CN117301036A

CN117301036A - A pneumatic soft robot for space-constrained unstructured environments

Info

Publication number: CN117301036A
Application number: CN202311305062.9A
Authority: CN
Inventors: 罗宗富; 赵子曰; 侯宛廷; 殷茵; 庄琪; 张涛; 张传富
Original assignee: Sun Yat Sen University
Current assignee: Sun Yat Sen University
Priority date: 2023-10-09
Filing date: 2023-10-09
Publication date: 2023-12-29

Abstract

The application discloses a pneumatic soft robot for a space-limited unstructured environment and a control method, wherein the robot comprises: the load platform, the front anchoring unit, the telescopic unit, the rear anchoring unit, the gas-electricity integrated pipeline, the gas source and the controller are sequentially arranged; the front anchoring unit comprises a front anchoring unit electromagnetic valve; the rear anchoring unit comprises a rear anchoring unit electromagnetic valve; the front anchoring unit is connected with the telescopic unit through the electromagnetic valve of the front anchoring unit to realize gas circuit connection; the front anchoring unit is connected with the air source through the electromagnetic valve of the rear anchoring unit and the gas-electricity integrated pipeline; the air source and the controller are used for jointly adjusting the volumes and the shapes of the front anchoring unit, the telescopic unit and the rear anchoring unit through the gas-electricity integrated pipeline. The robot is suitable for changing environments and has better practicability. The method and the device can be widely applied to the technical field of soft robots.

Description

Pneumatic soft robot for space-limited unstructured environment

Technical Field

The application relates to the technical field of soft robots, in particular to a pneumatic soft robot for a space-limited unstructured environment.

Background

Soft robotic designs typically require bionic participation. Inchworm is a common bionic object in soft robot design due to its unique movement mechanism. The body of inchworm is composed of several body segments, which can be stretched to be contracted into omega shape under the action of muscle, so that the body can be stretched, and a group of feet are respectively arranged in front and back of the body for anchoring itself. When inchworm advances, the body is first contracted, then the hind legs are anchored, then the body is stretched, the forelegs are anchored, finally the hind legs are released, and the body is contracted again, so that the whole advancing is realized.

The existing various pipeline soft robots are all duplicate of the structure. The minimum monomer of each robot is formed by sequentially connecting an anchoring mechanism, a telescopic mechanism and another anchoring mechanism, and the anchoring mechanism and the telescopic mechanism are driven according to the inchworm movement process, so that the movement of the robot in a pipeline is realized.

Compared with other schemes, the pipeline soft robot based on inchworm bionics has better adaptability to pipelines, and can primarily solve the problems existing in pipeline operation. However, the application of such pipeline robots in space-constrained unstructured environments presents certain difficulties, limited by their design objectives and mechanical structure, which are not applicable to more varied environments. Accordingly, there still exists a technical problem in the related art that needs to be solved.

Disclosure of Invention

The object of the present application is to solve at least one of the technical problems existing in the prior art to a certain extent.

To this end, it is an object of embodiments of the present application to provide a pneumatic soft robot for a spatially constrained unstructured environment; the robot can adapt to changing environments and has better practicability.

In order to achieve the technical purpose, the technical scheme adopted by the embodiment of the application comprises the following steps: a pneumatic soft robot for a space-limited unstructured environment comprises a load platform, a front anchoring unit, a telescopic unit, a rear anchoring unit, a gas-electricity integrated pipeline, a gas source and a controller which are sequentially arranged; the front anchoring unit comprises a front anchoring unit electromagnetic valve; the rear anchoring unit comprises a rear anchoring unit electromagnetic valve; the front anchoring unit is connected with the telescopic unit through the electromagnetic valve of the front anchoring unit to realize gas circuit connection; the front anchoring unit is connected with the air source through the electromagnetic valve of the rear anchoring unit and the gas-electricity integrated pipeline; the air source and the controller are used for jointly adjusting the volumes and the shapes of the front anchoring unit, the telescopic unit and the rear anchoring unit through the gas-electricity integrated pipeline.

In addition, a pneumatic soft robot for a space-constrained unstructured environment according to the above embodiments of the present invention may further have the following additional technical features:

further, in an embodiment of the present application, the gas-electric integrated pipeline includes a fusiform smooth foam block; the fusiform smooth foam blocks are arranged on the gas-electricity integrated pipeline at intervals.

Further, in this embodiment of the present application, each of the front anchoring unit and the rear anchoring unit further includes a protective layer, a balloon, and a friction pad; the protective layer wraps the balloon and is used for protecting the balloon from being damaged by the environment; the friction pad is arranged on the protective layer; the balloon is for receiving gas inflation itself to inflate the front and rear anchoring units; the friction pad is used for increasing the surface friction of the front anchoring unit and the rear anchoring unit.

Further, in the embodiment of the application, the load platform comprises a thermal imaging module, a gas sensor, a temperature and humidity sensor, a camera and a microphone module.

Further, in an embodiment of the present application, the diameter of the front anchoring unit and the rear anchoring unit in the axial direction when not expanded is smaller than the maximum diameter of the load platform in the axial direction.

Further, in an embodiment of the present application, the telescopic unit includes a bellows, a first air path connector, and a second air path connector; the first air passage joint is used for being connected with the electromagnetic valve of the rear anchoring unit; the second gas circuit joint is used for being connected with the front anchoring unit electromagnetic valve.

Further, in the embodiment of the present application, the rear anchoring unit solenoid valve and the front anchoring unit solenoid valve each include a normally closed end, a normally open end, and an air intake end.

Further, in an embodiment of the present application, the controller includes a microprocessor, a micro screen, a configuration panel, and a solid state relay.

