form of hardware or in the form of software functional modules.

[0027] If the integrated module is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or system that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0028] Although the description of the present invention has been quite detailed and specifically describes several described embodiments, it is not intended to be limited to any of these details or embodiments or any particular embodiment, but should be regarded as providing a broad possible interpretation of these claims in view of the prior art by reference to the appended claims, thereby effectively covering the intended scope of the present invention. In addition, the above description of the present invention is based on the embodiments foreseeable by the inventor, and its purpose is to provide a useful description, and those non-substantial changes to the present invention that have not yet been foreseen may still represent equivalent changes to the present invention.

[0029] The above is only a preferred embodiment of the present invention. The present invention is not limited to the above implementation. As long as the technical effect of the present invention is achieved by the same means, it should belong to the protection scope of the present invention. Within the protection scope of the present invention, its technical scheme and / or implementation method can have various modifications and changes.

Claims

1. A highly efficient robot obstacle avoidance control method in a dynamic environment, characterized in that: Includes the following: Segment the dynamic and static objects in the environment, obtain static objects and dynamic objects, and extract the center position information of dynamic objects; Calculate the motion velocity vector of the dynamic object according to the center position information of the dynamic object; Based on the motion velocity vector of the dynamic object, the possible encounter position between the robot and the dynamic object is calculated; Count the number of dynamic objects in the environment and determine hazard prediction constraints based on this; calculating a first motion vector of the robot and a second motion vector of the dynamic object, and determining an efficient control constraint based thereon; Solve the steering optimal control based on the danger prediction constraint and the efficient control constraint; The robot is controlled to avoid obstacles through optimal steering control.

2. The highly efficient robot obstacle avoidance control method in a dynamic environment according to claim 1, characterized in that: Specifically, the dynamic and static objects in the environment are segmented, including: The robot obtains two-way visual information in the environment through the left and right cameras preset on the robot, inputs the two-way visual information into the DRAM of the robot host, extracts the features of the two-way visual information to obtain feature information, and performs stereo matching on the two-way visual information to obtain the position information of the feature points; then the feature points are matched based on their feature information. K-means clustering is used to segment objects into static objects and dynamic objects and extract the central position information of dynamic objects.

3. The highly efficient robot obstacle avoidance control method in a dynamic environment according to claim 1, characterized in that: Specifically, according to the center position information of the dynamic object, the motion velocity vector of the dynamic object is calculated, including: Assume that the center position of the dynamic object at time t is , then the velocity vector of the dynamic object at time t is , T is the time interval between time t and time t-1.

4. The highly efficient robot obstacle avoidance control method in a dynamic environment according to claim 3, characterized in that: Specifically, based on the motion velocity vector of the dynamic object, the possible encounter position between the robot and the dynamic object is calculated, including: Assume the center position of the robot at the current moment , the center position at time t is , the robot's motion velocity vector is calculated according to the calculation method of the motion velocity vector of the dynamic object , then the robot's motion trajectory can be estimated by the motor encoder information carried by the robot and the Kalman filter equation, then the possible encounter position between the robot and the dynamic object It can be obtained by the intersection of two straight lines determined by the dynamic object and the robot's motion velocity vector.

5. The highly efficient robot obstacle avoidance control method in a dynamic environment according to claim 4, characterized in that: Specifically, the number of dynamic objects in the environment is counted, and based on this, hazard prediction constraints are determined, including: Assuming there are N dynamic objects in the environment, the hazard prediction constraint ,in; , , for and the speed of the i-th dynamic object The product of It means to obtain the minimum value of a product, i=1,…,N.

6. The highly efficient robot obstacle avoidance control method in a dynamic environment according to claim 5, characterized in that: Specifically, a first motion vector of the robot and a second motion vector of the dynamic object are calculated, and based on the first motion vector and the second motion vector of the dynamic object, an efficient control constraint is determined, including: Calculate the robot's first motion vector , calculate the second motion vector of the dynamic object ; Assume that the robot is a wheeled robot with left and right wheels. , is the rotation speed of the left and right wheels, then the efficient control constraint is, ； in Expressed as and Inner product operation of vectors; is the threshold value and satisfies ; k is a coefficient and satisfies , and k can be determined experimentally.

7. The highly efficient robot obstacle avoidance control method in a dynamic environment according to claim 6, characterized in that: Specifically, the optimal control of steering is solved based on the danger prediction constraint and the efficient control constraint, including: The optimal steering control calculation formula is as follows: ； In the formula ; ; is the weighted penalty matrix; is the reference trajectory of the robot, which is the straight line connecting the given motion initial point and target point; For reference speed control, it is determined according to actual needs; is the maximum value of the control quantity U, that is, the maximum speed of the drive motor. U refers to the speed of the drive motor. , the robot's position Satisfies the following wheeled robot motion model, namely ； In the above formula, R and D are the wheel radius and the distance between the two wheels of the robot respectively, and θ is the turning angle of the robot.

8. A highly efficient robot obstacle avoidance control system in a dynamic environment, characterized in that: Includes the following: The object state segmentation module is used to segment the dynamic and static objects in the environment, obtain static objects and dynamic objects, and extract the center position information of dynamic objects; A motion velocity vector calculation module, used to calculate the motion velocity vector of the dynamic object according to the center position information of the dynamic object; A possible encounter position calculation module, used for calculating the possible encounter position between the robot and the dynamic object based on the motion velocity vector of the dynamic object; A hazard prediction constraint determination module, used to count the number of dynamic objects in the environment and determine the hazard prediction constraints based on the count; An efficient control constraint determination module, used for calculating a first motion vector of the robot and a second motion vector of the dynamic object, and determining an efficient control constraint based thereon; Steering optimal control calculation module, used to solve the steering optimal control based on the danger prediction constraint and the efficient control constraint; The obstacle avoidance control module is used to control the robot to avoid obstacles through optimal steering control.

Images