A dynamic environment high-efficiency robot obstacle avoidance control method and system

Abstract

The application relates to a dynamic environment high-efficiency robot obstacle avoidance control method and system, which comprises the following steps: segmenting objects in an environment to obtain static objects and dynamic objects and extracting center position information of the dynamic objects; calculating a motion speed vector of the dynamic objects according to the center position information of the dynamic objects; calculating possible meeting positions of a robot and the dynamic objects based on the motion speed vector of the dynamic objects; counting the number of the dynamic objects in the environment and determining a danger prediction constraint based on the number; calculating a first motion vector of the robot and a second motion vector of the dynamic objects and determining a high-efficiency control constraint based on the first motion vector and the second motion vector; solving a steering optimal control based on the danger prediction constraint and the high-efficiency control constraint; and performing obstacle avoidance control on the robot through the steering optimal control. The application combines a visual sensor to enable the robot to realize obstacle avoidance control in a dynamic environment, so that the robot can work more effectively and safely in a complex dynamic environment.

Description

Technical Field

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

[0002] Autonomous and intelligent robotic applications face numerous challenges and key issues, such as autonomous obstacle avoidance, particularly in complex dynamic environments. Many challenges remain in terms of efficiency, safety, and reliability. With the advancement of robotics technology, efficient robot obstacle avoidance control holds great promise for future robotic applications.

[0003] At present, there are many methods for robot obstacle avoidance control, and the commonly used ones include the artificial potential method, the speed barrier method, the dynamic window method, and so on. The artificial potential method is simple and effective, but its disadvantages are also obvious. The robot is prone to jitter during the obstacle avoidance movement and the movement direction 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 maneuvering behavior and lower computational cost, but there is also jitter during obstacle avoidance. The dynamic window method's control of obstacle avoidance mainly relies on the weighted setting in the cost function, but the changes in the dynamic environment make it difficult to adjust its weighting, making it 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:

[0006] Specifically, a highly efficient robot obstacle avoidance control method in a dynamic environment is proposed, which includes the following:

[0007] Segment the dynamic and static objects in the environment, obtain static objects and dynamic objects, and extract the center position information of dynamic objects;

[0008] Calculate the motion velocity vector of the dynamic object according to the center position information of the dynamic object;

[0009] Calculate the possible encounter position between the robot and the dynamic object based on the motion velocity vector of the dynamic object;

[0010] Count the number of dynamic objects in the environment and determine hazard prediction constraints based on this;

[0011] 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;

[0012] Solve the steering optimal control based on the hazard prediction constraint and the efficient control constraint;

[0013] The robot is controlled to avoid obstacles through optimal steering control.

[0014] Furthermore, specifically, segmenting dynamic and static objects in the environment includes:

[0015] The robot obtains two-way visual information in the environment through the left and right cameras pre-installed on it, and inputs the two-way visual information into the DRAM of the robot host. At the same time, feature extraction is performed on the two-way visual information to obtain feature information, and the two-way visual information is 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.

[0016] Further, specifically, according to the center position information of the dynamic object, the motion velocity vector of the dynamic object is calculated, including:

[0017] Assume that the center position of the dynamic object at time t is X m,t =(x m,t ,y m,t ), then the velocity vector of the dynamic object at time t is V m,t =(X m,t -X m,t-1 ) / T;α m,t =arctan[(y m,t -y m,t-1 ) / (x m,t -x m,t-1 )], T is the time interval between time t and time t-1.

[0018] 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:

[0019] Assume that the center position of the robot at the current moment is X = (x, y), and the center position at time t is X t =(x t ,y t ), the robot's motion velocity vector V is calculated according to the calculation method of the motion velocity vector of the dynamic object t ,α t , 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 X between the robot and the dynamic object c,t =(x c,t,y c,t ) can be obtained by the intersection of two straight lines determined by the motion velocity vectors of the dynamic object and the robot.

[0020] Furthermore, specifically, the number of dynamic objects in the environment is counted, and based on this, the hazard prediction constraint is determined, including, assuming that there are N dynamic objects in the environment, the hazard prediction constraint

[0021] W1=exp(-||d o V t -Min[(d r V m,t )1,…,(d r V m,t ) i ,…,(d r V m,t ) N ]||2), where;

[0022] d r =||X t -X c,t ||2,d o =||X m,t -X c,t ||2,(d r V m,t ) i d r and the velocity V of the i-th dynamic object m，t The product of , Min[·] means to obtain the minimum value of a certain product, i=1,…,N.

