A continuum robot and a method for real-time perception of its body motion posture

Abstract

The application belongs to the field of robot motion posture perception, and particularly discloses a continuum robot and a method for realizing real-time perception of the motion posture of the continuum robot, which comprises a bellows backbone, skeletons, a cable and a camera system, wherein: the inner and outer walls of the bellows backbone are provided with bellows structures, and the bottom is provided with a base; a plurality of skeletons are uniformly and axially sleeved and fixed outside the bellows backbone; the upper end of the cable is fixed on the top skeleton and sequentially passes through each skeleton on the lower side, and the lower end of the cable is led out from the base; the camera system is installed on the base and located in the bellows backbone. The motion is realized by pulling the cable, and the image is acquired by the camera system, and then the position and direction of any point on the robot body are output based on the neural network. The application realizes the perception of the motion posture of the whole continuum robot, and can be applied to the motion control and interaction of the continuum robot.

Description

TECHNICAL FIELD

[0001] The present application belongs to the field of robot motion posture perception, and more particularly relates to a continuum robot and a method for real-time perception of the body motion posture of the continuum robot. BACKGROUND

[0002] The body perception capability of a continuum robot is very important for its motion control and safe interaction. The posture perception of existing continuum robots is mostly focused on the spatial pose information of the end point, and the overall perception of the whole body information depends on multiple distributed discrete sensors, which brings challenges to the structural design and wiring of the robot.

[0003] Therefore, there is an urgent need for a new continuum robot that can conveniently, stably and accurately perceive the overall motion posture information of its body in real time. SUMMARY

[0004] In view of the above defects or improvement needs of the prior art, the present application provides a continuum robot and a method for real-time perception of the body motion posture of the continuum robot, which aims to realize real-time perception of the whole body posture information of the robot.

[0005] To achieve the above-mentioned purpose, according to one aspect of the present application, a continuum robot is provided, comprising a bellows backbone, a skeleton, a cable and a camera system, wherein:

[0006] The inner and outer walls of the bellows backbone have a bellows structure, and the bottom is provided with a base;

[0007] A plurality of skeletons are uniformly fixed axially on the outside of the bellows backbone;

[0008] The upper end of the cable is fixed on the top skeleton and passes through each skeleton in turn, and the lower end of the cable passes out from the base;

[0009] The camera system is installed on the base and located inside the bellows backbone.

[0010] As a further preferred, the skeleton comprises a skeleton sheet and a clamping plate, the inner side of the skeleton sheet is nested in the bellows structure of the bellows backbone, and the outer side is provided with a hole for the cable to pass through; two clamping plates fix the skeleton sheet from the upper and lower sides.

[0011] As a further preferred, one skeleton comprises N skeleton sheets, and the N skeleton sheets are arranged uniformly in a circumferential direction on the bellows backbone; N cables are provided correspondingly, and each cable is connected to all skeleton sheets at the same circumferential position.

[0012] As a further preferred, N=3.

[0013] As a further preferred, the hole outside the skeleton piece is embedded with a conduit, the cable passes through the conduit and can freely slide in the conduit; the lower side of the cable is provided with an elbow pipe, the cable passes out of the elbow pipe; the upper end of the elbow pipe is fixed in the hole of the bottom end skeleton piece, and the lower end is fixed on the base.

[0014] As a further preferred, the cable adopts PE wire, and the conduit and the elbow pipe all adopt Teflon material.

[0015] As a further preferred, the lighting system is further included, and the lighting system is arranged around the camera system.

[0016] As a further preferred, the lighting system includes a middle hollow PCB board and LED lamp beads, the PCB board is installed on the base, and the lens of the camera system is arranged at the middle hollow part of the PCB board; a plurality of LED lamp beads are arranged on the PCB board.

[0017] According to another aspect of the present application, a method for real-time sensing of the posture of the body of the continuum robot is provided, comprising the following steps:

[0018] A series of target points are taken in the axial direction of the bellows backbone, and the relative positions of the target points on the bellows backbone are determined based on the distances of the target points from the bottom of the bellows backbone in the axial direction;

[0019] The bellows backbone image obtained by the camera system and the relative positions of the target points on the bellows backbone are input into the trained convolutional neural network model to obtain the spatial position coordinates of the target points on the bellows backbone;

[0020] The spatial position coordinates of the series of target points are obtained to determine the posture of the continuum robot.

