CN116276979A - Pose control method and device of robot, storage medium and electronic equipment - Google Patents
Pose control method and device of robot, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN116276979A CN116276979A CN202310144027.7A CN202310144027A CN116276979A CN 116276979 A CN116276979 A CN 116276979A CN 202310144027 A CN202310144027 A CN 202310144027A CN 116276979 A CN116276979 A CN 116276979A
- Authority
- CN
- China
- Prior art keywords
- robot
- position deviation
- motion data
- current
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1628—Programme controls characterised by the control loop
- B25J9/163—Programme controls characterised by the control loop learning, adaptive, model based, rule based expert control
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1602—Programme controls characterised by the control system, structure, architecture
- B25J9/161—Hardware, e.g. neural networks, fuzzy logic, interfaces, processor
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1612—Programme controls characterised by the hand, wrist, grip control
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Automation & Control Theory (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Physics & Mathematics (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Orthopedic Medicine & Surgery (AREA)
- Manipulator (AREA)
Abstract
The invention discloses a pose control method and device of a robot, a storage medium and electronic equipment, wherein the method comprises the following steps: acquiring current motion data of a robot; obtaining a current position deviation value of the robot according to the current motion data by utilizing a pre-established search database model, wherein the search database model comprises a corresponding relation between historical motion data of the robot and the historical position deviation value; and adjusting the pose of the robot according to the current position deviation value. According to the method, the position and the posture of the robot are adjusted by utilizing historical motion data fed back by a power mechanism of the robot, the motion of the robot is directly analyzed and learned from a perception angle, and the motion trend is known in advance through self-learning under the condition that the robot is subjected to what force in the operation process, so that the motion trend is pre-judged in advance and then fine deviation correcting actions are carried out, and the purpose of intelligent, flexible and rapid control of the self-motion position and posture of the robot is achieved.
Description
Technical Field
The invention relates to the technical field of pose control, in particular to a pose control method and device of a robot, a storage medium and electronic equipment.
Background
In the related art, a real-time position of a robot is obtained by adopting a mode of inputting a sensor (laser, vision, GNSS, inertial sensor, etc.) based on a pose correction mode of the robot, and then pose correction is performed after calculating a route deviation according to a route theoretically designed, so that an actual running track of the robot is close to the route theoretically designed, and a target function (such as inspection and operation of a designated area) is realized. But when the robot body is in deviation (such as turning and spinning action), the correction is slower, and the adaptability to slopes or uneven scenes is poor.
Disclosure of Invention
The present invention aims to solve at least one of the technical problems in the related art to some extent. Therefore, an object of the present invention is to provide a method for controlling the pose of a robot, which corrects the deviation in the motion process in a self-learning manner through motion sensing, so that the robot achieves the purposes of intelligent, flexible and rapid control of the motion pose of the robot.
A second object of the present invention is to provide a pose control device.
A third object of the present invention is to propose a computer readable storage medium.
A fourth object of the present invention is to propose an electronic device.
To achieve the above object, an embodiment of a first aspect of the present invention provides a method for controlling a pose of a robot, the method comprising: acquiring current motion data of the robot; obtaining a current position deviation value of the robot according to the current motion data by utilizing a pre-established search database model, wherein the search database model comprises a corresponding relation between historical motion data of the robot and the historical position deviation value; and adjusting the pose of the robot according to the current position deviation value.
According to the pose control method of the robot, the pose of the robot is adjusted by utilizing historical motion data fed back by the power mechanism of the robot, the motion of the robot is directly analyzed and learned from a perception angle, and the motion trend is generated under the condition that the robot receives what force in the running process is known in advance through self-learning, so that fine deviation rectifying actions are performed after the advance pre-judging, and the purpose of intelligent, flexible and rapid control of the motion pose of the robot is achieved.
In addition, the pose control method of the robot according to the embodiment of the invention may further have the following additional technical features:
according to one embodiment of the present invention, the process of establishing the search database model includes: acquiring structural body data, wherein the structural body data comprises a preset number of historical motion data, and acquisition time and historical position deviation values corresponding to the historical motion data; performing de-duplication processing on the structural body data, and establishing the search database model based on the rest structural body data; or, grouping the structural body data, and establishing the search data model based on the grouped structural body data.
According to one embodiment of the present invention, the performing a deduplication process on the structure data includes: performing de-duplication processing on the structural body data with repeated historical motion data and corresponding historical position deviation values; the grouping processing of the structure data includes: and carrying out grouping processing on the structural body data according to the value of the historical position deviation value.
