WO2022126352A1

WO2022126352A1 - Robot obstacle avoidance method and apparatus, robot, and storage medium

Info

Publication number: WO2022126352A1
Application number: PCT/CN2020/136354
Authority: WO
Inventors: 郑大可; 刘益彰; 庞建新; 谭欢; 熊友军
Original assignee: 深圳市优必选科技股份有限公司
Priority date: 2020-12-15
Filing date: 2020-12-15
Publication date: 2022-06-23

Abstract

A robot obstacle avoidance method and apparatus, a robot, and a storage medium, the method comprising: if a robot detects a concave obstacle during the process of travelling along an initial movement trajectory then, by dividing the concave obstacle into pairs of intersecting convex obstacles, the obstacle avoidance problem of the concave obstacle can be transformed into an obstacle avoidance problem of the pairs of intersecting convex obstacles, simplifying the difficulty of the obstacle avoidance of concave obstacles and, when the initial movement trajectory reaches the concave obstacle, enabling prediction of the intersection point of the initial movement trajectory and the surface of the concave obstacle; on the basis of the intersection point and intersection line, implementing obstacle avoidance correction of the initial movement trajectory to obtain a target movement trajectory, and implementing obstacle avoidance according to the target movement trajectory; the present method can implement effective obstacle avoidance of concave obstacles.

Description

Robot obstacle avoidance method and device, robot and storage medium

technical field

The invention relates to the technical field of robots, and in particular, to a method and device for avoiding obstacles of a robot, a robot and a storage medium.

Background technique

With the continuous research and application of robots, robots such as robotic arms, unmanned aerial vehicles, mobile robots, underwater robots, etc. all need to perform desired tasks in more and more complex environments. In the workshop environment, to carry objects or work together with humans, UAVs need to shuttle in complex geographical environments to complete corresponding reconnaissance tasks and so on. In these cases, in order to ensure the safety of people, other robots and the robot itself, and to be able to complete the corresponding work tasks, the robot needs to avoid concave obstacles in the working environment in real time, such as shelves, trees, workers, tables, other robots, etc. For robotics research, how to ensure that the robot can safely and effectively avoid concave obstacles in a scenario with concave obstacles is an important and challenging problem with practical application value.

SUMMARY OF THE INVENTION

The main purpose of the present invention is to provide a robot obstacle avoidance method and device, a robot and a storage medium, which can effectively realize the obstacle avoidance of concave obstacles.

In order to achieve the above object, a first aspect of the present invention provides a method for avoiding obstacles for a robot, the method comprising:

If the robot detects a concave obstacle in the process of traveling along the initial movement trajectory, it divides the concave obstacle into two convex obstacles that intersect each other according to the shape of the concave obstacle, and determines that the two intersect each other. The intersection of the two convex obstacles is at the intersection of the surfaces of the concave obstacles;

predicting the intersection of the initial movement trajectory and the surface of the concave obstacle when the initial movement trajectory reaches the concave obstacle;

The initial movement trajectory is corrected for obstacle avoidance according to the intersection point and the intersection line to obtain a target movement trajectory, and obstacle avoidance is performed according to the target movement trajectory.

In order to achieve the above object, a second aspect of the present invention provides a robot obstacle avoidance device, the device includes: a processor and a memory, a computer program is stored in the memory, and when the processor executes the computer program, the processor is caused to perform the following steps:

In order to achieve the above object, a third aspect of the present invention provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, causes the processor to perform the following steps:

In order to achieve the above object, a fourth aspect of the present invention provides a robotic arm, comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the following steps :

Adopting the embodiment of the present invention has the following beneficial effects:

