CN113203408A - Method for predicting position of robot based on floor sensor - Google Patents
Method for predicting position of robot based on floor sensor Download PDFInfo
- Publication number
- CN113203408A CN113203408A CN202110556842.5A CN202110556842A CN113203408A CN 113203408 A CN113203408 A CN 113203408A CN 202110556842 A CN202110556842 A CN 202110556842A CN 113203408 A CN113203408 A CN 113203408A
- Authority
- CN
- China
- Prior art keywords
- robot
- floor
- sensor
- vicon
- predicting
- 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
- 238000000034 method Methods 0.000 title claims abstract description 13
- QBWCMBCROVPCKQ-UHFFFAOYSA-N chlorous acid Chemical compound OCl=O QBWCMBCROVPCKQ-UHFFFAOYSA-N 0.000 claims description 27
- 230000003139 buffering effect Effects 0.000 claims description 3
- 230000001953 sensory effect Effects 0.000 claims description 3
- 230000007787 long-term memory Effects 0.000 claims description 2
- 230000005484 gravity Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000015654 memory Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/005—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 with correlation of navigation data from several sources, e.g. map or contour matching
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/10—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Navigation (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention provides a method for predicting the position of a robot based on a floor sensor, which is a method for helping the warehouse to integrally control the material flow by laying a sensor array on the floor of the warehouse, predicting the position information and the specific array position of the robot in the warehouse by virtue of a trained prediction algorithm and a trained model through sensor data of the floor. The method can well meet the requirement that the warehousing and distribution robot can acquire the position of the warehousing and distribution robot without other positioning systems.
Description
Technical Field
The invention relates to a method for predicting a position of a robot based on a floor sensor, and belongs to the technical field of robot path planning.
Background
With the increasing volume of goods transported, it is becoming more and more important to improve the efficiency of logistics, which thus requires a higher level of automation in terms of warehouse logistics. For robot control in a warehouse scene, position information of the robot is necessary information for controlling material flow, a plurality of sensors such as a laser radar, an inertial measurement unit and a milemeter are adopted for positioning of the logistics robot, the position and state information of the logistics robot is sensed, meanwhile, the logistics robot needs a floor to provide related position information in the moving process, and the sensors in the floor not only provide the position information, but also play a vital role in path planning of the robot.
Disclosure of Invention
The invention aims to provide a method for predicting the position of a robot based on a floor sensor, which not only has more accurate positioning, but also saves the cost.
In order to achieve the purpose, the invention is realized by the following technical scheme:
(1) in a sensor array laid on a floor, each node is provided with a magnetometer, an accelerometer, a screw meter and a wireless sensor node receiving signal strength indicator in the robot, and when the robot runs on the floor, data of floor sensors are collected and a data set is synthesized;
(2) training data is created by matching Vicon motion capture system and sensory floor data to each other, the observations of each sensor floor are matched to the closest Vicon data points according to a timestamp, a merged dataset is obtained, which contains sensor observations and location and time information for each observation;
(3) predicting the position coordinate information of the robot by using an LSTM long-term memory network algorithm, saving the information in the previous time step, and predicting the position of the current robot according to the information of the time step and the information of the sensor;
(4) and the position coordinate information of the robot is obtained through the training of a prediction algorithm.
Preferably, the sensor array provides observations of these features at a rate of 4 times per second, with a round trip time of 5 seconds for buffering and refreshing.
Preferably, the floor data and Vicon system creating training data comprises: RSSI, magnetometer (x, y, z), accelerometer (x, y, z) and gyroscope (x, y, z), timestamp, vicon location, and sensor identifiers in two columns of strip-and node-id.
Preferably, the current position of the robot is predicted based on the information of the time step and the information of the sensor, and the characteristic variables used are:
[ ax, ay, az ]: the value of [ g ] of the accelerometer in the x, y, z direction 1g = 9,81 m/s ˆ 2, az always facing the ground;
[ gx, gy, gz |: the gyroscope values are in the x, y, z directions in degrees per second [ dps ];
[ mx, my, mz ]: a microtesla magnetic intensity value [ mu T ];
[ r ]: RSSI, 0 indicates reception of a timeout/no packet;
and (3) predicting a label:
vicon _ x is the actual robot position tracked by the Vicon system in the x direction, and the unit is meter;
vicon _ y: the actual robot position, in meters, tracked by the Vicon system in the y-direction.
The invention has the advantages that: the invention proposes to use the relevant data provided by the floor sensors to predict the specific position of the robot, thereby reducing the use of the self-positioning sensors of the robot and multiplexing the information of the floor sensors to predict the specific position of the robot. The positioning is more accurate, and the cost is saved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention.
