Mobile robot blind area sensing method and device, mobile robot and storage medium

Abstract

The invention provides a blind area sensing method and device for a mobile robot, the mobile robot and a storage medium, and relates to the technical field of robots, the method comprehensively considers a sensing area and a blind area contour of the mobile robot in the current orientation, and the blind area contour of the mobile robot is obtained through the first blind area contour and the tail blind area contour. The safe sensing directed position of the mobile robot is determined, the single blind area sensing range of the mobile robot can be enlarged to the maximum extent, the total blind area sensing frequency is reduced, and the action sensing frequency is reduced.

Description

Technical Field

[0001] The present invention relates to the field of robot technology, and in particular to a mobile robot blind spot perception method, device, mobile robot and storage medium. Background Art

[0002] Nowadays, mobile robots have gradually entered thousands of households as automatic cleaning products, and obstacle avoidance is a basic requirement for mobile robots in their work process. At present, most mobile robot perception sensors use time of flight (TOF) or line laser to perceive obstacles. Due to the limited field of view (FOV) of the perception sensor or the failure to update the map in time, there are blind spots in the field of view. Mobile robots may collide or encounter abnormal situations in the blind spot of the field of view, so the blind spot needs to be re-perceived.

[0003] At present, the common method for perceiving blind spots is that the mobile robot uses a fixed action of rotating left and right to perceive the blind spot in the blind spot of the perception sensor. Since the mobile robot is in the blind spot of the perception sensor, this method can only perceive part of the blind spot in the case of a large blind spot, and cannot perceive the whole blind spot. The mobile robot is still likely to collide or encounter abnormal situations in the blind spot, which greatly reduces the user experience of the mobile robot. Moreover, when using fixed actions, the range of the blind spot that can be detected at one time is limited. For complex obstacles, it may take multiple times to fill the field of view to eliminate the blind spot, and the action is frequent. Summary of the invention

[0004] The present invention provides a mobile robot blind spot perception method, device, mobile robot and storage medium, which are used to solve the defects existing in the related technology.

[0005] The present invention provides a blind spot perception method for a mobile robot, comprising: If there is a blind spot in the current orientation of the mobile robot, and the distance between the blind spot and the mobile robot is less than a preset threshold, determine the current directional position of the mobile robot and the perception area in the current orientation; Extracting a first blind spot contour and a last blind spot contour in the perception area along a preset direction, and determining a safe perception directional position of the mobile robot when the first blind spot contour and the last blind spot contour are both in the field of view of the mobile robot; If the safety sensing directed position is not empty, the mobile robot is controlled to move from the current directed position to the safety sensing directed position, and then return from the safety sensing directed position to the current directed position to sense the blind spot in the sensing area.

[0006] According to a mobile robot blind spot perception method provided by the present invention, the step of determining the safe perception directional position of the mobile robot when the first blind spot contour and the last blind spot contour are both within the field of view of the mobile robot comprises: Determine a first contour point in the first blind spot contour and a second contour point in the last blind spot contour; a first line connecting the current directional position and the first contour point has a minimum angle with the body coordinate system of the mobile robot, and a second line connecting the current directional position and the second contour point has a maximum angle with the body coordinate system; The safety-perceived directional position is determined based on the perpendicular bisector of the third line connecting the first contour point and the second contour point in combination with the field of view of the mobile robot.

[0007] According to a blind spot perception method for a mobile robot provided by the present invention, the perpendicular bisector of a third line connecting the first contour point and the second contour point is combined with the field of view angle of the mobile robot to determine the safety perception directional position, including: Determine a ray starting from the first contour point or the second contour point, the angle between which and the perpendicular bisector is less than or equal to half of the field of view angle; If the circular area with the intersection of the ray and the perpendicular midline as the center and the radius of the mobile robot as the radius is in the safe area, the safety perception directed position is determined based on the intersection of the ray and the perpendicular midline and the direction of the perpendicular midline; Otherwise, the last blind spot contour is deleted from the perception area, and a new last blind spot contour is re-determined to determine the safety perception directional position when the first blind spot contour and the new last blind spot contour are both under the field of view angle.