The present invention provides an obstacle avoidance method for a robot. The method includes: if the robot detects a concave obstacle in the process of traveling along an initial moving track, dividing the concave obstacle into two groups according to the shape of the concave obstacle. The intersecting convex obstacles, determine the intersection position of the two convex obstacles at the intersection point of the pair on the intersection line of the surface of the concave obstacle, and predict that when the initial movement trajectory reaches the concave obstacle, the initial movement trajectory The intersection point with the surface of the concave obstacle; the initial movement trajectory is corrected for obstacle avoidance according to the above intersection point and intersection line to obtain the target movement trajectory, and obstacle avoidance is performed according to the target movement trajectory. When a concave obstacle is detected, by dividing the concave obstacle into two intersecting convex obstacles, the obstacle avoidance problem of the concave obstacle can be transformed into two intersecting convex obstacles It simplifies the difficulty of avoiding obstacles of concave obstacles, and the initial movement trajectory can be carried out based on the predicted intersection points and the intersection positions of the two intersecting convex obstacles on the intersecting line of the surface of the concave obstacles. The obstacle avoidance correction makes it possible to effectively realize the obstacle avoidance of concave obstacles.

Description of drawings

In order to explain the embodiments of the present invention or the technical solutions in the prior art more clearly, the following briefly introduces the accompanying drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained according to these drawings without creative efforts.

in:

1 is a schematic flowchart of a robot obstacle avoidance method in an embodiment of the present invention;

2 is a schematic diagram of a concave obstacle in an embodiment of the present invention;

FIG. 3 is another schematic flowchart of a method for obstacle avoidance of a robot in an embodiment of the present invention;

Fig. 4 is another schematic diagram of the concave obstacle in the embodiment shown in Fig. 2;

FIG. 5 is a structural block diagram of a robot in an embodiment of the present invention.

Detailed ways

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

Please refer to FIG. 1, which is a schematic flowchart of a robot obstacle avoidance method according to an embodiment of the present invention. The method includes:

Step 101: If the robot detects a concave obstacle in the process of traveling along the initial movement trajectory, it divides the concave obstacle into two intersecting convex obstacles according to the shape of the concave obstacle, and determines the two intersecting convex obstacles. The intersection of two convex obstacles is the intersection line of the surface of the concave obstacle;

In the embodiment of the present invention, after the robot receives the task instruction, it will determine the initial movement trajectory required to complete the task based on the task instruction. For example, after the drone receives the instruction to fly to the target location, it will The location of the location and the geographic location data of the environment determine the flight path, which is the initial movement trajectory.

And after the initial moving trajectory is determined, the robot will travel along the initial moving trajectory, and will detect obstacles in real time during the process of traveling, and perform obstacle avoidance processing in real time. Wherein, if an obstacle is detected, it will be further determined whether the obstacle is a convex obstacle or a concave obstacle, wherein the concave obstacle is the tangent of the outer edge of the shape of the object, and the object can be divided according to its shape For objects that can be divided into at least two parts, convex obstacles do not have the above-mentioned tangents that can be divided. It can be understood that other obstacles other than concave obstacles can be called convex obstacles.

Wherein, when a concave obstacle is detected, the concave obstacle will be divided into two intersecting convex obstacles according to the shape of the concave obstacle, and the The intersection line where the intersection is on the surface of the concave obstacle. It can be understood that the above-mentioned two-by-two intersection refers to the combination of convex obstacles. In the scenario of dividing into multiple convex obstacles, the multiple convex obstacles are connected by intersection to form the entire concave obstacle. the whole of things. In order to better understand the division of concave obstacles, please refer to FIG. 2 , which is a schematic diagram of a concave obstacle in an embodiment of the present invention. As shown in FIG. 2 , the concave obstacle is an electric drill as an example. Divided into three convex obstacles, the three convex obstacles are convex obstacle 1, convex obstacle 2 and convex obstacle 3, among which, convex obstacle 1 and convex obstacle 2 Two-by-two, convex obstacle 2 and convex obstacle 3 intersect two-by-two, and the intersecting position of the two-by-two convex obstacles is the intersection line, in Figure 2, the intersection lines are A and B , among which, the range of intersection line A is between point c1 and point c2, and the range of intersection line B is between point c3 and point c4. It can be understood that Figure 2 is only represented in the form of a plan view. A line is a line with a first connected closed loop. It can be understood that, for any concave obstacle, it can be divided into a plurality of convex obstacles.