According to one embodiment of the present invention, the obtaining the current position deviation value of the robot according to the current motion data by using a pre-established search database model includes: when a position deviation value is obtained according to the current motion data by utilizing a pre-established search database model, the position deviation value is used as the current position deviation value; when a plurality of position deviation values are obtained according to the current motion data by utilizing a pre-established search database model, the current position deviation value is obtained according to the plurality of position deviation values and the current pose data of the robot.
According to one embodiment of the present invention, the obtaining the current position deviation value according to the plurality of position deviation values and the current pose data of the robot includes: obtaining a current route of the robot according to the current pose data; determining the head direction of the robot according to the current route and the theoretical route; and determining the current position deviation value according to a plurality of position deviation values and the headstock orientation by utilizing the relation between the position deviation value and the headstock orientation in a pre-established search database model.
According to one embodiment of the present invention, the obtaining the current position deviation value of the robot according to the current motion data by using a pre-established search database model includes: when the historical motion data which are the same as the current motion data do not exist in the search database model, determining the historical motion data closest to the current motion data from the historical motion data smaller than the current motion data and the historical motion data larger than the current motion data based on the search database model, and recording the historical motion data as first historical motion data and second historical motion data; and obtaining the current position deviation value according to a first historical position deviation value corresponding to the first historical motion data and a second historical position deviation value corresponding to the second historical motion data.
According to one embodiment of the present invention, the adjusting the pose of the robot according to the current position deviation value includes: establishing a virtual target coordinate point according to the current position deviation value; according to the virtual target coordinate point and the theoretical positioning point, the expected linear speed and the expected angular speed are obtained; obtaining the expected rotating speed of the robot motor according to the expected linear speed and the expected angular speed by utilizing the motion model of the robot; and controlling the motor to operate according to the expected rotating speed.
According to one embodiment of the invention, the motion data comprises at least one of pressure data, acceleration data.
To achieve the above object, an embodiment of a second aspect of the present invention provides a pose control device for a robot, the device comprising: the acquisition module is used for acquiring current motion data of the robot; the searching module is used for obtaining the current position deviation value of the robot according to the current motion data by utilizing a pre-established searching database model, wherein the searching database model comprises the corresponding relation between the historical motion data of the robot and the historical position deviation value; and the control module is used for adjusting the pose of the robot according to the current position deviation value.
To achieve the above object, an embodiment of a third aspect of the present invention proposes a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a pose control method of a robot according to any of claims 1 to 7.
To achieve the above object, an embodiment of a fourth aspect of the present invention provides an electronic device, including a memory and a processor, where the memory stores a computer program, and when the computer program is executed by the processor, the method for controlling a pose of a robot according to the embodiment of the first aspect of the present invention is implemented.
Additional aspects and advantages of the invention 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 invention.
Drawings
Fig. 1 is a flowchart of a pose control method of a robot according to an embodiment of the present invention;
FIG. 2 is a flow chart of modeling a search database according to one embodiment of the invention;
FIG. 3 is a flow chart of adjusting the pose of a robot according to one embodiment of the present invention;
FIG. 4 is a schematic diagram of a deviation correcting device when a robot is in linear operation according to an embodiment of the present invention;
FIG. 5 is a schematic illustration of a robot correcting errors during spin-in-place in one embodiment of the present invention;
fig. 6 is a schematic diagram of a pose control device according to an embodiment of the present invention.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative and intended to explain the present invention and should not be construed as limiting the invention.
The following describes a method and apparatus for controlling the pose of a robot, a storage medium, and an electronic device according to embodiments of the present invention in detail with reference to descriptions 1 to 6 and specific embodiments.
Fig. 1 is a flowchart of a pose control method of a robot according to an embodiment of the present invention. As shown in fig. 1, the pose control method of the robot may include:
s1, acquiring current motion data of a robot.
In an embodiment of the invention, the current motion data is data fed back by a power mechanism of the robot. The power mechanism of the robot may include, among other things, a drive motor, a transmission mechanism, and sensors carried thereon (e.g., force sensors, encoders, IMUs (Inertial Measurement Unit, inertial measurement units), RTKs (Real Time Kinematic, real-time kinematic) positioning sensors, etc.).
S2, obtaining a current position deviation value of the robot according to the current motion data by utilizing a pre-established search database model, wherein the search database model comprises a corresponding relation between historical motion data of the robot and the historical position deviation value.
In an embodiment of the present invention, the pre-established search database model includes a correspondence of historical motion data and historical position deviation values of the robot. Wherein, the historical motion data is also the data fed back by the power mechanism of the robot.