Further, in the embodiment of the present application, the material of the protective layer is ultra-high molecular weight polyethylene fiber.

In another aspect, an embodiment of the present application further provides a method for controlling a pneumatic soft robot for a space-constrained unstructured environment, where the method includes:

the controller is opened, the electromagnetic valve of the anchoring unit is controlled by the air source to expand the anchoring unit and obtain first detection data of the robot; according to the first detection data, the controller determines a first detection result of the obstacle detection unit; the first detection result is used for a controller to judge whether the first anchoring of the robot is successful or not; the first sensed data includes a relationship between air pressure and time during inflation of the rear anchoring unit; when the first anchoring of the robot is successful, the controller closes the electromagnetic valve of the rear anchoring unit and the electromagnetic valve of the front anchoring unit, controls the air source to inflate the telescopic unit and controls the telescopic unit to axially extend for a preset distance, so that the first gravity center of the soft robot moves forwards; the controller opens the electromagnetic valve of the front anchoring unit, and controls the air source to inflate the front anchoring unit to expand the front anchoring unit and obtain second detection data of the robot; according to the second detection data, the controller obtains a second detection result of the obstacle detection unit; the second detection result is used for a controller to detect whether the robot is successfully anchored for the second time; the second detection data includes a relationship between air pressure and time during inflation of the pre-anchor unit; when the second anchoring of the robot is successful, the controller closes the electromagnetic valve of the front anchoring unit and controls the air source to output negative pressure, so that the front anchoring unit is restored to the state before expansion.

The advantages and benefits of the present application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the present application.

The utility model provides a can realize the whole removal of software robot through two anchor through load platform, preceding anchor unit, flexible unit, back anchor unit, gas-electricity integration pipeline, air supply and controller, and the preceding anchor unit, flexible unit, back anchor unit of this application only carry out axial movement moreover, and need not to curl to "omega" shape, can adapt to more application scenario, can improve software robot's environmental adaptation ability, improves software robot's practicality.

Drawings

FIG. 1 is a schematic diagram of a pneumatic soft robot for a spatially constrained unstructured environment in accordance with one embodiment of the present invention;

FIG. 2 is a schematic diagram illustrating steps of a method for controlling a pneumatic soft robot in a spatially constrained unstructured environment according to an embodiment of the present invention;

FIG. 3 is a schematic diagram of a pneumatic soft robot for a spatially constrained unstructured environment in accordance with another embodiment of the present invention;

FIG. 4 is a schematic view of the structure of the front anchor unit or the rear anchor unit according to one embodiment of the present invention;

FIG. 5 is a schematic view of a telescopic unit according to an embodiment of the present invention;

FIG. 6 is a schematic diagram of a gas-electricity integrated pipeline according to an embodiment of the present invention

FIG. 7 is a schematic view of a load cell according to an embodiment of the present invention

FIG. 8 is a schematic diagram of a training process of an artificial neural network model according to an embodiment of the invention

FIG. 9 is a flow chart of a soft robot implementing a motion cycle according to an embodiment of the invention

FIG. 10 is a schematic diagram showing the structural change of a soft robot for realizing a motion cycle according to an embodiment of the present invention;

FIG. 11 is a schematic diagram of a pneumatic soft robot control device for a spatially constrained unstructured environment in accordance with an embodiment of the present invention.

Detailed Description

Embodiments of the present invention are described in detail below with reference to the accompanying drawings, wherein the principles and processes of a pneumatic soft robot for a spatially constrained unstructured environment in the embodiments of the present invention are described below.

First, the defects of the prior art will be described

The limited space refers to a region where people and common equipment are hard to access due to narrow space. The limited space operation is an important subject of interest in many fields, and the fields of medical examination, surgical operation, pipeline inspection, complex equipment maintenance, post-earthquake search and rescue, geological disaster prevention for geological exploration and the like all relate to limited space exploration.

Due to the limitation of the structural rigidity of the rigid robot, the traditional rigid robot is difficult to operate in an environment with limited space, and the application of the rigid robot in the fields of ruin gap search and rescue, geological crack detection, pipeline inspection and the like is limited. With the development of materials and microelectronic technology, a large number of soft robots using a limited space as an application scene appear, wherein pipeline soft robots are a common and mature type.

Soft robotic designs typically require bionic participation. Inchworm is a common bionic object in soft robot design due to its unique movement mechanism. The body of inchworm is composed of several body segments, which can be stretched into straight form or contracted into omega form under the action of muscle, so that it can implement extension and contraction, and the front and rear of body are respectively equipped with a group of feet for anchoring self-body. When inchworm advances, the body is first contracted, then the hind legs are anchored, then the body is stretched, the forelegs are anchored, finally the hind legs are released, and the body is contracted again, so that the whole advancing is realized.

Compared with other schemes, the pipeline soft robot based on inchworm bionics has better adaptability to pipelines, and can primarily solve the problems existing in pipeline operation. However, the use of such pipeline robot software in a space-constrained unstructured environment presents difficulties, subject to the limitations of its design purpose and mechanical structure.

Unstructured environments are a concept that is opposed to structured environments. The structured environment refers to an environment with uniform environment surface, stable and known structure and change rule and known environment information. The pipe is a typical structured environment because the inner wall of the pipe is uniform, regular and fixed in shape, there are generally no abrupt obstacles, and the main environmental information changes are reflected by changes in the inner diameter and curvature of the pipe. In contrast, unstructured ambient surfaces are not uniform, the structure may change over time and the law of change is difficult to master. Ruin gaps, ground fissures, and severely damaged or silted pipes after geological disasters are all more common unstructured environments.