[0023] Further, specifically, calculating the first motion vector of the robot and the second motion vector of the dynamic object, and determining the efficient control constraints based on the first motion vector and the second motion vector of the dynamic object, including:

[0024] Calculate the robot's first motion vector ΔX=XX t , calculate the second motion vector of the dynamic object

[0025] ΔX m,t =X m,t -X m,t-1 ;

[0026] Assume that the robot is a wheeled robot with two wheels controlled on the left and right, and its speed control is U=(u L ,u R ),u L ,u R is the rotational speed of the left and right wheels, then the efficient control constraint is,

[0027]

[0028] Where (ΔX·ΔXm,t ) is expressed as ΔX and ΔX m,t Vector inner product operation; T s is the threshold value, and satisfies 0≤T s ≤1; k is a coefficient and satisfies 1.5≤k≤1.8, T s and k can be determined experimentally.

[0029] Furthermore, specifically, solving the steering optimal control based on the danger prediction constraint and the efficient control constraint includes:

[0030] The optimal steering control calculation formula is as follows:

[0031]

[0032] In the formula Q1, Q2 are weighted penalty matrices; X R is the reference trajectory of the robot, which is the straight line connecting the given motion starting point and target point; U r For reference speed control, it is determined according to actual needs; U max is the maximum value of the control quantity U, that is, the maximum speed of the driving motor. U refers to the speed of the driving motor. U=(u L ,u R ), the robot's position X satisfies the following wheeled robot motion model, namely

[0033]

[0034] In the above formula, R and D are the robot wheel radius and the distance between the two wheels, respectively, and θ is the robot's rotation angle.

[0035] The present invention also proposes a highly efficient robot obstacle avoidance control system in a dynamic environment, comprising the following:

[0036] 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;

[0037] A motion velocity vector calculation module is used to calculate the motion velocity vector of a dynamic object based on the center position information of the dynamic object;

[0038] A possible encounter position calculation module is used to calculate the possible encounter position between the robot and the dynamic object based on the motion velocity vector of the dynamic object;

[0039] a hazard prediction constraint determination module, configured to count the number of dynamic objects in the environment and determine hazard prediction constraints based on the count;

[0040] an efficient control constraint determination module, configured to calculate a first motion vector of the robot and a second motion vector of the dynamic object, and determine an efficient control constraint based thereon;

[0041] Steering optimal control calculation module, used to solve steering optimal control based on danger prediction constraints and efficient control constraints;

[0042] The obstacle avoidance control module is used to control the robot to avoid obstacles through optimal steering control.

[0043] The beneficial effects of the present invention are:

[0044] This paper proposes a highly efficient robot obstacle avoidance control method and system for dynamic environments. By calculating the possible encounter locations between the robot and dynamic objects, and then determining hazard prediction constraints and efficient control constraints, the system ultimately solves for optimal steering control, which is then used to control the robot's obstacle avoidance. By incorporating visual sensors, the present invention enables the robot to more efficiently implement obstacle avoidance control in dynamic environments, enabling the robot to operate more effectively and safely in complex dynamic environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The above and other features of the present disclosure will become more apparent through a detailed description of the embodiments shown in conjunction with the accompanying drawings. The same reference numerals in the drawings of the present disclosure represent the same or similar elements. Obviously, the drawings described below are only some embodiments of the present disclosure. It is possible for a person skilled in the art to derive other drawings based on these drawings without inventive effort. In the drawings:

[0046] 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

[0047] 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 and features in the embodiments of this application can be combined with each other unless there is a conflict. The same reference numerals used throughout the drawings indicate the same or similar parts.

[0048] Example 1, with reference to Figure 1 The present invention proposes a highly efficient robot obstacle avoidance control method in a dynamic environment, comprising the following steps:

[0049] 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;

[0050] Step 120: Calculate the motion velocity vector of the dynamic object based on the center position information of the dynamic object;

[0051] Step 130: Calculate the possible encounter position between the robot and the dynamic object based on the motion velocity vector of the dynamic object;

[0052] Step 140: Count the number of dynamic objects in the environment and determine the hazard prediction constraints based on the count;

[0053] Step 150: Calculate a first motion vector of the robot and a second motion vector of the dynamic object, and determine an efficient control constraint based thereon;

[0054] Step 160: Solve the steering optimal control based on the danger prediction constraint and the efficient control constraint;

[0055] Step 170: Perform obstacle avoidance control on the robot through optimal steering control.

[0056] In this first embodiment, the robot calculates the possible encounter locations with dynamic objects, determines hazard prediction constraints and efficient control constraints, and ultimately solves for optimal steering control, which is then used to control the robot's obstacle avoidance. By incorporating visual sensors, this invention enables the robot to more efficiently implement obstacle avoidance control in dynamic environments, allowing the robot to operate more effectively and safely in complex dynamic environments.