It should be noted that, the type of the historical motion data is consistent with the type of the current motion data of the acquired robot, or the type of the historical motion data includes the type of the current motion data of the acquired robot. So that the current position deviation value is obtained by searching according to the current motion data.
The method can be implemented by searching the current position deviation value of the current motion data by utilizing a pre-established search database model consistent with the current motion data type, so that the pose of the robot is adjusted according to the current position deviation value.
And S3, adjusting the pose of the robot according to the current position deviation value.
The method can be implemented, and the driving mechanism of the robot is adjusted according to the current position deviation value so as to adjust the pose of the robot and enable the actual running track of the robot to be consistent with the theoretical running track.
According to the pose control method of the robot, the pose of the robot is adjusted by utilizing historical motion data fed back by the power mechanism of the robot, the motion of the robot is directly analyzed and learned from a perception angle, and the motion trend is generated under the condition that the robot receives what force in the running process is known in advance through self-learning, so that fine deviation correcting actions are performed after the pre-judging is performed in advance, and the purpose of intelligent, flexible and rapid control of the motion pose of the robot is achieved.
In one embodiment of the present invention, the motion data may include at least one of pressure data, acceleration data.
In one embodiment of the present invention, as shown in FIG. 2, the process of creating a search database model may include:
s41, acquiring structural body data, wherein the structural body data comprises a preset number of historical motion data, and acquisition time and historical position deviation values corresponding to the historical motion data.
Specifically, historical motion data fed back by power mechanisms of a preset number of robots are obtained. The historical motion data comprises one or more types of historical motion data, such as pressure data, acceleration data and pressure data and acceleration data can be acquired simultaneously. Wherein, each historical motion data that obtains includes corresponding acquisition time and historical position deviation value.
It should be noted that, the type of the historical motion data is required to be consistent with the type of the current motion data of the acquired robot, or the type of the historical motion data is required to include the type of the current motion data of the acquired robot. So as to obtain the current position deviation value of the robot according to the current motion data of the robot.
When the historical motion data is acquired, the robot can store the historical motion data fed back by the power mechanism locally, and when the historical motion data is stored in a preset quantity, the locally stored historical motion data is packaged in batches and uploaded to the local area network server, or the historical motion data fed back by the power mechanism is uploaded to the local area network server in real time. Or not uploaded to the local area network server, and can be directly obtained from the robot when the historical motion data is obtained. The embodiment of the invention does not limit the mode of acquiring the historical motion data.
S42, performing de-duplication processing on the structural body data, and establishing a search database model based on the rest structural body data; or, the structure data is subjected to grouping processing, and a search data model is built based on the grouped structure data.
In order to improve the searching efficiency of the searching database model, the obtained structural body data can be subjected to de-duplication processing, and the searching database model is built based on the rest structural body data so as to search the current position deviation value of the current motion data by using the searching database model. The acquired structural body data may also be subjected to grouping processing, and a search data model may be built based on the grouped structural body data to search for a current position deviation value of the current motion data using the search database model.
In one embodiment of the present invention, performing deduplication processing on the structure data may include: performing de-duplication processing on the structural body data with repeated historical motion data and corresponding historical position deviation values; grouping the structure data may include: and carrying out grouping processing on the structural body data according to the value of the historical position deviation value.
In the implementation, the structural body data which are the same as the historical motion data and the corresponding historical position deviation values are removed, and the structural body data which are different from the historical motion data and the corresponding historical position deviation values are reserved, so that the subsequent searching speed for searching the current position deviation value according to the current motion data can be improved.
The structure data may be grouped according to the value of the historical position deviation value. The approximate data values are managed in a layered mode, and different deviations are classified into different layers, so that the searching speed of searching the current position deviation value according to the current motion data is improved.
As a specific embodiment, when the current motion data is pressure data, the historical motion pressure data is inserted into a dictionary in an additional mode and the like, and a pressure search database model is built. To distinguish the deviations, a correlation value search is performed before the historical motion pressure data is inserted, and the fuzzy processing is equivalent to the approximation without repeated insertion. The structure data can be grouped according to the value of the historical position deviation value.
As another specific embodiment, when the current motion data is acceleration data, the historical motion acceleration data is inserted into a dictionary in a mode of adding and the like, and an acceleration search database model is built. In order to distinguish the deviation, before the historical motion acceleration data is inserted, the correlation value search is carried out, and the approximate value equivalent is not repeatedly inserted in the blurring process. The structure data can be grouped according to the value of the historical position deviation value.
