CN112650235A - Robot obstacle avoidance control method and system and robot - Google Patents
Robot obstacle avoidance control method and system and robot Download PDFInfo
- Publication number
- CN112650235A CN112650235A CN202011501731.6A CN202011501731A CN112650235A CN 112650235 A CN112650235 A CN 112650235A CN 202011501731 A CN202011501731 A CN 202011501731A CN 112650235 A CN112650235 A CN 112650235A
- Authority
- CN
- China
- Prior art keywords
- obstacle
- robot
- current position
- moving
- obstacles
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000001514 detection method Methods 0.000 claims abstract description 37
- 230000002452 interceptive effect Effects 0.000 claims description 44
- 230000004888 barrier function Effects 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 11
- 230000003068 static effect Effects 0.000 claims description 8
- 238000001914 filtration Methods 0.000 description 11
- 230000003993 interaction Effects 0.000 description 6
- 241001465754 Metazoa Species 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 238000010408 sweeping Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 241000282414 Homo sapiens Species 0.000 description 2
- 230000000670 limiting effect Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000002829 reductive effect Effects 0.000 description 2
- 238000005260 corrosion Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0255—Control of position or course in two dimensions specially adapted to land vehicles using acoustic signals, e.g. ultra-sonic singals
Abstract
The invention relates to a robot obstacle avoidance control method, a system and a robot, wherein the obstacle avoidance control method comprises the following steps: acquiring obstacle detection information, and judging whether an obstacle exists in the advancing direction; when the obstacle exists in the advancing direction, acquiring the current position of the robot and current position image information, wherein the current position image information comprises an image in a target angle range; determining an influence area of the obstacle by combining the obstacle detection information and the current position image information; planning a new travel path of the robot according to the influence area of the obstacle and the current position and the target position of the robot; and performing drive control according to the planned new travel path. The method can identify the obstacles with different heights, determines respective influence areas aiming at the obstacles with different categories, can effectively deal with the obstacles with different forms, and improves the flexibility of obstacle avoidance; the problem of dead angle can be avoided, and the accuracy of avoiding the obstacle is effectively improved.
Description
Technical Field
The invention relates to the field of robot motion control, in particular to a robot obstacle avoidance control method, a system and a robot.
Background
With the continuous development of the technology, the service robot can undertake functions of routing inspection, distribution, welcoming, inquiry, guidance and the like, can effectively save manpower and material resources, and improves the service quality. Therefore, service robots are increasingly used in places such as bank halls and service halls, and in logistics and power industries.
By constructing a site map and combining a path planning algorithm, the service robot can perform autonomous navigation and autonomous obstacle avoidance and move and work in a site. However, in practical use, the service robot often encounters many uncertain factors, such as moving obstacles, dead corners, suspended obstacles, and the like. The existing obstacle avoidance method often uses a single obstacle detection and judgment scheme, and can not accurately identify obstacles in all forms, such as transparent obstacles, suspended obstacles, ropes and the like, which may influence the movement of the service robot. Meanwhile, the existing obstacle avoidance scheme can only acquire the information of the obstacles in the front fixed angle range, and if the size of the obstacles is very large, the obstacle avoidance scheme is likely to cause that the service robot cannot advance and the obstacle avoidance fails in the front fixed angle range and cannot find an evaded path.
Therefore, the existing obstacle avoidance scheme cannot flexibly and effectively deal with obstacles with different forms and needs to be improved.
Disclosure of Invention
Therefore, it is necessary to provide a robot obstacle avoidance control method, system and robot for solving the problems that the existing robot has a single obstacle avoidance method and cannot effectively deal with obstacles of different forms.
An embodiment of the application provides a robot obstacle avoidance control method, which includes:
acquiring obstacle detection information, and judging whether an obstacle exists in the advancing direction;
when the obstacle exists in the advancing direction, acquiring the current position of the robot and current position image information, wherein the current position image information comprises an image in a target angle range;
determining an influence area of the obstacle by combining the obstacle detection information and the current position image information;
planning a new travel path of the robot according to the influence area of the obstacle and the current position and the target position of the robot;
and performing drive control according to the planned new travel path.
In some embodiments, the obstacle includes a stationary obstacle and a moving obstacle, and the step of acquiring obstacle detection information and determining whether there is an obstacle in the traveling direction includes:
acquiring obstacle detection information in a front preset range by using a sensor; the obstacle detection information comprises the position, the size, the moving speed and the moving direction of the obstacle;
and judging whether an obstacle exists in the advancing direction or not according to the position, the moving speed and the moving direction of the obstacle.
In some embodiments, the step of determining whether there is an obstacle in the traveling direction according to the position, the moving speed, and the moving direction of the obstacle specifically includes;
when the obstacle is a static obstacle, judging whether the obstacle exists in the advancing direction according to the position of the obstacle;
when the obstacle is a moving obstacle, calculating a moving track of the obstacle according to the position, the moving speed and the moving direction of the obstacle; and when an intersection point exists between the moving track and the planned path of the robot, judging that an obstacle exists in the advancing direction.
