Robot obstacle avoidance system and control method

Abstract

The invention discloses a robot obstacle avoidance system and a control method, and relates to the technical field of robot control, the robot obstacle avoidance system comprises a data acquisition unit, a data fusion unit, a processor unit and an execution unit; wherein the data acquisition unit comprises a visual acquisition module, a sound wave acquisition module, a laser acquisition module and a pressure acquisition module; the visual acquisition modules are arranged in front of and behind the robot, the sound wave acquisition module and the laser acquisition module are distributed on a trunk of the robot, and the pressure acquisition module is arranged at a body bulge position of the robot. The technical problem that in the prior art, accurate obstacle avoidance cannot be carried out when an obstacle exists outside the plane is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of robot control, in particular to a robot obstacle avoidance system and control method. BACKGROUND

[0002] With the rapid development and progress of artificial intelligence technology, the intelligentization of robots has become the ultimate goal of the development of modern robots. With the continuous improvement of the development speed of robots, the scope of application is also expanding, and robots have assisted or replaced people in many fields to improve efficiency and precision.

[0003] In the field of mobile robots, 2D laser radar is currently mostly used as a sensor for perceiving the surrounding environment. In the process of robot travel, the data of laser radar is used as the basis for judging whether there is an obstacle in the direction of travel. Due to the characteristics of 2D laser sensors, they can only perceive the information of a plane parallel to the ground and at the same height as the laser radar, and cannot perceive obstacles outside the plane, unpredictable dangers, and cannot accurately avoid obstacles when there are obstacles outside the plane. A small part of robots use 3D vision sensors for obstacle avoidance, but only use one sensor to illuminate a single direction, which cannot take into account obstacle avoidance when the robot travels or moves in other directions, and may cause some damage to the robot. SUMMARY

[0004] The purpose of the present application is to provide a robot obstacle avoidance system and control method to solve at least one of the above technical problems.

[0005] In a first aspect, an embodiment of the present invention provides a robot obstacle avoidance system, comprising: a data acquisition unit, a data fusion unit, a processor unit and an execution unit; wherein the data acquisition unit comprises a vision acquisition module, an acoustic wave acquisition module, a laser acquisition module and a pressure acquisition module; the vision acquisition module is arranged in front and behind the robot, the acoustic wave acquisition module and the laser acquisition module are distributedly arranged on the torso of the robot, and the pressure acquisition module is arranged at a protruding position of the robot's body; the vision acquisition module is used to obtain visual image information of the robot's surrounding environment; the acoustic wave acquisition module and the laser acquisition module are used to obtain acoustic ranging information and laser ranging information between the robot and obstacles, respectively; The pressure acquisition module is used to obtain pressure information of the robot during walking; the data fusion unit is used to fuse the acoustic ranging information and the laser ranging information to obtain coordinate information of the obstacle relative to the robot; the processor unit is used to construct a three-dimensional model dot matrix of the environment based on the visual image information, and based on the three-dimensional model dot matrix of the environment and the coordinate information of the obstacle relative to the robot, determine whether the next action of the robot is within the collision range; if so, correct the operation trajectory of the robot; the processor unit is also used to determine whether there is an abnormality in the pressure information; if so, issue a stop operation instruction; the execution unit is used to execute the operation instruction of the robot.

[0006] Furthermore, it also includes a data processing unit for filtering and preliminarily analyzing the sensor data to obtain pre-processed sensor data; the sensor data includes: the visual image information, the acoustic ranging information, the laser ranging information and the pressure information.

[0007] Furthermore, it also includes a fill light unit, which is used to perform fill light operations for the visual acquisition module during the process of acquiring visual image information.

[0008] Furthermore, it also includes a data storage unit for storing the three-dimensional model dot matrix of the environment and the number of collisions and causes of collisions of the robot.