In one embodiment of the present invention, obtaining the current position deviation value of the robot according to the current motion data by using a pre-established search database model may include:
when a position deviation value is obtained according to the current motion data by utilizing a pre-established search database model, the position deviation value is used as the current position deviation value;
when a plurality of position deviation values are obtained according to the current motion data by utilizing a pre-established search database model, the current position deviation values are obtained according to the plurality of position deviation values and the current pose data of the robot.
In some embodiments, one or more bias values may be searched for when searching for their corresponding current position bias values based on current motion data in a pre-established search database model.
If the motion mechanism of the robot only feeds back one current pressure data or feeds back two consistent current pressure data, the position deviation value is used as the current position deviation value when a pre-established pressure search database model is utilized to obtain the position deviation value according to the current pressure data.
When two inconsistent current pressure data fed back by a motion mechanism of the robot are obtained, the current position deviation value can be obtained according to the two position deviation values and the current pose data of the robot, such as the head direction, by utilizing a pre-established pressure search database model respectively according to the two current pressure data.
As a specific embodiment, obtaining the current position deviation value according to the plurality of position deviation values and the current pose data of the robot includes: obtaining a current route of the robot according to the current pose data; determining the head direction of the robot according to the current route and the theoretical route; and determining the current position deviation value according to the plurality of position deviation values and the headstock orientation by utilizing the relation between the position deviation value and the headstock orientation in the pre-established search database model.
When a plurality of position deviation values are obtained based on two inconsistent current pressure data, a plurality of position deviation values are generally obtained, because the angle difference of the head orientation exists, and the current position deviation value of the robot can be determined according to the relation between the position deviation value and the head orientation in a pre-established search database model. Specifically, according to current pose data of the robot, such as pressure data, acceleration data, driving motor current and the like, a current route of the robot is obtained, the current route of the robot is compared with a theoretical route, whether the current vehicle body of the robot is on the left side or the right side of the theoretical route is determined, and then the direction of the vehicle head of the robot for correcting deviation is determined. And obtaining the current position deviation value according to the plurality of position deviation values and the determined head orientation by utilizing the relation between the position deviation value and the head orientation in the pre-established search database model.
As another specific embodiment, when the current position deviation value is obtained according to the plurality of position deviation values, the position deviation value in the preset range of the gaussian distribution center may be further selected from the plurality of position deviation values, and an average value of the position deviation values in the preset range of the gaussian distribution center may be calculated to obtain the current position deviation value.
It should be noted that, the process of solving the current deviation value may not be performed on the robot body.
In one embodiment of the present invention, obtaining the current position deviation value of the robot according to the current motion data by using a pre-established search database model may include:
when the historical motion data which are the same as the current motion data do not exist in the search database model, determining the historical motion data closest to the current motion data from the historical motion data smaller than the current motion data and the historical motion data larger than the current motion data based on the search database model, and recording the historical motion data as first historical motion data and second historical motion data;
and obtaining a current position deviation value according to the first historical position deviation value corresponding to the first historical motion data and the second historical position deviation value corresponding to the second historical motion data.
In some embodiments, when the pre-established search database model searches for its corresponding current position deviation value according to the current motion data, the pre-established search database model may not have the corresponding current motion data, resulting in no corresponding position deviation value being searched. The historical motion data closest to the current motion data can be determined from the historical motion data smaller than the current motion data based on the search database model and marked as first historical motion data, and the historical motion data closest to the current motion data can be determined from the historical motion data larger than the current motion data based on the search database model and marked as second historical motion data. The method comprises the steps of obtaining a first historical position deviation value corresponding to first historical motion data and a second historical position deviation value corresponding to second historical motion data, and obtaining a current position deviation value through calculation by using a least square method.
In the embodiment of the invention, the current motion data which do not correspond to the current motion data and the current position deviation value obtained by calculation of the current motion data can be inserted into the search database model so as to further expand the search database model.
In one embodiment of the present invention, as shown in fig. 3, adjusting the pose of the robot according to the current position deviation value includes:
s31, establishing a virtual target coordinate point according to the current position deviation value;
s32, obtaining expected linear velocity and expected angular velocity according to the virtual target coordinate point and the theoretical positioning point;
s33, obtaining the expected rotating speed of a robot motor according to the expected linear speed and the expected angular speed by utilizing a motion model of the robot;
s34, controlling the motor to operate according to the expected rotating speed.
In some embodiments, to reduce the deviation between the current position and the theoretical position of the robot, a virtual target coordinate point is established according to the current position deviation value and the theoretical target route, so that the actual running route of the robot approaches the theoretical target route. And determining the deviation between the virtual target coordinate point and the theoretical locating point according to the virtual target coordinate point and the theoretical locating point (theoretical locating point of the next step of the robot) determined by the theoretical target route, so as to determine the expected linear speed and the expected angular speed of the driving motor of the robot according to the deviation between the virtual target coordinate point and the theoretical locating point. And then, obtaining the expected rotating speed of the motor of the robot by utilizing a motion model of the robot according to the expected linear speed and the expected angular speed, and controlling the driving motor to operate according to the expected rotating speed so as to correct the robot in the motion process.