It can be understood that, by dividing the concave obstacle into a plurality of convex obstacles that intersect each other, the obstacle avoidance problem of the concave obstacle can be transformed into the obstacle avoidance problem of a plurality of convex obstacles, which simplifies the The difficulty of avoiding the concave obstacles makes it possible to avoid the concave obstacles.

Step 102, predicting the intersection of the initial movement trajectory and the surface of the concave obstacle when the initial movement trajectory reaches the concave obstacle;

In the embodiment of the present invention, after the concave obstacle is detected, the intersection point of the initial movement trajectory and the surface of the concave obstacle is also predicted, so as to avoid the obstacle.

It can be understood that the obstacle avoidance of the robot is real-time during the movement of the robot, and the detection of a concave obstacle is usually a moment before reaching the concave obstacle, or before reaching the concave obstacle. The preset duration, which is usually short, enables the robot to determine its obstacle avoidance strategy before reaching the concave obstacle. Therefore, it can be understood that the obstacle avoidance of the concave obstacle is determined before reaching the concave obstacle. After the robot detects the concave obstacle, it can predict when it reaches the concave obstacle according to its initial movement trajectory. , the intersection of the initial movement trajectory with the surface of the concave obstacle.

It should be noted that, in this embodiment of the present invention, after a concave obstacle is detected, the steps of dividing the concave obstacle into a plurality of convex obstacles that intersect in pairs and the step of determining the intersection point are not limited. The sequence, in the embodiment shown in FIG. 1, is described by first dividing into a plurality of convex obstacles and then determining the intersection points. In addition, after determining the above intersection points, the concave obstacles Divide into multiple convex obstacles, or, the steps of determining the intersection point and dividing the concave obstacles into convex obstacles can also be performed at the same time. In practical applications, the execution sequence of the above steps can be determined based on specific needs , which is not limited here.

Step 103: Perform obstacle avoidance correction on the initial movement trajectory according to the intersection point and the intersection line to obtain a target movement trajectory, and perform obstacle avoidance according to the target movement trajectory.

In the embodiment of the present invention, when a concave obstacle is detected, the concave obstacle is divided into two intersecting convex obstacles, so that the obstacle avoidance problem of the concave obstacle can be transformed into two The obstacle avoidance problem of two intersecting convex obstacles simplifies the difficulty of concave obstacle avoidance, and can be based on the predicted intersection point and the intersection position of the two intersecting convex obstacles on the surface of the concave obstacle. The intersection line performs obstacle avoidance correction on the initial movement trajectory, so that the obstacle avoidance of concave obstacles can be effectively realized.

In order to better understand the technical solutions in the embodiments of the present invention, please refer to FIG. 3 , which is another schematic flowchart of the method for obstacle avoidance of the robot in the embodiments of the present invention, including:

Step 301: If the robot detects a concave obstacle in the process of traveling along the initial movement trajectory, it divides the concave obstacle into two intersecting convex obstacles according to the shape of the concave obstacle, and determines the two intersecting convex obstacles. The intersection of two convex obstacles is the intersection line of the surface of the concave obstacle;

Step 302, predicting the intersection of the initial movement trajectory and the surface of the concave obstacle when the initial movement trajectory reaches the concave obstacle;

In this embodiment of the present invention, the foregoing

steps

301 and 302 are similar to the descriptions of

steps

101 and 102 in the embodiment shown in FIG. 1 , respectively. For details, please refer to the relevant descriptions in the embodiment shown in FIG. 1 . Do repeat.

In a feasible implementation manner, the above-mentioned initial movement trajectory may be a movement trajectory determined based on a dynamic system (Dynamic System, DS). Among them, DS is a concept in mathematics. There is a fixed rule in the DS system, which describes the evolution of a point in the geometric space with time. In this embodiment of the present invention, the robot can be used as a moving point, or the movable part of the robot can be used as a moving point, and the movement trajectory of the robot can be described based on DS.