[0009] In a second aspect, an embodiment of the present invention also provides a control method for a robot obstacle avoidance system, comprising: obtaining sensor data of the robot; the sensor data comprising visual image information, acoustic ranging information and laser ranging information between the robot and the obstacle, and pressure information of the robot during walking; performing data fusion on the acoustic ranging information and the laser ranging information to obtain coordinate information of the obstacle relative to the robot; constructing a three-dimensional model dot matrix of the environment based on the visual image information, and judging whether the next action of the robot is within a collision range based on the three-dimensional model dot matrix of the environment and the coordinate information of the obstacle relative to the robot; if so, correcting the running trajectory of the robot; judging whether there is an abnormality in the pressure information; and if so, issuing a stop operation instruction.

[0010] Furthermore, the sensor data of the robot is obtained, including: based on the visual acquisition module, obtaining visual image information of the robot's surrounding environment; based on the sound wave acquisition module and the laser acquisition module, respectively obtaining the sound wave ranging information and laser ranging information between the robot and the obstacle; based on the pressure acquisition module, obtaining the pressure information of the robot during walking.

[0011] Furthermore, based on the visual acquisition module, visual image information of the surrounding environment of the robot is obtained, including: scanning the overall environmental information of the robot through the visual acquisition module to obtain initial image information; judging whether there is a target area in the initial image information whose brightness is lower than a preset threshold; if so, performing a fill light operation on the corresponding position of the target area based on the fill light unit, and scanning the overall environment of the robot again based on the visual acquisition module, updating the initial image information, and obtaining the visual image information.

[0012] Furthermore, if there is an abnormality in the pressure information, the method also includes: controlling the robot to stop moving and obtaining sensor data of the robot; judging whether there is an obstacle in the direction of movement of the robot based on the sensor data; if so, correcting the running trajectory of the robot.

[0013] Furthermore, data fusion is performed on the acoustic ranging information and the laser ranging information to obtain coordinate information of the obstacle relative to the robot, including: establishing a coordinate system with the robot as the center origin; determining a coordinate set of the obstacle in the coordinate system based on the acoustic ranging information and the laser ranging information; and data fusion is performed on the coordinate set to obtain coordinate information of the obstacle relative to the robot.

[0014] In a third aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, the method provided in the embodiment of the present invention is implemented.

[0015] The present invention provides a robot obstacle avoidance system and control method, which collects and processes data from multiple sensors, then performs data fusion to comprehensively determine whether there are obstacles in the robot's running direction, so that the robot can effectively and reasonably avoid obstacles in all directions, improves the robot's obstacle avoidance accuracy, and alleviates the technical problem of the existing technology that it cannot accurately avoid obstacles when there are obstacles outside the plane. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the implementation methods of the present application or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the specific implementation methods or the description of the prior art. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0017] Figure 1 A schematic diagram of a robot obstacle avoidance system provided by an embodiment of the present invention; Figure 2 A schematic diagram of a data acquisition unit provided in an embodiment of the present invention; Figure 3 This is a flow chart of a control method for a robot obstacle avoidance system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The following will provide a clear and complete description of the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0019] Example 1 Figure 1 FIG. 1 is a schematic diagram of a robot obstacle avoidance system according to an embodiment of the present invention. Figure 1 As shown, the system includes: a data acquisition unit 10 , a data fusion unit 20 , a processor unit 30 and an execution unit 40 . Figure 2 FIG. 1 is a schematic diagram of a data acquisition unit according to an embodiment of the present invention. Figure 2As shown, the data acquisition unit 10 includes a visual acquisition module 11, an acoustic wave acquisition module 12, a laser acquisition module 13, and a pressure acquisition module 14. The visual acquisition module 11 is located at the front and rear of the robot, the acoustic wave acquisition module 12 and the laser acquisition module 13 are distributed throughout the robot's trunk, and the pressure acquisition module 14 is located at a raised position on the robot's body.

[0020] Preferably, the visual acquisition module 11 is installed not only on the robot's binoculars, but also behind the robot, so as to ensure 360° visual perception without blind spots and to obtain visual image information of the robot's surrounding environment.

[0021] Preferably, the acoustic wave acquisition module 12 and the laser acquisition module 13 are installed at the legs and arms of the robot, as well as at the abdomen of the robot, and are used to obtain acoustic wave ranging information and laser ranging information between the robot and obstacles, respectively.