It should be noted that, the position deviation value in the search database model is the difference value between the theoretical positioning point coordinate and the current position coordinate, and the deviation correction trend is formed by continuously establishing a virtual target coordinate point, and according to the theoretical positioning point coordinate determined by the theoretical target route, and the target linear speed, the angular speed, the deviation and the head direction of the driving mechanism, the real-time expected linear speed and the expected angular speed of the driving mechanism are obtained, and then the expected speed of each motor motion is calculated by the motion model, so that the deviation correction can be completed within a period of time.
According to one embodiment of the invention, when the robot is provided with two travelling wheels, the expected rotating speed of the motor of the robot is obtained according to the expected linear speed and the expected angular speed by using the motion model of the robot, and the expected rotating speed can be obtained according to the following equation.
F Upper part ＝0.5*G*(1-K)，F Lower part(s) ＝0.5*G*(1+K)。
Wherein F is Upper part And F Lower part(s) The force applied by two travelling wheels of the robot are respectively represented, G is gravity, K is a calculation coefficient, and the calculation can be carried out by a static pressure value.
Total energy equation for robot: e1 =w1+e2+e3. Wherein, E1 is electric quantity loss, W1 is kinetic energy, E2 is internal loss (electronic components generate heat, etc.), E3 is external loss (mainly expressed as friction force energy consumption), and the total energy equation is the theoretical energy conservation equation. The external force includes gravity and friction, and the friction is a motive force.
It should be noted that, E1 is a simultaneous equation for measuring and calculating the battery voltage, current, and capacity consumption in real time, W1 is a simultaneous equation for measuring and calculating the speed in real time by an accelerometer, E2 is a simultaneous equation for measuring and calculating the current in real time, E3 is a simultaneous equation for friction force, and when the motion jolts, the friction force changes, and two component forces along the motion direction and the vertical motion direction are generated, and the component force is the cause of the motion deviation.
Total motion equation of robot: ΣfxΔt= Σmvx; Σfy Δt= Σmvy; Σfz Δt= Σmvz.
The general mechanics equation of the robot: Σfx= Σmax; Σfy= Σmay; Σfz= Σmaz.
Where M is the mass of each part, vx is the velocity component in the x direction, vy is the velocity component in the y direction, vz is the velocity component in the z direction, ax is the acceleration component in the x direction, ay is the acceleration component in the y direction, and Az is the acceleration component in the z direction.
Specifically, different motion equations, mechanical equations and energy equations can be set up according to different motion processes, such as straight lines and turning, so that when the robot senses that the robot is subjected to a large offset force, the offset of the robot body relative to a theoretical route can be eliminated through the speed regulation adjustment of a large proportion, and the gesture is adjusted to continue running.
In one embodiment of the invention, when the database searching model is not established, the robot linearly runs, the current position deviation value is obtained according to the linear process in the speed and force feedback self-learning motion equation and the conversion coefficient, and the next-round motion deviation correction is updated according to the motion deviation of the previous round, so that the optimization is realized. Referring to fig. 4, the actual deviation rectifying control procedure is exemplified as follows: when lateral deviation occurs, when the position deviation value of delta y (y direction) > y_thred (y direction preset threshold value) is judged, deviation correction is performed, namely, curve motion control is realized by controlling a motion element (motor) of the robot to perform acceleration and deceleration, so that delta y < y_thred is enabled, and then the operation is continued.
In one embodiment of the invention, when the database searching model is not established, the robot spins in place (similar to a two-wheel differential scene), the spin process in a self-learning motion equation is fed back according to the speed and the force, the conversion coefficient is converted, the current position deviation value is obtained, and the next-wheel motion deviation correction is updated according to the motion deviation of the previous wheel, so that the optimization is realized. Referring to fig. 5, the actual deviation rectifying control procedure is exemplified as follows: when the rotation center deviates, judging that Deltax (position deviation value in x direction) > x_thred (preset threshold value in x direction) or Deltay (position deviation value in y direction) > y_thred (preset threshold value in y direction) performs motion correction, namely, performs acceleration and deceleration by controlling a motion element (a motor) to realize curve motion control (a common method does not perform motion control in spin and curve processes), the method provided by the embodiment of the invention performs correction in spin and curve processes, the correction instantaneity is higher, the possibility of direct derailment after spin or curve motion is reduced, and the Deltax < x_thred and Deltay < y_thred then continues to operate. Where "derailment" refers to the maximum threshold value of the projected distance of the current robot position from the theoretical route.
