CN115420292A - Positioning and navigation method and system for a wheel-legged steel bar binding robot - Google Patents

Abstract

The invention provides a positioning and navigation method and system for a wheel-leg type steel bar binding robot, which belongs to the technical field of steel bar automatic binding. The positioning and navigation method includes: establishing a building information node map of the steel bar net surface according to the profile information of the steel bar net surface at the construction site; Path planning for the wheel-legged steel bar binding robot based on the building information node map; the extended Kalman filter algorithm is used to position the wheel-legged steel bar binding robot according to the displacement increment measured by the monocular camera and the ranging information of the UWB positioning base station ; According to the current position and construction path, determine the movement direction of the wheel-legged steel bar binding robot, and perform the binding task. By positioning and navigating the wheel-legged steel bar binding robot in real time, the binding efficiency of steel bars at the construction site is improved.

Description

Positioning and navigation method and system for a wheel-legged steel bar binding robot

technical field

The invention relates to the technical field of steel bar automatic binding, in particular to a positioning and navigation method and system for a wheel-leg type steel bar binding robot.

Background technique

In the construction industry, steel bar binding is a labor-intensive industry. In the fields of bridge roof prefabrication and ground hardening of large-scale underground projects, it is usually necessary to lay steel skeletons in advance. The process needs to be done manually. This construction method has high cost and slow speed, especially the binding process of steel bar nodes is time-consuming and labor-intensive.

In order to solve the problem of low efficiency and high cost of manually binding a large number of steel bar nodes, there is a wheel-legged steel bar binding robot in the prior art, which can move horizontally and vertically on the steel mesh surface and automatically complete the identification and binding of steel bar nodes. . However, during the actual construction of the wheel-legged steel bar binding robot, due to the lack of positioning and navigation capabilities, the steel bar binding robot cannot move flexibly on the steel mesh surface, which affects the efficiency of the steel bar binding operation.

Contents of the invention

The purpose of the present invention is to provide a positioning and navigation method and system for a wheel-legged steel bar binding robot, which can solve the problem of low binding efficiency caused by the inability of the existing steel bar binding robot to position and navigate.

To achieve the above object, the present invention provides the following scheme:

A positioning and navigation method for a wheel-legged steel bar binding robot, comprising:

Obtain the profile information of the steel mesh surface at the construction site;

According to the outline information of the steel mesh surface, a building information node map of the steel mesh surface is established; the building information node map includes a plurality of steel bar nodes and position coordinates of each steel bar node;

Based on the building information node map, path planning is carried out to the wheel-leg type steel bar binding robot, and the construction path of the wheel-leg type steel bar binding robot is determined; the construction path includes a plurality of steel bar nodes and the position coordinates of each steel bar node;

Using the extended Kalman filter algorithm, according to the displacement increment of the wheel-legged steel bar binding robot measured by the monocular camera and the distance measurement information of the wheel-legged steel bar binding robot by the ultra-wideband UWB positioning base station, the wheel-leg The type steel bar binding robot is positioned to obtain the current position of the wheel-leg type steel bar binding robot; the monocular camera is set on the wheel-leg type steel bar binding robot; the UWB positioning base station is set on the construction site;

According to the current position and the construction path, the moving direction of the wheel-legged steel bar binding robot is determined, and a binding task is performed.

Optionally, the acquisition of the reinforcement mesh profile information on the construction site specifically includes:

Use drones to carry visual sensors to collect images of steel mesh surfaces in various areas of the construction site, and obtain multiple partial images;

Splicing multiple partial images to obtain construction site images;

The deep learning algorithm is used to segment the reinforcement instance in the image of the construction site, to determine the outline information of each reinforcement, the number of reinforcement, the distance between the reinforcement and the diameter of the reinforcement, and obtain the outline information of the reinforcement mesh.

Optionally, the visual sensor is a depth camera.

Optionally, the establishment of a building information node map of the reinforced mesh surface according to the profile information of the reinforced mesh surface specifically includes:

According to the outline information of the steel mesh surface, a building information model of the steel mesh surface is established;

According to the building information model, determine the position coordinates of each reinforcement node;

According to the location coordinates of each reinforcement node, a building information node map is established.