When the traditional pipeline soft robot works in an unstructured environment, the problems of insufficient trafficability, damaged or invalid anchoring mechanism, insufficient reliability and the like caused by larger radius can be faced. In addition, the current pipeline soft robot generally lacks an adaptive controller, and the operation of the anchoring mechanism and the telescopic mechanism follows manual control or preset open loop control operation, and cannot actively adapt to the time-varying characteristics of the unstructured environment, so that the operation efficiency in the unstructured environment is low, and even the robot can be damaged.

In the prior art, two typical soft robots are designed, one robot consists of a steering mechanism, an anchoring mechanism, a telescopic mechanism and an anchoring mechanism, the maximum diameter of the anchoring mechanism of the robot is 80mm, the diameter of the telescopic mechanism is 40mm, the robot can adapt to a pipeline with a certain inner diameter, and execute various tasks, but an air bag of the robot is directly contacted with the environment, the problems of insufficient anchoring force, easy damage of the air bag and the like exist, the driving pressure of the used rubber air bag is larger, the miniaturization is not facilitated, and certain danger exists during rupture.

The other robot is composed of a pneumatic expansion unit and a pneumatic expansion unit, can move in a pipeline, but has higher customization degree of a robot assembly, does not have a matched controller, and has low automation degree.

In summary, the application of the existing soft robots in the space-limited unstructured environment has great difficulty, and the requirement of working in the space-limited unstructured environment has long existed. Therefore, there is a need to design a pneumatic soft robot that can accommodate unstructured environments, has a high level of automation, and can perform a variety of tasks in unstructured environments as needed.

In view of the above technical problems, referring to fig. 1, the present application provides a pneumatic soft robot for a spatially-constrained unstructured environment. The robot can comprise a load platform 1, a front anchoring unit 2, a telescopic unit 3, a rear anchoring unit 4, a gas-electricity integrated pipeline 5, a gas source 6 and a controller 7 which are sequentially arranged along the motion axial direction of the soft robot; the front anchor unit 2 may include a front anchor unit solenoid valve; the rear anchor unit 4 may include a rear anchor unit solenoid valve; the front anchoring unit 2 is connected with the telescopic unit 3 through a front anchoring unit electromagnetic valve; the front anchoring unit 2 is connected with an air source 6 through a rear anchoring unit electromagnetic valve and an air-electricity integrated pipeline 5; the air source 6 and the controller 7 are used for jointly adjusting the volumes and the shapes of the front anchoring unit 2, the telescopic unit 3 and the rear anchoring unit 4 through the gas-electricity integrated pipeline 5. The load platform 1 can monitor the environment of the soft robot through devices such as a sensor, a microphone and the like, and can also transmit audio signals from the load platform 1 to the controller 7 through the microphone so as to realize audio capture in the environment.

Further, in some embodiments of the present application, the gas-electric integrated pipeline may comprise a fusiform smooth surface foam block; the spindle-shaped smooth foam blocks are arranged on the gas-electricity integrated pipeline at intervals.

Further, in some embodiments of the present application, both the front and rear anchoring units may also include a protective layer, a balloon, and a friction pad; the protective layer can wrap the balloon and can be used for protecting the balloon from being damaged by a spike structure or a spike object in the environment; the friction pad can be arranged on the protective layer; the friction pad can increase the friction force of the front anchoring unit and the rear anchoring unit, so that the robot can keep the stability of the robot when in motion. The balloon may be inflated by receiving gas, which upon inflation may expand the front or rear anchoring units and change the volume or shape of the anchoring units.

Further, in some embodiments of the present application, the load platform may include a thermal imaging module, a gas sensor, a temperature and humidity sensor, a camera, and a microphone module. The thermal imaging module may be used to discover thermal signatures of survivors within the ruins; the gas sensor can be used for detecting whether flammable gas exists underground or not and providing guidance for the use of subsequent rescue tools; the temperature and humidity sensor can be used for detecting the temperature and humidity of air; the camera can be used for observing the internal conditions of ruins; the silicon microphone module may be used to communicate information to underground survivors.

Further, in some embodiments of the present application, the diameter of the front and rear anchor units in the axial direction when unexpanded may be smaller than the maximum diameter of the load platform in the axial direction; the maximum diameter of the telescoping unit in the axial direction may be smaller than the diameters of the front anchor unit and the rear anchor unit. The load platform is positioned at the forefront end in the axial direction, and the maximum diameter of the load platform is larger than that of the front anchoring unit, the rear anchoring unit and the telescopic unit, so that the load platform can smoothly enter a space-limited unstructured environment, and a certain space still exists among the front anchoring unit, the rear anchoring unit and the telescopic unit, and the movement of a subsequent soft robot is not influenced.

Further, in some embodiments of the present application, the telescoping unit may include a bellows, a first gas circuit connector, and a second gas circuit connector; the first air passage joint is used for being connected with the electromagnetic valve of the rear anchoring unit; the second gas circuit joint is used for being connected with the electromagnetic valve of the front anchoring unit; the first air passage joint is connected with the electromagnetic valve of the rear anchoring unit; the second gas circuit joint is connected with the electromagnetic valve of the front anchoring unit, so that the front anchoring unit, the telescopic unit and the rear anchoring unit form a complete gas circuit capable of mutually transmitting gas.

Further, in some embodiments of the present application, the rear anchor unit solenoid valve and the front anchor unit solenoid valve may each include a normally closed end, a normally open end, and an air intake end; the air inlet end of the electromagnetic valve of the rear anchoring unit can be directly connected with an air source; the normal open end can be connected with a balloon inside the front anchoring unit; the normally closed end may be opened when release of gas within the balloon is desired.

Further, in some embodiments of the present application, the controller may include a microprocessor, a micro screen, a configuration panel, and a solid state relay; the microprocessor can be operated with two radial basis function neural network pre-training models, namely an anchor unit obstacle detector and a telescopic unit motion controller.

