Patent Application
20230103110
TECHNICAL FIELD
The present disclosure relates to the field of robotics, in particular to an underwater robot based on a variable-size auxiliary drive and a control method thereof.
With the continuous excavation of the depths of the ocean by humans, underwater survey robots are more and more widely used in water quality monitoring, submarine topographic survey, mineral survey, biota detection and other tasks. However, the underwater environment is often complex, which requires that the underwater detection robots must have sufficient cruising ability and anti-interference ability and also reduce the impact on the underwater ecological environment as much as possible. Traditional underwater robots are driven by relying on multiple pairs of screw propellers to provide power for horizontal and vertical directions respectively. When rotors in the vertical direction operate at different depths, they all need to keep operating to provide power or buoyancy for the robots, so more energy for controlling the ups and downs of the robots is consumed.
In view of this, to solve the above technical problems, an objective of the present disclosure is to provide an underwater robot based on a variable-size auxiliary drive and a control method thereof. The energy consumption of the underwater robot is reduced.
An embodiment of the present disclosure adopts the following technical solution:
An underwater robot based on a variable-size auxiliary drive, including:
a variable-size auxiliary drive module, including a first variable-size silo, at least two first variable-size units and at least two first gasbags, where the first gasbags are fixed to an outer side of the first variable-size silo, the first variable-size silo has a first accommodating space with at least two first accommodating subspaces, each of the first variable-size units includes a first micro push rod motor, a first push rod, a first push plate and a first gas guide tube, the first micro push rod motor, the first push rod and the first push plate are accommodated in the corresponding first accommodating subspace, the first push rod is fixed to the first push plate, and one of the first gas guide tubes correspondingly communicates with one of the first accommodating subspaces and one of the first gasbags; and
a main control system, electrically connected with the first micro push rod motors and configured to control the first micro push rod motors to drive the first push rods to drive the first push plates to extend and retract and to adjust the size of the first gasbags by the first gas guide tubes.
Further, the underwater robot based on the variable-size auxiliary drive includes the four first gasbags and the four first variable-size units, where the first accommodating space has the four first accommodating subspaces that are separated by partitions, each of the first accommodating subspaces is configured to accommodate one of the first variable-size units, the four first gasbags are arranged around the outer side of the first variable-size silo, and the first gasbags are fixed by fixing skeletons.
Further, the first variable-size silo includes a main body, a first seal cover and a second seal cover; and the main body includes the first accommodating space, the first seal cover is fixed to one end of the main body and provided with a plurality of first through holes, the second seal cover is fixed to the other end of the main body, each of the first seal cover and the second seal cover is provided with an embedded rabbet, the first through holes are arranged in correspondence to the first gas guide tubes, and the partitions are arranged in the embedded rabbets to separate the first accommodating subspaces independently.
Further, the first push plate is a sealing rubber push plate, and when the first push plate extends by a maximum distance, the corresponding first accommodating subspace and the corresponding first gasbag are sealed.
Further, the underwater robot based on the variable-size auxiliary drive further includes a propulsion module, where the propulsion module includes a steering rotor module including a steering rotor fixing frame, a first steering rotor and a second steering rotor, the steering rotor fixing frame is fixed to the variable-size auxiliary drive module and includes at least one hole for the first gas guide tubes to pass through, and the first steering rotor and the second steering rotor are symmetrically arranged on left and right sides of the steering rotor fixing frame; and the first steering rotor and the second steering rotor are connected with the main control system.
Further, the underwater robot based on the variable-size auxiliary drive further includes a head vision system, where the propulsion module further includes a tail propeller, the head vision system is arranged on a front side of the variable-size auxiliary drive module, the tail propeller is arranged on a rear side of the variable-size auxiliary drive module, and the head vision system includes a camera, a searchlight module and a sensor module that are connected with the main control system; and the main control system controls the brightness of the searchlight module according to the depth of the underwater robot based on the variable-size auxiliary drive in water and adjust the size of the first gasbags according to environmental data acquired by the camera and the sensor module to adjust an attitude.