Among them, after the robot receives the task command, it will use the task command and the continuous function based on the dynamic system to determine the initial movement trajectory of the robot. Specifically, after receiving the task instruction, the robot can determine the task content according to the task instruction, and use the task content and the collected environmental data to determine the original travel path, and further, according to the following dynamic system formula, This travel path is converted into the above-mentioned initial movement trajectory, wherein the formula of the dynamic system is as follows:

in,

represents the initial movement trajectory,

represents the pose information of the robot determined based on the above-mentioned travel path, and f(·) is a continuous function based on the dynamic system.

It can be understood that the initial movement trajectory of the robot based on the dynamic system can be determined in the above manner.

In another feasible implementation manner, the teaching motion DS model library of the robot in its application scenario may also be determined first, and the teaching motion DS model library is generated based on the teaching data of the teaching motion sample task. Taking the robot as a mechanical arm as an example, the movement trajectory of the robot arm refers to the movement trajectory of the end of the robot arm, and the movement trajectory of the robot arm can be described based on the DS principle. To complete a task, the task can consist of one action or multiple actions. For example, the human teaching activity can be: raising an arm, lowering an arm, picking up a cup, opening the refrigerator door, etc., which can be represented by A person performing the teaching activity actually demonstrates the operations of "raise the arm", "lower the arm", "pick up the refrigerator" and "open the refrigerator door", and obtain the video data of the person demonstrating the above actions, based on the DS principle Confirm the position of the end of the arm in the video data, and obtain the movement trajectory of the end of the arm in the process of performing the above action. The arm of the above-mentioned person corresponds to the mechanical arm, and the palm part of the arm is the end of the arm, and Corresponding to the end of the manipulator, the manipulator can simulate the arm of the above-mentioned personnel to perform tasks, and the movement trajectory of the end of the arm obtained based on the DS principle can be used as the movement trajectory of the DS model of the robot arm. Therefore, based on the movement trajectory The movement trajectory of the DS model corresponding to the corresponding action is obtained, so that the above-mentioned teaching motion DS model library can be obtained through the above method, and the robot arm can perform tasks by simulating real human actions, so as to have the ability to determine the movement autonomously and flexibly The ability of trajectory improves the autonomy and flexibility of the robotic arm.

It can be understood that, in the process of obtaining the above-mentioned teaching motion DS model library, the corresponding relationship between the task content and the movement trajectory of the DS model can also be established based on the task content actually indicated by the teaching activity, so that the robotic arm is receiving After the task instruction is reached, the task content can be obtained by parsing the task instruction, and based on the task content, the corresponding relationship in the teaching motion DS model library is searched, and the movement trajectory of the DS model corresponding to the task content is determined. For example, if the task instruction is "pick up the water glass", the content of the task can be parsed, and it can be determined that the content of the task is to pick up the object. Therefore, you can search for the corresponding "pick up object" in the teaching motion DS model library. The movement trajectory of the DS model is used as the above-mentioned initial movement trajectory.

Step 303: Determine the target modal matrix according to the intersection point and the intersection line;

Step 304 , using the target modal matrix to perform obstacle avoidance correction on the initial movement trajectory to obtain the target movement trajectory.

In the embodiment of the present invention, after the intersection point and the intersection line are obtained, a target modal matrix for performing obstacle avoidance correction on the initial movement trajectory will be determined based on the intersection point and intersection line, so as to realize obstacle avoidance on the initial movement trajectory Correction to get the target movement trajectory.

Wherein, in a feasible implementation manner, determining the target modal matrix according to the intersection point and the intersection line specifically includes:

Step a, calculate the surface function of each convex obstacle, and determine the positional relationship between the intersection point and the intersection line;

Step b: Determine the target modal matrix according to the surface function and positional relationship of each convex obstacle.

