CN109129474A - Manipulator active grabbing device and method based on multi-modal fusion - Google Patents
Manipulator active grabbing device and method based on multi-modal fusion Download PDFInfo
- Publication number
- CN109129474A CN109129474A CN201810911069.8A CN201810911069A CN109129474A CN 109129474 A CN109129474 A CN 109129474A CN 201810911069 A CN201810911069 A CN 201810911069A CN 109129474 A CN109129474 A CN 109129474A
- Authority
- CN
- China
- Prior art keywords
- grabbed
- manipulator
- modal fusion
- information
- fusion
- 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.)
- Granted
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
- B25J9/1694—Programme controls characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor controlled systems, sensor fusion
-
- 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
- B25J9/1679—Programme controls characterised by the tasks executed
-
- 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
- B25J9/1694—Programme controls characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor controlled systems, sensor fusion
- B25J9/1697—Vision controlled systems
Abstract
The present invention provides a kind of manipulator active grabbing device and method based on multi-modal fusion, wherein, the manipulator active grabbing device based on multi-modal fusion includes pedestal (1), mechanical arm (2), laser radar (3), binocular vision system (4), manipulator (5), one end of the mechanical arm (2), laser radar (3) are securedly mounted to respectively on pedestal (1), and the binocular vision system (4), manipulator (5) are securedly mounted to the other end of mechanical arm respectively;The manipulator active grasping means based on multi-modal fusion includes the following steps: step 1: perceiving object to be grabbed, obtains perception information;Step 2: according to the perception information, positioning object to be grabbed, obtain location information;Step 3: according to the location information, grabbing object to be grabbed.The present invention has fully considered the complex environment of space operations, effectively improves the ability to moving object crawl, is with a wide range of applications.
Description
Technical field
The present invention relates to robot for space positioning and crawl technical field, more particularly to the machinery based on multi-modal fusion
Hand active grabbing device and method, it is especially a kind of to merge the micro- heavy of CMOS camera binocular vision, laser radar and tactilely-perceptible
Robot localization and technology is actively grabbed under force environment.
Background technique
Our times major country space industry accelerated development, to explore the Life Science Experiment and space work that space is carried out
Industry is increasing.Traditional space development of the activity dependent on equipment preset instructions, space station staff directly operates or ground
Staff's remote operating lacks automatic real-time, interactive and learning process between environment, causes to be difficult to realize under microgravity environment
The complex jobs tasks such as moving object crawl.Realize that automatically grabbing operation correlation to moving object grinds under existing microgravity environment
Study carefully main concentrate to improve by tactilely-perceptible in conjunction with passive compliant type mechanism to overcome the impact force of moving object crawl process
Success rate and reliability are grabbed, manipulator active grasping manipulation is realized to multimodal information fusions such as comprehensive utilization tactile, visions
Study less, difficult point is that severe space environment disturbs and how real based on inaccurate heat transfer agent caused by sensor
The prediction etc. of existing object run track, therefore correlation and complementarity grab raising between the multi-modal sensor information of comprehensive utilization
Efficiency and robustness have great importance.
Summary of the invention
For the defects in the prior art, the manipulator active based on multi-modal fusion that the object of the present invention is to provide a kind of
Grabbing device and method.
According to an aspect of the present invention, a kind of manipulator active grabbing device based on multi-modal fusion provided, packet
Include pedestal, mechanical arm, laser radar, binocular vision system, manipulator;Wherein, one end of the mechanical arm, laser radar difference
It is securedly mounted on pedestal, the binocular vision system, manipulator are securedly mounted to the other end of mechanical arm respectively.
Preferably, it is packaged in the pedestal and appoints for multimodal information fusion, manipulator motion planning and crawl control
The deep learning image processor chip of business.
Preferably, the binocular vision system is mounted on the other end of mechanical arm using mechanical arm as axisymmetrical.
Preferably, it is equipped with inside the manipulator and is clamped for Real-time Feedback seized condition, prediction object pose, control
The touch sensor of power.