In some embodiments, the obstacle detection information includes a size of an obstacle, and the target angle is determined according to the size of the obstacle, a position of the obstacle and the robot.
In some embodiments, the obstacle is divided into a stationary obstacle, a non-interactive moving obstacle, and an interactive moving obstacle, and the step of determining the influence area of the obstacle by combining the obstacle detection information and the current position image information specifically includes:
carrying out image recognition on the current position image information to obtain areas occupied by the obstacles at different heights;
judging the type of the obstacle according to the obstacle detection information;
and when the obstacle is judged to be a static obstacle, integrating the occupied areas at all heights to obtain the influence area of the obstacle.
In some embodiments, the determining the influence area of the obstacle by combining the obstacle detection information and the current position image information further includes:
and when the obstacle is judged to be the non-interactive moving obstacle, determining the influence area of the obstacle according to the moving speed, the moving direction and the size of the obstacle, the planned path, the moving speed and the size of the robot.
In some embodiments, the step of planning a new travel path of the robot according to the influence area of the obstacle and the current position and the destination position of the robot includes:
and planning a new traveling path of the robot by adopting a tangent path algorithm according to the influence area of the obstacle and the current position and the target position of the robot.
An embodiment of the present application further provides an obstacle avoidance control system for a robot, including:
the obstacle judging unit is used for acquiring obstacle detection information and judging whether an obstacle exists in the advancing direction;
the image acquisition unit is used for acquiring the current position of the robot and current position image information when judging that an obstacle exists in the advancing direction, wherein the current position image information comprises an image in a target angle range;
the influence area judging unit is used for determining the influence area of the obstacle by combining the obstacle detection information and the current position image information;
the path revising unit is used for planning a new traveling path of the robot according to the influence area of the obstacle, the current position and the target position of the robot;
and the mobile traveling unit is used for carrying out driving control according to the planned new traveling path.
An embodiment of the present application further provides a robot, including a motion control component, a memory, and a processor, where the memory is used for storing a program;
the processor is configured to execute a program in the memory, control the motion control component, and implement the robot obstacle avoidance control method according to any one of the foregoing embodiments;
and the motion control component is used for driving the robot to move according to the control of the processor.
Another embodiment of the present application further provides a machine-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the robot obstacle avoidance control method according to any of the foregoing embodiments.
According to the obstacle avoidance control scheme for the robot, when the obstacle exists in the advancing direction, image information in a target angle range can be collected, the influence area of the obstacle is determined by identifying the image, and then the advancing path of the robot is re-planned according to the influence area of the obstacle. Compared with the existing scheme, the method has the advantages that the obstacles with different heights can be identified by means of image identification combined with the mode that the sensor detects the obstacles, respective influence areas are determined according to the obstacles with different types, the obstacles with different forms can be effectively dealt with, and the obstacle avoidance flexibility is improved; in addition, the image for identification is acquired within a certain rotation angle range, so that the problem of dead angles can be avoided, and the accuracy of obstacle avoidance is effectively improved.
Drawings
Fig. 1 is a schematic flowchart of a robot obstacle avoidance control method according to an embodiment of the present application;
FIG. 2 is a schematic diagram of an application of a tangent path algorithm;
fig. 3 is a schematic structural diagram of a frame of a robot obstacle avoidance control system according to an embodiment of the present application;
fig. 4 is a schematic diagram of a frame structure of a robot according to an embodiment of the present application.
Detailed Description
In order that the above objects, features and advantages of the present application can be more clearly understood, a detailed description of the present application will be given below with reference to the accompanying drawings and detailed description. In addition, the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein in the description of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.
As shown in fig. 1, an embodiment of the present application discloses a robot obstacle avoidance control method, including:
step S100, obtaining obstacle detection information and judging whether an obstacle exists in the advancing direction;
the robot may store a scene map and a planned path according to which the robot moves.
Obstacle detection information can be acquired by using a sensor; whether an obstacle exists in the traveling direction is determined based on the obstacle detection information. The sensor may be one or more of a lidar, an infrared sensor, an ultrasonic sensor, a depth camera.
In order to be able to identify transparent obstacles such as glass, in some embodiments, at least an ultrasonic sensor is used to determine obstacles in the direction of travel.
In order to improve the accuracy of obstacle detection and avoid missing small obstacles, the ultrasonic sensor can be combined with one or more of a laser radar, an infrared sensor and a depth camera on the basis of using the ultrasonic sensor.
In some embodiments, the obstacle detection information may be acquired using a depth camera, a lidar, and an ultrasonic sensor simultaneously. For example, a depth camera may be provided at the top front position of the robot to detect obstacles at different heights; the lidar and the ultrasonic sensor may be arranged at a bottom position or a middle position of the robot. The ultrasonic sensors may be provided in a number of 2 or more, distributed around the front of the robot. The laser radar can be arranged in 1, and is positioned in front of the robot. It will be appreciated that the depth camera, lidar and ultrasonic sensor may be located at other positions as well, depending on the actual requirements. The number of depth cameras, lidar and ultrasonic sensors may also be increased or decreased as desired.