Optionally, the path planning of the wheel-legged steel bar binding robot based on the building information node map to determine the construction path of the wheel-legged steel bar binding robot specifically includes:

Determine the robot model according to the size information of the wheel-leg type steel bar binding robot; the robot model is a rectangular frame;

Based on the robot model and the building information node map, the construction path of the wheel-legged steel bar binding robot is simulated to determine the position coordinates of the robot model during lateral movement and longitudinal movement;

According to the position coordinates during the lateral movement and the longitudinal movement of the robot model, the construction path of the wheel-leg type steel bar binding robot is obtained.

Optionally, the extended Kalman filter algorithm is used, according to the displacement increment of the wheel-legged steel bar binding robot measured by the monocular camera and the distance measurement information of the wheel-legged steel bar binding robot by the ultra-wideband UWB positioning base station , positioning the wheel-leg type steel bar binding robot to obtain the current position of the wheel-leg type steel bar binding robot, specifically including:

A plurality of UWB positioning base stations are set at the construction site, and a UWB coordinate system is established; the UWB coordinate system corresponds to the coordinate system in the building information node map;

Adopt monocular camera to measure the initial displacement increment of described wheel-leg formula steel bar binding robot;

Converting the initial displacement increment to the UWB coordinate system to obtain the target displacement increment;

For any UWB positioning base station, measure the distance between the UWB positioning base station and the wheel-leg type steel bar binding robot through the UWB positioning base station to obtain ranging information;

The extended Kalman filter algorithm is used to determine the current position of the wheel-legged steel bar binding robot according to the target displacement increment and the ranging information of each UWB positioning base station.

Optionally, the determining the movement direction of the wheel-legged steel bar binding robot according to the current position and the construction path, and performing a binding task specifically includes:

Calculate the distance between the current position and each reinforcement node in the construction path, and determine the target node; the target node is the reinforcement node closest to the current position in the construction path;

judging whether the distance between the current position and the target node is greater than a set threshold;

If the distance between the current position and the target node is greater than a set threshold, the wheel-legged steel bar binding robot continues to move along the original direction and performs a binding task; the original direction is horizontal or vertical;

If the distance between the current position and the target node is less than or equal to a set threshold, the wheel-legged steel bar binding robot moves from moving in the first direction to moving in the second direction, and performs a binding task; the second The two directions are directions perpendicular to the first direction on the horizontal plane.

Optionally, when the wheel-legged steel bar binding robot moves laterally, the wheel-legged steel bar binding robot moves along the horizontal direction of the steel bars by means of wheeled motion;

When the wheel-legged steel bar binding robot moves longitudinally, the wheel-legged steel bar binding robot moves in a direction perpendicular to the steel bar by using leg motion.

To achieve the above object, the present invention also provides the following solutions:

A positioning and navigation system for a wheel-legged steel bar binding robot, comprising:

A contour acquisition unit is used to obtain the contour information of the reinforcement mesh surface on the construction site;

The map establishment unit is connected with the outline acquisition unit, and is used to establish a building information node map of the steel mesh surface according to the outline information of the steel mesh surface; the building information node map includes a plurality of reinforcement nodes and each reinforcement node Position coordinates;

The path planning unit is connected with the map establishment unit, and is used to plan the path of the wheel-legged steel bar binding robot based on the building information node map, and determine the construction path of the wheel-legged steel bar binding robot; the construction path includes Multiple reinforcement nodes and the position coordinates of each reinforcement node;

The positioning unit is used to adopt the extended Kalman filter algorithm, according to the displacement increment of the wheel-legged steel bar binding robot measured by the monocular camera and the distance measurement information of the wheel-legged steel bar binding robot by the ultra-wideband UWB positioning base station, The wheel-leg type steel bar binding robot is positioned to obtain the current position of the wheel-leg type steel bar binding robot; the monocular camera is set on the wheel-leg type steel bar binding robot; the UWB positioning base station is set on the construction on site;

The navigation unit is respectively connected with the path planning unit and the positioning unit, and is used to determine the movement direction of the wheel-legged steel bar binding robot according to the current position and the construction path, and execute the binding task.