According to another aspect of the present invention, a kind of manipulator active grasping means based on multi-modal fusion is provided, is wrapped
Include following steps:
Step 1: perceiving object to be grabbed, obtain perception information;
Step 2: according to the perception information, positioning object to be grabbed, obtain location information;
Step 3: according to the location information, grabbing object to be grabbed.
Preferably, the perception information includes radar image, visual pattern, and the step 1 includes the following steps:
Step 1.1: the radar image of object to be grabbed is obtained by laser radar;
Step 1.2: the visual pattern of object to be grabbed is obtained by binocular vision system.
Preferably, the step 2 includes the following steps:
Step 2.1: information fusion being carried out to radar image and visual pattern, obtains object state information to be grabbed;
Step 2.2: according to the object state information to be grabbed obtained after fusion radar image and visual pattern, predicting wait grab
Take object operation posture and/or location information;
Step 2.3: predicting object operation posture to be grabbed and/or location information according to described, judge that object to be grabbed is
It is no to enter crawl range: if entering crawl range, will to predict object operation posture to be grabbed and/or location information as described in
Location information enters step 3 and continues to execute;If not entering crawl range, return step 2.1 is continued to execute.
Preferably, the step 3 includes the following steps:
Step 3.1: according to the location information for the object to be grabbed for entering crawl range, the crawl posture for adjusting manipulator is held
Row grasping manipulation;
Step 3.2: tactile data being perceived by touch sensor, judges whether to grab successfully: if grabbing successfully, terminating
Process;If crawl failure, return step 3.1 continue to execute.
Preferably, the binocular vision system object type to be grabbed and judges object and manipulator to be grabbed for identification
Spatial relation.
Preferably, the laser radar for identification contour of object to be grabbed and by object to be grabbed from visual pattern get the bid
It outpours and.
Compared with prior art, the present invention have it is following the utility model has the advantages that
1, the present invention has fully considered the complex environment of space operations, merges binocular vision, laser radar and tactilely-perceptible,
Robot is effectively increased under microgravity environment to moving object positioning and active Grasping skill.
2, the present invention is obtained moving object to be grabbed from binocular vision system using the collected information of laser radar
It marks out and in image, avoid the defect that Conventional visual method is interfered vulnerable to strong light, it is accurate to improve object identification to be grabbed
Rate simultaneously reduces computer vision system image recognition difficulty.
3, the present invention is carried out multi-modal using the image that RNN-LSTM algorithm acquires binocular vision system and laser radar
Information fusion, solves the problems, such as single multimodality environment perception information imperfection.
4, crawl object trajectory is treated using time-space relationship reasoning algorithm the present invention is based on multi-modal fusion information to carry out in advance
It surveys, real-time judgment gestures of object to be grabbed and its relative space position between manipulator improve manipulator and grab successfully
Probability.
5, the present invention uses touch sensor Real-time Feedback object pose information, real-time control and optimal grasp power, improves
Crawl success rate.
Detailed description of the invention
Upon reading the detailed description of non-limiting embodiments with reference to the following drawings, other feature of the invention,
Objects and advantages will become more apparent upon:
Fig. 1 is that the present invention is based on the general structure schematic diagrams of the manipulator active grabbing device of multi-modal fusion.
Fig. 2 be Fig. 1 in binocular vision system, mechanical arm, manipulator three positional diagram.
Fig. 3 is that the present invention is based on the flow charts of the manipulator active grasping means of multi-modal fusion.
Specific embodiment
The present invention is described in detail combined with specific embodiments below.Following embodiment will be helpful to the technology of this field
Personnel further understand the present invention, but the invention is not limited in any way.It should be pointed out that the ordinary skill of this field
For personnel, without departing from the inventive concept of the premise, several changes and improvements can also be made.These belong to the present invention
Protection scope.
The present invention causes binocular vision system to be difficult to accurately obtain for environmental factors such as the severe illumination of space and electromagnetic fields
The problem of moving object information to be grabbed, by introducing surrounding objects under laser radar real-time monitoring microgravity environment, by following
Memory network algorithm, that is, RNN-LSTM algorithm carries out information fusion to radar image and visual pattern to ring neural network-length in short-term,
And binocular vision system is corrected on this basis, accurately object state information to be grabbed is obtained, using based on depth
The running track that the time-space relationship reasoning algorithm of the theories of learning treats crawl object is predicted, is finally equipped with touching using end
Feel that the manipulator of sensor executes grasping manipulation, improves and grab successful probability.