[0008] According to a blind spot perception method for a mobile robot provided by the present invention, the perception area is a semicircular area with the center of the mobile robot as the center and the effective observation distance of the mobile robot as the radius.

[0009] According to a mobile robot blind spot perception method provided by the present invention, the safe perception directional position of the mobile robot when the first blind spot contour and the last blind spot contour are simultaneously under the field of view angle of the mobile robot is determined, and then further includes: If the safety perception directional position is empty, the mobile robot is controlled to rotate at the current directional position to perceive the blind area of ​​the field of vision within the perception area.

[0010] According to a mobile robot blind spot perception method provided by the present invention, extracting the first blind spot contour and the last blind spot contour in the perception area along a preset direction includes: Extracting each blind spot contour within the sensing area and the centroid of each blind spot contour; Based on the positions of the centroids of the blind spot contours in the body coordinate system of the mobile robot, the blind spot contours are sorted along the preset direction to obtain the first blind spot contour and the last blind spot contour.

[0011] The present invention also provides a mobile robot blind spot sensing device, comprising: A current position determination module, configured to determine the current directional position of the mobile robot and the sensing area in the current orientation if there is a blind spot in the current orientation of the mobile robot and the distance between the blind spot and the mobile robot is less than a preset threshold; A blind spot contour extraction module, used to extract the first blind spot contour and the last blind spot contour in the perception area along a preset direction, and determine the safe perception directional position of the mobile robot when the first blind spot contour and the last blind spot contour are both in the field of view of the mobile robot; The blind spot perception module is used to control the mobile robot to move from the current directional position to the safety perception directional position if the safety perception directional position is not empty, and then return from the safety perception directional position to the current directional position to perceive the blind spot of vision within the perception area.

[0012] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a mobile robot blind spot perception method as described in any one of the above is implemented.

[0013] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the mobile robot blind spot perception method as described in any one of the above is implemented.

[0014] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the mobile robot blind spot perception method as described in any one of the above is implemented.

[0015] The present invention provides a mobile robot blind spot perception method, device, mobile robot and storage medium. The method comprehensively considers the perception area and blind spot contour of the mobile robot in the current direction, and determines the safe perception directional position of the mobile robot through the first blind spot contour and the last blind spot contour. The range of the mobile robot's single blind spot perception can be increased to the greatest extent, so as to reduce the number of overall blind spot perceptions and reduce the frequency of perception actions. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present invention or related technologies, the drawings required for use in the embodiments or related technical descriptions are briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 It is a flow chart of the blind spot perception method of a mobile robot provided by the present invention.

[0018] Figure 2 It is the local grid map of the mobile robot in the mobile robot blind spot perception method provided by the present invention.

[0019] Figure 3 It is a schematic diagram of calculating the intersection point when determining the safe perception directional position in the mobile robot blind spot perception method provided by the present invention.

[0020] Figure 4 This is a schematic diagram of the motion trajectory of the mobile robot in the blind spot perception method of the mobile robot provided by the present invention: Figure 5 It is a structural schematic diagram of the blind spot sensing device of a mobile robot provided by the present invention.

[0021] Figure 6 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] Figure 1 FIG. 1 is a flow chart of a blind spot sensing method for a mobile robot provided in an embodiment of the present invention, such as Figure 1 As shown, the method includes: S1, if there is a blind spot in the current orientation of the mobile robot, and the distance between the blind spot and the mobile robot is less than a preset threshold, determine the current directional position of the mobile robot and the perception area in the current orientation; S2, extracting the first blind spot contour and the last blind spot contour in the perception area along a preset direction, and determining the safe perception directional position of the mobile robot when the first blind spot contour and the last blind spot contour are both in the field of view of the mobile robot; S3, if the safety sensing directed position is not empty, control the mobile robot to move from the current directed position to the safety sensing directed position, and then return from the safety sensing directed position to the current directed position to sense the blind spot in the sensing area.

[0024] Specifically, the mobile robot blind spot perception method provided in the embodiment of the present invention is executed by a mobile robot host, and the mobile robot host is configured in the mobile robot. The mobile robot can be a sweeping robot or other autonomous mobile intelligent robot, which is not specifically limited here.

[0025] First, execute step S1. The current orientation of the mobile robot is the current movement direction. During the movement of the mobile robot, the blind spots and obstacles in the field of view can be recorded in real time in the Sanger map.