Fig. 1 shows the sensing node deployment and robot coordinate information of the floor according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention provides a method for predicting the position of a robot based on a floor sensor. The main contents are as follows:
in a sensor array laid on the floor, each node is provided with a magnetometer, an accelerometer, a gyroscope and a wireless sensor node Received Signal Strength Indicator (RSSI) in the robot. Observations of these features are provided at a rate of approximately 4 times per second, with a round trip time of 5 seconds for buffering and refreshing (sensor reads per strip in sequence). The Vicon system accurately tracks the robot in a three-dimensional coordinate system and provides time stamps, XYZ coordinate positions of the robot, and rotation information. As the robot travels over the floor, data from the floor sensors is collected and a data set is synthesized.
Training data is created by matching Vicon motion capture system and sensory floor data to each other, with each sensor floor observation matching the closest Vicon data point according to a timestamp. We obtain a consolidated data set containing sensor observations and the location and time information for each observation.
Training data was created from floor data and Vicon system: RSSI, magnetometer (x, y, z), accelerometer (x, y, z) and gyroscope (x, y, z), timestamp, vicon location, and identifier of the sensor (in two columns, strip-and node-id).
By using the LSTM long-time memory network algorithm, the position coordinate information of the robot can be predicted. The movement information and data of the robot are data having time series, so that it is possible to efficiently save information in the previous time step using the LSTM algorithm and predict the current position of the robot from the information of the time step and the information of the sensor.
Training a prediction algorithm based on the training data enables it to reliably predict the specific position of the robot, i.e. the coordinate information. Feature variables used in the prediction:
[ ax, ay, az ]: the value of [ g ] of the accelerometer in the x, y, z direction (1g = 9,81 m/s ˆ 2) (az always facing the ground (1 g-earth gravity)).
[ gx, gy, gz |: the gyroscope values are in the x, y, z directions in degrees per second [ dps ].
[ mx, my, mz ]: microtesla magnetic intensity value [ mu T ].
[ r ]: RSSI, 0, indicates reception of a timeout/no packet.
And (3) predicting a label:
vicon _ x: the actual robot position tracked by the Vicon system in the x-direction, in meters (distance to Vicon (0,0))
Vicon _ y: the actual robot position tracked by the Vicon system in the y-direction, in meters (distance Vicon (0,0))
Through the training of the prediction algorithm, the position coordinate information of the robot can be reliably obtained.
Claims (4)
1. A method for predicting a position of a robot based on a floor sensor, comprising the steps of:
(1) in a sensor array laid on a floor, each node is provided with a magnetometer, an accelerometer, a screw meter and a wireless sensor node receiving signal strength indicator in the robot, and when the robot runs on the floor, data of floor sensors are collected and a data set is synthesized;
(2) training data is created by matching Vicon motion capture system and sensory floor data to each other, the observations of each sensor floor are matched to the closest Vicon data points according to a timestamp, a merged dataset is obtained, which contains sensor observations and location and time information for each observation;
(3) predicting the position coordinate information of the robot by using an LSTM long-term memory network algorithm, saving the information in the previous time step, and predicting the position of the current robot according to the information of the time step and the information of the sensor;
(4) and the position coordinate information of the robot is obtained through the training of a prediction algorithm.
2. The method for predicting robot position based on floor sensors of claim 1, wherein the sensor array provides observations of these features at a rate of 4 times per second, with a round trip time of 5 seconds for buffering and refreshing.
3. The method for predicting robot position based on floor sensors of claim 1, wherein the floor data and Vicon system creating training data comprises: RSSI, magnetometer (x, y, z), accelerometer (x, y, z) and gyroscope (x, y, z), timestamp, vicon location, and sensor identifiers in two columns of strip-and node-id.