In some embodiments, when the sensor is used to detect an obstacle, obstacle detection information within a front preset range may be obtained. The front preset range may include not only the traveling direction but also regions on both sides of the traveling direction. The obstacle detection information may include not only the position and size of the obstacle but also the moving speed and moving direction of the obstacle. Depending on whether the obstacle is movable or not, the obstacle may be divided into a stationary obstacle and a moving obstacle. And for the moving obstacle, calculating the moving track of the moving obstacle according to the position, the moving speed and the moving direction, and judging whether the moving track of the moving obstacle is intersected with the planned path of the robot or not.
Thus, when the obstacle is judged to exist in the traveling direction, the method not only comprises the step of detecting the static obstacle in the traveling direction, but also comprises the step of moving the obstacle of which the moving track and the planned path have an intersection point.
Furthermore, in order to more accurately judge whether the moving obstacle belongs to the obstacle in the traveling direction, the moving speed of the robot can be acquired, and whether the robot and the moving obstacle reach the intersection point at the same time is judged. Only when the robot and the moving obstacle reach the intersection point at the same time, the obstacle in the advancing direction can be judged.
When determining whether the robot and the moving obstacle reach the intersection at the same time, the robot and the moving obstacle may be used as one mass point, or the sizes of the robot and the moving obstacle may be considered at the same time.
Step S300, when judging that an obstacle exists in the advancing direction, acquiring the current position of the robot and current position image information, wherein the current position image information comprises an image in a target angle range;
the target angle may be set to a fixed value. For example, the target angle may be set to 180 ° in the direction of travel of the robot, i.e. the entire front of the robot. The target angle may also be set to 270 deg., 135 deg. on either side, with the direction of travel of the robot being the centre line. It is understood that the target angle can be freely determined according to actual conditions.
The target angle may also be determined according to the determined obstacle, for example, according to the size of the obstacle preliminarily detected by the sensor, and according to the distance between the obstacle and the robot, the coverage angle of the obstacle relative to the robot is determined, and then the target angle is determined according to the coverage angle.
For example, the margin angle may be increased based on the coverage angle of the obstacle to obtain the target angle. The margin angle is added to provide an image of an area where a new travel path may exist to facilitate planning of the new travel path. The margin angle may be set to a fixed value or may be determined according to the size of the robot. In the latter scheme, the minimum passing angle corresponding to the minimum passing width for the robot to pass through can be determined according to the size of the obstacle and the distance between the obstacle and the robot. The margin angle may be N minimum pass angles, where N is a positive integer. The minimum passing width may be the width of the robot, or may be a width slightly larger than the width of the robot, for example, the width of the robot plus an offset value allowed during movement.
The larger the target angle is, the more information contained in the current position image information is, more help can be provided for subsequent processing, for example, when a new traveling path is planned, not only forward walking can be performed, but also a scheme of backward walking and detour can be planned, and the obstacle avoidance mode is more flexible.
When the current position image information is obtained, the robot can be controlled to rotate the target angle, so that the image in the target angle range is obtained.
Step S500, determining an influence area of the obstacle by combining the obstacle detection information and the current position image information;
the moving obstacles can be divided into interactive moving obstacles and non-interactive moving obstacles according to whether the obstacles can interact or not. The interaction means that the robot can perform communication interaction with the obstacle, for example, path information such as a planning path, a destination position and the like and other information are interacted in a wireless communication mode.
The detected moving obstacles may be human beings or animals, pushed furniture, sweeping robots and other non-interactive robots, and may also be other similar robots. For the robot, communication interaction cannot be performed between the robot and a person, an animal, pushed furniture, a sweeping robot and the like, so that the person, the animal, the pushed furniture, the sweeping robot and the like are non-interactive moving obstacles. For the robots of the same type, path information such as a planning path, a destination position and the like can be interacted among the robots, and the moving speed and the moving direction of one of the robots can be controlled through interaction. Thus, a robot of the same kind may be an interactively movable obstacle. Of course, the movable barrier capable of interacting may also include other kinds of robots as long as the two can perform communication interaction.
Thus, obstacles can be divided into stationary obstacles, interactive moving obstacles and non-interactive moving obstacles.
According to the obstacle detection information, the type of the obstacle in the static obstacle and the moving obstacle can be determined. The determination of the interactive moving obstacle can be performed by performing image recognition on the current position image information, for example, by means of image recognition, the similarity between the moving obstacle and the robot is determined, and if the similarity exceeds a preset determination threshold, the moving obstacle can be determined as the interactive moving obstacle. In some embodiments, the robot may also send an interaction request to the moving obstacle, and if the moving obstacle returns corresponding feedback information, it is determined that the moving obstacle is an interactive moving obstacle, otherwise, it is determined that the moving obstacle is an non-interactive moving obstacle.
Different kinds of obstacles may have different ways of determining their area of influence. For stationary obstacles, the area of influence may be determined directly from the area occupied by the stationary obstacle. In determining the area occupied by the stationary obstacle, it may be performed in combination with the obstacle detection information and the current position image information. By carrying out image recognition on the current position image information, the areas occupied by the obstacles at different heights can be recognized, and the influence areas of the static obstacles are obtained by integrating the areas occupied by the static obstacles at all heights. In this way, the influence area of the stationary obstacle with a narrow lower part and a wide upper part can be effectively identified.