According to an aspect of the present invention, a kind of manipulator active grabbing device based on multi-modal fusion provided, such as
Shown in Fig. 1, including pedestal 1, mechanical arm 2, laser radar 3, binocular vision system 4, manipulator 5;Wherein, the mechanical arm 2
One end, laser radar 3 are securedly mounted to respectively on pedestal 1, and the binocular vision system 4, manipulator 5 are securedly mounted to machine respectively
The other end of tool arm.Wherein, it is packaged in the pedestal 1 for multimodal information fusion, manipulator motion planning and crawl control
The deep learning image processor chip of task processed.As shown in Fig. 2, the binocular vision system 4 is axisymmetrical with mechanical arm 2
It is mounted on the other end of mechanical arm 2.Be equipped with inside the manipulator 5 for Real-time Feedback seized condition, prediction object pose,
Control the touch sensor of clamping force.The binocular vision system 4 object type to be grabbed and judges object to be grabbed for identification
The spatial relation of body and manipulator 5.The laser radar 3 for identification contour of object to be grabbed and will object be grabbed from
It marks out and in visual pattern.
According to another aspect of the present invention, a kind of manipulator active grasping means based on multi-modal fusion is provided, especially
It is actively grabbed using the manipulator based on multi-modal fusion of the manipulator active grabbing device based on multi-modal fusion
Method is taken, as shown in figure 3, including the following steps:
Step 1: perceiving object to be grabbed, obtain perception information;
Step 2: according to the perception information, positioning object to be grabbed, obtain location information;
Step 3: according to the location information, grabbing object to be grabbed.
Wherein, the perception information includes radar image, visual pattern, and the step 1 includes the following steps:
Step 1.1: the radar image of object to be grabbed is obtained by laser radar 3;
Step 1.2: the visual pattern of object to be grabbed is obtained by binocular vision system 4.
The step 2 includes the following steps:
Step 2.1: information fusion being carried out to radar image and visual pattern by RNN-LSTM algorithm, obtains object to be grabbed
Body status information;
Step 2.2: according to the object state information to be grabbed obtained after fusion radar image and visual pattern, passing through space-time
Relation inference algorithm predicts object operation posture to be grabbed and/or location information;
Step 2.3: predicting object operation posture to be grabbed and/or location information according to described, judge that object to be grabbed is
It is no to enter crawl range: if entering crawl range, will to predict object operation posture to be grabbed and/or location information as described in
Location information enters step 3 and continues to execute;If not entering crawl range, return step 2.1 is continued to execute.
The step 3 includes the following steps:
Step 3.1: according to the location information for the object to be grabbed for entering crawl range, adjusting the crawl posture of manipulator 5
Execute grasping manipulation;
Step 3.2: tactile data being perceived by touch sensor, judges whether to grab successfully: if grabbing successfully, terminating
Process;If crawl failure, return step 3.1 continue to execute.
Specific embodiments of the present invention are described above.It is to be appreciated that the invention is not limited to above-mentioned
Particular implementation, those skilled in the art can make a variety of changes or modify within the scope of the claims, this not shadow
Ring substantive content of the invention.In the absence of conflict, the feature in embodiments herein and embodiment can any phase
Mutually combination.
Claims (10)
1. a kind of manipulator active grabbing device based on multi-modal fusion, which is characterized in that including pedestal (1), mechanical arm
(2), laser radar (3), binocular vision system (4), manipulator (5);Wherein, one end of the mechanical arm (2), laser radar
(3) it is securedly mounted to respectively on pedestal (1), the binocular vision system (4), manipulator (5) are securedly mounted to mechanical arm respectively
The other end.