Optionally, the contour acquisition unit includes:

The image acquisition module is used to use the unmanned aerial vehicle to carry the visual sensor to collect the image of the steel mesh surface in each area of the construction site to obtain multiple partial images;

The splicing module is connected with the image acquisition module, and is used to splice multiple partial images to obtain construction site images;

The target detection module is connected with the splicing module, and is used to segment the image of the construction site using a deep learning algorithm to segment the reinforcement instance, determine the contour information of each reinforcement, the number of reinforcements, the spacing between the reinforcements and the diameter of the reinforcement, and obtain the contour information of the reinforcement mesh surface .

According to the specific embodiment provided by the present invention, the present invention discloses the following technical effects: first, according to the outline information of the steel mesh surface at the construction site, a building information node map of the steel mesh surface is established, and then based on the building information node map, the wheel-leg type steel bar The binding robot performs path planning to determine the construction path of the wheel-legged steel bar binding robot, and then uses the extended Kalman filter algorithm, according to the displacement increment measured by the monocular camera and the ranging information of the UWB positioning base station, the wheel-legged steel bar binding robot Carry out positioning to obtain the current position of the wheel-legged steel bar binding robot, and finally determine the movement direction of the wheel-legged steel bar binding robot according to the current position and construction path, and perform the binding task. By real-time positioning of the wheel-legged steel bar binding robot and Navigation, which improves the binding efficiency of steel bars on the construction site.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the accompanying drawings required in the embodiments. Obviously, the accompanying drawings in the following description are only some of the present invention. Embodiments, for those of ordinary skill in the art, other drawings can also be obtained according to these drawings without paying creative labor.

Fig. 1 is the flow chart of the positioning and navigation method of the wheel-legged steel bar binding robot of the present invention;

Fig. 2 is the schematic diagram of construction path planning;

Figure 3 is a flowchart of combined positioning of monocular camera and UWB;

Fig. 4 is a block diagram of the positioning and navigation system of the wheel-legged steel bar binding robot of the present invention.

Symbol Description:

Outline acquisition unit-1, map establishment unit-2, path planning unit-3, positioning unit-4, navigation unit-5, robot model-A, steel bar node-B, construction path-C.

detailed description

The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

The purpose of the present invention is to provide a positioning and navigation method and system for a wheel-legged steel bar binding robot, which improves the binding efficiency of steel bars at the construction site by positioning and navigating the wheel-legged steel bar binding robot in real time.

In order to make the above objects, features and advantages of the present invention more comprehensible, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

Embodiment one

As shown in Figure 1, the positioning and navigation method of the wheel-leg type steel bar binding robot provided in this embodiment includes:

S1: Obtain the profile information of the reinforcement mesh on the construction site.

Specifically, firstly, the visual sensor carried by the UAV is used to collect the images of the steel mesh surface in each area of the construction site, and multiple partial images are obtained. In this embodiment, the depth camera is fixed on the drone to collect images of the construction environment. The visual sensor is a depth camera. Then multiple partial images are spliced to obtain the construction site image. Specifically, a feature-based image mosaic technology is used to stitch the acquired partial images to obtain a complete image of the construction area. Then, the deep learning algorithm is used to segment the reinforcement instance in the image of the construction site to determine the outline information of each reinforcement, the number of reinforcement, the distance between the reinforcement and the diameter of the reinforcement, and obtain the outline information of the reinforcement mesh. In this embodiment, the Mask R-CNN deep learning algorithm is used to segment the reinforcement instance on the construction site image.

S2: Establish a building information node map of the reinforced mesh surface according to the outline information of the reinforced mesh surface. The building information node map includes a plurality of reinforcement nodes and position coordinates of each reinforcement node.

Further, S2 includes:

S21: Establish a BIM (Building Information Modeling, building information model) of the steel mesh surface according to the profile information of the steel mesh surface.

S22: Determine the position coordinates of each reinforcement node according to the building information model. Specifically, the position of each steel bar is obtained by parsing the IFC file. Then calculate the coordinate value of each reinforcement node in the building information model. Rebar nodes are intersection points of rebar.