When image recognition is performed on the current position image information, preprocessing may be performed first. And the preprocessing can comprise filtering processing and filling processing. The filtering process is performed to reduce noise and smooth the curve. And filtering processing, including two broad categories of schemes of linear filtering and nonlinear filtering. The linear filtering can adopt a weighted average filtering algorithm of a domain average filtering algorithm and the like, and the nonlinear filtering can adopt a median filtering algorithm, a Gaussian map filtering algorithm and the like. And filling, namely filling holes and gaps by mainly utilizing mathematical morphology algorithms, such as expansion, corrosion, opening operation, closing operation and the like, so that obstacles in the image can be identified in a follow-up manner.
It will be appreciated that since the robot also has its own height, it requires a region of passage as long as there are no obstacles within the height of the robot. Therefore, when the influence area of the stationary obstacle is determined, only the area occupied by the stationary obstacle within the height of the robot may be integrated.
It will be appreciated that the current position image information may be a video, comprising image frames of several consecutive frames. An optical flow algorithm may also be used to perform image recognition on the current position image information.
In some embodiments, multiple obstacles may be detected. When determining the influence areas of the plurality of obstacles, it is also necessary to consider whether the interval between the occupied areas of the plurality of obstacles is greater than the minimum passing width of the robot. And if the interval between the occupied areas of the two obstacles is smaller than the minimum passing width of the robot, regarding the two obstacles as a virtual obstacle, and fusing the occupied areas of the two obstacles together to form the influence area of the virtual obstacle for the use of the subsequent steps.
For the non-interactive moving obstacle, the influence area of the non-interactive moving obstacle can be determined according to the moving speed, the moving direction and the size of the non-interactive moving obstacle, and the planned path, the moving speed and the size of the robot.
For example, the area of influence of a non-interactable moving obstacle may be determined as follows.
Calculating the movement track of the non-interactive moving barrier according to the size, the movement speed and the movement direction of the non-interactive moving barrier, and determining the intersection area of the movement track and the planned path by combining the planned path of the robot;
calculating a first prediction time when the robot starts to enter the intersection area and a second prediction time when the robot leaves the intersection area according to the planned path and the moving speed of the robot;
and calculating the movement track range of the non-interactive moving obstacle between the first prediction time and the second prediction time as the influence area of the non-interactive moving obstacle.
When the movement track of the non-interactive moving obstacle is calculated, the current position image information can be utilized for image recognition, and the type of the non-interactive moving obstacle is determined. The categories of the non-interactive moving obstacles can be classified into a predictable category, a low deviation category and a high deviation category according to the degree of predictability of the moving track. The high deviation category is mainly human and animal, and the movement track of the high deviation category may have a higher deviation relative to the movement track predicted on the duration data. The low deviation category may be an object that has a certain driving capability but can move according to its own plan or rule, such as a sweeping robot that performs a specific task and is not interactive, because of its own driving capability, a certain deviation may occur on a historical movement track. Predictable categories, typically referring to objects without driving capability, such as pushed seats and the like, the movement evasion of which is typically highly predictable. For the high deviation category, when the movement track is predicted, a large deviation amount needs to be added, so that the obtained movement track is a large area. For the low deviation category, when the movement track is predicted, a small offset is added, and the obtained movement track is a relatively large area. And if the category can be predicted, the movement track can be predicted by directly using historical movement data in the detected obstacle information.
For the interactive moving barrier, the robot can interact with the interactive moving barrier to obtain a planned path of the interactive moving barrier;
determining a junction area according to the planned path of the robot and the planned path of the interactive movable barrier;
calculating a first prediction time when the robot starts to enter the intersection area and a second prediction time when the robot leaves the intersection area according to the planned path and the moving speed of the robot;
and calculating the movement track range of the interactive movable barrier between the first prediction time and the second prediction time as the influence area of the interactive movable barrier.
In order to reduce the variation of the new travel path during obstacle avoidance, when the robot interacts with the interactive moving obstacle, a request can be sent to the interactive moving obstacle to request to reduce the moving speed of the interactive moving obstacle. Therefore, the moving track range of the interactive moving barrier between the first prediction time and the second prediction time can be reduced, and the influence area of the interactive moving barrier is further reduced.
It will be appreciated that in some cases, by reducing the speed of movement of the interactive moving obstacle, the robot and the interactive moving obstacle may not reach the intersection at the same time, and the interactive moving obstacle may no longer constitute an obstacle in the direction of travel.
In some embodiments, when the robot interacts with an interactive moving obstacle, task priorities can be interacted, a party with a high task priority can pass through the robot preferentially, and a party with a low task priority needs to avoid the obstacle. At this time, if the task priority of the robot is higher than the interactive moving obstacle, the influence area of the interactive moving obstacle is 0. Otherwise, the determination may be made according to the method of determining the influence area of the interactive moving obstacle. It is to be understood that, when determining the one that preferentially passes through, the one that has the shorter distance may be selected as the one that preferentially passes through, based on the distance between the robot and the intersection area and the distance between the movable obstacle that can interact with the intersection area.