An embodiment of the present disclosure further provides a control method, used in the underwater robot based on the variable-size auxiliary drive, and including:
acquiring real-time data, where the real-time data includes the environmental data and/or atmospheric pressure data, and the atmospheric pressure data includes an atmospheric pressure of each of the first gasbags; and
controlling, by the main control system, the first micro push rod motors and the propulsion module according to the real-time data.
Further, controlling the first micro push rod motors and the propulsion module according to the real-time data comprises:
when the atmospheric pressure of one of the first gasbags changes abnormally, controlling the first micro push rod motor corresponding to the first gasbag to control the corresponding first push plate to extend by the maximum distance to seal the first gasbag and the first accommodating subspace corresponding to the first gasbag, adjusting the size of the remaining of the first gasbags to make the underwater robot face the water surface, and controlling the propulsion module to operate at a full speed;
or,
when the environmental data includes a target object approaching the underwater robot, controlling the propulsion module to operate at a reduced speed, and controlling the first micro push rod motors to adjust the size of the first gasbags; and when the underwater robot is adjusted to face an open area, controlling the propulsion module to operate at an increased speed.
Further, the environmental data includes target image data; and the control method further includes:
when the depth in the water changes, adjusting the brightness of the searchlight module, wherein the brightness is directly proportional to the depth in the water; and
acquiring original image data after the brightness is adjusted, and coloring and dehazing the original image data, so as to obtain the target image data.
Further, controlling the first micro push rod motors according to the real-time data comprises:
inputting the environmental data into a deep deterministic policy gradient model, so as to determine an optimal attitude of the underwater robot; and
controlling the first micro push rod motors to adjust the underwater robot to the optimal attitude.
The present disclosure has the following technical effects: the variable-size auxiliary drive module and the main control system are arranged; the variable-size auxiliary drive module includes the first variable-size silo, the at least two first variable-size units and the at least two first gasbags; the first gasbags are fixed to the outer side of the first variable-size silo; the first variable-size silo has the first accommodating space with the at least two first accommodating subspaces; each of the first variable-size units includes the first micro push rod motor, the first push rod, the first push plate and the first gas guide tube; the first micro push rod motor, the first push rod and the first push plate are accommodated in the corresponding first accommodating subspace; the first push rod is fixed to the first push plate; one of the first gas guide tubes correspondingly communicates with one of the first accommodating subspaces and one of the first gasbags; and the main control system is electrically connected with the first micro push rod motors and configured to control the first micro push rod motors to drive the first push rods to drive the first push plates to extend and retract and to adjust the size of the first gasbags by the first gas guide tubes. By changing the size of the first gasbags, buoyancy may be provided for the underwater robot, thereby reducing the energy consumption for controlling the ups and downs of the underwater robot.
To make those skilled in the art better understand the solutions of the present application, the technical solutions in the embodiments of the present disclosure are clearly and completely described below with reference to the accompanying drawings in the embodiments of the present disclosure. Apparently, the described embodiments are merely a part rather than all of the embodiments of the present disclosure. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present disclosure without creative efforts shall fall within the protection scope of the present disclosure.
The terms “first”, “second”, “third” and “fourth” in the description, claims and accompanying drawings of the present application are used to distinguish different objects, rather than to describe a specific sequence. Furthermore, the terms “include”, “have” and any variation thereof are intended to cover non-exclusive inclusion. For example, processes, methods, systems, products or devices including a series of steps or units are not limited to listed steps or units, but optionally also include unlisted steps or units, or optionally also include other steps or units inherent to these processes, methods, products or devices.
Reference herein to the “embodiments” means that specific features, structures or characteristics described with reference to the embodiments may be included in at least one embodiment of the present application. The appearances of the phrase at various positions in the description are not necessarily all referring to the same embodiment, nor separate or alternative embodiments that are mutually exclusive of other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.