Further, in some embodiments of the present application, the material of the protective layer is ultra-high molecular weight polyethylene fibers. The material has the characteristics of good stab resistance, good flexibility and small thickness, can protect the balloon inside the anchoring unit from being damaged by the environment, can adapt to more conforming environments, and can provide more expansion space for the anchoring unit due to the small thickness.

In addition, referring to fig. 2, corresponding to the method of fig. 1, a method for controlling a pneumatic soft robot for a space-limited unstructured environment is further provided in an embodiment of the present application, where the method may include steps S101-S106 for controlling a pneumatic soft robot for a space-limited unstructured environment according to any one of the previous claims.

S101, opening a solenoid valve of the anchoring unit by a controller, controlling the anchoring unit to expand by an air source, and acquiring first detection data of the robot;

s102, according to first detection data, the controller determines a first detection result of the obstacle detection unit; the first detection result is used for a controller to judge whether the first anchoring of the robot is successful; the first detection data comprises the relationship between the air pressure and time during the expansion of the rear anchoring unit;

s103, when the first anchoring of the robot is successful, the controller closes the electromagnetic valve of the rear anchoring unit and the electromagnetic valve of the front anchoring unit, and controls the air source to inflate the telescopic unit and controls the telescopic unit to axially extend for a preset distance, so that the first gravity center of the soft robot moves forward;

s104, the controller opens the electromagnetic valve of the front anchoring unit, and controls the air source to inflate the front anchoring unit to expand the front anchoring unit and obtain second detection data of the robot;

s105, according to the second detection data, the controller obtains a second detection result of the obstacle detection unit; the second detection result is used for the controller to judge whether the robot is successfully anchored for the second time; the second detection data comprises the relationship between the air pressure and time during the expansion of the front anchoring unit;

And S106, when the second anchoring of the robot is successful, the controller closes the electromagnetic valve of the front anchoring unit and controls the air source to output negative pressure so that the front anchoring unit is restored to the state before expansion.

The specific structure and control principle of the present application are described below with reference to the accompanying drawings:

first, for the structure of the soft robot:

referring to fig. 3, the soft robot may include a load platform, a front anchor unit, a telescopic unit, a rear anchor unit, a gas-electric integrated pipeline, a gas source, and a controller. The front anchor unit has the same structure as the rear anchor unit, hereinafter referred to as "anchor unit". The anchoring unit can be divided into two parts of PAM and a connector, and the specific structure is shown in fig. 4.

In fig. 4, PAM is divided into an inner layer and an outer layer, and the inner layer is a single-port balloon. The outer layer is a protective fabric which wraps the inner layer balloon, and the fabric is made of flexible stab-resistant materials. Because the fabric does not have the ductility of the inner balloon, in order for the fabric to expand as the inner balloon is inflated, it is necessary that the fabric be in a relaxed state when the inner balloon is not inflated. In order to improve the friction force between the fabric and the environment contact surface after the inner balloon is inflated and avoid sharp objects on the contact surface from penetrating through the fabric holes to damage the inner balloon, a plurality of high-friction gaskets are adhered to the surface of the fabric.

One end of the PAM inner balloon opening is referred to as the "open end" and the other end is referred to as the "blind end". A connector is fixed at the PAM open end. The connecting piece is a flexible ring, a miniature two-position three-way electromagnetic valve is fixed in the ring, three ports of the electromagnetic valve are an air inlet end, a normal open end and a normal closed end, gas is input from the air inlet end, when the power supply is disconnected, the gas is output from the normal closed end, and after the power supply is connected, the gas is output from the normal open end.

The normal open end of the electromagnetic valve is connected with the opening of the inner balloon and is subjected to sealing treatment. The ring is provided with a small hole, and the cable penetrates into the hollow cavity of the inner layer and the outer layer of the PAM from the small hole and is led out from the other end of the PAM. In order to enable the cable to extend along with the expansion of the PAM, the cable in the PAM needs to be properly prolonged, and limit positions are arranged at the penetrating and the leading-out positions.

The structure of the telescopic unit can be seen in fig. 5. In fig. 5, the telescoping unit body is a flexible bellows having a tube diameter that approximates the diameter of the anchoring unit when not inflated. The two ends of the corrugated pipe are respectively provided with an opening, and each opening is respectively connected with the opening end of one anchoring unit. The bellows is connected with one end of the front anchoring unit, and the opening is connected with the air inlet end of the electromagnetic valve at the opening end of the front anchoring unit. The bellows is connected with one end of the rear anchoring unit, and the opening is connected with the normally closed end of the electromagnetic valve at the opening end of the rear anchoring unit. The first expansion joints at two ends of the corrugated pipe are respectively provided with a small hole, a cable penetrating out of the opening end of the front anchoring unit penetrates into one end of the corrugated pipe through the small holes, leaves from the other end of the corrugated pipe and penetrates into the opening end of the rear anchoring unit, and finally penetrates out of the blind end of the rear anchoring unit to form an electric passage penetrating through the whole soft robot. In order to enable the cable to adapt to the axial expansion of the corrugated pipe, the length of the cable left in the corrugated pipe is slightly larger than the maximum expansion length of the corrugated pipe, and the small holes at the two ends are subjected to airtight treatment, so that gas is prevented from leaking from the threaded small holes when the corrugated pipe is pressurized.

The structure of the load platform can be seen in fig. 7. In fig. 7, the load platform is fixed at the blind end of the front anchor unit, the diameter of the platform is similar to that of the anchor unit when not inflated, the main body is a hollow flexible paraboloid, the required sensors or end effectors are arranged in the paraboloid, the surface is reserved with openings required by the operation of related devices, and the cables of the devices pass through the whole robot in the mode and leave from the blind end of the rear anchor unit.