And step S700, planning a new traveling path of the robot according to the influence area of the obstacle, the current position and the target position of the robot.
After the influence area of the obstacle, the current position and the target position of the robot are obtained, a new traveling path of the robot can be planned according to a tangent path algorithm.
For example, as shown in the figure, it is assumed that the robot is at the position a, the area of influence of the obstacle S is a circular area of Rs, and the destination position is B, then according to the tangent path algorithm, a tangent path from the position a to the circular area of Rs may be taken as a tangent path of the robot avoiding the obstacle S, such as a-C1 (or another tangent path a-C2) from the position a to the position C1. Then, from the position C1, a predicted path to the destination position B, namely C1-B, is planned. Two paths in front and at the back, namely the tangent path A-C1 and the predicted path C1-B, can jointly form a new traveling path A-C1-B.
When the area of influence of the obstacle S is not circular, there may be two or more tangential paths. At this time, the tangential path with the minimum length can be selected, and then the predicted path is planned according to the target position, so as to obtain a new traveling path of the robot.
It is to be understood that, when there are a plurality of tangential paths, a predicted path to the target position may be calculated for each tangential path, and then the one with the smallest sum of the tangential paths and the predicted path may be selected and identified as the new travel path of the robot.
And step S900, performing drive control according to the planned new travel path.
After the new travel path is determined, the robot can move accordingly. In the subsequent moving process, the method can be continuously repeated, and a new traveling path is planned again aiming at the newly encountered obstacles.
According to the obstacle avoidance control method for the robot, when the obstacle exists in the advancing direction, image information in a target angle range is collected, the influence area of the obstacle is determined by identifying the image, and then the advancing path of the robot is re-planned according to the influence area of the obstacle. Compared with the existing scheme, the method has the advantages that the obstacles with different heights can be identified by means of image identification combined with the mode that the sensor detects the obstacles, respective influence areas are determined according to the obstacles with different types, the obstacles with different forms can be effectively dealt with, and the obstacle avoidance flexibility is improved; in addition, the image for identification is acquired within a certain rotation angle range, so that the problem of dead angles can be avoided, and the accuracy of obstacle avoidance is effectively improved.
It should be noted that, for simplicity of description, the method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the embodiments are not limited by the order of acts described, as some steps may occur in other orders or concurrently depending on the embodiments. Further, those skilled in the art will also appreciate that the embodiments described in the specification are presently preferred and that no particular act is required of the embodiments of the application.
An embodiment of the present application further provides an obstacle avoidance control system for a robot, as shown in fig. 3, including:
an obstacle determination unit 100 configured to acquire obstacle detection information and determine whether an obstacle is present in a traveling direction;
an image obtaining unit 300 configured to obtain a current position of the robot when it is determined that an obstacle exists in the traveling direction, and current position image information, the current position image information including an image within a target angle range;
an influence area determination unit 500 configured to determine an influence area of the obstacle by combining the obstacle detection information and the current position image information;
a path revising unit 700 for planning a new travel path of the robot according to the influence area of the obstacle and the current position and the target position of the robot;
and a moving unit 900 for performing driving control according to the planned new travel path.
For the detailed working modes of the obstacle determination unit 100, the image acquisition unit 300, the affected area determination unit 500, the path revision unit 700, and the moving travel unit 900, reference may be made to the description in the foregoing method embodiments, and no further description is given here.
The robot obstacle avoidance control system provided by the embodiment of the application can acquire image information in a target angle range when detecting that an obstacle exists in a traveling direction, determines an influence area of the obstacle by identifying the image, and then replans a traveling path of the robot according to the influence area of the obstacle. Compared with the existing scheme, the scheme can identify the obstacles with different heights by combining the mode of detecting the obstacles by the image identification and the sensor, determines respective influence areas aiming at the obstacles with different categories, can effectively deal with the obstacles with different forms, and improves the flexibility of obstacle avoidance; in addition, the image for identification is acquired within a certain rotation angle range, so that the problem of dead angles can be avoided, and the accuracy of obstacle avoidance is effectively improved.
An embodiment of the present application further provides a robot, as shown in fig. 4, including a motion control unit 10, a memory 20, and a processor 30, where the memory 20 is used for storing a program; a processor 30, configured to execute a program in a memory, control the motion control unit 10, and implement the robot obstacle avoidance control method according to any of the embodiments; and a motion control part 10 for driving the robot to move according to the control of the processor 300.
An embodiment of the present application further provides a machine-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the robot obstacle avoidance control method according to any of the above embodiments.
The system/computer device integrated components/modules/units, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow in the method according to the above embodiments may be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable storage medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.
Each functional module/component in the embodiments of the present application is only one logical functional division, and there may be another division manner in actual implementation. They may be integrated into the same processing module/component, or each module/component may exist alone physically, or two or more modules/components may be integrated into the same module/component. The integrated modules/components can be implemented in the form of hardware, or can be implemented in the form of hardware plus software functional modules/components.
