CN107315349B - Ball hitting motion control method of robot - Google Patents
Ball hitting motion control method of robot Download PDFInfo
- Publication number
- CN107315349B CN107315349B CN201710640042.5A CN201710640042A CN107315349B CN 107315349 B CN107315349 B CN 107315349B CN 201710640042 A CN201710640042 A CN 201710640042A CN 107315349 B CN107315349 B CN 107315349B
- Authority
- CN
- China
- Prior art keywords
- robot
- hitting
- batting
- motion
- point
- 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.)
- Active
Links
- 230000033001 locomotion Effects 0.000 title claims abstract description 60
- 238000000034 method Methods 0.000 title claims abstract description 27
- 230000001133 acceleration Effects 0.000 claims description 13
- 238000005457 optimization Methods 0.000 claims description 3
- 238000000354 decomposition reaction Methods 0.000 claims description 2
- 238000004458 analytical method Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 230000004044 response Effects 0.000 description 5
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005206 flow analysis Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000033764 rhythmic process Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Other Investigation Or Analysis Of Materials By Electrical Means (AREA)
- Manipulator (AREA)
Abstract
The embodiment of the invention discloses a ball hitting motion control method of a robot. The method comprises the following steps: estimating a hitting point position of the table tennis according to an air travel track of the table tennis, wherein the hitting point position is a hitting point position within a preset cubic space range; judging a hitting point area where the hitting point is located; selecting a motion control model corresponding to the ball hitting point area, and calculating motion parameters in the ball hitting motion of the robot; and controlling the robot to carry out batting according to the motion parameters. The method for controlling the ball hitting motion of the robot provided by the embodiment of the invention improves the adaptability and robustness of the control of the ball hitting motion of the table tennis robot.
Description
Technical Field
The embodiment of the invention relates to the technical field of robots, in particular to a ball hitting motion control method of a robot.
Background
The table tennis robot is an automatic device capable of hitting the table tennis rebounded from the half-ball table to the half-ball table of the opposite side, can realize the multi-return table tennis competition, and can be widely applied to the training of professional athletes and the interaction of amateurs. Because the table tennis is a sport with high speed, multiple changes and wide operation range, the realization of hitting the ball accurately in a large range puts higher requirements on the rapidity, the adaptability and the safety of the table tennis robot, and the invention provides a method for controlling the hitting motion of the table tennis robot on the basis.
At present, many domestic and foreign research institutions realize the goal of hitting balls by the table tennis robot, but the hitting ball motion control of the table tennis robot generally has the defects of being provided with a hitting surface and having a small hitting range. The prior patent 201110136109.4 discloses a method for obtaining the hitting posture and hitting speed of the bat of the table tennis robot, which predicts the hitting point by configuring the hitting height, the table tennis needs to bounce to a fixed height to hit the ball, which cannot cope with low-level ball, and the patent does not discuss the motion control of the robot hitting the ball; most of table tennis robots are provided with a hitting surface in the front-back direction, and the theoretical collision point of a table tennis ball and a racket at the tail end of the robot is in the plane.
Disclosure of Invention
In view of the above technical problems, embodiments of the present invention provide a method for controlling a ball hitting motion of a robot, so as to improve adaptability and robustness of a table tennis robot.
The embodiment of the invention provides a ball hitting motion control method of a robot, which comprises the following steps:
estimating a hitting point position of the table tennis according to an air travel track of the table tennis, wherein the hitting point position is a hitting point position within a preset cubic space range;
judging a hitting point area where the hitting point is located;
selecting a motion control model corresponding to the ball hitting point area, and calculating motion parameters in the ball hitting motion of the robot;
and controlling the robot to carry out batting according to the motion parameters.
According to the ball hitting motion control method of the robot provided by the embodiment of the invention, the ball hitting point position of the table tennis is estimated according to the air travel track of the table tennis, the ball hitting point area where the ball hitting point position is located is judged, the motion control model corresponding to the ball hitting point area is selected, the motion parameters in the ball hitting motion of the robot are calculated, the robot is controlled to perform the ball hitting motion according to the motion parameters, and the adaptability and the robustness of the table tennis robot can be improved.