[0021] As a further preferred, after the bellows backbone image and the relative positions of the target points on the bellows backbone are input into the trained convolutional neural network model: the image is flattened into a 512-dimensional vector, the new vector is obtained after the vector is multiplied by the relative positions of the target points on the bellows backbone; the new vector and the relative positions of the target points on the bellows backbone are combined to obtain a 513-dimensional feature vector; and the spatial position coordinates of the target points are output according to the feature vector.

[0022] Overall, compared with the prior art, the above technical solutions conceived by the present application mainly have the following technical advantages:

[0023] 1. The bellows backbone designed in the present application takes into account the structural stability and the ability of flexible movement, and provides installation space and information for the built-in camera system; combined with the visual feedback arranged in the body, a single camera can realize real-time sensing of the whole body posture information of the robot, and has a wide application prospect.

[0024] 2. The continuum robot of the present application has a general driving form, which is not limited to linear driving, pneumatic driving or other driving forms, and has a simple and compact structure.

[0025] 3. The method for sensing the real-time posture of the continuum robot of the present application combines the camera image and the relative position of the target point, can select the target point by itself, and realizes the sensing of the spatial posture of any point of the continuum robot, instead of being limited to the end point or specific limited points. BRIEF DESCRIPTION OF DRAWINGS

[0026] Figure 1 Fig. 1 is a schematic diagram of the overall structure of the continuum robot of the present application;

[0027] Figure 2 Fig. 3 is a schematic diagram of the assembly structure of the bellows backbone and the skeleton of the present application;

[0028] Figure 3 Fig. 4 is a schematic diagram of the skeleton structure of the present application, wherein (a) is an exploded view of the skeleton, and (b) is a schematic diagram of the cross section of the skeleton;

[0029] Figure 4 Fig. 5 is a schematic diagram of the base structure of the present application, wherein (a) is a schematic diagram of the base, and (b) is an exploded view of the base;

[0030] Figure 5 Fig. 6 is an exploded view of the continuum robot structure of the present application.

[0031] In all the drawings, the same reference signs are used to represent the same elements or structures, wherein: 1 is a bellows backbone, 2 is a skeleton, 21 is a skeleton sheet, 22 is a clamping plate, 3 is a base, 31 is a base frame, 32 is a base cover, 4 is a cable assembly, 41 is a cable, 42 is a guide pipe, 43 is an elbow pipe, 5 is an illumination system, 51 is a PCB board, 52 is an LED lamp bead, 6 is a camera system, 61 is a lens, 62 is a control board, and 7 is a top cover. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solutions and advantages of the present application more clear, the present application is further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application. In addition, the technical features involved in each embodiment of the present application described below can be combined with each other as long as they do not conflict with each other.

[0033] The continuum robot provided by the embodiment of the present application is as follows: Figure 1 and Figure 5As shown, including the bellows backbone 1, skeleton 2, base 3, cable assembly 4, lighting system 5, camera system 6 and top cover 7, wherein:

[0034] The bellows backbone 1 has obvious corrugated structure on the inner and outer walls, when the bellows backbone 1 produces movement deformation, the corrugation on the inner and outer walls of the bellows backbone will also produce deformation at the same time; preferably, the bellows backbone 1 as a whole adopts white material, and the outside is sprayed with black paint, which reduces the influence of external environmental light intensity on the operation of the built-in camera system. The top cover 7 is fixed on the top of the bellows backbone 1 by using threaded fasteners, and the base 3 is arranged at the bottom of the bellows backbone 1.