4. The method for predicting the position of a robot based on a floor sensor according to claim 1, wherein the position of the current robot is predicted based on the information of the time step and the information of the sensor, and the characteristic variables used are:
[ ax, ay, az ]: the value of [ g ] of the accelerometer in the x, y, z direction 1g = 9,81 m/s ˆ 2, az always facing the ground;
[ gx, gy, gz |: the gyroscope values are in the x, y, z directions in degrees per second [ dps ];
[ mx, my, mz ]: a microtesla magnetic intensity value [ mu T ];
[ r ]: RSSI, 0 indicates reception of a timeout/no packet;
and (3) predicting a label:
vicon _ x is the actual robot position tracked by the Vicon system in the x direction, and the unit is meter;
vicon _ y: the actual robot position, in meters, tracked by the Vicon system in the y-direction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110556842.5A CN113203408A (en) | 2021-05-21 | 2021-05-21 | Method for predicting position of robot based on floor sensor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110556842.5A CN113203408A (en) | 2021-05-21 | 2021-05-21 | Method for predicting position of robot based on floor sensor |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113203408A true CN113203408A (en) | 2021-08-03 |
Family
ID=77022825
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110556842.5A Pending CN113203408A (en) | 2021-05-21 | 2021-05-21 | Method for predicting position of robot based on floor sensor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113203408A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104142149A (en) * | 2014-07-03 | 2014-11-12 | 广东顺德中山大学卡内基梅隆大学国际联合研究院 | Human and robot identification and location method based on intelligent optical fiber floor |
| CN107456745A (en) * | 2017-09-30 | 2017-12-12 | 天津商业大学 | A kind of Basketball Tactical training machine people |
| CN108171748A (en) * | 2018-01-23 | 2018-06-15 | 哈工大机器人（合肥）国际创新研究院 | A kind of visual identity of object manipulator intelligent grabbing application and localization method |
| CN108871375A (en) * | 2018-04-24 | 2018-11-23 | 北京大学 | A kind of calibration system and method for three-dimensional space magnetic orientation system |
| CN111207741A (en) * | 2020-01-16 | 2020-05-29 | 西安因诺航空科技有限公司 | Unmanned aerial vehicle navigation positioning method based on indoor vision vicon system |
| CN111596656A (en) * | 2020-04-30 | 2020-08-28 | 南京理工大学 | Heavy-load AGV hybrid navigation device based on binocular video and magnetic sensors |
-
2021
- 2021-05-21 CN CN202110556842.5A patent/CN113203408A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104142149A (en) * | 2014-07-03 | 2014-11-12 | 广东顺德中山大学卡内基梅隆大学国际联合研究院 | Human and robot identification and location method based on intelligent optical fiber floor |
| CN107456745A (en) * | 2017-09-30 | 2017-12-12 | 天津商业大学 | A kind of Basketball Tactical training machine people |
| CN108171748A (en) * | 2018-01-23 | 2018-06-15 | 哈工大机器人（合肥）国际创新研究院 | A kind of visual identity of object manipulator intelligent grabbing application and localization method |
| CN108871375A (en) * | 2018-04-24 | 2018-11-23 | 北京大学 | A kind of calibration system and method for three-dimensional space magnetic orientation system |
| CN111207741A (en) * | 2020-01-16 | 2020-05-29 | 西安因诺航空科技有限公司 | Unmanned aerial vehicle navigation positioning method based on indoor vision vicon system |
| CN111596656A (en) * | 2020-04-30 | 2020-08-28 | 南京理工大学 | Heavy-load AGV hybrid navigation device based on binocular video and magnetic sensors |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Qin et al. | Vehicles on RFID: Error-cognitive vehicle localization in GPS-less environments | |
| CN103052151A (en) | Terminal positioning method and device as well as mobile terminal | |
| You et al. | Hybrid indoor positioning system for pedestrians with swinging arms based on smartphone IMU and RSSI of BLE | |
| CN103471586A (en) | Sensor-assisted terminal combination positioning method and sensor-assisted terminal combination positioning device | |
| CN111766561A (en) | Unmanned aerial vehicle positioning method based on UWB technology | |
| CN101650433B (en) | Method for obtaining self-movement locus of object | |
| CN110260860B (en) | Indoor movement measurement positioning and attitude determination method and system based on foot inertial sensor | |
| Gupta et al. | Road grade estimation using crowd-sourced smartphone data | |
| CN107504968A (en) | A kind of trajectory track method based on PDR and mobile target entry and exit point | |
| CN101644769A (en) | Method for acquiring 3D motion trace of object | |
| CN113203408A (en) | Method for predicting position of robot based on floor sensor | |
| CN201464652U (en) | Positioning electric device obtaining motion trail of object's own | |
| CN116582926A (en) | Underground rubber-tyred vehicle fusion positioning method based on UWB and IMU | |
| CN101650432A (en) | System for tracking three-dimensional movement locus of object on a basis of network computing | |
| CN101650185B (en) | Electronic device for obtaining self-movement locus of object | |
| CN104006811B (en) | A kind of method and device of navigation shoe indoor navigation correction | |
| CN205720685U (en) | One quickly follows the tracks of hunting system | |
| Ahmed et al. | Minimizing GPS dependency for a vehicle’s trajectory identification by using data from smartphone inertial sensors and onboard diagnostics device | |
| CN101644578A (en) | Tracking system for object motion trace based on network computing | |
| CN101655553A (en) | Electronic equipment for obtaining three-dimensional movement locus of object | |
| KR101161097B1 (en) | Method, apparatus and system for tracking lost device | |
| CN116558513B (en) | Indoor terminal positioning method, device, equipment and medium | |
| CN201464655U (en) | Electronic equipment used for positioning and obtaining motion trajectory of object and based on network computation | |
| CN201508184U (en) | Web exhibition-based positioning and tracking system of three-dimensional trajectory of object | |
| CN113242519B (en) | Mobile wireless sensor node positioning method based on multi-information fusion |
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: 20210803 |