In the embodiments of the present disclosure, Y represents a front-rear direction (longitudinal direction), Z represents a left-right direction (horizontal direction), and X represents an up-down direction (vertical direction).
As shown in
As shown in
As shown in
As shown in
As shown in
As shown in
As shown in
In the embodiment of the present disclosure, the main control system is electrically connected with the first micro push rod motors 113 and the second micro push rod motors and configured to control the first micro push rod motors 113 to drive the first push rods 114 to drive the first push plates 115 to extend and retract and to adjust the size of the first gasbags 112 by the first gas guide tubes 116. Specifically, when the first micro push rod motors 113 are controlled to drive the first push rods 114 to extend, air in the first accommodating subspaces 1111 may be delivered to the first gasbags 112 by the first gas guide tubes 116, so as to increase the size of the first gasbags 112; and in contrast, when the first micro push rod motors 113 are controlled to drive the first push rods 114 to retract, the air in the first gasbags 112 may be delivered to the first accommodating subspaces 1111 by the first gas guide tubes 116, so as to reduce the size of the first gasbags 112. It should be noted that the second micro push rod motors and the second push plates have a same control principle, that will not be repeated here. It should be noted that the size of the first gasbags 112 may provide the buoyancy for the underwater robot, and by adopting different size adjustment policies for the four first gasbags 112, the buoyancy of the underwater robot in different directions may be controlled, thereby controlling an attitude of the underwater robot; and on this basis, the size of the second gasbags 121 may be further combined to provide stronger buoyancy for the underwater robot, and by a size adjustment policy of adding the four second gasbags 121 in a total of the eight gasbags, the diversity of controlling the buoyancy of the underwater robot in the different directions may be enriched, thereby controlling the attitude of the underwater robot in a more diverse and refined manner.
In the embodiment of the present disclosure, the main control system is further configured to control the brightness of the searchlight module according to the depth of the underwater robot based on the variable-size auxiliary drive in water and to adjust the size of the first gasbags 112 and the second gasbags 121 according to environmental data acquired by the camera 31 and the sensor module so as to adjust the attitude. Optionally, the sensor module includes but is not limited to a depth sensor, an inertial measurement unit (IMU), a temperature sensor, etc., the depth sensor is configured to acquire the depth (the depth in the water) of the underwater robot in the water, and the camera 31 is configured to acquire image data around the underwater robot. It should be noted that the environmental data includes but is not limited to data acquired by the camera 31 and the sensor module.
In the embodiment of the present disclosure, the variable-size auxiliary drive module 1 further includes an atmospheric pressure unit, and the atmospheric pressure unit includes a plurality of first pressure sensors and a plurality of second pressure sensors, where each of the first pressure sensors is arranged on an inner wall of the corresponding first gasbag 112 and configured to acquire a first atmospheric pressure of each of the first gasbag 112, and each of the second pressure sensors is arranged on an inner wall of the corresponding second gasbag 121 and configured to acquire a second atmospheric pressure of each of the second gasbags 121.
As shown in
S100: real-time data is acquired.
In the embodiment of the present disclosure, the real-time data includes the environmental data and/or atmospheric pressure data. It should be noted that the atmospheric pressure data may include an atmospheric pressure, specifically a first atmospheric pressure, of each of the first gasbags, and an atmospheric pressure, specifically a second atmospheric pressure, of each of the second gasbags; and the environmental data includes but is not limited to the data acquired by the camera and the sensor module.
S200: the main control system controls the first micro push rod motors and the propulsion module according to the real-time data.
It may be understood that when the variable-size auxiliary drive module includes the second variable-size auxiliary drive submodule, the main control system may control the first micro push rod motors, the second micro push rod motors and the propulsion module according to the real-time data. It should be noted that in the embodiment of the present application, the first micro push rod motors and the first gasbags have the same control principle as the second micro push rod motors and the second gasbags, so the control principle of the first micro push rod motors and the first gasbags are taken as an example for description, but it does not represent that the control method in the embodiment of the present disclosure does not include the control on the second micro push rod motors and the second gasbags.