[0022] Specifically, the pressure acquisition module 14 is used to obtain pressure information of the robot during walking.

[0023] Preferably, the pressure acquisition module 14 is arranged at the toe position of the robot.

[0024] The data fusion unit 20 is used to fuse the acoustic ranging information and the laser ranging information to obtain the coordinate information of the obstacle relative to the robot.

[0025] The processor unit 30 is used to construct a three-dimensional model of the environment based on the visual image information, and to determine whether the robot's next action is within the collision range based on the three-dimensional model of the environment and the coordinate information of the obstacle relative to the robot; if so, the robot's running trajectory is corrected.

[0026] The processor unit 30 is further configured to determine whether the pressure information is abnormal; if so, issue a stop operation instruction.

[0027] The execution unit 40 is used to execute the operation instructions of the robot.

[0028] Specifically, if Figure 1 As shown, it also includes a data processing unit 50 for filtering and preliminarily analyzing the sensor data to obtain pre-processed sensor data; wherein the sensor data includes: visual image information, acoustic ranging information, laser ranging information and pressure information.

[0029] like Figure 1 As shown, a fill light unit 60 is also included, which is used to perform fill light operations for the visual acquisition module in the process of acquiring visual image information.

[0030] Specifically, it is judged whether there is a region that cannot be recognized due to light, and if there is, the region is lighted by the light supplement unit 60, and the environmental information at the region is scanned again.

[0031] Specifically, as shown in Figure 1 It also includes a data storage unit 70 for storing the environmental three-dimensional model point array and storing the collision times and collision reasons of the robot.

[0032] Embodiment Two Figure 3 is a flowchart of a control method of a robot obstacle avoidance system according to an embodiment of the application. As shown in Figure 3 The method specifically includes the following steps: Step S302, acquiring sensor data of the robot; the sensor data includes visual image information, sound wave ranging information and laser ranging information between the robot and the obstacle, and pressure information of the robot in the walking process.

[0033] Step S304, data fusion is performed on the sound wave ranging information and the laser ranging information to obtain coordinate information of the obstacle relative to the robot.

[0034] Step S306, constructing an environmental three-dimensional model point array based on the visual image information, and judging whether the next action of the robot is within a collision range based on the environmental three-dimensional model point array and the coordinate information of the obstacle relative to the robot. If yes, step S308 is executed; if no, step S310 is executed.

[0035] The collision range refers to a range in which collision will occur when the robot performs the next action.

[0036] Step S308, correcting the running track of the robot.

[0037] Step S310, controlling the robot to move according to the preset running track.

[0038] Step S312, judging whether the pressure information is abnormal. If yes, step S314 is executed; if no, step S310 is executed.

[0039] Step S314, issuing a stop operation instruction.

[0040] Specifically, step S302 further includes the following steps: Step S3021, acquiring visual image information of the surrounding environment in which the robot is located based on a visual acquisition module; specifically, the surrounding environment in which the robot is located is scanned 360° omnidirectionally based on the visual acquisition module.

[0041] Specifically, the overall environment information where the robot is located is scanned by the visual acquisition module to obtain initial image information. It is judged whether the initial image information has a target region with a brightness lower than a preset threshold. If yes, the target region corresponding position is lighted based on the light supplement unit, and the overall environment where the robot is located is scanned again based on the visual acquisition module, and the initial image information is updated to obtain visual image information.

[0042] In step S3022, the sound wave ranging information and the laser ranging information between the robot and the obstacle are obtained based on the sound wave acquisition module and the laser acquisition module respectively.

[0043] In step S3023, the pressure information of the robot in the walking process is obtained based on the pressure acquisition module.

[0044] Specifically, as shown in Figure 3 If the pressure information is abnormal, the method further includes: In step S316, the robot is controlled to stop moving, and the sensor data of the robot is obtained. In step S318, it is judged whether there is an obstacle in the moving direction of the robot based on the sensor data; if yes, step S308 is executed; if no, step S310 is executed.