S23: Establish a BIM node map according to the position coordinates of each reinforcement node.

S3: Based on the building information node map, perform path planning for the wheel-legged steel bar binding robot, and determine the construction path of the wheel-legged steel bar binding robot. The construction path includes a plurality of reinforcement nodes and position coordinates of each reinforcement node.

Specifically, S3 includes:

S31: Determine the robot model according to the size information of the wheel-legged steel bar binding robot. The robot model is a rectangular frame.

S32: Based on the robot model and the building information node map, simulate the construction path of the wheel-legged steel bar binding robot, and determine the position coordinates of the robot model during lateral movement and longitudinal movement.

Specifically, import the robot model and BIM node map into ROS (RobotOperating System, robot operating system) to establish a simulation environment. In the simulation environment, the movement of the robot model is simulated, and all position coordinates when the robot model moves laterally to the edge of the steel mesh surface are recorded in the BIM node map. Considering the working range of the wheel-legged steel bar binding robot, simulate the longitudinal movement of the robot model on the edge of the steel mesh surface to the adjacent unbound area, and record the position coordinates of all robots in this state.

S33: Obtain the construction path of the wheel-legged steel bar binding robot according to the position coordinates of the robot model during the lateral movement and the longitudinal movement. Specifically, all position coordinates are connected end to end in order to form a construction path.

Using the BIM node map to complete the planning principle of the construction path of the wheel-legged steel bar binding robot on the horizontal steel mesh surface is shown in Figure 2. In the figure, A is the robot model, B is the location of the steel bar node in the BIM node map, and C is the location of the steel bar in the BIM node map. The construction path planned on the steel mesh surface.

S4: Using the extended Kalman filter algorithm, according to the displacement increment of the wheel-legged steel bar binding robot measured by the monocular camera and the distance measurement information of the wheel-legged steel bar binding robot by the ultra-wideband UWB positioning base station, the The wheel-leg type steel bar binding robot is positioned to obtain the current position of the wheel-leg type steel bar binding robot. The monocular camera is arranged on the wheel-leg type steel bar binding robot. The UWB positioning base station is set on the construction site.

Specifically, the pose of the wheel-legged steel bar binding robot is estimated by monocular vision and UWB positioning base station. S4 specifically includes:

S41: Setting multiple UWB (ultra wide band, ultra wide band) positioning base stations on the construction site, and establishing a UWB coordinate system. The UWB coordinate system corresponds to the coordinate system in the building information node map. Specifically, a certain number of UWB positioning base stations are arranged according to the size of the construction environment, and a UWB coordinate system aligned with the BIM coordinate system is established according to the coordinates of the steel mesh surface as the coordinate system for combined positioning.

S42: Using a monocular camera to measure the initial displacement increment of the wheel-leg type steel bar binding robot.

In this embodiment, the frequency is first set for the monocular camera and the UWB positioning base station, and data are collected respectively. Specifically, the monocular camera is a monocular visual odometer. A monocular camera is used to capture images of the surrounding environment of a wheel-legged steel bar binding robot. Then calculate the displacement increment of two adjacent frames of images.

S43: Transform the initial displacement increment into the UWB coordinate system to obtain a target displacement increment.

Specifically, it is first necessary to calibrate the monocular camera installed on the wheel-legged steel bar binding robot, eliminate the systematic error of the monocular camera, and establish the pose relationship between the camera coordinate system and the UWB coordinate system. The displacement increment measured by the monocular visual odometer is transformed into the UWB coordinate system through space transformation.

S44: For any UWB positioning base station, measure the distance between the UWB positioning base station and the wheel-leg type steel bar binding robot through the UWB positioning base station to obtain distance measurement information.

S45: Using the extended Kalman filter algorithm, according to the target displacement increment and the ranging information of each UWB positioning base station, determine the current position of the wheel-legged steel bar binding robot. That is to determine the position coordinates of the wheel-legged binding robot on the steel mesh surface.