Drawings
Other features, objects and advantages of the invention will become more apparent upon reading of the detailed description of non-limiting embodiments made with reference to the following drawings:
fig. 1 is a flowchart of a ball hitting motion control method of a robot according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a batting state machine provided by the embodiment of the invention;
FIG. 3 is a schematic illustration of the division of 4 striking strategies provided by an embodiment of the present invention;
FIG. 4 is a schematic view of a near table shot provided by an embodiment of the present invention;
fig. 5 is a schematic view of a drive shot provided by an embodiment of the present invention;
FIG. 6 is a schematic view of a left backhand shot provided by an embodiment of the present invention;
fig. 7 is a schematic view of a right backhand shot provided by an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
The method is suitable for the ping-pong robot with a guide rail in the short side direction of the ping-pong table and a tandem mechanical arm with at least 5 degrees of freedom. The guide rails are similar to left and right steps when people hit balls, so that the problem that the working space of the mechanical arm cannot cover the table tennis table in a large range is solved; the mechanical arm simulates the arm of a human to complete various swinging actions. The x axis of the coordinate system of the ping-pong robot is defined to coincide with the linear motion of the guide rail, the y axis is the projection of the middle line of the long edge of the ping-pong table on the horizontal plane where the guide rail is located, the intersection point of the x axis and the y axis determines the origin O of the coordinate system, and the z axis is vertically upward, as shown in fig. 3. The origin of a racket coordinate system at the tail end of the table tennis robot is defined to be positioned at the center of the racket, the z-axis is perpendicular to the racket surface and is a normal direction of the racket, the y-axis points to the racket handle, and the x-axis is determined by a right-hand rule. The racket has a front side and a back side, wherein the front side is the side pointing to the normal line, and the back side is the side departing from the normal line, as shown in fig. 4.
The method for controlling the ball hitting motion of the table tennis robot refers to a process of how the robot obtains the motion parameters of a racket at the tail end and drives each joint to complete the ball hitting action, and mainly comprises a ball hitting response analysis module, a ball hitting strategy selection module and a motion trajectory planning module, as shown in fig. 1, the flow analysis of the whole ball hitting motion system is as follows:
the racket motion parameter in the hitting response analysis module refers to a hitting point (x) required for realizing target hitting controlh,yh,zh) Speed of racket (v)xh,vyh,vzh) Normal to the racket (x)zph,yzph,zzph) And the remaining movement time thThese parameters are obtained by the prediction system and are outside the scope of the present invention. The coordinate values of the hitting point, the speed of the racket and the normal line of the racket are described in the coordinate system of the table tennis robot, and the residual motion time thRefers to the time from the current position of the bat to the expected impact with the table tennis ball.
The hitting state machine in the hitting response analysis module refers to three possible states of the current table tennis robot: hold wait, go to hit ball, and return wait, as shown in fig. 2. The holding waiting means that the table tennis robot is at a waiting point of a certain configuration and is kept still to wait for the racket motion parameters of the prediction system; the process that the table tennis robot drives the bat to go to the hitting point from a waiting point or a certain posture of returning to the waiting point after the last hitting is carried out, and during the process, a new hitting request of the acquisition and prediction system is closed, namely new hitting point information cannot be responded; the return-to-wait refers to the process of returning to the waiting point after the bat at the tail end of the table tennis robot reaches the hitting point and finishes the collision with the table tennis, during which the hitting request is turned on again, and new hitting point information is responded. After obtaining the racket motion parameters, putting a batting application to a batting state machine, and if the robot is in a state of going to the batting state machine at the moment, the batting request is rejected, and rhythm prompt information is output; if the robot is on hold or returns to wait for 2 state machines, then the stroke request is allowed to be processed. Generally speaking, in a slow-beat ball hitting task, the table tennis robot will have enough time to go to the ball hitting point from the static state of the waiting point and then return to the waiting point to keep static each time, while in a fast-beat ball hitting task, the table tennis robot may still receive a new set of ball hitting requests in the process of going to the waiting point from the ball hitting point, at the moment, the table tennis robot will try to give up going to the waiting point and directly turn to the moving target of the ball hitting point to realize ball hitting, when the beat is fast to a certain degree, the table tennis robot still goes to the process of ball hitting and receives a new set of ball hitting requests, the table tennis robot will ignore the new ball hitting requests and continue to complete the movement plan, and the mode of adopting the ball hitting state machine can effectively adapt to the fast-beat ball hitting task and simultaneously ensure a high effective ball hitting success rate, and the robustness of the system is improved.