2. the manipulator active grabbing device according to claim 1 based on multi-modal fusion, which is characterized in that the base
It is packaged in seat (1) at the deep learning image for multimodal information fusion, manipulator motion planning and crawl control task
Manage device chip.
3. the manipulator active grabbing device according to claim 1 based on multi-modal fusion, which is characterized in that described double
Mesh vision system (4) is with the other end that mechanical arm (2) are that axisymmetrical is mounted on mechanical arm (2).
4. the manipulator active grabbing device according to claim 1 based on multi-modal fusion, which is characterized in that the machine
It is equipped with inside tool hand (5) for Real-time Feedback seized condition, prediction object pose, the touch sensor for controlling clamping force.
5. a kind of manipulator active grasping means based on multi-modal fusion, which comprises the steps of:
Step 1: perceiving object to be grabbed, obtain perception information;
Step 2: according to the perception information, positioning object to be grabbed, obtain location information;
Step 3: according to the location information, grabbing object to be grabbed.
6. the manipulator active grasping means according to claim 5 based on multi-modal fusion, which is characterized in that the sense
Know that information includes radar image, visual pattern, the step 1 includes the following steps:
Step 1.1: the radar image of object to be grabbed is obtained by laser radar (3);
Step 1.2: the visual pattern of object to be grabbed is obtained by binocular vision system (4).
7. the manipulator active grasping means according to claim 5 based on multi-modal fusion, which is characterized in that the step
Rapid 2 include the following steps:
Step 2.1: information fusion being carried out to radar image and visual pattern, obtains object state information to be grabbed;
Step 2.2: according to the object state information to be grabbed obtained after fusion radar image and visual pattern, predicting object to be grabbed
Running body posture and/or location information;
Step 2.3: predict object to be grabbed operation posture and/or location information according to described, judge object to be grabbed whether into
Enter to grab range: if entering crawl range, object operation posture to be grabbed and/or location information will be predicted as the positioning
Information enters step 3 and continues to execute;If not entering crawl range, return step 2.1 is continued to execute.
8. the manipulator active grasping means according to claim 5 based on multi-modal fusion, which is characterized in that the step
Rapid 3 include the following steps:
Step 3.1: according to the location information for the object to be grabbed for entering crawl range, the crawl posture of adjustment manipulator (5) is held
Row grasping manipulation;
Step 3.2: tactile data being perceived by touch sensor, judges whether to grab successfully: if grabbing successfully, terminating to flow
Journey;If crawl failure, return step 3.1 continue to execute.
9. described in the manipulator active grabbing device or claim 6 according to claim 1 based on multi-modal fusion
The manipulator active grasping means based on multi-modal fusion, which is characterized in that the binocular vision system (4) for identification to
Crawl object type and the spatial relation for judging object to be grabbed Yu manipulator (5).
10. described in the manipulator active grabbing device or claim 6 according to claim 1 based on multi-modal fusion
The manipulator active grasping means based on multi-modal fusion, which is characterized in that the laser radar (3) is for identification wait grab
Object to be grabbed simultaneously is marked out to come from visual pattern by contour of object.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810911069.8A CN109129474B (en) | 2018-08-10 | 2018-08-10 | Multi-mode fusion-based active manipulator grabbing device and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810911069.8A CN109129474B (en) | 2018-08-10 | 2018-08-10 | Multi-mode fusion-based active manipulator grabbing device and method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109129474A true CN109129474A (en) | 2019-01-04 |