The structure of the gas-electricity integrated pipeline can be referred to as fig. 6. In fig. 6, the main body of the gas-electric integrated pipeline is a flexible gas hose with the length adjustable according to the requirement, and a fusiform smooth foam block is arranged on the hose at intervals for preventing the hose from contacting with the environment. A section of short hose is connected from the air inlet end of the electromagnetic valve of the rear anchoring unit, and the hose penetrates through PAM of the anchoring unit and penetrates out from the blind end of the anchoring unit. And connecting an air inlet end hose of the rear anchoring unit electromagnetic valve with the end A of a Y-shaped tee joint at one end of the gas-electricity integrated pipeline, and connecting a cable joint of the rear anchoring unit with a cable joint at the end B of the Y-shaped tee joint. The A end of the Y-shaped three-way joint at the other end of the gas source and gas-electricity integrated pipeline is connected with the gas source, and the B end cable joint is connected with the controller.

The air source main body is a direct current whipping dual-purpose air pump with an air pressure sensor. The dual-purpose air pump for whipping is one of the air pumps, and can output positive pressure and negative pressure. The air source is provided with two communication buses, the first one is used for the controller to access the data of the air pressure sensor, which is called an air pressure measuring bus, and the second one is used for the controller to control the power and the output type (namely positive pressure or negative pressure) of the pump, which is called an air pump control bus. Both buses are connected with the controller.

The controller is connected with two paths of communication buses of the air source, a front anchoring unit electromagnetic valve control line and a rear anchoring unit electromagnetic valve control line. The controller mainly comprises a microprocessor, a micro screen, a configuration panel and a solid state relay. The microprocessor is provided with two radial basis function neural network pre-training models, namely an anchoring unit obstacle detector and a telescopic unit motion controller.

The obstacle detector of the anchoring unit belongs to a classifier, the model learns the air pressure-time characteristics of two modes of free expansion and limited expansion of the anchoring unit under the given air pump power during training, wherein the free expansion refers to the situation that the anchoring unit is inflated when the periphery is free of obstacles, the limited expansion refers to the situation that the anchoring unit is blocked by the periphery obstacles during inflation, and the air pressure-time curves of the two situations are different, so that a data set can be established through experiments, and the corresponding model can be trained through a supervised learning method. In the process of robot movement, the front anchoring unit and the rear anchoring unit are required to be started alternately, in the process of anchoring unit inflation, a microprocessor periodically reads the air pressure of the corresponding anchoring unit and the sensor time stamp through an air pressure measuring bus, the model is input for reasoning, whether the anchoring unit encounters an obstacle or not is determined according to the output result of the model, if the result is true, the anchoring unit is successfully anchored, and the telescopic unit can be inflated.

The motion controller of the telescopic unit belongs to a fitting device, and the model fits a curve of the extension distance and the inflation time of the telescopic unit under the given air pump power during training. In the moving process of the robot, after the rear anchor unit is anchored, the telescopic unit is inflated to extend along the axial direction, so that the gravity center of the robot is moved. In the inflation and extension process of the telescopic unit, the microprocessor inputs a model to infer according to the single movement distance set by a user, so as to obtain the required inflation time, thereby realizing quantitative control on the movement of the robot.

The balloon used by the anchoring unit can be spherical or ellipsoidal, and the specification is determined by the channel size of the application scene. Taking a 5 inch balloon as an example, when the balloon is not inflated, the diameter of the balloon after folding is about 5mm, and the maximum diameter of the balloon after inflation is about 127mm. The flexible stab-resistant material can be selected from ultra-high molecular weight polyethylene fibers (UHMWPE), and has the characteristics of good stab-resistant performance, good flexibility, low density and small thickness.

The specifications of the two three-way electromagnetic valves used by the anchoring unit are determined by application scenes. Taking a common electromagnetic valve as an example, the specification of the optional minimum electromagnetic valve is not more than 15mm by 12.5mm.

There are a variety of bellows that differ greatly in materials, specifications, and properties, and are not named by specifications. According to the deformation recovery characteristic of the expansion joint of the corrugated pipe, the corrugated pipe can be divided into two types, wherein the deformation can be automatically maintained after the expansion joint is stretched by external force without continuously applying external force, the expansion joint is called as a steady-state corrugated pipe, and the deformation can not be automatically maintained after the expansion joint is stretched by external force. The bellows used by the telescopic unit is a steady-state bellows, and the specification is determined by application scenes. Taking the existing steady-state corrugated pipe as an example, the diameter of the corrugated pipe can be selected from 9mm, 19mm, 20mm, 29mm, 40mm and the like, and the length of the corrugated pipe can be customized or cut according to the needs.

Secondly, building a soft robot:

before the software robot is built, the controller program is compiled into firmware except the neural network model and is programmed into the microprocessor. The construction method may comprise the steps of:

1. and (5) building an anchoring unit.

1.1, manufacturing an inner layer of the PAM core body. One latex balloon is taken, one end and the other end of the opening of the balloon respectively penetrate through two small silica gel gaskets, and the two small silica gel gaskets are fixed by flexible adhesive. A silica gel short tube penetrates into the balloon from the opening end of the balloon and is sealed by flexible sealant.

1.2, laying cables. A silica gel air pipe and a multi-core wire are taken, the length of the multi-core wire is slightly longer than half of the maximum perimeter of an anchoring unit, and the two wires are bonded into a pipeline along the axial direction by using a flexible adhesive. And (3) punching holes on the gaskets in the step (1.1), penetrating the pipeline from one side of the gaskets, penetrating the other side of the gaskets, and injecting glue into the holes to fix the pipeline. Gas circuit joints and line joints are arranged at two ends of the pipeline.