After dividing the concave obstacle into multiple convex obstacles, the center point of the multiple convex obstacles will be determined, and the target pose information when the initial movement trajectory of the robot reaches the surface of the concave obstacle will be determined, and calculate the vector between the above-mentioned target pose information and the center points of multiple convex obstacles respectively, obtain the initial vector of each convex obstacle, and further determine the preset standard coordinate system of each convex obstacle The length values on each axis of , determine the surface function of each convex obstacle based on the above-mentioned initial vector of each convex obstacle and the length value on each axis, where the surface function is used to describe the convex obstacle surface shape.

Wherein, the above-mentioned standard coordinate system may be a Cartesian coordinate system.

Taking a concave obstacle divided into N convex obstacles as an example,

is the center point of the i-th convex obstacle, then

Represents the vector between the above-mentioned target pose information and the center point of the i-th convex obstacle. And the surface function of the i-th convex obstacle is as follows:

in,

Represents the surface function of the ith convex obstacle, 3 represents the three direction axes of the standard coordinate system, if the standard coordinate system is a Cartesian coordinate system, it represents the X axis, the Y axis and the Z axis, and j represents the jth axis axis,

represents the length of the i-th convex obstacle on the j-th axis,

represents the vector between the target pose information and the center point of the i-th convex obstacle,

Represents the shape parameter of the i-th convex obstacle on the j-th axis, by adjusting

The convex obstacle may be a spherical, ellipsoidal or square object.

In the above manner, the surface function of each convex obstacle can be obtained. And further, the positional relationship between the intersection point and the intersection line can be determined. Specifically, the target pose information of the intersection point and the pose information of the intersection line can be used to compare, if the target pose information of the intersection line includes the intersection point. If the target pose information is used, the positional relationship between the intersection point and the intersection line is determined as: the intersection point is located on the intersection line, otherwise, the intersection point is not located on the intersection line, as shown in Figure 2, it is necessary to determine whether the intersection point is located at the intersection point. On line A and intersection line B, as long as it is located on any intersection line, it can be determined that the intersection point is located on the intersection line.

In the embodiment of the present invention, the positional relationship between the intersection point and the intersection line determines the method for determining the target modal matrix, which will be described separately below:

(1) When the positional relationship is that the intersection point is not located on the intersection line, at this time, the problem of avoiding concave obstacles can be solved as avoiding the plurality of convex obstacles. The method is as follows: each convex obstacle can be used. The modal matrix of each convex obstacle is obtained by the surface function of the obstacle; the combined modal matrix is obtained by combining the modal matrix of each convex obstacle, and the combined modal matrix is used as the target modal matrix.

Among them, to determine the modal matrix of the i-th convex obstacle as an example, the normal vector of the i-th convex obstacle can be obtained by using the surface function of the i-th convex obstacle, as follows:

in,

represents the surface function of the i-th convex obstacle, and (ξ) ₁ , (ξ) ₂ , and (ξ) ₃ represent the X-axis, Y-axis, and Z-axis in the Cartesian coordinate system, respectively.

After obtaining the normal vector of the i-th convex obstacle above, the modal matrix of the i-th convex obstacle will be further determined according to the following formula:

in,

in,

represents the modal matrix of the ith convex obstacle,

represents the normal vector of the ith convex obstacle,

and

Expressed as the basis vector of the hyperplane corresponding to the normal vector of the ith convex obstacle.

in,

Understandably,

and

are parameters constructed based on the surface function of the ith convex obstacle.

It can be understood that through the above method, the modal matrix of each convex obstacle can be obtained, and the modal matrix of each convex obstacle can be combined according to the following formula to obtain the combined modal matrix. The modal matrix can be regarded as the target modal matrix, and the formula of the combined modal matrix is as follows:

in,

represents the modal matrix of the ith convex obstacle, N represents the number of convex obstacles,

represents the combined modal matrix.

Further, after obtaining the above-mentioned combined modal matrix, the initial movement trajectory of the robot can be used to perform obstacle avoidance correction to obtain the target movement trajectory, wherein the formula of the target movement trajectory is as follows:

Among them, f(ξ) represents the initial movement trajectory,

represents the combined modal matrix,

Indicates the target movement trajectory after obstacle avoidance correction.