[0026] If at a certain moment it is detected that there is a blind spot in the current direction of the mobile robot, and the distance between the blind spot and the mobile robot is less than a preset threshold, it means that the mobile robot needs to perceive the blind spot, otherwise the mobile robot may experience an abnormality when entering the blind spot. Therefore, the current directional position of the mobile robot and the perception area in the current direction can be determined first.

[0027] It is understandable that the blind area of ​​vision refers to an unsafe area of ​​the mobile robot, and the mobile robot is not aware of the specific situation therein, and cannot know whether there are obstacles or other situations therein. The preset threshold can be set as needed and is not specifically limited here.

[0028] The current directional position of the mobile robot may include the current position of the mobile robot and the orientation of the mobile robot at the current position. Here, the current position of the mobile robot may be the current position of the center of the mobile robot.

[0029] The perception area in the current direction of the mobile robot can be the field of view of the mobile robot, or it can be a semicircular area in the current direction of the mobile robot, which is a circular area with the center of the mobile robot as the center and the effective observation distance of the mobile robot as the radius. There is no specific limitation here.

[0030] Then, step S2 is performed to extract the first blind spot contour and the last blind spot contour in the sensing area along a preset direction, where the preset direction includes a clockwise direction or a counterclockwise direction.

[0031] The perception area may contain multiple blind area contours, each blind area contour may be a blind area connected domain, and the blind area contours may constitute a blind area connected domain set. The extraction of the blind area contours in the perception area may be achieved through computer vision (CV) technology.

[0032] Furthermore, the blind area contours may be sorted along a preset direction, and a first blind area contour and a last blind area contour in the sorting may be determined.

[0033] If the first blind spot contour and the last blind spot contour are both within the field of view of the mobile robot, the mobile robot can perceive as many blind spots as possible in one blind spot perception process. Therefore, the safe perception directional position of the mobile robot can be determined when the first blind spot contour and the last blind spot contour are both within the field of view of the mobile robot.

[0034] The safety perception directional position of the mobile robot may include the safety perception position of the mobile robot and the orientation of the mobile robot at the safety perception position. Here, the safety perception position of the mobile robot may be the center position of the mobile robot when the mobile robot is in the safety area and perceives the blind area of ​​the perception area.

[0035] In this step, the safety perception directional position of the mobile robot may be empty or not. If the safety perception directional position of the mobile robot is empty, it means that there is no safe space in front of the mobile robot to perceive the blind spot in the perception area. At this time, perception can be performed by the implementation method in the prior art, which is not specifically limited here.

[0036] If the safety perception directed position of the mobile robot is not empty, it means that there is sufficient safety space in front of the mobile robot to perceive the blind area of ​​the visual field in the perception area. At this time, step S3 is executed.

[0037] In step S3, according to the steering rule of the mobile robot, the motion trajectory of the mobile robot can be formed by moving from the current directed position to the safe sensing directed position, and then the mobile robot is controlled to move along the motion trajectory from the current directed position to the safe sensing directed position, and the mobile robot is controlled along the reverse trajectory of the motion trajectory from the safe sensing directed position back to the current directed position to perceive the blind spots in the perception area.

[0038] The blind spot perception method of a mobile robot provided in an embodiment of the present invention determines the current directional position of the mobile robot and the perception area in the current orientation when there is a visual blind spot in the current orientation of the mobile robot and the distance between the visual blind spot and the mobile robot is less than a preset threshold; then extracts the first blind spot contour and the last blind spot contour along the preset direction in the perception area, and determines the safe perception directional position of the mobile robot when the first blind spot contour and the last blind spot contour are both in the field of view of the mobile robot; finally, when the safe perception directional position is not empty, controls the mobile robot to travel back and forth between the current directional position and the safe perception directional position once, and perceives the visual blind spot in the perception area. This method comprehensively considers the perception area and the blind spot contour of the mobile robot in the current orientation, and determines the safe perception directional position of the mobile robot through the first blind spot contour and the last blind spot contour, which can maximize the range of the single blind spot perception of the mobile robot, so as to reduce the number of overall blind spot perceptions and reduce the frequency of perception actions.