1.3, manufacturing an outer layer of the PAM core body. A sheet of UHMWPE fabric of 40 g/square meter was taken and bonded using a polyethylene specific glue to form a cylinder with a diameter set to the maximum expansion radius of the anchoring unit and a length slightly longer than the balloon length. And (3) properly cutting and closing the two ends of the cylinder, sleeving the two closed ends outside the gasket at 1.1, and fixing the two closed ends by using flexible sealant. The high friction pads are secured to the fabric outer surface using a flexible adhesive.

1.4, manufacturing a connector. And (2) taking a miniature two-position three-way electromagnetic valve, and connecting the normally open end of the electromagnetic valve to the silica gel short pipe in the step (1.1). Two short silica gel pipes are respectively connected to the air inlet end and the normally closed end of the electromagnetic valve. And (2) connecting two wires of the electromagnetic valve with the connector in the step (1.2) through a circuit connector. The solenoid valve was sleeved into a small silicone gasket which was aligned with the gasket mounted on the open end of the balloon in step 1.1 and secured with a flexible adhesive.

1.5, if the manufactured anchoring unit is a front anchoring unit, sealing the normally closed end of the electromagnetic valve.

1.6, repeating steps 1.1 to 1.5 to make a second anchoring unit.

2. And (5) building a telescopic unit.

And 2.1, laying pipelines. And taking a steady-state corrugated pipe, and enabling a section of multi-core wire to pass through the corrugated pipe, so that the length of the wire in the pipe is slightly longer than the maximum length of the corrugated pipe after the expansion. And (3) punching a small hole on the last expansion joint at the two ends of the corrugated pipe, penetrating the lead out of the small hole, sealing the small hole, and installing circuit connectors at the two ends of the penetrated lead.

2.2, mounting the unit main body. Two gas path joints are respectively arranged at two ends of the corrugated pipe and sealed by flexible sealant.

3. And (5) building a load platform.

And 3.1, selecting a task load. The soft robot can be provided with different types of sensors and end effectors according to task requirements. In this embodiment, a lepton3.5 micro thermal imaging module, an SGP40 gas sensor, an SHT35 temperature and humidity sensor, an OV9734 micro camera, and a TDA1308 silicon microphone module are selected as examples for seismic search and rescue. The thermal imaging module is used for finding thermal signals of survivors in ruins; the SGP40 is used for detecting whether flammable gas exists underground or not and providing guidance for the use of subsequent rescue tools; the SHT35 is used for detecting the temperature and the humidity of air; the miniature camera is used for observing the internal conditions of ruins; the silicon microphone module is used to communicate information to underground survivors.

And 3.2, installing a task load. Drawing a PCB for the sensor, welding the sensor to the flexible PCB, welding a multi-core wire to lead out power supply and a bus, spraying a waterproof coating on the PCB, and protecting the sensor.

And 3.3, processing a load platform. A parabolic hull and a base of a load platform are machined from a flexible material. According to the PCB engineering file, a corresponding notch is processed at the vertex of the paraboloid, the flexible PCB is mounted on the notch by using a flexible adhesive, and the multi-core wire is led out from the tail of the paraboloid.

4. And manufacturing a gas-electricity integrated pipeline.

A silica gel hose is taken, two ends of the hose are respectively connected with a Y-shaped three-way joint, two joints which are not used are an end A and an end B, a multi-core cable passes through the inside of the hose, and the multi-core cable passes out of the end B of the three-way joint at two ends and is sealed by sealant. A group of spindle-shaped smooth foam blocks are manufactured, holes are drilled on the axes of the foam blocks, and a hose is penetrated through the foam blocks and fixed by flexible adhesive.

5. And assembling the soft robot.

And (3) aligning the open ends of the two anchoring units constructed in the step (1) to the two ends of the telescopic unit constructed in the step (2). The air inlet end of the electromagnetic valve of the front anchoring unit is connected with the air passage joint at one end of the telescopic unit through a silica gel hose, the two are connected through a joint, and the two are fixed through a silica gel bolt.

The air inlet end of the electromagnetic valve of the rear anchoring unit is connected with the air passage joint at the other end of the telescopic unit through a silica gel hose, the two cables are connected in the same mode, and the two cables are fixed through a silica gel bolt.

Connecting the load platform cable with the front anchoring unit blind end cable through an interface, aligning the load platform with the front anchoring unit axle center, and fixing the load platform cable and the front anchoring unit blind end cable by using a silica gel bolt.

And connecting an air inlet end hose of the rear anchoring unit electromagnetic valve with the end A of a Y-shaped tee joint at one end of the gas-electricity integrated pipeline, and connecting a cable joint of the rear anchoring unit with a cable joint at the end B of the Y-shaped tee joint.

The A end of the Y-shaped three-way joint at the other end of the gas source and gas-electricity integrated pipeline is connected with the gas source, and the B end cable joint is connected with the controller.

6. And training an artificial neural network model.

The process of training the artificial neural network model may refer to fig. 8, and in fig. 8 the training may include the steps of:

6.1, acquiring an anchor unit obstacle detector dataset. The soft robot is placed into a hard tube with the radius slightly larger than that of the robot, and the unit is anchored after being fixed. And one-dimensional laser radar is fixed at the other end of the transparent tube. And simultaneously starting an air source and a laser radar, and recording displacement-time data of the telescopic unit.

And 6.2, training an anchor unit obstacle detector model. A radial basis function neural network model of a single hidden layer is constructed, the number of nodes of an input layer is set to be 1, the number of nodes of the hidden layer is set to be 32, and the number of nodes of an output layer is set to be 1. The model is supervised trained.