In order to better understand the technical solution in the embodiment of the present invention, please refer to FIG. 4 , which is another schematic diagram of the concave obstacle shown in FIG. 2 in the embodiment of the present invention. In this schematic diagram,

represents the center point of convex obstacle 1,

represents the center point of convex obstacle 2,

Represents the center point of convex obstacle 3. The intersection line in Figure 4 is the intersection line.

in,

represents the intersection point, and the intersection point is located on the surface of the convex obstacle 3,

represents the normal vector of convex obstacle 3,

and

Represents the base vector of the hyperplane corresponding to the normal vector of convex obstacle 3. Based on the above method, the combined modal matrix when the intersection point is on the convex obstacle 3 can be effectively realized, and the combined modal component can be used as the target modal matrix to perform obstacle avoidance correction, thereby effectively realizing obstacle avoidance processing.

(2) When the positional relationship is that the intersection point is located on the intersection line, determine the first convex obstacle and the second convex obstacle forming the target intersection line, and the target intersection line is the intersection line where the intersection point is located; The first surface function of the convex obstacle and the second surface function of the second convex obstacle determine the target modal matrix.

Specifically, the first surface function may be used to determine the first normal vector of the intersection point at the first convex obstacle, and the second surface function may be used to determine the second normal vector of the second convex obstacle. If the intersection point is

It means that the first convex obstacle is a convex obstacle m, and the second convex obstacle is a convex obstacle n, and the first difference between the intersection point and the center point of the convex obstacle m can be calculated, that is,

And the second difference between the intersection point and the center point of the convex obstacle n can be calculated, that is

Using the first difference and the second difference, calculate the normal vector of the convex obstacle m, which is the first normal vector of the first convex obstacle, and calculate the normal vector of the convex obstacle m, that is, is the second normal vector of the second convex obstacle.

Among them, the formula of the first normal vector is as follows:

Among them, the formula of the second normal vector is as follows:

of which,

represents the surface function of the mth convex obstacle,

represents the surface function of the nth convex obstacle, and b represents the mark of a point on the intersection of the mth convex obstacle and the nth convex obstacle.

After obtaining the above-mentioned first normal vector and second normal vector, the intersection point will be constructed by using the first surface function, the second surface function, the first normal vector and the second normal vector

The target modal matrix of the concave obstacle at .

The target modal matrix is as follows:

in,

pinv() stands for pseudo-inverse.

in,

Represents a vector perpendicular to both the first normal vector and the second normal vector. By constructing the vector, when the initial movement trajectory is corrected for obstacle avoidance, the corrected target movement trajectory can be moved outward along the tangent of the surface normal vector of the first obstacle and the second obstacle, to avoid obstacles.

Further, after obtaining the above-mentioned target modal matrix, the target modal matrix can be used to perform obstacle avoidance correction on the initial movement trajectory of the robot to obtain the target movement trajectory, wherein the formula of the target movement trajectory is as follows:

Among them, f(ξ) represents the initial movement trajectory,

Representation based on intersection point

Determine the target modal matrix,

Indicates the target movement trajectory after obstacle avoidance correction.

In the embodiment of the present invention, the above-mentioned obstacle avoidance correction method enables the robot to correct the path along the intersection line where the first convex obstacle and the second convex obstacle intersect, so as to realize the real-time tracking of the concave obstacle by the robot Avoidance.

represents the center point of convex obstacle 1,

represents the center point of convex obstacle 2,

in,

Represents the intersection point, which is located on the intersection line of convex obstacle 1 and convex obstacle 2, e ₁₂ represents the first normal vector of convex obstacle 1 and the second normal of convex obstacle 2 The vectors are all vertical vectors, and this vector is the obstacle avoidance direction of the initial movement trajectory, that is, the corrected target movement trajectory can move in this direction to achieve obstacle avoidance.

in,

Indicates the intersection point

the normal vector on the convex obstacle 1 of ,

Indicates the intersection point

The normal vector on convex obstacle 2, e ₁₂ means both perpendicular to

and

vector.