Specifically, firstly, according to the absolute position information obtained by the UWB positioning base station, the absolute scale estimation of the monocular visual odometer is performed by using the least square method. Then according to the displacement increment measured by the monocular visual odometer, the non-line-of-sight error identification is performed on the round-trip time ranging value of the UWB positioning base station. Finally, the displacement increment of the visual odometer and the ranging information of the UWB positioning base station are used as measurement values, and the extended Kalman filter algorithm is used for data fusion to determine the current position of the wheel-legged steel bar binding robot. In this embodiment, the state update and measurement update are performed through the loosely coupled fusion mode of the EKF (Extended Kalman Filter, Extended Kalman Filter) algorithm, and finally the positioning information of the wheel-legged steel bar binding robot is obtained. The process of combined positioning of monocular camera and UWB is shown in Figure 3.

In practical applications, it is necessary to use the monocular camera and UWB to locate the base station, and at the same time use the EKF to fuse the information obtained by the two sensors to achieve the purpose of enhancing the positioning accuracy and stability.

S5: Determine the movement direction of the wheel-legged steel bar binding robot according to the current position and the construction path, and perform a binding task.

Specifically, S5 includes:

S51: Calculate the distance between the current position and each reinforcement node in the construction path, and determine a target node. The target node is the steel bar node closest to the current position in the construction path.

S52: Determine whether the distance between the current position and the target node is greater than a set threshold.

S53: If the distance between the current position and the target node is greater than a set threshold, the wheel-legged steel bar binding robot continues to move in the original direction, and performs a binding task. The original direction is horizontal or vertical.

S54: If the distance between the current position and the target node is less than or equal to a set threshold, the wheel-legged steel bar binding robot changes from moving along the first direction to moving along the second direction, and performs a binding task. The second direction is a direction perpendicular to the first direction on a horizontal plane. Specifically, when the first direction is horizontal, the second direction is vertical, and when the first direction is vertical, the second direction is horizontal. That is, according to the current motion state of the wheel-legged steel bar binding robot, it changes from lateral motion to longitudinal motion or from longitudinal motion to lateral motion, and performs the binding task.

In this embodiment, when the wheel-leg type steel bar binding robot moves laterally, the wheel-leg type steel bar binding robot moves along the horizontal direction of the steel bars by means of wheel motion. When the wheel-legged steel bar binding robot moves longitudinally, the wheel-legged steel bar binding robot moves in a direction perpendicular to the steel bar by using leg motion.

The invention improves the flexibility of the wheel-leg binding robot in the binding construction of the steel mesh surface by positioning and navigating the wheel-leg binding robot in real time.

Embodiment two

In order to implement the method corresponding to the first embodiment above to achieve corresponding functions and technical effects, a positioning and navigation system for a wheel-leg type steel bar binding robot is provided below.

As shown in FIG. 4 , the positioning and navigation system of the wheel-legged steel bar binding robot provided in this embodiment includes: a contour acquisition unit 1 , a map establishment unit 2 , a path planning unit 3 , a positioning unit 4 and a navigation unit 5 .

Wherein, the contour acquisition unit 1 is used to obtain the contour information of the reinforcement mesh surface on the construction site.

Specifically, the contour acquisition unit 1 includes: an image acquisition module, a splicing module and a target detection module. The image acquisition module is used to use the drone to carry the visual sensor to collect the image of the steel mesh surface in each area of the construction site, and obtain multiple partial images. The splicing module is connected with the image acquisition module, and the splicing module is used to splice multiple partial images to obtain construction site images. The target detection module is connected with the splicing module, and the target detection module is used to use a deep learning algorithm to perform reinforcement instance segmentation on the construction site image, determine the contour information of each reinforcement, the number of reinforcements, the spacing of the reinforcements and the diameter of the reinforcements, and obtain the reinforcement mesh surface profile information.

The map building unit 2 is connected with the outline acquisition unit 1, and the map building unit 2 is used to create a building information node map of the steel mesh surface according to the outline information of the steel mesh surface. The building information node map includes a plurality of reinforcement nodes and position coordinates of each reinforcement node.