And 6.3, collecting a motion controller data set of the telescopic unit. The rear anchoring unit of the soft robot is fixed on an iron stand, and the front anchoring unit is freely suspended. And starting the air source, recording air pressure-time data of the anchoring unit, and adding a label with a value of 0 for each air pressure-time data pair, wherein the label means data corresponding to free expansion. A hard tube having a radius slightly larger than that of the front anchor unit is fitted over the front anchor unit and fixed to the iron stand by a jig. And starting the air source, recording air pressure-time data of the anchoring unit, and adding a label with a value of 1 for each air pressure-time data pair, wherein the label is data corresponding to limited expansion.

And 6.4, establishing a motion controller model of the telescopic unit. A radial basis function neural network model of a single hidden layer is constructed, the number of nodes of an input layer is set to be 1, the number of nodes of the hidden layer is set to be 64, and the number of nodes of an output layer is set to be 1. The model is supervised trained.

And 6.5, importing the model. And writing the two groups of model parameter files obtained through training into a microprocessor of the controller.

The microprocessor is a stm32F103 singlechip produced by an artificial semiconductor, and other microprocessors with core Cortex-M4F can be selected.

The learning rate of the radial basis function neural network model training process can be set to be 1e-5.

Finally, for the control of the soft robot:

for the expression of the control process, for simplifying the expression, the air inlet end of the electromagnetic valve of the front anchoring unit of the robot is recorded as A1, the normal open end is B1, and the normal closed end is C1; the air inlet end of the electromagnetic valve of the rear anchoring unit is A2, the normal open end is B2, and the normal closed end is C2. The air source is connected with A2 through a gas-electricity integrated pipeline. The air source and the solenoid valve default to a shut-off state.

Referring to fig. 9 and 10, when the robot starts to advance, the solenoid valve of the rear anchoring unit is turned on, the A2 and the B2 are turned on, the air source is turned on, the air source outputs positive pressure, the rear anchoring unit expands, the controller reads air pressure-time data, the obstacle detector of the anchoring unit is called, if the output result is true, the anchoring is finished, and the air source is cut off.

The rear anchor unit solenoid valve is turned off, and A2 and C2 are turned on, and at this time, the front anchor unit solenoid valve is also turned off, and A1 and C1 are turned on (C1 is sealed). At this time, the air source is connected with the telescopic unit. And (3) calling a motion controller of the telescopic unit, calculating the time t required for reaching the preset length d, switching on an air source, enabling the air source to output positive pressure, and switching off the air source after the working time t to finish the first forward movement of the gravity center of the robot.

The front anchoring unit electromagnetic valve is connected, so that the A1 and the B1 are connected, and at the moment, the rear anchoring unit electromagnetic valve is also in a cut-off state, and the A2 and the C2 are connected. The air source is connected, the air source outputs positive pressure, the pressurized air enters the front anchoring unit through the telescopic unit, the front anchoring unit is inflated, meanwhile, the controller reads air pressure-time data, the anchoring unit obstacle detector is called, if the output result is true, the anchoring is finished, and the air source is cut off.

The front anchor unit solenoid valve is turned off to turn on A1 and C1, and at this time, the rear anchor unit solenoid valve is also turned off, and A2 and C2 are turned on. And (3) switching on the air source to enable the air source to output negative pressure, and after the working time t, switching off the air source to finish the second forward movement of the center of gravity of the robot and finish one movement period of the robot.

When the robot needs to perform a plurality of periodic motions, the quantitative control of the motion of the robot can be realized by repeating the process and adjusting the preset length d according to the requirement.

The beneficial effects achieved are the same as those achieved by the pneumatic soft robot embodiment described above for the spatially constrained unstructured environment.

Corresponding to the method of fig. 1, the embodiment of the present application further provides a pneumatic soft robot control device for a space-limited unstructured environment, and the specific structure of the pneumatic soft robot control device may refer to fig. 11, and may include:

at least one processor;

at least one memory for storing at least one program;

the at least one program, when executed by the at least one processor, causes the at least one processor to implement the pneumatic soft robot control method for a spatially constrained unstructured environment.

It should be noted that, the content in the above method embodiment is applicable to the embodiment of the present device, and the specific functions implemented by the embodiment of the present device are the same as those of the embodiment of the above method, and the achieved beneficial effects are the same as those of the embodiment of the above method.

Corresponding to the method of fig. 1, the embodiment of the present application further provides a storage medium having stored therein processor executable instructions which, when executed by a processor, are adapted to carry out the described method of controlling a pneumatic soft robot for a spatially constrained unstructured environment.

It should be noted that, the content in the above embodiment of the method for controlling a pneumatic soft robot in a space-limited unstructured environment is applicable to the embodiment of the storage medium, and the functions specifically implemented by the embodiment of the storage medium are the same as those in the embodiment of the method for controlling a pneumatic soft robot in a space-limited unstructured environment, and the beneficial effects achieved by the embodiment of the method for controlling a pneumatic soft robot in a space-limited unstructured environment are the same as those achieved by the embodiment of the method for controlling a pneumatic soft robot in a space-limited unstructured environment.

In some alternative embodiments, the functions/acts noted in the block diagrams may occur out of the order noted in the operational illustrations. For example, two blocks shown in succession may in fact be executed substantially concurrently or the blocks may sometimes be executed in the reverse order, depending upon the functionality/acts involved. Furthermore, the embodiments presented and described in the flowcharts of this application are provided by way of example in order to provide a more thorough understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed, and in which sub-operations described as part of a larger operation are performed independently.