Optionally, the step S200 includes the step S210 or S220:
S210: when the atmospheric pressure of one of the first gasbags changes abnormally, the first micro push rod motor corresponding to the first gasbag is controlled to control the corresponding first push plate to extend by the maximum distance to seal the first gasbag and the first accommodating subspace corresponding to the first gasbag, the size of the remaining of the first gasbags is adjusted to make the underwater robot face the water surface, and the propulsion module is controlled to operate at a full speed.
As shown in
Optionally, when the main control system controls the first micro push rod motors according to the real-time data, the environmental data may be input into a deep deterministic policy gradient model, the deep deterministic policy gradient model may be used to make an analysis and output the optimal attitude of the underwater robot, and then the main control system controls the first micro push rod motors (and/or the second micro push rod motors) to adjust the underwater robot to the optimal attitude. For example, when the head vision system or the steering rotor module of the underwater robot faces the water surface, the underwater robot has multiple possible attitudes, and the optimal attitude may make the underwater robot more stable, the distance of escaping from the water surface shorter or the time to escape the water surface shortest, thereby further improving the efficiency of the underwater robot leaving the water surface and enhancing the safety.
For example, when there is an optimal moment M′ in the optimal attitude, for example, by taking the first gasbags located on the upper right side and the lower right side of the first variable-size silo as an example, the buoyancy F1 and the buoyancy F3 are respectively generated and respectively projected to be tangent to the shape (such as a circle) of one end of the main body of the first variable-size silo and the directions of connection lines between points where the two buoyancies are located and the center of the circle, the angles between the directions of the two buoyancies and the connection lines between the points where the two buoyancies are located and the center of the circle are set to be θ and β, the distances from the two buoyancies to the center of the circle are both R, and then there is an actual moment M=(F1*SIN θ−F3*COS β)*R, so the main control system may adjust parameters in the actual moment M by adjusting the size of the first gasbags to adjust the actual moment M, and the actual torque M is adjusted to the optimal torque M′. A relationship between the size of each of the first gasbags and the buoyancy is as follows: ΔF=ρ*g*ΔV, where ΔF is the buoyancy changed within unit time, ρ is the density of a liquid in which it is located, g is a gravitational acceleration in an area, and ΔV is the size of the first gasbag changed within unit time.
It should be noted that the deep deterministic policy gradient model may be determined based on training by reinforcement learning or a deep deterministic policy gradient (DDPG) algorithm. For example, reading may read and acquire the data or continuous information such as an action set of the underwater robot, and such continuous information may be acquired by robotic physical simulation platforms such as ROS and GYM; after the model is parameterized, nondiscrete continuous information such as states and actions is converted into corresponding state values and action values, where different state values correspond to the attitudes of the underwater robot presented by expansion of the first gasbags (or including the second gasbags) at different parts to various degrees without the involution of the first steering rotor and the second steering rotor, and the action values correspond to the distances, increased or reduced by the first micro push rod motors, of the first push rods; a motion device probably selects a motion policy in a continuous motion set, the state values and the action values are input into a judgment device, estimated values are acquired by training a Q network and compared with target estimated values, a loss function is imported to calculate parameters, the acquired parameters will be input into optimizers of an action device and the judgment device respectively, the weight of the network is updated, and a state value of an action policy selected by the action device at a next moment is updated; and it is worth noting that when a decision is made each time, a Q function Q(st, a, r, st+1), in which the Q function is an evaluation function, st is the state value at this moment, a is the action value at this moment, r is a total reward value at this moment, and st+1 is the state value at the next moment, will be stored in an experience pool, and the experience pool will perform partial sample playback, that is, probably selects a Q value at each moment, and the parameters of the action device and the judgment device are updated to determine the optimal action (attitude) according to the total reward value.