It will be evident to those skilled in the art that the embodiments of the present application are not limited to the details of the foregoing illustrative embodiments, and that the embodiments of the present application can be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the embodiments being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned. Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. Several units, modules or means recited in the system, apparatus or terminal claims may also be implemented by one and the same unit, module or means in software or hardware. The terms first, second, etc. are used to denote names, but not any particular order.
Claims (10)
1. A robot obstacle avoidance control method is characterized by comprising the following steps:
acquiring obstacle detection information, and judging whether an obstacle exists in the advancing direction;
when the obstacle exists in the advancing direction, acquiring the current position of the robot and current position image information, wherein the current position image information comprises an image in a target angle range;
determining an influence area of the obstacle by combining the obstacle detection information and the current position image information;
planning a new travel path of the robot according to the influence area of the obstacle and the current position and the target position of the robot;
and performing drive control according to the planned new travel path.
2. The robot obstacle avoidance control method according to claim 1, wherein the obstacles include a stationary obstacle and a moving obstacle, and the step of acquiring obstacle detection information and determining whether there is an obstacle in a traveling direction specifically includes:
acquiring obstacle detection information in a front preset range by using a sensor; the obstacle detection information comprises the position, the size, the moving speed and the moving direction of the obstacle;
and judging whether an obstacle exists in the advancing direction or not according to the position, the moving speed and the moving direction of the obstacle.
3. The robot obstacle avoidance control method according to claim 2, wherein the step of determining whether there is an obstacle in the direction of travel according to the position, the moving speed, and the moving direction of the obstacle specifically includes;
when the obstacle is a static obstacle, judging whether the obstacle exists in the advancing direction according to the position of the obstacle;
when the obstacle is a moving obstacle, calculating a moving track of the obstacle according to the position, the moving speed and the moving direction of the obstacle; and when an intersection point exists between the moving track and the planned path of the robot, judging that an obstacle exists in the advancing direction.
4. The robot obstacle avoidance control method according to claim 1,
the obstacle detection information comprises the size of an obstacle, and the target angle is determined according to the size of the obstacle and the positions of the obstacle and the robot.
5. The robot obstacle avoidance control method according to claim 1, wherein the obstacles are divided into stationary obstacles, non-interactive moving obstacles, and the step of determining the influence area of the obstacle by combining obstacle detection information and current position image information specifically includes:
carrying out image recognition on the current position image information to obtain areas occupied by the obstacles at different heights;
judging the type of the obstacle according to the obstacle detection information;
and when the obstacle is judged to be a static obstacle, integrating the occupied areas at all heights to obtain the influence area of the obstacle.
6. The robot obstacle avoidance control method according to claim 5, wherein the step of determining an area of influence of the obstacle in combination with the obstacle detection information and the current position image information further comprises:
and when the obstacle is judged to be the non-interactive moving obstacle, determining the influence area of the obstacle according to the moving speed, the moving direction and the size of the obstacle, the planned path, the moving speed and the size of the robot.
7. The robot obstacle avoidance control method according to claim 1, wherein the step of planning a new travel path of the robot according to an influence area of the obstacle, a current position of the robot, and a target position of the robot specifically comprises:
and planning a new traveling path of the robot by adopting a tangent path algorithm according to the influence area of the obstacle and the current position and the target position of the robot.
8. The utility model provides a barrier control system is kept away to robot which characterized in that includes:
the obstacle judging unit is used for acquiring obstacle detection information and judging whether an obstacle exists in the advancing direction;
the image acquisition unit is used for acquiring the current position of the robot and current position image information when judging that an obstacle exists in the advancing direction, wherein the current position image information comprises an image in a target angle range;
the influence area judging unit is used for determining the influence area of the obstacle by combining the obstacle detection information and the current position image information;
the path revising unit is used for planning a new traveling path of the robot according to the influence area of the obstacle, the current position and the target position of the robot;
and the mobile traveling unit is used for carrying out driving control according to the planned new traveling path.
9. A robot comprising a motion control unit, a memory and a processor,
the memory is used for storing programs;
the processor is used for executing the program in the memory, controlling the motion control component and realizing the robot obstacle avoidance control method of any one of claims 1 to 7;
and the motion control component is used for driving the robot to move according to the control of the processor.