In the embodiment of the present invention, the above-mentioned method can solve the obstacle avoidance process for concave obstacles in the scenario that the intersection point is located on the intersection line, so that obstacle avoidance can be effectively realized.

In one embodiment, a robot obstacle avoidance device is proposed, the device includes: a processor and a memory, where a computer program is stored in the memory, and when the processor executes the computer program, the processor executes the following steps:

If the robot detects a concave obstacle in the process of traveling along the initial movement trajectory, it will divide the concave obstacle into two convex obstacles that intersect each other according to the shape of the concave obstacle, and determine the two convex obstacles that intersect each other. The intersection position of the shaped obstacle is the intersection line of the surface of the concave obstacle;

Predict the intersection of the initial movement trajectory and the surface of the concave obstacle when the initial movement trajectory reaches the concave obstacle;

According to the intersection point and the intersection line, the initial movement trajectory is corrected for obstacle avoidance, and the target movement trajectory is obtained, and obstacle avoidance is carried out according to the target movement trajectory.

In the embodiment of the present invention, the content involved in the steps in the above-mentioned robot obstacle avoidance device is similar to the content described in the above-mentioned embodiments related to the robot obstacle avoidance method. For details, please refer to the content in the foregoing method embodiment. No further elaboration here.

When a concave obstacle is detected, by dividing the concave obstacle into two intersecting convex obstacles, the obstacle avoidance problem of the concave obstacle can be transformed into two intersecting convex obstacles It simplifies the difficulty of avoiding obstacles of concave obstacles, and the initial movement trajectory can be carried out based on the predicted intersection points and the intersection positions of the two intersecting convex obstacles on the intersecting line of the surface of the concave obstacles. The obstacle avoidance correction makes it possible to effectively realize the obstacle avoidance of concave obstacles.

Figure 5 shows an internal structure diagram of the robot in one embodiment. Specifically, the robot may be a terminal or a server. As shown in Figure 5, the robot includes a processor, memory and network interface connected through a system bus. Wherein, the memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the robot stores an operating system, and also stores a computer program. When the computer program is executed by the processor, the processor can implement the age recognition method. A computer program may also be stored in the internal memory, and when the computer program is executed by the processor, the processor may execute the age identification method. Those skilled in the art can understand that the structure shown in FIG. 5 is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the robot to which the solution of the present application is applied. More or fewer components are shown in the figures, either in combination or with different arrangements of components.

In one embodiment, a robot is proposed, comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the following steps:

In one embodiment, a computer-readable storage medium is provided, which stores a computer program, and when the computer program is executed by a processor, causes the processor to perform the following steps:

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium , when the program is executed, it may include the flow of the above-mentioned method embodiments. Wherein, any reference to memory, storage, database or other medium used in the various embodiments provided in this application may include non-volatile and/or volatile memory. Nonvolatile memory may include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain Road (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, all It is considered to be the range described in this specification.

The above-mentioned embodiments only represent several embodiments of the present application, and the descriptions thereof are relatively specific and detailed, but should not be construed as a limitation on the scope of the patent of the present application. It should be pointed out that for those skilled in the art, without departing from the concept of the present application, several modifications and improvements can be made, which all belong to the protection scope of the present application. Therefore, the scope of protection of the patent of the present application shall be subject to the appended claims.

Claims

A robot obstacle avoidance method, characterized in that the method comprises:

If the robot detects a concave obstacle in the process of traveling along the initial movement trajectory, it divides the concave obstacle into two convex obstacles that intersect each other according to the shape of the concave obstacle, and determines that the two intersect each other. The intersection of the two convex obstacles is at the intersection of the surfaces of the concave obstacles;

predicting the intersection of the initial movement trajectory and the surface of the concave obstacle when the initial movement trajectory reaches the concave obstacle;

The initial movement trajectory is corrected for obstacle avoidance according to the intersection point and the intersection line to obtain a target movement trajectory, and obstacle avoidance is performed according to the target movement trajectory.
The method according to claim 1, wherein, performing obstacle avoidance correction on the initial movement trajectory according to the intersection point and the intersection line to obtain a target movement trajectory, comprising:

determining a target modal matrix according to the intersection point and the intersection line;