Specifically, the map building unit 2 includes: a BIM model building module, a node coordinate determining module and a map building module. The BIM model building module is connected with the outline acquisition unit 1, and the BIM model building module is used to create a building information model of the steel mesh surface according to the outline information of the steel mesh surface. The node coordinate determination module is connected with the BIM model establishment module, and the node coordinate determination module is used to determine the position coordinates of each reinforcement node according to the building information model. The map creation module is used to create a building information node map according to the position coordinates of each reinforcement node.

The path planning unit 3 is connected to the map building unit 2, and the path planning unit 3 is used to plan the path of the wheel-legged steel bar binding robot based on the building information node map, and determine the construction path of the wheel-legged steel bar binding robot. The construction path includes a plurality of reinforcement nodes and position coordinates of each reinforcement node.

Specifically, the path planning unit 3 includes: a robot model determination module, a simulation module and a path determination module. The robot model determination module is used to determine the robot model according to the size information of the wheel-leg type steel bar binding robot. The robot model is a rectangular frame. The simulation module is respectively connected with the map building unit 2 and the robot model determination module, and the simulation module is used to simulate the construction path of the wheel-legged steel bar binding robot based on the robot model and the building information node map, and determine the robot The position coordinates of the model during lateral movement and longitudinal movement. The path determination module is connected with the simulation module, and the path determination module is used to obtain the construction path of the wheel-legged steel bar binding robot according to the position coordinates of the robot model during lateral movement and longitudinal movement.

The positioning unit 4 is used to adopt the extended Kalman filter algorithm, according to the displacement increment of the wheel-legged steel bar binding robot measured by the monocular camera and the distance measurement information of the wheel-legged steel bar binding robot by the ultra-wideband UWB positioning base station, The wheel-leg type steel bar binding robot is positioned to obtain the current position of the wheel-leg type steel bar binding robot. The monocular camera is arranged on the wheel-leg type steel bar binding robot. The UWB positioning base station is set on the construction site.

Specifically, the positioning unit 4 includes: a coordinate system determination module, a displacement measurement module, a coordinate conversion module, a distance measurement module and a fusion module. The coordinate system determination module is used to set multiple UWB positioning base stations on the construction site and establish a UWB coordinate system. The UWB coordinate system corresponds to the coordinate system in the building information node map. The displacement measurement module is used to measure the initial displacement increment of the wheel-leg type steel bar binding robot by using a monocular camera. The coordinate conversion module is connected with the displacement measurement module, and the coordinate conversion module is used to convert the initial displacement increment into the UWB coordinate system to obtain the target displacement increment. The ranging module is used for any UWB positioning base station, and measures the distance between the UWB positioning base station and the wheel-legged steel bar binding robot through the UWB positioning base station to obtain ranging information. The fusion module is connected with the coordinate conversion module and the ranging module, and the fusion module is used to determine the distance of the wheel-legged steel bar binding robot according to the target displacement increment and the ranging information of each UWB positioning base station by using the extended Kalman filter algorithm. current location.

The navigation unit 5 is respectively connected with the path planning unit 3 and the positioning unit 4, and the navigation unit 5 is used to determine the movement direction of the wheel-legged steel bar binding robot according to the current position and the construction path, and execute Binding task.

Specifically, the navigation unit 5 includes: a distance calculation module, a judgment module, a direction maintenance module and a direction change module. The distance calculation module is connected with the path planning unit 3 and the positioning unit 4 respectively, and is used to calculate the distance between the current position and each reinforcement node in the construction path, and determine the target node. The target node is the steel bar node closest to the current position in the construction path. A judging module, configured to judge whether the distance between the current location and the target node is greater than a set threshold. The direction maintaining module is connected with the judging module, and is used to keep the wheel-legged steel bar binding robot moving in the original direction and perform the binding task when the distance between the current position and the target node is greater than a set threshold. The original direction is horizontal or vertical. The direction changing module is connected with the judging module, and is used to switch the wheel-legged steel bar binding robot from moving along the first direction to moving along the second direction when the distance between the current position and the target node is less than or equal to the set threshold. directional movement, and perform lashing tasks. The second direction is a direction perpendicular to the first direction on a horizontal plane.