In one embodiment of the invention, when the database searching model is not established, and the robot runs in a circular arc curve, the motion deviation is obtained by combining a curve motion process in a self-learning motion equation according to speed and force feedback and a theoretical rotation radius conversion coefficient, and the next round of motion deviation is updated according to the motion deviation of the previous round, so that the optimization is realized. The actual deviation correction control process is similar to the robot in-situ spinning scene.
It should be noted that, when a part of the sensors is to be removed after a period of self-learning, the self-learning function (autonomous identification data source) is turned off, and the motion correction optimization is performed by the completed motion database.
It should be noted that, according to the position deviation value obtained by searching the database model without building, the true motion deviation can be obtained by multiplying the position deviation value by the probability coefficient. The probability coefficient is a conversion coefficient, and the probability coefficient is a probability distribution coefficient obtained in the case of multi-solution. For example, there are a plurality of bias solutions on the approximated external load (related by pressure and acceleration feedback), and the plurality of bias solutions have a certain distribution rule, such as gaussian distribution, that is, there is a bias center point, the number ratio of the point closer to the center point (the center point distance is a threshold set in advance) to all the solutions is taken as a probability distribution coefficient, and if the probability distribution coefficient is high, the center bias value is considered to be reliable, that is, the center bias value is taken as the final true bias.
It should be noted that the above process of solving the position deviation value may not be performed on the robot body.
It should be noted that, after the search database model is established, the search database model may be directly used to search, so as to determine the current position deviation value.
It should be noted that, by optimizing the model in a self-learning manner, a part of the sensors (such as RTKs, cameras, and other sensors for positioning navigation) of the front layout can be removed later from the practical point of view, so that the maintenance cost of the device is reduced. Before the sensor is removed, judgment needs to be carried out, after the sensor is removed, no positioning data is needed, and correction is carried out by searching a database model and directly corresponding to proper correction action (the wheel speed of a designated differential wheel).
According to the pose control method of the robot, a motion-deviation relation is obtained according to a search database model, namely, a plurality of deviation solutions are obtained when the external force is approximately exerted (the direction of the head of the robot is considered, and the like), data analysis is carried out, solutions near the center are left in accordance with Gaussian distribution, and a final deviation value is obtained through mean value calculation.
According to the pose control method of the robot, curve fitting is carried out on deviation according to original data such as force, acceleration and current, curve fitting is carried out on deviation correcting action according to the deviation (calculation of a curve equation is carried out by using a polynomial after point drawing is counted), and the relation of what deviation correcting action the robot carries out when what motion occurs is found. And through motion changes (force, current and the like), the deviation correcting action required by the user is predicted in advance according to the deviation rule in the established search database model, and the deviation correcting is performed under the condition of small deviation, so that the optimization process is performed.
According to the pose control method provided by the embodiment of the invention, in a slope or uneven scene, the motion correction in the slope or uneven scene can be perfected, the linear correction response speed is improved, the correction actions in the turning and spinning processes are optimized, and the motion is more close to the theoretical track.
According to the pose control method of the robot, provided by the embodiment of the invention, under the condition that the force is the reason for changing the motion state of an object, which motion trend (predicted result) is generated under the condition that the force (pressure sensor) is predicted in advance in the running process of the robot is learned, so that the motion track of the robot is better attached to the theoretical route, and the running efficiency is improved.
The invention provides a pose control device of a robot.
Fig. 6 is a schematic view of a pose control device of a robot according to an embodiment of the present invention. As shown in fig. 6, the pose control device 100 of the robot may include: an acquisition module 10, a search module 20 and a control module 30.
The acquisition module 10 is used for acquiring current motion data of the robot; the searching module 20 is configured to obtain a current position deviation value of the robot according to the current motion data by using a pre-established searching database model, where the searching database model includes a correspondence between historical motion data of the robot and the historical position deviation value; the control module 30 is used for adjusting the pose of the robot according to the current position deviation value.
It should be noted that, other specific implementations of the pose control device for a robot provided by the embodiment of the present invention may refer to other specific implementations of the pose control method for a robot of the foregoing embodiment of the present invention.
According to the pose control device of the robot, the pose of the robot is adjusted by utilizing historical motion data fed back by the power mechanism of the robot, the motion mode of the robot is directly analyzed and learned from a perception angle, and the motion trend is generated under the condition that the robot receives what force in the running process is known in advance through self-learning, so that fine deviation rectifying actions are performed after the advance pre-judging, and the purpose of intelligent, flexible and rapid control of the motion pose of the robot is achieved.