10. A machine readable storage medium having stored thereon a computer program, wherein the computer program, when executed by a processor, implements the robot obstacle avoidance control method of any of claims 1-7.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202020295669 | 2020-03-11 | ||
| CN2020202956699 | 2020-03-11 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112650235A true CN112650235A (en) | 2021-04-13 |
Family
ID=75355097
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011501731.6A Pending CN112650235A (en) | 2020-03-11 | 2020-12-18 | Robot obstacle avoidance control method and system and robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112650235A (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111240342A (en) * | 2020-03-12 | 2020-06-05 | 南京奥拓电子科技有限公司 | Robot obstacle avoidance control method and device, robot and robot system |
| CN113359754A (en) * | 2021-06-25 | 2021-09-07 | 深圳市海柔创新科技有限公司 | Obstacle avoidance method, obstacle avoidance device, electronic device, and storage medium |
| CN113390417A (en) * | 2021-06-25 | 2021-09-14 | 深圳市优必选科技股份有限公司 | Robot and navigation method, device and computer readable storage medium thereof |
| CN113532461A (en) * | 2021-07-08 | 2021-10-22 | 山东新一代信息产业技术研究院有限公司 | Robot autonomous obstacle avoidance navigation method, equipment and storage medium |
| CN113807795A (en) * | 2021-10-19 | 2021-12-17 | 上海擎朗智能科技有限公司 | Method for identifying congestion in robot distribution scene, robot and distribution system |
| CN114089756A (en) * | 2021-11-16 | 2022-02-25 | 合肥瓦力觉启机器人科技有限公司 | Robot obstacle avoidance method and system |
| CN114265399A (en) * | 2021-11-25 | 2022-04-01 | 北京顺造科技有限公司 | Obstacle recognition method and automatic cleaning equipment |
| CN114326729A (en) * | 2021-12-27 | 2022-04-12 | 上海擎朗智能科技有限公司 | Movement and movement control method, electronic device and medium |
| CN114360274A (en) * | 2021-12-13 | 2022-04-15 | 珠海格力智能装备有限公司 | Distribution vehicle navigation method, system, computer equipment and storage medium |
| CN114721404A (en) * | 2022-06-08 | 2022-07-08 | 超节点创新科技(深圳)有限公司 | Obstacle avoidance method, robot and storage medium |
| CN114879701A (en) * | 2022-06-23 | 2022-08-09 | 池州市安安新材科技有限公司 | Robot track obstacle avoidance method and system |
| CN115705045A (en) * | 2021-08-03 | 2023-02-17 | 北京小米移动软件有限公司 | Autonomous cruising method and device of movable equipment and movable equipment |
| CN115718489A (en) * | 2022-11-10 | 2023-02-28 | 中元宇(北京)物联网科技有限公司 | Path planning method and system of epidemic prevention intelligent robot |
| WO2023115658A1 (en) * | 2021-12-22 | 2023-06-29 | 广东栗子科技有限公司 | Intelligent obstacle avoidance method and apparatus |
| WO2023148944A1 (en) * | 2022-02-04 | 2023-08-10 | 日本電気株式会社 | Action scheduling system, action scheduling device, and action scheduling method |
| CN114089756B (en) * | 2021-11-16 | 2024-04-30 | 合肥瓦力觉启机器人科技有限公司 | Robot obstacle avoidance method and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102799185A (en) * | 2012-09-05 | 2012-11-28 | 浙江大学 | Intelligent safety patrol system based on DaNI mobile robot platform |
| CN103645733A (en) * | 2013-12-02 | 2014-03-19 | 江苏建威电子科技有限公司 | A robot automatically finding a charging station and a system and method for automatically finding a charging station thereof |
| CN108351649A (en) * | 2015-09-15 | 2018-07-31 | 深圳市大疆创新科技有限公司 | System and method for UAV interactive instructions and control |
| CN108885459A (en) * | 2018-06-08 | 2018-11-23 | 珊口（深圳）智能科技有限公司 | Air navigation aid, navigation system, mobile control system and mobile robot |
| CN110757446A (en) * | 2018-07-25 | 2020-02-07 | 深圳市优必选科技有限公司 | Robot recharging login method and device and storage device |
-
2020
- 2020-12-18 CN CN202011501731.6A patent/CN112650235A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102799185A (en) * | 2012-09-05 | 2012-11-28 | 浙江大学 | Intelligent safety patrol system based on DaNI mobile robot platform |
| CN103645733A (en) * | 2013-12-02 | 2014-03-19 | 江苏建威电子科技有限公司 | A robot automatically finding a charging station and a system and method for automatically finding a charging station thereof |
| CN108351649A (en) * | 2015-09-15 | 2018-07-31 | 深圳市大疆创新科技有限公司 | System and method for UAV interactive instructions and control |
| CN108885459A (en) * | 2018-06-08 | 2018-11-23 | 珊口（深圳）智能科技有限公司 | Air navigation aid, navigation system, mobile control system and mobile robot |
| CN110757446A (en) * | 2018-07-25 | 2020-02-07 | 深圳市优必选科技有限公司 | Robot recharging login method and device and storage device |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111240342A (en) * | 2020-03-12 | 2020-06-05 | 南京奥拓电子科技有限公司 | Robot obstacle avoidance control method and device, robot and robot system |
| CN113359754A (en) * | 2021-06-25 | 2021-09-07 | 深圳市海柔创新科技有限公司 | Obstacle avoidance method, obstacle avoidance device, electronic device, and storage medium |
| CN113390417A (en) * | 2021-06-25 | 2021-09-14 | 深圳市优必选科技股份有限公司 | Robot and navigation method, device and computer readable storage medium thereof |