[0039] On the basis of the above embodiment, the step of determining the safe sensed directional position of the mobile robot when the first blind spot contour and the last blind spot contour are both within the field of view of the mobile robot includes: Determine a first contour point in the first blind spot contour and a second contour point in the last blind spot contour; a first line connecting the current directional position and the first contour point has a minimum angle with the body coordinate system of the mobile robot, and a second line connecting the current directional position and the second contour point has a maximum angle with the body coordinate system; The safety-perceived directional position is determined based on the perpendicular bisector of the third line connecting the first contour point and the second contour point in combination with the field of view of the mobile robot.

[0040] Specifically, when determining the safety perception directional position, a tangent is drawn from the current directional position to the first blind spot contour, and the tangent with the smallest angle with the body coordinate system of the mobile robot is used as the first connecting line, and the tangent point with the first blind spot contour is the first contour point. A tangent is drawn from the current directional position to the last blind spot contour, and the tangent with the largest angle with the body coordinate system of the mobile robot is used as the second connecting line, and the tangent point with the last blind spot contour is the second contour point.

[0041] It can be understood that the body coordinate system of the mobile robot can be a coordinate system constructed with the center of the mobile robot as the origin, the orientation of the mobile robot as the x-axis, and the direction perpendicular to the orientation of the mobile robot as the y-axis, and then the angle with the body coordinate system of the mobile robot can be the angle with the y-axis.

[0042] After that, the first contour point and the second contour point can be connected to obtain a third line, and the perpendicular bisector of the third line, i.e., the perpendicular median, can be determined. The perpendicular median, combined with the field of view of the mobile robot, can be used to determine the safety perception directed position. For example, the safety perception position of the mobile robot in the safety perception directed position can be determined in combination with the field of view of the mobile robot and the radius of the mobile robot, and the orientation of the mobile robot at the safety perception position can be parallel to the perpendicular median and toward one side of each blind spot contour.

[0043] In an embodiment of the present invention, by determining the first contour point in the first blind spot contour and the second contour point in the last blind spot contour, the field of view range required for a single blind spot perception can be determined, and then the perpendicular bisector of the third line connecting the first contour point and the second contour point, combined with the field of view angle of the mobile robot, the directed position of the safety perception can be accurately determined, and the determination efficiency can be improved through mathematical operations.

[0044] On the basis of the above embodiment, the method of determining the safety-perceived directional position based on the perpendicular bisector of the third line connecting the first contour point and the second contour point in combination with the field of view of the mobile robot includes: Determine a ray starting from the first contour point or the second contour point, the angle between which and the perpendicular bisector is less than or equal to half of the field of view angle; If the circular area with the intersection of the ray and the perpendicular midline as the center and the radius of the mobile robot as the radius is in the safe area, the safety perception directed position is determined based on the intersection of the ray and the perpendicular midline and the direction of the perpendicular midline; Otherwise, the last blind spot contour is deleted from the perception area, and a new last blind spot contour is re-determined to determine the safety perception directional position when the first blind spot contour and the new last blind spot contour are both under the field of view angle.

[0045] Specifically, in the process of determining the safety-perceived directional position, the first contour point or the second contour point can be used as a starting point to determine a ray whose angle with the perpendicular bisector is equal to half of the field of view angle of the mobile robot.

[0046] Then, it is determined whether the circular areas with the intersection of the ray and the median perpendicular as the center and the radius of the mobile robot as the radius are all in the safe area, that is, whether the entire mobile robot falls into the safe area. The safe area can be an open area without obstacles or abnormal situations that the mobile robot has detected. If the circular areas are all in the safe area, the intersection of the ray and the median perpendicular can be used as the safe sensing position, and the direction of the median perpendicular can be used as the orientation of the mobile robot at the safe sensing position.

[0047] If part of the circular area is within the safe area, the first contour point or the second contour point can be used as the starting point to determine the ray whose angle with the perpendicular bisector is less than half of the field of view angle of the mobile robot, and to determine whether the circular area with the intersection of the ray and the perpendicular bisector as the center and the radius of the mobile robot as the radius is all within the safe area, until an intersection is determined on the perpendicular bisector that makes the circular area all within the safe area.