Each embodiment in this specification is described in a progressive manner, each embodiment focuses on the difference from other embodiments, and the same and similar parts of each embodiment can be referred to each other. As for the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and for the related information, please refer to the description of the method part.

In this paper, specific examples have been used to illustrate the principle and implementation of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; meanwhile, for those of ordinary skill in the art, according to the present invention Thoughts, there will be changes in specific implementation methods and application ranges. In summary, the contents of this specification should not be construed as limiting the present invention.

Claims (10)

1. A positioning navigation method of a wheel-leg type steel bar bundling robot is characterized by comprising the following steps:

acquiring the profile information of a reinforcing steel bar net surface on a construction site;

building a building information node map of the steel bar net surface according to the profile information of the steel bar net surface; the building information node map comprises a plurality of steel bar nodes and position coordinates of the steel bar nodes;

based on the building information node map, planning a path of the wheel-leg type steel bar bundling robot, and determining a construction path of the wheel-leg type steel bar bundling robot; the construction path comprises a plurality of steel bar nodes and position coordinates of the steel bar nodes;

positioning the wheel-legged reinforcement bar binding robot by adopting an extended Kalman filtering algorithm according to the displacement increment of the wheel-legged reinforcement bar binding robot measured by a monocular camera and the ranging information of the ultra wide band UWB positioning base station to the wheel-legged reinforcement bar binding robot to obtain the current position of the wheel-legged reinforcement bar binding robot; the monocular camera is arranged on the wheel-leg type steel bar bundling robot; the UWB positioning base station is arranged on a construction site;

and determining the motion direction of the wheel-leg type steel bar bundling robot according to the current position and the construction path, and executing a binding task.

2. The positioning and navigation method for the wheel-leg type steel bar binding robot according to claim 1, wherein the acquiring of the steel bar mesh profile information at the construction site specifically comprises:

an unmanned aerial vehicle carrying a vision sensor is adopted to acquire reinforcing steel bar mesh surface images of each area of a construction site to obtain a plurality of local images;

splicing the local images to obtain a construction site image;

and (3) carrying out steel bar example segmentation on the construction site image by adopting a deep learning algorithm, and determining the profile information, the number of the steel bars, the interval of the steel bars and the diameter of the steel bars of each steel bar to obtain the profile information of the mesh surface of the steel bars.

3. The method for positioning and navigating the wheel-legged rebar tying robot according to claim 2, wherein the vision sensor is a depth camera.

4. The method for positioning and navigating the wheel-leg type reinforcement bar binding robot according to claim 1, wherein the building information node map of the reinforcement bar mesh surface is established according to the reinforcement bar mesh surface profile information, and specifically comprises:

building a building information model of the steel bar net surface according to the profile information of the steel bar net surface;

determining the position coordinates of each steel bar node according to the building information model;

and establishing a building information node map according to the position coordinates of the reinforcing steel bar nodes.

5. The method according to claim 1, wherein the step of planning a path of the wheel-legged reinforcement bar-binding robot based on the building information node map to determine a construction path of the wheel-legged reinforcement bar-binding robot comprises:

determining a robot model according to the size information of the wheel-leg type steel bar bundling robot; the robot model is a rectangular frame;

based on the robot model and the building information node map, performing simulation on a construction path of the wheel-leg type steel bar bundling robot, and determining position coordinates of the robot model in the processes of transverse movement and longitudinal movement;

and obtaining a construction path of the wheel-leg type steel bar bundling robot according to the position coordinates of the robot model in the processes of transverse movement and longitudinal movement.