| CN113532461A (en) * | 2021-07-08 | 2021-10-22 | 山东新一代信息产业技术研究院有限公司 | Robot autonomous obstacle avoidance navigation method, equipment and storage medium |
| CN113532461B (en) * | 2021-07-08 | 2024-02-09 | 山东新一代信息产业技术研究院有限公司 | Robot autonomous obstacle avoidance navigation method, equipment and storage medium |
| CN115705045A (en) * | 2021-08-03 | 2023-02-17 | 北京小米移动软件有限公司 | Autonomous cruising method and device of movable equipment and movable equipment |
| CN113807795A (en) * | 2021-10-19 | 2021-12-17 | 上海擎朗智能科技有限公司 | Method for identifying congestion in robot distribution scene, robot and distribution system |
| CN114089756A (en) * | 2021-11-16 | 2022-02-25 | 合肥瓦力觉启机器人科技有限公司 | Robot obstacle avoidance method and system |
| CN114089756B (en) * | 2021-11-16 | 2024-04-30 | 合肥瓦力觉启机器人科技有限公司 | Robot obstacle avoidance method and system |
| CN114265399A (en) * | 2021-11-25 | 2022-04-01 | 北京顺造科技有限公司 | Obstacle recognition method and automatic cleaning equipment |
| CN114360274A (en) * | 2021-12-13 | 2022-04-15 | 珠海格力智能装备有限公司 | Distribution vehicle navigation method, system, computer equipment and storage medium |
| CN114360274B (en) * | 2021-12-13 | 2023-04-07 | 珠海格力智能装备有限公司 | Distribution vehicle navigation method, system, computer equipment and storage medium |
| WO2023115658A1 (en) * | 2021-12-22 | 2023-06-29 | 广东栗子科技有限公司 | Intelligent obstacle avoidance method and apparatus |
| CN114326729A (en) * | 2021-12-27 | 2022-04-12 | 上海擎朗智能科技有限公司 | Movement and movement control method, electronic device and medium |
| WO2023148944A1 (en) * | 2022-02-04 | 2023-08-10 | 日本電気株式会社 | Action scheduling system, action scheduling device, and action scheduling method |
| CN114721404B (en) * | 2022-06-08 | 2022-09-13 | 超节点创新科技(深圳)有限公司 | Obstacle avoidance method, robot and storage medium |
| CN114721404A (en) * | 2022-06-08 | 2022-07-08 | 超节点创新科技(深圳)有限公司 | Obstacle avoidance method, robot and storage medium |
| CN114879701A (en) * | 2022-06-23 | 2022-08-09 | 池州市安安新材科技有限公司 | Robot track obstacle avoidance method and system |
| CN115718489A (en) * | 2022-11-10 | 2023-02-28 | 中元宇(北京)物联网科技有限公司 | Path planning method and system of epidemic prevention intelligent robot |
| CN115718489B (en) * | 2022-11-10 | 2023-08-15 | 中元宇(北京)物联网科技有限公司 | Path planning method and system for epidemic prevention intelligent robot |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112650235A (en) | Robot obstacle avoidance control method and system and robot | |
| US11967161B2 (en) | Systems and methods of obstacle detection for automated delivery apparatus | |
| Sabattini et al. | The pan-robots project: Advanced automated guided vehicle systems for industrial logistics | |
| CN104536445A (en) | Mobile navigation method and system | |
| CN104737085A (en) | Robot and method for autonomous inspection or processing of floor areas | |
| CN102339019A (en) | Intelligent wheel chair obstacle avoidance method based on fuzzy neural network | |
| CN109683617B (en) | Automatic driving method and device and electronic equipment | |
| CN111103875B (en) | Method, apparatus and storage medium for avoiding | |
| CN110705385B (en) | Method, device, equipment and medium for detecting angle of obstacle | |
| Cherubini et al. | A new tentacles-based technique for avoiding obstacles during visual navigation | |
| Yan et al. | Robot perception of static and dynamic objects with an autonomous floor scrubber | |
| US11498587B1 (en) | Autonomous machine motion planning in a dynamic environment | |
| CN112171675A (en) | Obstacle avoidance method and device for mobile robot, robot and storage medium | |
| CN116576857A (en) | Multi-obstacle prediction navigation obstacle avoidance method based on single-line laser radar | |
| Beinschob et al. | Advances in 3d data acquisition, mapping and localization in modern large-scale warehouses | |
| Behrje et al. | An autonomous forklift with 3d time-of-flight camera-based localization and navigation | |
| CN115268443A (en) | Robot obstacle avoidance path planning method | |
| CN116540726A (en) | Intelligent obstacle avoidance method, system and medium for patrol robot | |
| Eiffert et al. | Resource and response aware path planning for long-term autonomy of ground robots in agriculture | |
| Wang et al. | Robust online obstacle detection and tracking for collision-free navigation of multirotor uavs in complex environments | |
| US20230147624A1 (en) | Autonomous mobile robots for coverage path planning | |
| Zeng et al. | Mobile robot exploration based on rapidly-exploring random trees and dynamic window approach | |
| KR102119161B1 (en) | Indoor position recognition system of transpotation robot | |
| Bista et al. | Image-based indoor topological navigation with collision avoidance for resource-constrained mobile robots | |
| KR102286656B1 (en) | Method of modifying path using around map and robot implementing thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210413 |