CN109129474B CN109129474B (en) | 2020-07-14 |
Family
ID=64792860
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810911069.8A Active CN109129474B (en) | 2018-08-10 | 2018-08-10 | Multi-mode fusion-based active manipulator grabbing device and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109129474B (en) |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109993763A (en) * | 2019-03-28 | 2019-07-09 | 北京理工大学 | The probe position method and system merged based on image recognition with force feedback |
CN110666792A (en) * | 2019-09-04 | 2020-01-10 | 南京富尔登科技发展有限公司 | Multi-point-position cooperative control manufacturing and assembling device and method based on information fusion |
CN111168685A (en) * | 2020-02-17 | 2020-05-19 | 上海高仙自动化科技发展有限公司 | Robot control method, robot, and readable storage medium |
CN111730606A (en) * | 2020-08-13 | 2020-10-02 | 深圳国信泰富科技有限公司 | Grabbing action control method and system of high-intelligence robot |
CN111958596A (en) * | 2020-08-13 | 2020-11-20 | 深圳国信泰富科技有限公司 | Action planning system and method for high-intelligence robot |
CN112060085A (en) * | 2020-08-24 | 2020-12-11 | 清华大学 | Robot operation pose control method based on visual-touch multi-scale positioning |
CN112207804A (en) * | 2020-12-07 | 2021-01-12 | 国网瑞嘉(天津)智能机器人有限公司 | Live working robot and multi-sensor identification and positioning method |
CN112777555A (en) * | 2021-03-23 | 2021-05-11 | 江苏华谊广告设备科技有限公司 | Intelligent oiling device and method |
CN113433941A (en) * | 2021-06-29 | 2021-09-24 | 之江实验室 | Multi-modal knowledge graph-based low-level robot task planning method |
CN113954076A (en) * | 2021-11-12 | 2022-01-21 | 哈尔滨工业大学(深圳) | Robot precision assembling method based on cross-modal prediction assembling scene |
CN115431279A (en) * | 2022-11-07 | 2022-12-06 | 佛山科学技术学院 | Mechanical arm autonomous grabbing method based on visual-touch fusion under weak rigidity characteristic condition |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0263952A2 (en) * | 1986-10-15 | 1988-04-20 | Mercedes-Benz Ag | Robot unit with moving manipulators |
CN1343551A (en) * | 2000-09-21 | 2002-04-10 | 上海大学 | Hierarchical modular model for robot's visual sense |
CN107576960A (en) * | 2017-09-04 | 2018-01-12 | 苏州驾驶宝智能科技有限公司 | The object detection method and system of vision radar Spatial-temporal Information Fusion |
CN107838932A (en) * | 2017-12-14 | 2018-03-27 | 昆山市工研院智能制造技术有限公司 | A kind of robot of accompanying and attending to multi-degree-of-freemechanical mechanical arm |
CN108214487A (en) * | 2017-12-16 | 2018-06-29 | 广西电网有限责任公司电力科学研究院 | Based on the positioning of the robot target of binocular vision and laser radar and grasping means |
-
2018
- 2018-08-10 CN CN201810911069.8A patent/CN109129474B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0263952A2 (en) * | 1986-10-15 | 1988-04-20 | Mercedes-Benz Ag | Robot unit with moving manipulators |
CN1343551A (en) * | 2000-09-21 | 2002-04-10 | 上海大学 | Hierarchical modular model for robot's visual sense |
CN107576960A (en) * | 2017-09-04 | 2018-01-12 | 苏州驾驶宝智能科技有限公司 | The object detection method and system of vision radar Spatial-temporal Information Fusion |
CN107838932A (en) * | 2017-12-14 | 2018-03-27 | 昆山市工研院智能制造技术有限公司 | A kind of robot of accompanying and attending to multi-degree-of-freemechanical mechanical arm |
CN108214487A (en) * | 2017-12-16 | 2018-06-29 | 广西电网有限责任公司电力科学研究院 | Based on the positioning of the robot target of binocular vision and laser radar and grasping means |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109993763A (en) * | 2019-03-28 | 2019-07-09 | 北京理工大学 | The probe position method and system merged based on image recognition with force feedback |
CN110666792A (en) * | 2019-09-04 | 2020-01-10 | 南京富尔登科技发展有限公司 | Multi-point-position cooperative control manufacturing and assembling device and method based on information fusion |
CN111168685A (en) * | 2020-02-17 | 2020-05-19 | 上海高仙自动化科技发展有限公司 | Robot control method, robot, and readable storage medium |
CN111730606A (en) * | 2020-08-13 | 2020-10-02 | 深圳国信泰富科技有限公司 | Grabbing action control method and system of high-intelligence robot |