[0045] Specifically, step S304 further includes the following steps: In step S3041, a coordinate system with the robot as the center origin is established. In step S3042, the coordinate set of the obstacle in the coordinate system is determined based on the sound wave ranging information and the laser ranging information. In step S3043, the coordinate set is data fused to obtain the coordinate information of the obstacle relative to the robot.

[0046] Specifically, first, a coordinate system with the robot as the center origin is established, in which the front is x and the top is y; then the coordinate system of the obstacle distribution is measured and calculated, the distance of a certain direction detected by the sensor (sound wave acquisition module and laser acquisition module) is L, which is the distance of the obstacle, and the corresponding angle on the coordinate system is δ. For a type of detection sensor, the distance measured from the obstacle is the average value of multiple data, and if there is only one, it is a single value p.

[0047] According to different types of sensors, the coordinate set of the obstacle is obtained, and the coordinate set of the obstacle is converted into the robot coordinate system, and the conversion formula is: Where (x, y) is the robot body coordinate, and φ is the installation angle.

[0048] The distance of any point of the sensor to the representation in the robot body is calculated: D=RP, p is the distance data of the sensor.

[0049] The data is fused, the maximum envelope of the robot walking is determined more accurately through the sensor, assuming that the maximum and minimum envelopes are Lmax and Lmin, and the maximum and minimum coordinate sets are: The data fusion is to collect the value of each data and represent it through the maximum and minimum coordinate sets, and the robot plans the trajectory and avoids obstacles through the coordinates and the size and step of the robot.

[0050] From the above description, the robot obstacle avoidance system and the control method are provided, and compared with the prior art, the following technical effects are obtained. 1. According to the effective fusion of multiple sensors, various data are collected and processed, a suitable control data is provided for the main control, the robot can effectively and reasonably avoid obstacles in various directions, and when a certain collision occurs, the robot can quickly respond and move forward according to the planned trajectory, the obstacle avoidance accuracy of the robot is improved. At the same time, if a collision occurs, it can be reasonably processed to ensure the safety of the robot, realize the efficient obstacle avoidance processing function, and improve the control accuracy.

[0051] 3. The application increases the accurate obstacle avoidance mode and the processing function when a collision occurs, ensures that the robot can normally and stably work when unnecessary collision occurs, and improves the performance index of the robot.

[0052] 4. The data acquisition unit and the data fusion unit provided by the embodiment of the application collect and fuse multiple data into available data, which is beneficial to the stability of the robot, improves the reliability of obstacle avoidance, and increases the robustness of the system.

[0053] 5. The data acquisition and storage unit provided by the embodiment of the application mainly stores three-dimensional images of various environmental information and stores the number and reason of the collision, so as to facilitate subsequent optimization of the overall performance.

[0054] 6. The light supplement unit provided by the embodiment of the application is mainly used for supplementing the light source of visual acquisition, which is helpful to improve the accuracy and reliability of the collected data.

[0055] The application also provides a computer readable storage medium, the computer readable storage medium stores computer instructions, and the computer instructions are executed by a processor to realize the method provided by the embodiment of the application.

[0056] It will be obvious to a person skilled in the art that the application is not limited to the details of the foregoing exemplary embodiments and can be implemented in other concrete forms without departing from the spirit or essential characteristics of the application. The embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the application 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. No reference signs in the claims should be considered as limiting the scope of the claims to the identity of the reference signs therein.

[0057] Furthermore, it should be understood that although the description is made on the basis of the embodiments, not every embodiment contains only one independent technical solution, and the description of the specification is only for the sake of clarity, and those skilled in the art should consider the specification as a whole, and the technical solutions in each embodiment can also be appropriately combined to form other embodiments that those skilled in the art can understand.