[0048] If the rays whose angle with the perpendicular bisector is less than or equal to half of the field of view angle of the mobile robot are determined with the first contour point or the second contour point as the starting point, and no intersection point can be determined on the perpendicular bisector so that the circular areas are all within the safe area, then it is necessary to delete the last blind spot contour from the perception area, and then re-determine a new last blind spot contour, that is, the second to last blind spot contour in the sorting result of the blind spot contours within the perception area can be used as the new last blind spot contour.

[0049] Thereafter, according to the above steps, the safety-perceived directional position where the first blind spot contour and the new last blind spot contour are both in the field of view angle can be determined.

[0050] It is understandable that if the above methods are unable to determine the safety perception directional position, the safety perception directional position can be considered to be empty, and the visual blind spot within the perception area can be perceived through the implementation method in the prior art.

[0051] On the basis of the above embodiment, the step of determining the safe sensed directional position of the mobile robot when the first blind spot contour and the last blind spot contour are both under the field of view of the mobile robot further includes: If the safety perception directional position is empty, the mobile robot is controlled to rotate at the current directional position to perceive the blind area of ​​the field of vision within the perception area.

[0052] Specifically, when the safety perception directional position is empty, the mobile robot can be controlled to rotate at the current directional position, that is, rotate on the spot, to perceive the blind spot in the perception area.

[0053] On the basis of the above embodiment, extracting the first blind spot contour and the last blind spot contour in the perception area along a preset direction includes: Extracting each blind spot contour within the sensing area and the centroid of each blind spot contour; Based on the positions of the centroids of the blind spot contours in the body coordinate system of the mobile robot, the blind spot contours are sorted along the preset direction to obtain the first blind spot contour and the last blind spot contour.

[0054] Specifically, when extracting the first blind spot contour and the last blind spot contour along a preset direction in the perception area, the contours of each blind spot in the perception area can be firstly extracted by computer vision technology, and the centroid of each blind spot contour can be determined.

[0055] Then, the blind spot contours can be sorted along the preset direction according to the position of the center of mass of each blind spot contour in the body coordinate system of the mobile robot. The first blind spot contour in the sorting result is the first blind spot contour, and the last blind spot contour in the sorting result is the last blind spot contour.

[0056] Figure 2 It is the local Sanger map of the mobile robot, where the gray area is the blind area, the white area is the safe area sensed by the mobile robot, and the colored area is the obstacle. Figure 2 The red line segment in the middle indicates the current orientation of the mobile robot. There is a blind spot in the current orientation of the mobile robot, that is, the gray area on the right, and the distance between the blind spot and the mobile robot is less than a preset threshold. The blind spot needs to be sensed to prevent the mobile robot from entering the blind spot.

[0057] The complete process of the mobile robot blind spot perception method provided in the embodiment of the present invention includes: There is a blind spot in the current orientation of the mobile robot, and the distance between the blind spot and the mobile robot is less than a preset threshold, and the mobile robot is about to encounter the blind spot, and the current directional position P1 of the mobile robot is determined; Extract the perception area in the current direction of the mobile robot, that is, the semicircular area M with the center of the mobile robot as the center and the effective observation distance of the mobile robot as the radius; Extract the blind area contour within the semicircular area M, and determine the first blind area contour A and the last blind area contour B along the preset direction within the perception area, then the ordered set N is (A, B); Draw a tangent from P1 to A, and take the nearest counterclockwise tangent point a as the first contour point; draw a tangent from P1 to B, and take the farthest counterclockwise tangent point b as the second contour point; Connect the first contour point and the second contour point to get the third line ab, the midpoint of ab is d, and the vertical line through point d is the perpendicular bisector of the third line ab; draw a ray through point a with an angle equal to the mobile robot's field of view angle / 2 with the vertical line, and the intersection point with the perpendicular bisector is c. Figure 3 As shown, the angle acd is equal to the field of view angle of the mobile robot / 2. ​​At this time, the circular area with point c as the center and the radius of the mobile robot as the radius will encounter the blind area contour A, so it is necessary to find the point P2 on the extension line of dc that makes the circular area in the safe area as the safety perception directed position, such as Figure 4 As shown; The motion trajectory formed by P1P2 is the trajectory that conforms to the motion constraints of the mobile robot. The mobile robot can then be controlled to move from P1 to P2 along the motion trajectory, and then return from P2 to P1 along the reverse trajectory of the motion trajectory, completing a perception of the blind spot in the perception area.