The working space analysis in the hitting response analysis module refers to the preliminary judgment of the hitting point position (x) of the racketh,yh,zh) Whether or not within the working space of the robot, i.e. xmin≤xh≤xmax，ymin≤yh≤ymaxAnd zmin≤zh≤zmaxIf not, giving up the motion parameters of the racket and outputting the out-of-limit prompt information, wherein xmin，xmax，ymin，ymax，zminAnd zmaxRespectively represents the minimum value and the maximum value allowed by the hitting point in the coordinate system x, y and z of the table tennis robot.
The table tennis robot batting strategy selection module has the main functions that different batting strategies are selected to complete inverse kinematics solution according to the batting interval to which the position of the batting point of the bat belongs, and the angle q of each joint at the batting moment is obtainedihAnd angular velocity
As shown in fig. 3, the hitting strategy selection module includes 4 strategies of hitting a table tennis ball near, hitting a table tennis ball far, hitting a backhand and hitting a forehand according to the positions of the hitting points around and around the coordinate system of the table tennis robot. With redundant optimization of specific targets, the inverse kinematics of the 4 hitting strategies differed slightly.
The distance judgment in the batting strategy selection module refers to the configuration of a distance value ycfgWhen hitting the ball|yh|＞ycfgWhen the current is determined to be yh|≤ycfgAnd (4) judging left and right. The front and back judgment means to analyze the hitting point yhWhen y ishWhen the number is more than 0, the hitting point is far away from the front of the table tennis robot, the track of the table tennis is generally a short table tennis, a table tennis hitting strategy is adopted, as shown in fig. 4, the z value of the y-axis unit vector of the table tennis coordinate system under the world coordinate system is configured to be more than 0, namely the z value isyphThe risk that the table tennis robot collides with the table tennis table can be effectively reduced if the table tennis robot is more than 0; when y ishWhen the number is less than 0, the ball hitting point is far behind the robot, the table tennis is generally a high-distance ball at the moment, a long-distance table ball hitting strategy is adopted, as shown in fig. 5, the z value of the y-axis unit vector of the table tennis coordinate system under the table tennis robot coordinate system is configured to be less than 0, namely the z value is smaller than 0yphLess than 0, so that the risk of ball hitting failure caused by collision of the table tennis ball with the table tennis robot before the table tennis ball collides with the racket can be effectively reduced. The left and right judgment means to analyze the hitting point xhWhen x is a symbol ofhWhen the number is less than 0, the hitting point is at the left side position of the robot, a backhand hitting strategy is adopted, and a racket normal vector z is configured as shown in figure 6phY value under the coordinate system of the table tennis robot is less than 0, namely yzphIf less than 0, the back side of the racket is used for hitting the ball; when x ishWhen the ball hitting point is at the right side position of the robot, a forehand ball hitting strategy is adopted, and a racket normal vector z is configured as shown in figure 7phY value under the coordinate system of the table tennis robot is larger than 0, namely yzphAnd if the height is more than 0, the ball is hit by using the front surface of the racket.
The near table batting strategy and the far table batting strategy both adopt inverse kinematics 1 to solve joint angles, which is inverse kinematics based on kinematic decomposition, and in order to fully exert the working space of the mechanical arm in the front and rear directions, the displacement q of a guide rail at the batting point moment is configured1h＝xhSpeed of
Namely, the displacement of the ball hitting point in the left-right direction is realized only by the guide rail, and the mechanical arm realizes the remaining end constraint (y)h,zh,xzph,yzph,zzph,vxh,vyh,vzh) And completing the angle q of each joint of the mechanical arm by utilizing a redundancy optimization inverse kinematics algorithmihAnd angular velocity
The subscript i indicates the number of each joint. The forehand batting strategy and the backhand batting strategy both adopt inverse kinematics 2 to solve joint angles, the inverse kinematics is optimized based on operability, the operability of the mechanical arm in the batting direction is maximum, and the angle q of each joint of the table tennis robot at the batting point is obtainedihAnd angular velocity
Subscript i represents the serial number of each joint, the limiting safety problem caused by the fact that a hitting point is too close to a mechanical arm base in inverse kinematics 1 can be effectively solved by adopting the mode, the distance between the hitting point and the mechanical arm base is increased by utilizing a guide rail, the mechanical arm can achieve more flexible hitting due to larger operability, and the operability in the hitting speed direction is βpIs calculated as
Where p is a unit column vector of the direction of the hitting speed, θ is each joint angle of the robot arm, and J (θ) represents a jacobian matrix of the robot arm. And if the inverse kinematics 1 or the inverse kinematics 2 fails to solve, outputting a prompt message of solving errors and terminating the batting request.
The motion trail planning module of the table tennis robot has the main function of planning the joint motion of the table tennis robot from a current point to a hitting point and then to a waiting point. The robot waiting point state in the motion trail planning module refers to the configuration of a group of joint angles qieWhen the table tennis robot is in the state of keeping waiting, the table tennis robot keeps still at the set of joint angles, namely the waiting point is the target stop point after the current hitting, so the joint angular velocity corresponding to the waiting point
Angular acceleration
The subscript i indicates the number of each joint. The current point state of the robot in the motion trail planning module refers to the angle q of each current joint of the ping-pong roboticAngular velocity
And angular acceleration
The subscript i indicates the number of each joint, and in particular, q when the table tennis robot is in a hold wait state machineic＝qie，
Joint space trajectory planning in the motion trajectory planning module refers to planning according to the current t of the table tennis robotcAngle q of each joint at any momenticAngular velocity
And angular acceleration
Hitting point thAngle q of each joint at any momentihAngular velocity
Returning to the robot waiting point t after hitting the balleAngle q of each joint at any momentieAngular velocity
And angular acceleration
The motion trail of each joint of the ping-pong robot for completing the batting request is obtained by adopting a 7 th-order polynomial interpolation algorithm, namely the angle q of each joint corresponding to each control periodijAngular velocity
And angular acceleration
Wherein t iseThe index i represents the number of each joint, and j represents each control cycle.
Depending on the constraints of the angles, angular velocities and angular accelerations of the current point, the hitting point and the waiting point, the polynomial coefficient (b) of the 7 th-order polynomial interpolation of each joint can be solved by the following system of linear equationsi7,bi6,bi5,bi4,bi3,bi2,bi1,bi0) Wherein the subscript i represents the number of each joint.
In the above formula, qic、
And
respectively representing the angle, angular velocity and angular acceleration of the ith joint at the current time point, qih、
Respectively representing the angle, the angular velocity and the angular acceleration of the ith joint at the ball striking point, qie、
And
respectively representing the angle, angular velocity and angular acceleration of the ith joint during the waiting period, amnA predetermined constant representing the motion control model, bi7To bi0The interpolation coefficients of the polynomial are represented.
The joint limiting and collision analysis in the motion trail planning module refers to the judgment of whether the joint angle, the angular velocity and the angular acceleration of each joint planned in each period exceed the limits and whether a racket collides with a table, namely qimin≤qij≤qimax，
And zpj≥zpminWhether or not q is satisfied simultaneouslyimin，qimax，
And
respectively the minimum and maximum values allowed for the angle, angular velocity and angular acceleration of each joint, zpjZ value track, z value track of batting sports bat in coordinate system of table tennis robot acquired by positive kinematics calculationpminIs the minimum height value allowed by the racket. If the safety error is not met, outputting safety error prompt information and terminating the batting request; if the requirement is met, the table tennis robot executes a batting request and drives each joint to complete batting tasks.
Compared with the prior art, the invention has the advantages that:
1. the response of the return waiting state in the batting state machine to a new batting request realizes the online modification of the movement planning track, and can effectively improve the adaptability of the table tennis robot to batting with fast beat;
2. 4 strategies of near table hitting, far table hitting, forehand hitting and backhand hitting are selected according to different areas where hitting points belong, and compared with the traditional method for configuring the hitting surface, the control method for the hitting motion effectively increases the flexibility and the hitting range of the table tennis robot;
3. the batting motion control method adopts 7-degree polynomial interpolation to complete joint track planning of the current point, the batting point and the waiting point, and reduces the maximum value of the angular acceleration value of the joint on the premise of ensuring the continuity and stability of batting motion.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (4)
1. A ball hitting motion control method of a robot, comprising:
estimating a hitting point position of the table tennis according to an air travel track of the table tennis, wherein the hitting point position is a hitting point position within a preset cubic space range;
judging a hitting point area where the hitting point is located; the ball striking point region includes: a near platform area, a far platform area, a right forehand area and a left backhand area;
selecting a motion control model corresponding to the ball hitting point area, and calculating motion parameters in the ball hitting motion of the robot; the motion control model comprises 4 strategies of near table batting, far table batting, backhand batting and forehand batting; solving the near table batting strategy and the far table batting strategy by inverse kinematics based on motion decomposition; the forehand batting strategy and the backhand batting strategy adopt inverse kinematics solution based on operability optimization; the motion parameters include: angles, angular velocities, angular accelerations of the respective joints;
obtaining the motion trail of each joint of the ping-pong robot for completing the batting request by adopting a 7 th-order polynomial interpolation algorithm according to the motion parameters, and judging whether the joint angle, the angular velocity and the angular acceleration planned by each joint in each period exceed the limit and whether the racket collides with the table; and controlling the robot to perform batting according to the judgment result.
2. The method of claim 1, further comprising:
according to the constraint conditions of the angles, the angular velocities and the angular accelerations of the current point, the hitting point and the waiting point, the polynomial coefficient of 7-degree polynomial interpolation of each joint is solved through the following linear equation system:
wherein the subscript i represents the number of each joint; q. q.sic、
And
respectively representing the angle, the angular velocity and the angular acceleration of the ith joint at the current time point; q. q.sih、
Respectively representing the angle, the angular speed and the angular acceleration of the ith joint at a ball hitting point; q. q.sie、
And
respectively representing the angle, the angular speed and the angular acceleration of the ith joint in a waiting time period; a ismnA preset constant representing the motion control model; bi7To bi0The interpolation coefficients of the polynomial are represented.
3. The method of claim 1, wherein the state of the robot comprises: hold wait state, go to hit ball state, and return to wait state.
4. A method according to claim 3, characterized in that if the robot receives a new ball hitting request in a return waiting state, the robot jumps immediately from the return waiting state to a go to ball hitting state.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710640042.5A CN107315349B (en) | 2017-07-31 | 2017-07-31 | Ball hitting motion control method of robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710640042.5A CN107315349B (en) | 2017-07-31 | 2017-07-31 | Ball hitting motion control method of robot |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107315349A CN107315349A (en) | 2017-11-03 |
| CN107315349B true CN107315349B (en) | 2020-08-21 |
Family
ID=60174877
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710640042.5A Active CN107315349B (en) | 2017-07-31 | 2017-07-31 | Ball hitting motion control method of robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107315349B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111283700B (en) * | 2020-05-11 | 2020-08-14 | 上海庞勃特科技有限公司 | Table tennis service robot, table tennis service method and computer-readable storage medium |
| CN113650010B (en) * | 2021-08-04 | 2022-08-16 | 乒乓动量机器人(昆山)有限公司 | Motion control method and system of table tennis robot and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008036383A (en) * | 2006-08-09 | 2008-02-21 | Quantaview Inc | Arm type robot for playing match of table tennis |
| CN102200760A (en) * | 2011-05-25 | 2011-09-28 | 中国科学院自动化研究所 | Method for acquiring ball-hitting gesture and ball-hitting speed of ping-pong robot racket |
| CN102509025A (en) * | 2011-11-25 | 2012-06-20 | 苏州大学 | Method for quick solution of six-degree-of-freedom humanoid dexterous arm inverse kinematics |
| CN103019024A (en) * | 2012-11-29 | 2013-04-03 | 浙江大学 | System for realtime and accurate observation and analysis of table tennis rotating and system operating method |
| CN103389738A (en) * | 2013-06-25 | 2013-11-13 | 北京理工大学 | Method and device for table tennis robot to predict table tennis ball trajectory |
| CN104678766A (en) * | 2015-01-29 | 2015-06-03 | 苏州大学 | Method for solving optimal batting configuration for flight ball body operation of humanoid manipulator |
| CN106390409A (en) * | 2016-11-17 | 2017-02-15 | 中科新松有限公司 | Ball-hitting method and device for table tennis robot |
| CN106426200A (en) * | 2016-10-14 | 2017-02-22 | 深圳四博智联科技有限公司 | Table tennis robot and control method thereof |
| CN106669125A (en) * | 2016-12-31 | 2017-05-17 | 安徽工业大学 | Method and system for predicting return way of table tennis training partner robot on basis of electromyographic signals |
-
2017
- 2017-07-31 CN CN201710640042.5A patent/CN107315349B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008036383A (en) * | 2006-08-09 | 2008-02-21 | Quantaview Inc | Arm type robot for playing match of table tennis |
| CN102200760A (en) * | 2011-05-25 | 2011-09-28 | 中国科学院自动化研究所 | Method for acquiring ball-hitting gesture and ball-hitting speed of ping-pong robot racket |
| CN102509025A (en) * | 2011-11-25 | 2012-06-20 | 苏州大学 | Method for quick solution of six-degree-of-freedom humanoid dexterous arm inverse kinematics |
| CN103019024A (en) * | 2012-11-29 | 2013-04-03 | 浙江大学 | System for realtime and accurate observation and analysis of table tennis rotating and system operating method |
| CN103389738A (en) * | 2013-06-25 | 2013-11-13 | 北京理工大学 | Method and device for table tennis robot to predict table tennis ball trajectory |
| CN104678766A (en) * | 2015-01-29 | 2015-06-03 | 苏州大学 | Method for solving optimal batting configuration for flight ball body operation of humanoid manipulator |
| CN106426200A (en) * | 2016-10-14 | 2017-02-22 | 深圳四博智联科技有限公司 | Table tennis robot and control method thereof |
| CN106390409A (en) * | 2016-11-17 | 2017-02-15 | 中科新松有限公司 | Ball-hitting method and device for table tennis robot |
| CN106669125A (en) * | 2016-12-31 | 2017-05-17 | 安徽工业大学 | Method and system for predicting return way of table tennis training partner robot on basis of electromyographic signals |
Non-Patent Citations (1)
| Title |
|---|
| 仿人7自由度机械臂位置层面轨迹规划研究;崔泽等;《机械制造》;20120930;第50卷(第577期);第29-30页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107315349A (en) | 2017-11-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Mülling et al. | A biomimetic approach to robot table tennis | |
| Matsushima et al. | A learning approach to robotic table tennis | |
| US10124230B2 (en) | Swing analysis method using a sweet spot trajectory | |
| Salehian et al. | A dynamical system approach for softly catching a flying object: Theory and experiment | |
| US10456653B2 (en) | Swing quality measurement system | |
| CN109794937B (en) | Football robot cooperation method based on reinforcement learning | |
| CN110458281B (en) | Method and system for predicting deep reinforcement learning rotation speed of table tennis robot | |
| CN107315349B (en) | Ball hitting motion control method of robot | |
| CN110496377B (en) | Virtual table tennis player ball hitting training method based on reinforcement learning | |
| Fligge et al. | Minimum jerk for human catching movements in 3D | |
| CN111283700B (en) | Table tennis service robot, table tennis service method and computer-readable storage medium | |
| Yang et al. | Ball motion control in the table tennis robot system using time-series deep reinforcement learning | |
| CN106390409A (en) | Ball-hitting method and device for table tennis robot | |
| Ji et al. | Model-based trajectory prediction and hitting velocity control for a new table tennis robot | |
| CN107498556A (en) | A kind of ping-pong robot bus control system and control method | |
| CN111369629A (en) | Ball return trajectory prediction method based on binocular visual perception of swinging, shooting and hitting actions | |
| Yang et al. | Control system design for a 5-DOF table tennis robot | |
| Terasawa et al. | Achievement of dynamic tennis swing motion by offline motion planning and online trajectory modification based on optimization with a humanoid robot | |
| Yang et al. | Varsm: Versatile autonomous racquet sports machine | |
| Murakami et al. | Motion planning for catching a light-weight ball with high-speed visual feedback | |
| CN107899225B (en) | Table tennis serving score identification method based on motion trail | |
| Gardner et al. | Batting flying objects to the target in 2d | |
| US8460120B1 (en) | Method for auto-aligning golf club head | |
| CN207342200U (en) | A kind of intelligent soccer robot | |
| CN110711368B (en) | Ball hitting method and device of table tennis 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210907 Address after: 257 jinzang Road, Pudong New Area, Shanghai, 201206 Patentee after: Shanghai Chuangyi Technology Co.,Ltd. Address before: Room 101, West, building 11, 351 jinzang Road, Pudong New Area, Shanghai, 201206 Patentee before: SIASUN Co.,Ltd. |
|
| TR01 | Transfer of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Control method for hitting ball motion of robots Granted publication date: 20200821 Pledgee: Industrial Bank Co.,Ltd. Shanghai Branch Pledgor: Shanghai Chuangyi Technology Co.,Ltd. Registration number: Y2024310000016 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right |