Claims

1. A robot obstacle avoidance system, characterized in that: include: A data acquisition unit, a data fusion unit, a processor unit, and an execution unit; wherein the data acquisition unit includes a visual acquisition module, an acoustic wave acquisition module, a laser acquisition module, and a pressure acquisition module; the visual acquisition module is arranged at the front and rear of the robot, the acoustic wave acquisition module and the laser acquisition module are distributedly arranged on the torso of the robot, and the pressure acquisition module is arranged at a protruding position on the body of the robot; The visual acquisition module is used to obtain visual image information of the robot's surrounding environment; The acoustic wave acquisition module and the laser acquisition module are used to respectively acquire acoustic wave ranging information and laser ranging information between the robot and the obstacle; The pressure acquisition module is used to obtain pressure information of the robot during walking; The data fusion unit is used to fuse the acoustic ranging information and the laser ranging information to obtain coordinate information of the obstacle relative to the robot; The processor unit is configured to construct a three-dimensional model of the environment based on the visual image information, and determine whether the robot's next movement is within a collision range based on the three-dimensional model of the environment and the coordinate information of the obstacle relative to the robot; if so, modify the robot's trajectory; The processor unit is further configured to determine whether the pressure information is abnormal; if so, issue a stop operation instruction; The execution unit is used to execute the operation instructions of the robot.

2. The robot obstacle avoidance system according to claim 1, characterized in that: It also includes a data processing unit for filtering and preliminarily analyzing the sensor data to obtain pre-processed sensor data; the sensor data includes: the visual image information, the acoustic ranging information, the laser ranging information and the pressure information.

3. The robot obstacle avoidance system according to claim 1, characterized in that: It also includes a fill light unit, which is used to perform fill light operations for the visual acquisition module during the process of acquiring visual image information.

4. The robot obstacle avoidance system according to claim 1, characterized in that: It also includes a data storage unit for storing the three-dimensional model dot matrix of the environment and the number of collisions and causes of collisions of the robot.

5. A control method for a robot obstacle avoidance system according to any one of claims 1 to 4, characterized in that: include: Acquiring sensor data of the robot; the sensor data includes visual image information, acoustic and laser ranging information between the robot and obstacles, and pressure information of the robot during walking; Performing data fusion on the acoustic ranging information and the laser ranging information to obtain coordinate information of the obstacle relative to the robot; constructing a three-dimensional model of the environment based on the visual image information, and determining whether the robot's next action is within a collision range based on the three-dimensional model of the environment and coordinate information of obstacles relative to the robot; If yes, the running trajectory of the robot is corrected; Determining whether the pressure information is abnormal; If so, a stop operation instruction is issued.

6. The method according to claim 5, characterized in that: Get the robot's sensor data, including: Based on the visual acquisition module, obtain visual image information of the robot's surrounding environment; Acquire acoustic ranging information and laser ranging information between the robot and the obstacle based on the acoustic wave acquisition module and the laser acquisition module respectively; Based on the pressure acquisition module, pressure information of the robot during walking is obtained.

7. The method according to claim 6, characterized in that: Based on the visual acquisition module, visual image information of the robot's surrounding environment is obtained, including: Scanning the overall environment information of the robot through the visual acquisition module to obtain initial image information; Determining whether the initial image information contains a target area with a brightness lower than a preset threshold; If yes, a fill light operation is performed on the corresponding position of the target area based on the fill light unit, and the overall environment of the robot is scanned again based on the visual acquisition module, and the initial image information is updated to obtain the visual image information.

8. The method according to claim 5, wherein: If the pressure information is abnormal, the method further includes: Controlling the robot to stop moving and acquiring sensor data of the robot; Determining whether there is an obstacle in the direction of movement of the robot based on the sensor data; If yes, the running trajectory of the robot is corrected.

9. The method according to claim 5, characterized in that: Performing data fusion on the acoustic ranging information and the laser ranging information to obtain coordinate information of the obstacle relative to the robot includes: Establishing a coordinate system with the robot as the center origin; Determining a coordinate set of an obstacle in the coordinate system based on the acoustic ranging information and the laser ranging information; Data fusion is performed on the coordinate set to obtain coordinate information of the obstacle relative to the robot.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, the method according to any one of claims 5 to 9 is implemented.

Images