The initial movement trajectory is corrected for obstacle avoidance by using the target modal matrix to obtain a target movement trajectory.
The method according to claim 2, wherein the determining the target modal matrix according to the intersection point and the intersection line comprises:

Calculate the surface function of each of the convex obstacles, and determine the positional relationship between the intersection point and the intersection line;

The target modal matrix is determined according to the surface function and the positional relationship of each of the convex obstacles.
The method according to claim 3, wherein the determining the target modal matrix according to the surface function of each of the convex obstacles and the positional relationship comprises:

When the positional relationship is that the intersection point is not located on the intersection line, obtain the modal matrix of each convex obstacle by using the surface function of each convex obstacle;

Combining the modal matrices of each of the convex obstacles to obtain a combined modal matrix, and using the combined modal matrix as the target modal matrix.
The method according to claim 2, wherein the determining the target modal matrix according to the surface function of each of the convex obstacles and the positional relationship comprises:

When the positional relationship is that the intersection point is located on the intersection line, determine a first convex obstacle and a second convex obstacle that form a target intersection line, and the target intersection line is where the intersection point is located intersecting lines;

The target modal matrix is determined according to the first surface function of the first convex obstacle and the second surface function of the second convex obstacle.
The method according to claim 5, wherein the target mode is determined according to a first surface function of the first convex obstacle and a second surface function of the second convex obstacle matrix, including:

A first normal vector of the intersection point at the first convex obstacle is determined using the first surface function, and a first normal vector of the intersection point at the second convex obstacle is determined using the second surface function the second normal vector;

The target mode matrix is constructed using the first surface function, the second surface function, the first normal vector, and the second normal vector.
The method according to claim 1, wherein the method further comprises:

receive task instructions;

Using the task instruction and the continuous function based on the dynamic system, the initial movement trajectory of the robot is determined.
A robot obstacle avoidance device, characterized in that the device includes a processor and a memory, and a computer program is stored in the memory, and when the processor executes the computer program, the processor is caused to perform the following steps:

If the robot detects a concave obstacle in the process of traveling along the initial movement trajectory, it divides the concave obstacle into two convex obstacles that intersect each other according to the shape of the concave obstacle, and determines that the two intersect each other. The intersection of the two convex obstacles is at the intersection of the surfaces of the concave obstacles;

predicting the intersection of the initial movement trajectory and the surface of the concave obstacle when the initial movement trajectory reaches the concave obstacle;

The initial movement trajectory is corrected for obstacle avoidance according to the intersection point and the intersection line to obtain a target movement trajectory, and obstacle avoidance is performed according to the target movement trajectory.
A computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the processor is caused to perform the following steps:

If the robot detects a concave obstacle in the process of traveling along the initial movement trajectory, it divides the concave obstacle into two convex obstacles that intersect each other according to the shape of the concave obstacle, and determines that the two intersect each other. The intersection of the two convex obstacles is at the intersection of the surfaces of the concave obstacles;

predicting the intersection of the initial movement trajectory and the surface of the concave obstacle when the initial movement trajectory reaches the concave obstacle;

The initial movement trajectory is corrected for obstacle avoidance according to the intersection point and the intersection line to obtain a target movement trajectory, and obstacle avoidance is performed according to the target movement trajectory.
A robot comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the following steps:

If the robot detects a concave obstacle in the process of traveling along the initial movement trajectory, it divides the concave obstacle into two convex obstacles that intersect each other according to the shape of the concave obstacle, and determines that the two intersect each other. The intersection of the two convex obstacles is at the intersection of the surfaces of the concave obstacles;

predicting the intersection of the initial movement trajectory and the surface of the concave obstacle when the initial movement trajectory reaches the concave obstacle;

The initial movement trajectory is corrected for obstacle avoidance according to the intersection point and the intersection line to obtain a target movement trajectory, and obstacle avoidance is performed according to the target movement trajectory.