For example, the underwater robot may have a first attitude, such as one of the attitudes adopted by accelerated diving, there are different methods to obtain the attitude based on control information extracted by the action device in the intelligent control algorithm (deep deterministic policy gradient algorithm), the essence is to generate a clockwise moment on an XOY surface to make the head face an obliquely downward side of the water surface, a machine body will execute the “optimal attitude” selected probably by the intelligent control algorithm, and the selection of the “optimal attitude” depends on model training parameters of reinforcement learning, that is, when the adjustment of the attitude is completed, the first micro push rod motors change the buoyancy by the distance selected by the intelligent control algorithm, so as to obtain the optimal torque M′ required for steering; and a second attitude is an attitude policy adopted by the machine body facing a vertical narrow environment, a third one is an attitude policy adopted when facing a horizontal narrow environment, and methods, the same as above, to achieve the two attitudes depend on the “optimal attitude” selected by the intelligent attitude control algorithm, where a specific algorithm flow is as follows: the head vision system acquires image data of a terrain ahead, the head vision system or the main control system performs rectangular segmentation of a light color gamut of the image data, a generated maximum rectangular anchor frame is namely a space that may accommodate the machine body to pass, and the main control system decides a best passing attitude, executes the “optimal attitude”, gradually reduces an attitude difference, and adjusts the attitude to a decision-making attitude; and by this narrow environment, it can be understood that the attitudes of the underwater robot are not limited to the above attitudes.
S220: when the environmental data includes a target object approaching the underwater robot, the propulsion module is controlled to operate at a reduced speed, and the first micro push rod motors are controlled to adjust the size of the first gasbags; and when the underwater robot is adjusted to face an open area, the propulsion module is controlled to operate at an increased speed.
As shown in
Optionally, the control method in the embodiment of the present disclosure further includes the steps S310-S320, where the steps S310-S320 and the steps S100 and S200 do not limit an execution sequence, specifically:
S310: when the depth in the water changes, the brightness of the searchlight module is adjusted.
Specifically, when the depth in the water changes, the main control system adjusts the brightness of the searchlight module, where the brightness is directly proportional to the depth in the water, and the larger the depth in the water is, the higher the brightness is, otherwise, the lower the brightness is. In the embodiment of the present disclosure, by adjusting the brightness of the searchlight module, the illumination lost by Rayleigh scattering of water molecules and impurities in the water may be supplemented, thereby reducing the influence of underwater light scattering faced by deep underwater image data or video data, and making the data acquired by the camera clearer.
S320: original image data is acquired after the brightness is adjusted, and the original image data is colored and dehazed, so as to obtain target image data.
Specifically, after the brightness is adjusted, the camera acquires the original image data by shooting, and the main control system colors the original image data by adversarial nerves, repairs the saturation of the original image data, and then further processes the original image data by a dehazing algorithm to improve the image quality of the target image data. It should be noted that the target image data, as a part of the environmental data, is used for the main control system to make a judgment, including but not limited to the identification and judgment of the target object, on the condition according to the target image data, so as to improve the identification accuracy of the target object.
In conclusion, the underwater robot based on the variable-size auxiliary drive according to the embodiment of the present disclosure is small in size and light in weight, which reduces the energy consumption of the underwater robot. Underwater whole lifting may be controlled by the variable-size auxiliary drive module, and a pitch angle and a sideslip angle are subjected to attitude adjustment by the variable-size auxiliary drive module. Compared with a traditional underwater survey robot, the underwater robot based on the variable-size auxiliary drive is more energy-saving, has flexible attitudes and may be subjected to more complex attitude control; the control of the main control system may reduce the dependence of the attitude control or correction on manual work, and the searchlight module of the head vision system may overcome the underwater light scattering often encountered in underwater survey tasks and may effectively extract environmental features and transmit information to the main control system; and in an emergency, for example, when the gasbags are ruptured or there is the target object, the main control system effectively helps itself to get out of danger.