CN111958596A (en) * | 2020-08-13 | 2020-11-20 | 深圳国信泰富科技有限公司 | Action planning system and method for high-intelligence robot |
CN111958596B (en) * | 2020-08-13 | 2022-03-04 | 深圳国信泰富科技有限公司 | Action planning system and method for high-intelligence robot |
CN111730606B (en) * | 2020-08-13 | 2022-03-04 | 深圳国信泰富科技有限公司 | Grabbing action control method and system of high-intelligence robot |
CN112060085B (en) * | 2020-08-24 | 2021-10-08 | 清华大学 | Robot operation pose control method based on visual-touch multi-scale positioning |
CN112060085A (en) * | 2020-08-24 | 2020-12-11 | 清华大学 | Robot operation pose control method based on visual-touch multi-scale positioning |
CN112207804A (en) * | 2020-12-07 | 2021-01-12 | 国网瑞嘉(天津)智能机器人有限公司 | Live working robot and multi-sensor identification and positioning method |
CN112777555A (en) * | 2021-03-23 | 2021-05-11 | 江苏华谊广告设备科技有限公司 | Intelligent oiling device and method |
CN113433941A (en) * | 2021-06-29 | 2021-09-24 | 之江实验室 | Multi-modal knowledge graph-based low-level robot task planning method |
CN113954076A (en) * | 2021-11-12 | 2022-01-21 | 哈尔滨工业大学(深圳) | Robot precision assembling method based on cross-modal prediction assembling scene |
CN113954076B (en) * | 2021-11-12 | 2023-01-13 | 哈尔滨工业大学(深圳) | Robot precision assembling method based on cross-modal prediction assembling scene |
CN115431279A (en) * | 2022-11-07 | 2022-12-06 | 佛山科学技术学院 | Mechanical arm autonomous grabbing method based on visual-touch fusion under weak rigidity characteristic condition |
Also Published As
Publication number | Publication date |
---|---|
CN109129474B (en) | 2020-07-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109129474A (en) | Manipulator active grabbing device and method based on multi-modal fusion | |
CN110785268B (en) | Machine learning method and device for semantic robot grabbing | |
CN106826822A (en) | A kind of vision positioning and mechanical arm crawl implementation method based on ROS systems | |
CN106256512A (en) | Robot device including machine vision | |
JP2016522089A (en) | Controlled autonomous robot system for complex surface inspection and processing | |
WO2014089316A1 (en) | Human augmentation of robotic work | |
US11014243B1 (en) | System and method for instructing a device | |
CN110421556A (en) | A kind of method for planning track and even running method of redundancy both arms service robot Realtime collision free | |
CN110497405B (en) | Force feedback man-machine cooperation anti-collision detection method and module for driving and controlling integrated control system | |
CN107984474A (en) | A kind of humanoid intelligent robot of half body and its control system | |
JPH0830327A (en) | Active environment recognition system | |
CN116755474A (en) | Electric power line inspection method and system for unmanned aerial vehicle | |
Zhang et al. | Multi‐target detection and grasping control for humanoid robot NAO | |
CN116494201A (en) | Monitoring integrated power machine room inspection robot and unmanned inspection method | |
Xue et al. | Gesture-and vision-based automatic grasping and flexible placement in teleoperation | |
US11052541B1 (en) | Autonomous robot telerobotic interface | |
CN114905508A (en) | Robot grabbing method based on heterogeneous feature fusion | |
Ranjan et al. | Identification and control of NAO humanoid robot to grasp an object using monocular vision | |
Formica et al. | Neural networks based human intent prediction for collaborative robotics applications | |
Du et al. | A novel natural mobile human-machine interaction method with augmented reality | |
Kuan et al. | Challenges in VR-based robot teleoperation | |
Schnaubelt et al. | Autonomous assistance for versatile grasping with rescue robots | |
CN112959342B (en) | Remote operation method for grabbing operation of aircraft mechanical arm based on operator intention identification | |
WO2022170279A1 (en) | Systems, apparatuses, and methods for robotic learning and execution of skills including navigation and manipulation functions | |
Cheng-Jun et al. | Design of mobile robot teleoperation system based on virtual reality |
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 |