The invention provides a computer readable storage medium.
In this embodiment, a computer program is stored on a computer readable storage medium, and when the computer program is executed by a processor, the pose control method of the robot as described above is implemented.
The invention provides an electronic device.
In this embodiment, the electronic device may include a memory, a processor, and a computer program stored in the memory, which when executed by the processor, implements the pose control method of the robot as described above.
The computer readable storage medium and the electronic equipment of the embodiment of the invention utilize the pose control method of the robot to enable the robot to achieve the purposes of intelligentization, flexibility and rapid control of the motion pose of the robot.
It should be noted that the logic and/or steps represented in the flowcharts or otherwise described herein, for example, may be considered as a ordered listing of executable instructions for implementing logical functions, and may be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. 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 instruction 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 invention may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction 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 description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means 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 invention. 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.
In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings are merely for convenience in describing the present invention and simplifying the description, and do not indicate or imply that the device or element being referred to must have a specific orientation, be configured and operated in a specific orientation, and therefore should not be construed as limiting the present invention.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present invention, the meaning of "plurality" means at least two, for example, two, three, etc., unless specifically defined otherwise.
In the present invention, unless explicitly specified and limited otherwise, the terms "mounted," "connected," "secured," and the like are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; either directly or indirectly, through intermediaries, or both, may be in communication with each other or in interaction with each other, unless expressly defined otherwise. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art according to the specific circumstances.
In the present invention, unless expressly stated or limited otherwise, a first feature "up" or "down" a second feature may be the first and second features in direct contact, or the first and second features in indirect contact via an intervening medium. Moreover, a first feature being "above," "over" and "on" a second feature may be a first feature being directly above or obliquely above the second feature, or simply indicating that the first feature is level higher than the second feature. The first feature being "under", "below" and "beneath" the second feature may be the first feature being directly under or obliquely below the second feature, or simply indicating that the first feature is less level than the second feature.
While embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the invention, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the invention.
Claims (11)
1. A method for controlling the pose of a robot, the method comprising:
acquiring current motion data of the robot;
obtaining a current position deviation value of the robot according to the current motion data by utilizing a pre-established search database model, wherein the search database model comprises a corresponding relation between historical motion data of the robot and the historical position deviation value;
and adjusting the pose of the robot according to the current position deviation value.
2. The method according to claim 1, wherein the process of creating the search database model includes:
acquiring structural body data, wherein the structural body data comprises a preset number of historical motion data, and acquisition time and historical position deviation values corresponding to the historical motion data;
performing de-duplication processing on the structural body data, and establishing the search database model based on the rest structural body data; or, grouping the structural body data, and establishing the search data model based on the grouped structural body data.
3. The method according to claim 2, wherein the performing the de-duplication process on the structure data includes: performing de-duplication processing on the structural body data with repeated historical motion data and corresponding historical position deviation values;
the grouping processing of the structure data includes: and carrying out grouping processing on the structural body data according to the value of the historical position deviation value.
4. The method for controlling the pose of the robot according to claim 1, wherein the obtaining the current position deviation value of the robot according to the current motion data by using a pre-established search database model comprises:
when a position deviation value is obtained according to the current motion data by utilizing a pre-established search database model, the position deviation value is used as the current position deviation value;
when a plurality of position deviation values are obtained according to the current motion data by utilizing a pre-established search database model, the current position deviation value is obtained according to the plurality of position deviation values and the current pose data of the robot.
5. The method according to claim 4, wherein the obtaining the current position deviation value from the plurality of position deviation values and the current position posture data of the robot includes:
obtaining a current route of the robot according to the current pose data;
determining the head direction of the robot according to the current route and the theoretical route;
and determining the current position deviation value according to a plurality of position deviation values and the headstock orientation by utilizing the relation between the position deviation value and the headstock orientation in a pre-established search database model.
6. The method according to claim 4, wherein the obtaining the current position deviation value of the robot from the current motion data using a pre-established search database model includes:
when the historical motion data which are the same as the current motion data do not exist in the search database model, determining the historical motion data closest to the current motion data from the historical motion data smaller than the current motion data and the historical motion data larger than the current motion data based on the search database model, and recording the historical motion data as first historical motion data and second historical motion data;
and obtaining the current position deviation value according to a first historical position deviation value corresponding to the first historical motion data and a second historical position deviation value corresponding to the second historical motion data.