[0057] As a preferred embodiment of the present invention, specifically, segmenting the dynamic and static objects in the environment includes:

[0058] The robot obtains two-way visual information in the environment through the left and right cameras pre-installed on it, and inputs the two-way visual information into the DRAM of the robot host. At the same time, feature extraction is performed on the two-way visual information to obtain feature information, and the two-way visual information is 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.

[0059] 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:

[0060] Assume that the center position of the dynamic object at time t is X m,t =(x m,t ,y m,t ), then the velocity vector of the dynamic object at time t is V m,t =(X m,t -X m,t-1 ) / T;α m,t =arctan[(y m,t -ym,t-1 ) / (x m,t -x m,t-1 )], T is the time interval between time t and time t-1. The subscripts with m represent the X, V, and α of the dynamic object, which are used to distinguish the corresponding parameters of the robot.

[0061] As a preferred embodiment of the present invention, specifically, based on the motion velocity vector of the dynamic object, calculating the possible encounter position between the robot and the dynamic object includes:

[0062] Assume that the center position of the robot at the current moment is X = (x, y), and the center position at time t is X t =(x t ,y t ), the robot's motion velocity vector V is calculated according to the calculation method of the motion velocity vector of the dynamic object t ,α t , 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 X between the robot and the dynamic object c,t =(x c,t ,y c,t ) can be obtained by the intersection of two straight lines determined by the motion velocity vectors of the dynamic object and the robot.

[0063] 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:

[0064] Assuming there are N dynamic objects in the environment, the hazard prediction constraint

[0065] W1=exp(-||d o V t -Min[(d r V m,t )1,…,(d r V m,t ) i ,…,(d r V m,t ) N ]||2), where;

[0066] d r =||X t -X c,t ||2,d o =||X m,t -X c,t ||2,(d r V m,t ) i d r and the velocity V of the i-th dynamic object m，tThe product of , Min[·] means to obtain the minimum value of a certain product, i=1,…,N.

[0067] 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 and the second motion vector of the dynamic object, including:

[0068] Calculate the robot's first motion vector ΔX=XX t , calculate the second motion vector of the dynamic object

[0069] ΔX m,t =X m,t -X m,t-1 ;

[0070] Assume that the robot is a wheeled robot with two wheels controlled on the left and right, and its speed control is U=(u L ,u R ),u L ,u R is the rotational speed of the left and right wheels, then the efficient control constraint is,

[0071]

[0072] Where (ΔX·ΔX m,t ) is expressed as ΔX and ΔX m,t Vector inner product operation; T s is the threshold value, and satisfies 0≤T s ≤1; k is a coefficient and satisfies 1.5≤k≤1.8, T s and k can be determined experimentally.

[0073] 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:

[0074] The optimal steering control calculation formula is as follows:

[0075] Here is the optimal control U when solving the minimum value of (J1+J2) under the constraints, that is, U*, J1 is a function of (X, U), that is: J1=J1(X, U), because the control U is implicit in X; J2 is a function of U, J2=J2(U).

[0076] In the formula Q1, Q2 are weighted penalty matrices; X R is the reference trajectory of the robot, which is the straight line connecting the given motion starting point and target point; U r For reference speed control, it is determined according to actual needs; U maxis the maximum value of the control quantity U, that is, the maximum speed of the driving motor. U refers to the speed of the driving motor. U=(u L ,u R ), the robot's position X satisfies the following wheeled robot motion model, namely

[0077]

[0078] In the above formula, R and D are the robot wheel radius and the distance between the two wheels, respectively, and θ is the robot's rotation angle.

[0079] The present invention also proposes a highly efficient robot obstacle avoidance control system in a dynamic environment, comprising the following:

[0080] 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;

[0081] A motion velocity vector calculation module is used to calculate the motion velocity vector of a dynamic object based on the center position information of the dynamic object;

[0082] A possible encounter position calculation module is used to calculate the possible encounter position between the robot and the dynamic object based on the motion velocity vector of the dynamic object;

[0083] a hazard prediction constraint determination module, configured to count the number of dynamic objects in the environment and determine hazard prediction constraints based on the count;

[0084] an efficient control constraint determination module, configured to calculate a first motion vector of the robot and a second motion vector of the dynamic object, and determine an efficient control constraint based thereon;

[0085] Steering optimal control calculation module, used to solve steering optimal control based on danger prediction constraints and efficient control constraints;

[0086] The obstacle avoidance control module is used to control the robot to avoid obstacles through optimal steering control.

[0087] In addition, the functional modules in various embodiments of the present invention may be integrated into a single processing module, or each module may exist physically separately, or two or more modules may be integrated into a single module. The aforementioned integrated modules may be implemented in the form of hardware or software functional modules.

[0088] If the integrated module is implemented in the form of a software functional 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 process 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, magnetic 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.