6. The method according to claim 1, wherein the positioning and navigating method for the wheel-legged reinforcement bar binding robot by using the extended kalman filter algorithm is configured to position the wheel-legged reinforcement bar binding robot according to the displacement increment of the wheel-legged reinforcement bar binding robot measured by the monocular camera and the distance measurement information of the ultra wideband UWB positioning base station on the wheel-legged reinforcement bar binding robot, so as to obtain the current position of the wheel-legged reinforcement bar binding robot, specifically includes:

setting a plurality of UWB positioning base stations on a construction site, and establishing a UWB coordinate system; the UWB coordinate system corresponds to a coordinate system in the building information node map;

measuring the initial displacement increment of the wheel-leg type steel bar bundling robot by adopting a monocular camera;

converting the initial displacement increment to a UWB coordinate system to obtain a target displacement increment;

aiming at any UWB positioning base station, measuring the distance between the UWB positioning base station and the wheel leg type steel bar bundling robot through the UWB positioning base station to obtain ranging information;

and determining the current position of the wheel-leg type steel bar bundling robot according to the target displacement increment and the ranging information of each UWB positioning base station by adopting an extended Kalman filtering algorithm.

7. The method for positioning and navigating the wheel-leg type steel bar binding robot according to claim 1, wherein the determining the movement direction of the wheel-leg type steel bar binding robot according to the current position and the construction path and performing the binding task specifically comprises:

calculating the distance between the current position and each steel bar node in the construction path, and determining a target node; the target node is a steel bar node which is closest to the current position in the construction path;

judging whether the distance between the current position and the target node is larger than a set threshold value or not;

if the distance between the current position and the target node is larger than a set threshold value, the wheel-leg type steel bar bundling robot continues to move along the original direction and executes a bundling task; the original direction is transverse or longitudinal;

if the distance between the current position and the target node is smaller than or equal to a set threshold value, the wheel-leg type steel bar bundling robot is changed from moving along a first direction to moving along a second direction, and a bundling task is executed; the second direction is a direction perpendicular to the first direction on a horizontal plane.

8. The positioning and navigation method of a wheel-legged reinforcement bar binding robot according to claim 7, wherein the wheel-legged reinforcement bar binding robot moves in a horizontal direction of a reinforcement bar in a wheel-type motion while the wheel-legged reinforcement bar binding robot moves in a lateral direction;

when the wheel-leg type steel bar bundling robot moves along the longitudinal direction, the wheel-leg type steel bar bundling robot moves along the direction vertical to the steel bars by adopting leg type movement.

9. The utility model provides a wheel-legged rebar tying robot's location navigation, its characterized in that, wheel-legged rebar tying robot's location navigation includes:

the contour acquisition unit is used for acquiring the contour information of the steel bar mesh surface of a construction site;

the map establishing unit is connected with the outline acquisition unit and used for establishing a building information node map of the steel bar net surface according to the outline information of the steel bar net surface; the building information node map comprises a plurality of steel bar nodes and position coordinates of the steel bar nodes;

the path planning unit is connected with the map establishing unit and used for planning the path of the wheel-leg type steel bar bundling robot based on the building information node map and determining the construction path of the wheel-leg type steel bar bundling robot; the construction path comprises a plurality of steel bar nodes and position coordinates of the steel bar nodes;

the positioning unit is used for positioning the wheel-leg type steel bar bundling robot according to the displacement increment of the wheel-leg type steel bar bundling robot measured by the monocular camera and the ranging information of the ultra-wideband UWB positioning base station on the wheel-leg type steel bar bundling robot by adopting an extended Kalman filtering algorithm to obtain the current position of the wheel-leg type steel bar bundling robot; the monocular camera is arranged on the wheel-leg type steel bar bundling robot; the UWB positioning base station is arranged on a construction site;

and the navigation unit is respectively connected with the path planning unit and the positioning unit and is used for determining the motion direction of the wheel-leg type steel bar bundling robot according to the current position and the construction path and executing a binding task.

10. The positioning and navigation system for a wheel-legged rebar tying robot according to claim 9, wherein the profile acquisition unit includes:

the image acquisition module is used for acquiring the steel bar mesh surface images of each area of a construction site by adopting an unmanned aerial vehicle carrying a visual sensor to obtain a plurality of local images;

the splicing module is connected with the image acquisition module and is used for splicing the local images to obtain a construction site image;

and the target detection module is connected with the splicing module and used for carrying out reinforcement instance segmentation on the construction site image by adopting a deep learning algorithm, determining the profile information, the number of reinforcements, the distance between the reinforcements and the diameter of the reinforcements of each reinforcement and obtaining the profile information of the mesh surface of the reinforcements.

Images