Furthermore, while the present application is described in the context of functional modules, it should be appreciated that, unless otherwise indicated, one or more of the functions and/or features may be integrated in a single physical device and/or software module or one or more of the functions and/or features may be implemented in separate physical devices or software modules. It will also be appreciated that a detailed discussion of the actual implementation of each module is not necessary to an understanding of the present application. Rather, the actual implementation of the various functional modules in the apparatus disclosed herein will be apparent to those skilled in the art from consideration of their attributes, functions and internal relationships. Thus, those of ordinary skill in the art will be able to implement the present application as set forth in the claims without undue experimentation. It is also to be understood that the specific concepts disclosed are merely illustrative and are not intended to be limiting upon the scope of the application, which is to be defined by the appended claims and their full scope of equivalents.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, including several programs for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable programs for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with a program execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the programs from the program execution system, apparatus, or device and execute the programs. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the program execution system, apparatus, or device.

More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.

It is to be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable program execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.

In the foregoing description of the present specification, descriptions of the terms "one embodiment/example", "another embodiment/example", "certain embodiments/examples", and the like, are intended to mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

While embodiments of the present application have been shown and described, it will be understood by those of ordinary skill in the art that: many changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the application, the scope of which is defined by the claims and their equivalents.

While the preferred embodiment of the present invention has been described in detail, the present invention is not limited to the embodiments described above, and various equivalent modifications and substitutions can be made by those skilled in the art without departing from the spirit of the present invention, and these equivalent modifications and substitutions are intended to be included in the scope of the present invention as defined in the appended claims.

Claims

1. A pneumatic soft robot for a spatially constrained unstructured environment, comprising:

the load platform, the front anchoring unit, the telescopic unit, the rear anchoring unit, the gas-electricity integrated pipeline, the gas source and the controller are sequentially arranged; the front anchoring unit comprises a front anchoring unit electromagnetic valve, PAM and a connecting piece; the rear anchoring unit comprises a rear anchoring unit electromagnetic valve, PAM and a connecting piece; the front anchoring unit is connected with the telescopic unit through the electromagnetic valve of the front anchoring unit to realize gas circuit connection; the front anchoring unit is connected with the air source through the electromagnetic valve of the rear anchoring unit and the gas-electricity integrated pipeline; the air source and the controller are used for jointly adjusting the volumes and the shapes of the front anchoring unit, the telescopic unit and the rear anchoring unit through the gas-electricity integrated pipeline.

2. A pneumatic soft robot for use in a spatially constrained unstructured environment according to claim 1, wherein said gas-electric integrated pipeline comprises a fusiform smooth surface foam block; the fusiform smooth foam blocks are arranged on the gas-electricity integrated pipeline at intervals.

3. The pneumatic soft robot for a space-constrained unstructured environment of claim 1, wherein the front and rear anchoring units each further comprise a protective layer, a balloon, and a friction pad; the protective layer wraps the balloon and is used for protecting the balloon from being damaged by the environment; the friction pad is arranged on the protective layer; the balloon is for receiving gas inflation itself to inflate the front and rear anchoring units; the friction pad is used for increasing the surface friction of the front anchoring unit and the rear anchoring unit.

4. The pneumatic soft robot for a spatially-constrained unstructured environment of claim 1, wherein the load platform comprises a thermal imaging module, a gas sensor, a temperature and humidity sensor, a camera, and a microphone module.

5. A pneumatic soft robot for spatially constrained unstructured environments according to claim 1, wherein the diameter of the front and rear anchoring units in the axial direction when unexpanded is smaller than the maximum diameter of the load platform in the axial direction.

6. The pneumatic soft robot for a space-constrained unstructured environment of claim 5, wherein the telescoping unit comprises a bellows, a first air path joint, and a second air path joint; the first air passage joint is used for being connected with the electromagnetic valve of the rear anchoring unit; the second gas circuit joint is used for being connected with the front anchoring unit electromagnetic valve.

7. The pneumatic soft robot for a space-constrained unstructured environment of claim 1, wherein the rear anchor unit solenoid valve and the front anchor unit solenoid valve each comprise a normally closed end, a normally open end, and an air intake end.

8. A pneumatic soft robot for use in a space-constrained unstructured environment according to claim 1, wherein said controller comprises a microprocessor, a micro-screen, a configuration panel, and a solid state relay.

9. A pneumatic soft robot for use in a spatially-constrained unstructured environment according to claim 3, wherein the material of the protective layer is ultra-high molecular weight polyethylene fibers.

10. A method for controlling a pneumatic soft robot for a spatially-constrained unstructured environment, characterized in that it comprises:

the controller is opened, the electromagnetic valve of the anchoring unit is controlled by the air source to expand the anchoring unit and obtain first detection data of the robot;

according to the first detection data, the controller determines a first detection result of the obstacle detection unit; the first detection result is used for a controller to judge whether the first anchoring of the robot is successful or not; the first sensed data includes a relationship between air pressure and time during inflation of the rear anchoring unit;

when the first anchoring of the robot is successful, the controller closes the electromagnetic valve of the rear anchoring unit and the electromagnetic valve of the front anchoring unit, controls the air source to inflate the telescopic unit and controls the telescopic unit to axially extend for a preset distance, so that the first gravity center of the soft robot moves forwards;

the controller opens the electromagnetic valve of the front anchoring unit, and controls the air source to inflate the front anchoring unit to expand the front anchoring unit and obtain second detection data of the robot;

According to the second detection data, the controller obtains a second detection result of the obstacle detection unit; the second detection result is used for a controller to judge whether the robot is successfully anchored for the second time; the second detection data includes a relationship between air pressure and time during inflation of the pre-anchor unit;

when the second anchoring of the robot is successful, the controller closes the electromagnetic valve of the front anchoring unit and controls the air source to output negative pressure, so that the front anchoring unit is restored to the state before expansion.