[0089] Although the present invention has been described in considerable detail and with particularity with respect to several described embodiments, it is not intended to be limited to any of these details or embodiments or any particular embodiment, but rather should be construed as providing a broad possible interpretation of these claims in view of the prior art by reference to the appended claims, thereby effectively encompassing the intended scope of the invention. In addition, the invention has been described above in terms of embodiments foreseen by the inventors for the purpose of providing a useful description, and those insubstantial modifications of the invention that are not currently foreseen may still represent equivalent modifications of the invention.

[0090] The above description is merely a preferred embodiment of the present invention. The present invention is not limited to the above-described embodiments. As long as the technical effects of the present invention are achieved by the same means, they shall fall within the scope of protection of the present invention. Within the scope of protection of the present invention, various modifications and variations of the technical solutions and / or implementation methods may be made.

Claims

1. A highly efficient robot obstacle avoidance control method in a dynamic environment, characterized in that: These include: 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; Calculate the possible encounter position between the robot and the dynamic object based on the motion velocity vector of the dynamic object; 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 hazard prediction constraint and the efficient control constraint; Obstacle avoidance control of the robot through optimal steering control; 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 X m,t =(x m,t ,y m,t ), then the velocity vector of the dynamic object at time t is V m,t =(X m,t -X m,t-1 ) / T;α m,t =arctan[(y m,t -y m,t-1 ) / (x m,t -x m,t-1 )], T is the time interval between time t and time t-1; 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 that the center position of the robot at the current moment is X = (x, y), and the center position at time t is X t =(x t ,y t ), the robot's motion velocity vector V is calculated according to the calculation method of the motion velocity vector of the dynamic object t ,α t , 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 X between the robot and the dynamic object c,t =(x c,t ,y c,t ) can be obtained by the intersection of two straight lines determined by the motion velocity vectors of the dynamic object and the robot; 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 W1=exp(-||d o V t -Min[(d r V m,t )1,…,(d r V m,t ) i ,…,(d r V m,t ) N ]||2), where; d r =||X t -X c,t ||2,d o =||X m,t -X c,t ||2,(d r V m,t ) i d r and the velocity V of the i-th dynamic object m，t The product of , Min[·] means to obtain the minimum value of a certain product, i=1,…,N; Specifically, the first motion vector of the robot and the second motion vector of the dynamic object are calculated, and based on this, efficient control constraints are determined, including: Calculate the robot's first motion vector ΔX=XX t , calculate the second motion vector of the dynamic object ΔX m,t =X m,t -X m,t-1 ; Assume that the robot is a wheeled robot with two wheels controlled on the left and right, and its speed control is U=(u L ,u R ),u L ,u R is the rotational speed of the left and right wheels, then the efficient control constraint is, Where (ΔX·ΔX m,t ) is expressed as ΔX and ΔX m,t Vector inner product operation; T s is the threshold value, and satisfies 0≤T s ≤1; k is a coefficient and satisfies 1.5≤k≤1.8, T s and k can be determined experimentally; Specifically, the optimal control solution is solved based on the hazard prediction constraint and the efficient control constraint, including: The optimal steering control calculation formula is as follows: In the formula Q1, Q2 are weighted penalty matrices; X R is the reference trajectory of the robot, which is the straight line connecting the given motion starting point and target point; U r For reference speed control, it is determined according to actual needs; U max is the maximum value of the control quantity U, that is, the maximum speed of the driving motor. U refers to the speed of the driving motor. U=(u L ,u R ), the robot's position X satisfies the following wheeled robot motion model, namely In the above formula, R and D are the robot wheel radius and the distance between the two wheels, respectively, and θ is the robot's rotation angle.

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, and extracts the features of the two-way visual information to obtain feature information. The two-way visual information is matched stereoscopically to obtain the position information of the feature points. The feature points are then matched based on their feature information. K-means clustering is used to segment the objects into static objects and dynamic objects and extract the center position information of the dynamic objects.

3. A highly efficient robot obstacle avoidance control system in a dynamic environment, characterized in that: The steps of the method according to any one of claims 1 to 2 are applied, and the system comprises 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 is used to calculate the motion velocity vector of a dynamic object based on the center position information of the dynamic object; A possible encounter position calculation module is used to calculate 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, configured to count the number of dynamic objects in the environment and determine hazard prediction constraints based on the count; an efficient control constraint determination module, configured to calculate a first motion vector of the robot and a second motion vector of the dynamic object, and determine an efficient control constraint based thereon; Steering optimal control calculation module, used to solve steering optimal control based on danger prediction constraints and efficient control constraints; The obstacle avoidance control module is used to control the robot to avoid obstacles through optimal steering control.

Images