[0035] In the axial direction of the bellows backbone 1, several skeletons 2 are arranged uniformly and equidistantly on the bellows backbone 1, as shown in Figure 2 As shown, the skeleton 2 includes skeleton sheet 21 and clamping plate 22, as shown in Figure 3 A group of skeletons 2 includes N skeleton sheets 21, which are arranged uniformly in the circumferential direction on the bellows backbone 1, and the inner side of the skeleton sheet 21 is nested in the corrugated structure of the bellows backbone 1; in this embodiment, N=3, that is, three skeleton sheets 21 are arranged at an interval of 120° in the circumferential direction; the three skeleton sheets 21 are clamped in the middle by two clamping plates 22 and are clamped by bolts, so as to fix the group of skeletons 2 on the bellows backbone 1.

[0036] The base 3 includes base frame 31 and base cover 32 thereon, the base frame 31 reserves a plurality of apertures for the built-in camera system 6, and the wiring of the lighting system 5 is used for power supply and signal transmission, and the base 3 is preferably made of 3D printing material which can withstand 200℃ high temperature.

[0037] The cable assembly 4 includes cable 41, guide pipe 42 and elbow pipe 43, the number of the cable 41 corresponds to the number of the skeleton sheets 21 in a group of skeletons 2, that is, each cable 41 connects all the skeleton sheets 21 at the same circumferential position, and the cable 41 is preferably made of PE wire; the guide pipe 42 is fixed in the circular hole of all the skeleton sheets 21 except the first section skeleton at the bottom by glue; one end of the elbow pipe 43 is fixed in the circular hole of the first section skeleton sheet 21 at the bottom by glue, and the other end of the elbow pipe 43 passes through the circular hole of the base frame 31. The upper side of the cable 41 is fixed on the top skeleton sheet 2, and then passes through the guide pipe 42 in each section skeleton sheet 21 in turn, and finally passes through the elbow pipe 43, and the lower side of the cable 41 extends out of the elbow pipe 43, and the cable 41 can slide freely in the guide pipe 42 and the elbow pipe 43. The guide pipe 42 and the elbow pipe 43 are preferably made of Teflon material, which can greatly reduce the friction with the cable 41. By driving the cable 41, the free bending movement of the bellows backbone 1 in space can be realized.

[0038] The camera system 6 includes lens 61 and control board 62, as shown in Figure 4As shown, the lens 61 is glued on the base cover 32 and located in the bellows trunk 1, and can capture the deformation of the bellows structure of the inner wall of the bellows in real time during the motion of the continuum robot; the lens 61 is connected to the control board 62 through a flexible flat cable, there are four protruding circular tables in the base frame 31, the structure size of the circular table matches the mounting hole on the control board 62, the control board 62 is fixed on the circular table in the base frame 31, and the wiring of the control board 62 is led out from the reserved hole on the base frame 31.

[0039] The lighting system 5 includes a hollow PCB board 51 and LED lamp beads 52, the PCB board 51 is fixed on the base cover 32, the lens 61 is located at the center of the hollow of the PCB board 51, and the four LED lamp beads 52 are welded on the PCB board 51, and the lighting system 5 is connected with an electric wire led out from the reserved hole on the base frame 31; when the lighting system 5 is powered on, the internal environment of the bellows trunk 1 can be illuminated.

[0040] The embodiment of the application provides a kind of continuum robot's body motion posture real-time sensing method, comprising the following steps:

[0041] A series of target points are taken in the axial direction of the bellows trunk (selected according to needs), and the length of the target point along the axial direction of the bellows trunk from the bottom is taken as the relative position of the target point on the bellows trunk; Specifically, the length can be normalized to a real number in the range of 0 to 1, i.e. the relative position of 0 indicates the target point at the bottom, and the relative position of 1 indicates the target point at the end;

[0042] When the continuum robot moves, the camera system collects the internal image information of the bellows trunk in real time;

[0043] The internal image information and the relative position of the target point on the bellows trunk are input into the trained convolutional neural network model, and the spatial position coordinates of the target point are output;

[0044] Specifically, after the internal image and the relative position of the target point on the bellows trunk are input into the trained convolutional neural network model, the image is convolved and flattened into a 512-dimensional vector, and the vector is multiplied by the relative position of the target point on the bellows trunk to obtain a new vector; the relative position of the target point on the bellows trunk is combined in the new vector to obtain a 513-dimensional feature vector; the feature vector passes through a fully connected layer to output the spatial position coordinates of the target point.