An embodiment of the present disclosure further provides an electronic device, including a processor and a memory, where the memory stores at least one instruction, at least one program, and a code set or instruction set therein, that are loaded and executed by the processor to implement the control method of the foregoing embodiment. The electronic device in the embodiment of the present disclosure includes, but is not limited to, any intelligent terminal such as a mobile phone, a tablet computer, a computer, and a vehicle-mounted computer.
The contents in the embodiment of the above method are all applicable to the embodiment of this device, and the embodiment of this device has the same specific functions and achieved beneficial effects as the embodiment of the above method.
An embodiment of the present disclosure further provides a computer-readable storage medium, storing at least one instruction, at least one program, and a code set or instruction set therein, that are loaded and executed by the processor to implement the control method of the foregoing embodiment.
Embodiments of the present disclosure further provide a computer program product or computer program, including computer instructions, that are stored in the computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and executes the computer instructions, thereby making the computer device execute the control method of the foregoing embodiment.
The terms “first”, “second”, “third”, and “fourth” (if they exist) in the description and accompanying drawings of the present application are used to distinguish similar objects, rather than to describe a specific sequence or sequence. It is to be understood that the data used in this way may be interchanged under appropriate circumstances, so that the embodiment of the application described herein may be implemented in sequences other than those illustrated or described herein. Furthermore, the terms “include”, “have” and any variation thereof are intended to cover non-exclusive inclusion. For example, processes, methods, systems, products or devices including a series of steps or units are not necessarily limited to clearly listed steps or units, but may include unclearly unlisted steps or units, or other steps or units inherent to these processes, methods, products or devices.
It should be understood that, in this application, “at least one (item)” refers to one or more, and “a plurality of” refers to two or more. “And/or” is used to describe an association relationship between associated objects, and it indicates that there may be three kinds of relationships. For example, “A and/or B” may indicate that: only A, only B, and both A and B exist, where A and B may be singular or plural. The character “/” generally indicates that the contextual associated objects are an “or” relationship. “At least one item (piece) below” or similar expressions thereof refer to any combination of these items, including any combination of singular item (piece) or plural items (piece). For example, at least one item (piece) of a, b and c, may represent: a, b, c, “a and b”, “a and c”, “b and c”, or “a, b and c”, where a, b, c may be one or more.
In the several embodiments provided in this application, it should be understood that the disclosed device and method may be implemented in other ways. For example, the embodiment of the device described above is merely illustrative. For example, the division of units is merely a logical function division. In actual implementation, there may be other division ways. For example, multiple units or components may be combined or integrated to another system, or some features may be ignored or not implemented. According to another point, shown or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection of devices or units through some interfaces, and may be in electrical, mechanical or other forms. Units described as separate components may or may not be physically separated, and components shown as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the objective of the solution in this embodiment. In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, each unit may exist physically alone, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or a software functional unit.
The integrated unit, if implemented in the form of the software functional unit and sold or used as a stand-alone product, may be stored in one computer-readable storage medium. Based on such understanding, the technical solution of the present application essentially, a part that contributes to the prior art, or all or part of the technical solution may be embodied in the form of a software product, and the computer software product is stored in one storage medium and includes multiple instructions for making one computer device (which may be a personal computer, a server, or a network device) execute all or part of the steps of the method in each embodiment of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM for short), a random access memory (RAM for short), a magnetic disk or a compact disc that may store programs.
The above embodiments are merely used to describe the technical solution of the present disclosure, but not to limit it; although the present disclosure has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: they still may modify the technical solution described in the above embodiments, or equivalently replace part or all of technical features in the technical solution; and these modifications or replacements do not make the essence of the corresponding technical solution depart from the spirit and scope of the technical solution of each embodiment of the present disclosure.
| Number | Date | Country | Kind |
|---|---|---|---|
| 2021111191002 | Sep 2021 | CN | national |