[0058] like Figure 5 As shown, based on the above embodiments, an embodiment of the present invention provides a blind spot sensing device for a mobile robot, comprising: A current position determination module 51 is used to determine the current directional position of the mobile robot and the sensing area in the current orientation if there is a blind spot in the current orientation of the mobile robot and the distance between the blind spot and the mobile robot is less than a preset threshold; A blind spot contour extraction module 52 is used to extract the first blind spot contour and the last blind spot contour in the perception area along a preset direction, and determine the safe perception directional position of the mobile robot when the first blind spot contour and the last blind spot contour are both in the field of view of the mobile robot; The blind spot perception module 53 is used to control the mobile robot to move from the current directed position to the safety perception directed position if the safety perception directed position is not empty, and then return from the safety perception directed position to the current directed position to perceive the blind spot of vision within the perception area.

[0059] On the basis of the above-mentioned embodiment, in the blind spot perception device of the mobile robot provided in the embodiment of the present invention, the blind spot contour extraction module is specifically used for: Determine a first contour point in the first blind spot contour and a second contour point in the last blind spot contour; a first line connecting the current directional position and the first contour point has a minimum angle with the body coordinate system of the mobile robot, and a second line connecting the current directional position and the second contour point has a maximum angle with the body coordinate system; The safety-perceived directional position is determined based on the perpendicular bisector of the third line connecting the first contour point and the second contour point in combination with the field of view of the mobile robot.

[0060] On the basis of the above-mentioned embodiment, in the blind spot perception device of the mobile robot provided in the embodiment of the present invention, the blind spot contour extraction module is specifically used for: Determine a ray starting from the first contour point or the second contour point, the angle between which and the perpendicular bisector is less than or equal to half of the field of view angle; If the circular area with the intersection of the ray and the perpendicular midline as the center and the radius of the mobile robot as the radius is in the safe area, the safety perception directed position is determined based on the intersection of the ray and the perpendicular midline and the direction of the perpendicular midline; Otherwise, the last blind spot contour is deleted from the perception area, and a new last blind spot contour is re-determined to determine the safety perception directional position when the first blind spot contour and the new last blind spot contour are both under the field of view angle.

[0061] On the basis of the above-mentioned embodiment, in the mobile robot blind spot sensing device provided in the embodiment of the present invention, the sensing area is a semicircular area with the center of the mobile robot as the center and the effective observation distance of the mobile robot as the radius.

[0062] On the basis of the above-mentioned embodiment, in the blind spot sensing device for a mobile robot provided in the embodiment of the present invention, the blind spot sensing module is further used for: If the safety perception directional position is empty, the mobile robot is controlled to rotate at the current directional position to perceive the blind area of ​​the field of vision within the perception area.

[0063] On the basis of the above-mentioned embodiment, in the blind spot perception device of the mobile robot provided in the embodiment of the present invention, the blind spot contour extraction module is specifically used for: Extracting each blind spot contour within the sensing area and the centroid of each blind spot contour; Based on the positions of the centroids of the blind spot contours in the body coordinate system of the mobile robot, the blind spot contours are sorted along the preset direction to obtain the first blind spot contour and the last blind spot contour.

[0064] Specifically, the functions of each module in the mobile robot blind spot sensing device provided in the embodiment of the present invention correspond one-to-one to the operating procedures of each step in the above-mentioned method embodiment, and the effects achieved are also consistent. Please refer to the above-mentioned embodiment for details, and no further details will be given in the embodiment of the present invention.

[0065] Figure 6 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 6 As shown, the electronic device may include: a processor 610, a communication interface 620, a memory 630 and a communication bus 640, wherein the processor 610, the communication interface 620 and the memory 630 communicate with each other through the communication bus 640. The processor 610 may call the logic instructions in the memory 630 to execute the blind spot perception method of the mobile robot provided in the above embodiments.

[0066] In addition, the logic instructions in the above-mentioned memory 630 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention, or the part that contributes to the relevant technology or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0067] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the mobile robot blind spot perception method provided in the above embodiments.

[0068] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the mobile robot blind spot perception method provided in the above embodiments.

[0069] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0070] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiment.

[0071] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A blind spot perception method for a mobile robot, characterized in that: include: If there is a blind spot in the current orientation of the mobile robot, and the distance between the blind spot and the mobile robot is less than a preset threshold, determine the current directional position of the mobile robot and the perception area in the current orientation; Extracting a first blind spot contour and a last blind spot contour in the perception area along a preset direction, and determining a safe perception directional position of the mobile robot when the first blind spot contour and the last blind spot contour are both in the field of view of the mobile robot; If the safety sensing directed position is not empty, the mobile robot is controlled to move from the current directed position to the safety sensing directed position, and then return from the safety sensing directed position to the current directed position to sense the blind spot in the sensing area.

2. The blind spot perception method of a mobile robot according to claim 1, characterized in that: The step of determining the safe sensed directional position of the mobile robot when the first blind spot contour and the last blind spot contour are both within the field of view of the mobile robot comprises: Determine a first contour point in the first blind spot contour and a second contour point in the last blind spot contour; a first line connecting the current directional position and the first contour point has a minimum angle with the body coordinate system of the mobile robot, and a second line connecting the current directional position and the second contour point has a maximum angle with the body coordinate system; The safety-perceived directional position is determined based on the perpendicular bisector of the third line connecting the first contour point and the second contour point in combination with the field of view of the mobile robot.

3. The blind spot perception method of a mobile robot according to claim 2, characterized in that: The determining of the safety-perceived directional position based on the perpendicular bisector of the third line connecting the first contour point and the second contour point in combination with the field of view angle of the mobile robot comprises: Determine a ray starting from the first contour point or the second contour point, the angle between which and the perpendicular bisector is less than or equal to half of the field of view angle; If the circular area with the intersection of the ray and the perpendicular midline as the center and the radius of the mobile robot as the radius is in the safe area, the safety perception directed position is determined based on the intersection of the ray and the perpendicular midline and the direction of the perpendicular midline; Otherwise, the last blind spot contour is deleted from the perception area, and a new last blind spot contour is re-determined to determine the safety perception directional position when the first blind spot contour and the new last blind spot contour are both under the field of view angle.

4. The blind spot perception method of a mobile robot according to claim 2, characterized in that: The sensing area is a semicircular area with the center of the mobile robot as the center and the effective observation distance of the mobile robot as the radius.

5. The blind spot perception method of a mobile robot according to any one of claims 1 to 4, characterized in that: The step of determining the safe sensed directional position of the mobile robot when the first blind spot contour and the last blind spot contour are both under the field of view of the mobile robot, further comprises: If the safety perception directional position is empty, the mobile robot is controlled to rotate at the current directional position to perceive the blind area of ​​the field of vision within the perception area.

6. The blind spot perception method of a mobile robot according to any one of claims 1 to 4, characterized in that: The extracting of the first blind area contour and the last blind area contour in the perception area along a preset direction includes: Extracting each blind spot contour within the sensing area and the centroid of each blind spot contour; Based on the positions of the centroids of the blind spot contours in the body coordinate system of the mobile robot, the blind spot contours are sorted along the preset direction to obtain the first blind spot contour and the last blind spot contour.

7. A blind spot sensing device for a mobile robot, characterized in that: include: A current position determination module, configured to determine the current directional position of the mobile robot and the sensing area in the current orientation if there is a blind spot in the current orientation of the mobile robot and the distance between the blind spot and the mobile robot is less than a preset threshold; A blind spot contour extraction module, used to extract the first blind spot contour and the last blind spot contour in the perception area along a preset direction, and determine the safe perception directional position of the mobile robot when the first blind spot contour and the last blind spot contour are both in the field of view of the mobile robot; The blind spot perception module is used to control the mobile robot to move from the current directional position to the safety perception directional position if the safety perception directional position is not empty, and then return from the safety perception directional position to the current directional position to perceive the blind spot of vision within the perception area.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the mobile robot blind spot perception method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the mobile robot blind spot perception method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the mobile robot blind spot perception method according to any one of claims 1 to 6 is implemented.

Images