[0045] A series of unlimited number of target points on the relative position of the bellows trunk are input into the convolutional neural network model, and the convolutional neural network model can simultaneously output a series of unlimited number of spatial coordinates of the target points. Finally, the body motion posture real-time sensing of the continuum robot based on visual information feedback is realized.

[0046] Those skilled in the art can easily understand that the above description is only the preferred embodiment of the present application, and is not intended to limit the present application. Any modification, equivalent replacement and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A continuum robot, characterized in that, The utility model relates to a kind of continuous body robot, including bellows backbone (1), framework (2), cable (41) and camera system (6), wherein: The bellows backbone (1) is provided with a base (3) at the bottom, and the inner and outer walls of the bellows backbone (1) have a corrugated structure. A plurality of framework (2) is uniformly fixed on the outside of the bellows backbone (1) in the axial direction. The upper end of the cable (41) is fixed on the top framework (2), and sequentially passes through each framework (2) on the lower side, and the lower end of the cable (41) is out of the base (3). The camera system (6) is installed on the base (3) and located in the bellows backbone (1). The framework (2) includes framework sheet (21) and clamping plate (22), the inner side of the framework sheet (21) is nested in the corrugated structure of the bellows backbone (1), and the outer side is provided with a hole for the cable (41) to pass through; 2 clamping plates (22) are fixed on the framework sheet (21) from the upper and lower sides. One framework (2) includes N pieces of framework sheet (21), and N pieces of framework sheet (21) are uniformly arranged on the bellows backbone (1) in the circumferential direction; correspondingly provided with N cables (41), each cable (41) connects all framework sheets (21) at the same circumferential position. The hole on the outer side of the framework sheet (21) is embedded with a conduit (42), and the cable (41) passes through the conduit (42) and can freely slide in the conduit (42); the lower side of the cable (41) is provided with an elbow (43), and the cable (41) is out of the elbow (43); the upper end of the elbow (43) is fixed in the hole of the bottom framework sheet (21), and the lower end is fixed on the base (3).

2. The continuum robot of claim 1, wherein, N=3。 3. The continuum robot of claim 1, wherein, The cable (41) is made of PE wire, and the conduit (42) and the elbow (43) are made of Teflon material.

4. The continuum robot of any one of claims 1-3, wherein, It also includes a lighting system (5) arranged around the camera system (6).

5. The continuum robot of claim 4, wherein, The lighting system (5) includes a PCB board (51) with a hollow middle part and LED lamp beads (52), the PCB board (51) is installed on the base (3), and the lens of the camera system (6) is arranged at the hollow middle part of the PCB board (51); a plurality of LED lamp beads (52) are arranged on the PCB board (51).

6. A method of real-time perception of the body motion posture of a continuum robot according to any one of claims 1-5, characterized in that, The utility model includes the following steps: A series of target points are taken in the axial direction of the bellows backbone (1), and the relative positions of the target points on the bellows backbone (1) are determined based on the distance of the target points from the bottom of the bellows backbone (1) in the axial direction; The image of the bellows backbone (1) obtained by the camera system (6) and the relative positions of the target points on the bellows backbone (1) are input into the trained convolutional neural network model to obtain the spatial position coordinates of the target points on the bellows backbone (1); The spatial position coordinates of a series of target points are obtained to determine the pose of the continuous body robot.

7. The method of claim 6, wherein the method further comprises: determining a pose of the body of the robot based on the plurality of images. The corrugated pipe backbone (1) image and the relative position of the target point on the corrugated pipe backbone (1) are input into the trained convolutional neural network model: the image is flattened into a 512-dimensional vector, the vector is multiplied by the relative position of the target point on the corrugated pipe backbone (1) to obtain a new vector; the new vector is combined with the relative position of the target point on the corrugated pipe backbone (1) to obtain a 513-dimensional feature vector; and the spatial position coordinates of the target point are output according to the feature vector.

Images