7. The method according to claim 1, wherein the adjusting the pose of the robot according to the current position deviation value includes:
establishing a virtual target coordinate point according to the current position deviation value;
according to the virtual target coordinate point and the theoretical positioning point, the expected linear speed and the expected angular speed are obtained;
obtaining the expected rotating speed of the robot motor according to the expected linear speed and the expected angular speed by utilizing the motion model of the robot;
and controlling the motor to operate according to the expected rotating speed.
8. The pose control method according to claim 1, wherein the motion data comprises at least one of pressure data and acceleration data.
9. A pose control device of a robot, the device comprising:
the acquisition module is used for acquiring current motion data of the robot;
the searching module is used for obtaining the current position deviation value of the robot according to the current motion data by utilizing a pre-established searching database model, wherein the searching database model comprises the corresponding relation between the historical motion data of the robot and the historical position deviation value;
and the control module is used for adjusting the pose of the robot according to the current position deviation value.
10. A computer-readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the method of controlling the pose of a robot according to any of claims 1-8.
11. An electronic device comprising a memory, a processor, the memory having stored thereon a computer program, characterized in that the computer program, when executed by the processor, implements the method of pose control of a robot according to any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310144027.7A CN116276979A (en) | 2023-02-14 | 2023-02-14 | Pose control method and device of robot, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310144027.7A CN116276979A (en) | 2023-02-14 | 2023-02-14 | Pose control method and device of robot, storage medium and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116276979A true CN116276979A (en) | 2023-06-23 |
Family
ID=86802379
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310144027.7A Pending CN116276979A (en) | 2023-02-14 | 2023-02-14 | Pose control method and device of robot, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116276979A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116872220A (en) * | 2023-09-07 | 2023-10-13 | 中建三局集团华南有限公司 | Control system of watering robot for building site |
| CN117618125A (en) * | 2024-01-25 | 2024-03-01 | 科弛医疗科技(北京)有限公司 | Image trolley |
-
2023
- 2023-02-14 CN CN202310144027.7A patent/CN116276979A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116872220A (en) * | 2023-09-07 | 2023-10-13 | 中建三局集团华南有限公司 | Control system of watering robot for building site |
| CN116872220B (en) * | 2023-09-07 | 2023-11-07 | 中建三局集团华南有限公司 | Control system of watering robot for building site |
| CN117618125A (en) * | 2024-01-25 | 2024-03-01 | 科弛医疗科技(北京)有限公司 | Image trolley |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116276979A (en) | Pose control method and device of robot, storage medium and electronic equipment | |
| US11209276B2 (en) | Devices and methods for a sensor platform of a vehicle | |
| CN106080598B (en) | Real-time goal pace control | |
| CN108725585B (en) | Trajectory tracking control method and device for autonomous parking of vehicle | |
| Amidi et al. | Integrated mobile robot control | |
| CN110262509B (en) | Automatic vehicle driving method and device | |
| Kelly et al. | Rough terrain autonomous mobility—Part 1: A theoretical analysis of requirements | |
| US20060097683A1 (en) | Mobile robot | |
| US20170344025A1 (en) | Self-position estimating apparatus and self-position estimating method | |
| JP2669074B2 (en) | Vehicle speed sensitive steering control device for autonomous vehicle | |
| JP6617482B2 (en) | Autonomous vehicle system | |
| US11912360B2 (en) | Vehicle control method, vehicle control system, and vehicle | |
| JP2019113926A (en) | Model predictive control device | |
| JP2007283910A (en) | Obstacle avoidance control device and obstacle avoidance control program | |
| US20220165010A1 (en) | Systems and methods for monocular based object detection | |
| CN110001630A (en) | A kind of distributed-driving electric automobile automatic parking wheelpath differential correction system and method | |
| JP4978622B2 (en) | Inverted moving body and method for judging abnormality thereof | |
| Iagnemma et al. | Experimental study of high-speed rough-terrain mobile robot models for reactive behaviors | |
| JP5859093B1 (en) | Trajectory tracking control device | |
| Sahoo et al. | Design and development of a heading angle controller for an unmanned ground vehicle | |
| CN115525054B (en) | Method and system for controlling tracking of edge path of unmanned sweeper in large industrial park | |
| WO2021177255A1 (en) | Driving assistance device and driving assistance method | |
| KR102156164B1 (en) | Method for generating trajectory and avoiding collision using velocity control uncertainty of 2-wheel mobile robot and 2-wheel mobile robot using the same | |
| JP2021026302A (en) | Information processing apparatus, information processing method, and program | |
| De Luca et al. | Experiments in visual feedback control of a wheeled mobile robot |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |