CN107877512A - A kind of machine mouse and experimental mouse kinematic similarity evaluation method - Google Patents
A kind of machine mouse and experimental mouse kinematic similarity evaluation method Download PDFInfo
- Publication number
- CN107877512A CN107877512A CN201710903569.2A CN201710903569A CN107877512A CN 107877512 A CN107877512 A CN 107877512A CN 201710903569 A CN201710903569 A CN 201710903569A CN 107877512 A CN107877512 A CN 107877512A
- Authority
- CN
- China
- Prior art keywords
- mouse
- kinematic
- similarity
- experimental
- bio
- 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
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
- B25J9/1638—Programme controls characterised by the control loop compensation for arm bending/inertia, pay load weight/inertia
-
- 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
- B25J9/1605—Simulation of manipulator lay-out, design, modelling of manipulator
-
- 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
- B25J9/1607—Calculation of inertia, jacobian matrixes and inverses
-
- 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
- B25J9/1633—Programme controls characterised by the control loop compliant, force, torque control, e.g. combined with position 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
- B25J9/1656—Programme controls characterised by programming, planning systems for manipulators
- B25J9/1661—Programme controls characterised by programming, planning systems for manipulators characterised by task planning, object-oriented languages
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention proposes a kind of machine mouse and experimental mouse kinematic similarity evaluation method.The machine mouse motion design of kinematic parameter based on experimental mouse, it is made up of the kinematic parameter acquisition of experimental mouse, kinematic Simulation, the experiment of machine mouse and the part of similarity evaluation four.Kinematic similarity is evaluated to characterize the parameter of experimental mouse motion feature (each duration, angle of pitch αp, pitching height hp, cross track distance dyWith driftage radius ryDeng) it is foundation, choose two typical behaviours and carry out the imitation experiment of machine mouse, it is proposed that method for evaluating similarity is used as using dynamic time warping (DTW).According to kinematic similarity evaluation result, control strategy is continued to optimize.The present invention evaluates the kinematic similitude degree that machine mouse imitates experimental mouse from quantitative angle, can realize and the high similarity of experimental mouse motion is imitated.
Description
Technical field
The invention belongs to bio-robot technical field, and in particular to a kind of machine mouse bionic movement evaluation method.Pass through
This method can be designed effectively moves with machine mouse of the experimental mouse motion with high similarity, realizes machine mouse high quality
Bionic movement.
Background technology
Because experimental mouse body make-up and drug response and the mankind approach, therefore it is often used as the animal model of human diseases
(animal with human diseases analog representation), it is to study human diseases rule and newtype drug test and the crucial money screened
Source.But conventional animal model behavior assessment experiment condition is uncontrollable, length experimental period, the behavior interactive testing between animal
The problem of repeatability is low, whard to control be present, and there is also error etc. for control group in experimentation.Therefore, by means of can
Programming and the bio-robot freely configured replace animal, by reproducing corresponding animal behavior, are interacted with animal,
Through the new method for becoming international research animal behavior.Machine mouse is interacted applied to experimental mouse behavior, improves behavior interaction
The controllability of middle experiment condition, it is easy to implement automation experiment, further research experiment mouse behaviouristics.In order to preferably realize
Machine mouse interacts with experimental mouse, and machine mouse needs to make the action and motion for having height similarity with experimental mouse.Establish fortune
The similarity degree that dynamic method for evaluating similarity can imitate machine mouse experimental mouse motion quantifies, and motion mould is improved for machine mouse
It is imitative that important references standard is provided.
(" the Design and control of a biomimetic robotic rat in non-patent literature 1
Interaction with laboratory rats ", SHI, Qing etc., IEEE/ASME Transactions on
Mechatronics, volume 20, volume 4, the 1832-1842 pages, in August, 2015), author, which refer to one kind, can imitate reality
The bionic machine mouse of mouse action is tested, and experiment is interacted with experimental mouse.The bionic machine mouse can imitate all kinds of of experimental mouse
Action (such as：Run, uprightly, climb pressure, turn round, manage hair, sniff etc. action), so as to one or a group experimental mouse
Interact experiment.
The bionic machine mouse is only capable of imitating all kinds of actions of experimental mouse from visual effect, does not go out from quantitative angle
Hair goes to evaluate this similitude；Method due to lacking a this kinematic similarity of quantitative assessment, therefore be difficult the mould in motion
Machine mouse is improved on imitative, limits the application of the Optimal Control Strategy of machine mouse.
The content of the invention
The purpose of the present invention is：In order to realize high similarity motion mimics of the machine mouse to experimental mouse, it is proposed that Yi Zhongping
The method of both valencys kinematic similarity.
Technical scheme is as follows.
A kind of evaluation method of kinematic similarity, comprises the following steps,
S1：Pass through the exercise data of the first object of seizure；
S2：Inverse kinematics are carried out, obtain the joint angle and posture of the second object；
S3：Set up the kinematics corresponding relation of the first object and the second object；
S4：The exercise data of the second object is caught, the kinematic parameter for obtaining the first object and the second object changes over time
Curve；
S5：By method for evaluating similarity, the first object and the second object motion similitude are evaluated.
Further, the motion of the first object is read in the step S1 frame by frame again by shooting the first object motion video
Parameter.
Further, the exercise data in the step S1 includes each duration, and angle of pitch αp, pitching
Height hp, cross track distance dyWith driftage radius ryThe value that four parameters change over time.
Further, the step S5 assesses the similitude of motion using dynamic time warping (DTW) method.
Further, dynamic time warping (DTW) method is by extending time series and shortened, to calculate
Similitude between two time serieses.
Further, the step S5 uses expression of the accumulation distance (AD) as similitude.
Present invention also offers a kind of bio-robot control method, comprise the following steps,
S10：Catch the kinematic parameter of experimental animal；
S20：Inverse kinematics are carried out, obtain the joint angle and posture of bio-robot；
S30：Kinematics mapping is carried out to experimental animal and the bio-robot；
S40：Obtain the kinematic parameter of bio-robot；
S50：The similarity evaluation moved using dynamic time warping (DTW) method；
S60：Whether the kinematic similitude degree of judgment experiment animal and the bio-robot meets to require, if being unsatisfactory for requiring
Then go to step S30；
S70：Obtain the action with maximum comparability.
Further, the experimental animal is experimental mouse, and the bio-robot is machine mouse.
Further, two typical behaviours are applicable in the step S10 and carry out similarity evaluation：When expression attack,
During the behavior of self-defence, first run, upright continuous action again, be defined as behavior pattern 1 (BP1)；Second, expression is visited
Rope surrounding environment or with it is similar climb pressure and the behavior such as interact when, a series of actions for generally carry out sniff, climbing pressure, withdraw, general
It is defined as behavior pattern 2 (BP2).
The beneficial effects of the invention are as follows：
(1) it is of the invention from angle of pitch αp, pitching height hp, cross track distance dyWith driftage radius ryFour kinematic parameters, to determine
Assess the kinematic similarity of machine mouse and experimental mouse in amount ground；
(2) present invention uses dynamic time warping (DTW) method, and advantage is the speed speed of machine mouse motion hardly
Influence the matching with experimental mouse kinematic similarity.
(3) present invention can guide machine mouse in the case where meeting kinematic conditions, realize the high similarity to experimental mouse motion
Imitate.
Brief description of the drawings
Fig. 1 is the machine mouse control flow schematic diagram according to the kinematic similarity evaluation method of the present invention；
Fig. 2 is 7 cradle head machine mouse kinematics models；
Fig. 3 is that experimental mouse defines with machine mouse kinematic parameter；
Fig. 4 is the experiment analysis results under BP1 patterns；
Fig. 5 is the experiment analysis results under BP2 patterns.
Embodiment
The invention will be further described with technical scheme below in conjunction with the accompanying drawings, but is not intended as the restriction of the present invention.
Fig. 1 show according to the present invention kinematic similarity evaluation method machine mouse control flow schematic diagram, including with
Lower step.
S10：Catch the kinematic parameter of experimental animal；
S20：Inverse kinematics are carried out, obtain the joint angle and posture of bio-robot；
S30：Kinematics mapping is carried out to experimental animal and the bio-robot；
S40：Obtain the kinematic parameter of bio-robot；
S50：The similarity evaluation moved using dynamic time warping (DTW) method；
S60：Whether the kinematic similitude degree of judgment experiment animal and the bio-robot meets to require, if being unsatisfactory for requiring
Then go to step S30；
S70：Obtain the action with maximum comparability.
Fig. 2 show 7 rotary joint machine mouse kinematics models.Coordinate system (xt,yt,zt) origin be machine mouse wheel portion with
Ground contact points Jt, world coordinate system and coordinate system (xt,yt,zt) overlap.Coordinate system (x0,y0,z0) it is fixed on first rotation
Artis, by world coordinate system along ztTranslation obtains.Coordinate system (xi,yi,zi) (i=1,2...7) be fixed on from buttocks to
Each rotary joint point J of neckiPlace.θi(i=1,2...7) respective joint angle is represented.Prenasale is defined as Js。
Experimental mouse is illustrated in figure 2 to define with machine mouse kinematic parameter.Three figures represent pitch orientation motion above, below
Three figures represent yaw direction motion.Angle of pitch αpIt is defined as J1J5Around J1Rotate to the angle (rotation counterclockwise overlapped with horizontal line
Switch to just, clockwise turn to negative)；Pitching height hpIt is defined as JsTo the vertical range on ground；Cross track distance dyIt is defined as Jt
With JsThe horizontal range of point-to-point transmission；Go off course radius ryIt is defined as by J3、J4、J6、JtAnd JsThe optimal radius of circle of five point fittings.
Obviously, elevating movement can be by αpAnd hpTo describe, yawing rotation can be by dyAnd ryTo describe.In addition to compare machine mouse
Relative to the maneuverability of pitching and the yawing rotation of experimental mouse, the extreme value of four previous parameters is defined： WithThe maximum angle of pitch, maximum pitching height, minimum cross track distance and most are represented respectively
Small driftage radius.In order to obtain this four extreme values of experimental mouse, the experimental mouse image that analysis x-ray imager is caught, to three realities
Test mouse to sample respectively 10 minutes, amount to the video of 30 minutes.This four extreme values can be obtained by measuring and calculating： The wherein long BL of unit bodies is defined as mouse and is in flat posture of lying prone
When, from JtTo JsHorizontal range.This four of machine mouse can be measured and calculate again by collection machine mouse sport video
Extreme value：As can be seen that experimental mouse is transported with machine mouse
Extremely similar in dynamic performance, machine mouse can complete the larger MPA and MYR almost identical with experimental mouse, but with relative
In experimental mouse less MPH and larger MYD, this is due to experimental mouse have relative to the machine mouse of rigid body it is higher flexible
Property and ductility.
By a large amount of observation experiment mouse behavioral activities, choose two typical behaviours and carry out the imitation experiment of machine mouse：BP1 and
BP2.Video is marked frame by frame, so as to calculate each action duration, αp、hp、dy、ryDeng kinematic parameter；Again
The posture in each joint is calculated by inverse kinematics；By experimental mouse and the joint corresponding relation of machine mouse, appropriate adjustment is closed
Posture is saved, the joint posture of experimental mouse is mapped on machine mouse；Joint posture is converted into speed and the position of each motor
Put, by suitable control algolithm, system controlled motor reaches specified location with setting speed；In experimentation, by experimental mouse
Behavior be split as several actions, control machine mouse is combined simulation to each action in order, tests be repeated 3 times every time,
The average value for taking 3 experiments is the motion parameter of machine mouse simulated experiment；Read frame by frame again by shooting machine mouse sport video
The kinematic parameter of machine mouse is taken, draws out curve of the kinematic parameter of machine mouse and experimental mouse on time change；It is suitable to choose
Sampling time, obtain the sampled value of experimental mouse and machine mouse, recycle dynamic time warping (DTW) method to experimental mouse with
Machine mouse kinematic similarity is evaluated.
Using expression of the accumulation distance (AD) as similitude, pitching height hpAs experiment parameter, machine mouse is every kind of
Tested respectively with two kinds of friction speeds under behavior pattern (BP1 and BP2), experimental result can be obtained as shown in Figure 3,4.
Fig. 4 (a) curves represent the pitching height h of experimental mouse and machine mouse twice under friction speedp, (b) (c) represents experimental mouse and machine
The device mouse DTW results that friction speed compares respectively twice, the point in figure represent the Euclidean distance of two curves, White curves table
Show optimal path, dark diagonal is represented if the ideal path that two curves obtain when identical.It can be obtained by calculating
AD values to (b) are 0.5741, and the AD values of (c) are 0.6058, so can quantitatively represent experimental mouse and the motion of machine mouse
Similitude.Similarly Fig. 4 can obtain the AD values under BP2, and respectively 0.0192 and 0.0252.It is obvious that AD values are remote under BP1
It is higher than more than experimental mouse and machine mouse kinematic similarity under BP2, is illustrated under BP2 under BP1.Reason is realistic under BP1
The pitching of mouse and machine mouse is tested highly more than 1.5BL, this is easy to for experimental mouse, but for machine mouse almost
It is impossible.DTW result can also help positioning experiment mouse to move the most like or least similar time to machine mouse
Section, optimal path is closer with ideal path, illustrates that similarity is higher, vice versa.Such as Fig. 4 (b) (c), transverse axis 0-0.8s and
2.6s-7s two sections of two Curve Matching it is very good, illustrate that experimental mouse and the motion of machine mouse are almost complete within this twice
It is identical.Therefore constantly control strategy can be optimized according to the result of similarity evaluation, is controlled with actual test to adjust
The speed and angle of each motor, and the cooperation between each motor are made, to realize that the posture to each joint is carried out accurately
Control, so as to reach the effect that experimental mouse is moved high similarity and imitated.
Claims (9)
1. a kind of evaluation method of kinematic similarity, comprises the following steps,
S1：Pass through the exercise data of the first object of seizure；
S2：Inverse kinematics are carried out, obtain the joint angle and posture of the second object；
S3：Set up the kinematics corresponding relation of the first object and the second object；
S4：The exercise data of the second object is caught, obtains the song that the kinematic parameter of the first object and the second object changes over time
Line；
S5：By method for evaluating similarity, the first object and the second object motion similitude are evaluated.
2. kinematic similarity evaluation method according to claim 1, it is characterised in that pass through shooting the in the step S1
One object sport video reads the kinematic parameter of the first object frame by frame again.
3. kinematic similarity evaluation method according to claim 1, it is characterised in that the exercise data in the step S1
Including each duration, and angle of pitch αp, pitching height hp, cross track distance dyWith driftage radius ryFour parameters with
The value of time change.
4. first object of evaluation according to claim 1 and the second object motion method for evaluating similarity, it is characterised in that
The step S5 assesses the similitude of motion using dynamic time warping (DTW) method.
5. kinematic similarity evaluation method according to claim 4, it is characterised in that the dynamic time warping (DTW)
Method is by extending time series and shortened, to calculate the similitude between two time serieses.
6. kinematic similarity evaluation method according to claim 1, it is characterised in that the step S5 uses accumulation distance
(AD) expression as similitude.
7. a kind of bio-robot control method, comprises the following steps,
S10：Catch the kinematic parameter of experimental animal；
S20：Inverse kinematics are carried out, obtain the joint angle and posture of bio-robot；
S30：Kinematics mapping is carried out to experimental animal and the bio-robot；
S40：Obtain the kinematic parameter of bio-robot；
S50：The similarity evaluation moved using dynamic time warping (DTW) method；
S60：Whether the kinematic similitude degree of judgment experiment animal and the bio-robot meets to require, turns if being unsatisfactory for requiring
To step S30；
S70：Obtain the action with maximum comparability.
8. bio-robot control method according to claim 7, it is characterised in that the experimental animal is experimental mouse,
The bio-robot is machine mouse.
9. bio-robot control method according to claim 8, it is characterised in that two are applicable in the step S10
Typical behaviour carries out similarity evaluation：First, in expression attack, the behavior defended oneself, first run, upright again continuously moved
Make, be defined as behavior pattern 1 (BP1)；Second, expression explore surrounding environment or with it is similar climb pressure and the behavior such as interact when,
The a series of actions for generally carry out sniff, climbing pressure, withdrawing, is defined as behavior pattern 2 (BP2).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710903569.2A CN107877512A (en) | 2017-09-29 | 2017-09-29 | A kind of machine mouse and experimental mouse kinematic similarity evaluation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710903569.2A CN107877512A (en) | 2017-09-29 | 2017-09-29 | A kind of machine mouse and experimental mouse kinematic similarity evaluation method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107877512A true CN107877512A (en) | 2018-04-06 |
Family
ID=61780962
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710903569.2A Pending CN107877512A (en) | 2017-09-29 | 2017-09-29 | A kind of machine mouse and experimental mouse kinematic similarity evaluation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107877512A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1830635A (en) * | 2005-03-10 | 2006-09-13 | 北京理工大学 | Human imitation robot action similarity evaluation based on human body motion track |
| CN101412218A (en) * | 2008-10-28 | 2009-04-22 | 北京理工大学 | Human movement path-based method for evaluating similarity of robot rhythmic actions |
| KR20140136141A (en) * | 2013-05-20 | 2014-11-28 | 김도조 | Robot animal and robot zoo comprising the same |
| CN104816298A (en) * | 2015-05-12 | 2015-08-05 | 北京理工大学 | Similarity elevating method of humanoid robot tumble action |
| CN104933730A (en) * | 2014-03-19 | 2015-09-23 | 通用汽车环球科技运作有限责任公司 | Multi-View Human Detection Using Semi-Exhaustive Search |
| CN105184767A (en) * | 2015-07-22 | 2015-12-23 | 北京工业大学 | Moving human body attitude similarity measuring method |
| CN106446757A (en) * | 2016-05-20 | 2017-02-22 | 北京九艺同兴科技有限公司 | Human body motion data similarity automatic evaluation method |
| CN107169117A (en) * | 2017-05-25 | 2017-09-15 | 西安工业大学 | A kind of manual draw human motion search method based on autocoder and DTW |
-
2017
- 2017-09-29 CN CN201710903569.2A patent/CN107877512A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1830635A (en) * | 2005-03-10 | 2006-09-13 | 北京理工大学 | Human imitation robot action similarity evaluation based on human body motion track |
| CN101412218A (en) * | 2008-10-28 | 2009-04-22 | 北京理工大学 | Human movement path-based method for evaluating similarity of robot rhythmic actions |
| KR20140136141A (en) * | 2013-05-20 | 2014-11-28 | 김도조 | Robot animal and robot zoo comprising the same |
| CN104933730A (en) * | 2014-03-19 | 2015-09-23 | 通用汽车环球科技运作有限责任公司 | Multi-View Human Detection Using Semi-Exhaustive Search |
| CN104816298A (en) * | 2015-05-12 | 2015-08-05 | 北京理工大学 | Similarity elevating method of humanoid robot tumble action |
| CN105184767A (en) * | 2015-07-22 | 2015-12-23 | 北京工业大学 | Moving human body attitude similarity measuring method |
| CN106446757A (en) * | 2016-05-20 | 2017-02-22 | 北京九艺同兴科技有限公司 | Human body motion data similarity automatic evaluation method |
| CN107169117A (en) * | 2017-05-25 | 2017-09-15 | 西安工业大学 | A kind of manual draw human motion search method based on autocoder and DTW |
Non-Patent Citations (3)
| Title |
|---|
| QING SHI等: "Design and Control of a Biomimetic Robotic Rat for Interaction With Laboratory Rats", 《IEEE/ASME TRANSACTIONS ON MECHATRONICS》 * |
| 李康等: "机器鼠的仿鼠运动程度评估", 《机器人》 * |
| 柯文德: "基于人体运动相似性的仿人机器人运动规划关键技术研究", 《中国博士学位论文全文数据库 信息科技辑》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lourens et al. | Communicating emotions and mental states to robots in a real time parallel framework using Laban movement analysis | |
| Seo et al. | Anatomy builder VR: Applying a constructive learning method in the virtual reality canine skeletal system | |
| CN103996056B (en) | Tattoo image classification method based on deep learning | |
| Oudeyer et al. | Intrinsically motivated learning of real-world sensorimotor skills with developmental constraints | |
| CN110000787A (en) | A kind of control method of super redundant mechanical arm | |
| Duarte et al. | KSGphysio-Kinect serious game for physiotherapy | |
| WO2007076516A3 (en) | Brain-based device having a cerebellar model for predictive motor control | |
| CN101739709A (en) | Control method of three-dimensional facial animation | |
| Vourvopoulos et al. | Brain-controlled serious games for cultural heritage | |
| CN105597281B (en) | Method and device for evaluating and training fine motion function of fingers | |
| Kolhe et al. | Smart communication system for agriculture | |
| CN107877512A (en) | A kind of machine mouse and experimental mouse kinematic similarity evaluation method | |
| Li et al. | Using artificial intelligence for the construction of university physical training and teaching systems | |
| Bakkum et al. | Embodying cultured networks with a robotic drawing arm | |
| CN109910001A (en) | A kind of Fang She robot hybrid three-dimensional gait control method | |
| Miglino et al. | Breedbot: an evolutionary robotics application in digital content | |
| CN112734704B (en) | Skill training evaluation method under neural network machine learning recognition objective lens | |
| CN112379695B (en) | Control method of rump-tail cooperative variant control system of imitated prey bird | |
| Doddo et al. | Board# 121: MAKER: a study of multi-robot systems recreated for high school students | |
| CN106910233A (en) | A kind of movement simulating method of virtual insect cartoon role | |
| Boccanfuso et al. | Adaptive robot design with hand and face tracking for use in autism therapy | |
| Wang et al. | Robot gaining robust pouring skills through fusing vision and audio | |
| Maeda et al. | Time series data analysis for sport skill | |
| Li et al. | Motion evaluation of a modified multi-link robotic rat | |
| Sun | Aerobics movement decomposition action teaching system based on intelligent vision sensor |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180406 |